Release 2021.02.04

Syntax: -o common_template -o type:type_template
Types supported: subtitle|thumbnail|description|annotation|infojson|pl_description|pl_infojson

.github/ISSUE_TEMPLATE/1_broken_site.md

@@ -21,7 +21,7 @@ assignees: ''
 
 <!--
 Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dlc:
-- First of, make sure you are using the latest version of yt-dlp. Run `youtube-dlc --version` and ensure your version is 2021.01.16. If it's not, see https://github.com/pukkandan/yt-dlp on how to update. Issues with outdated version will be REJECTED.
+- First of, make sure you are using the latest version of yt-dlp. Run `youtube-dlc --version` and ensure your version is 2021.01.29. If it's not, see https://github.com/pukkandan/yt-dlp on how to update. Issues with outdated version will be REJECTED.
 - Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser.
 - Make sure that all URLs and arguments with special characters are properly quoted or escaped as explained in https://github.com/pukkandan/yt-dlp.
 - Search the bugtracker for similar issues: https://github.com/pukkandan/yt-dlp. DO NOT post duplicates.
@@ -29,7 +29,7 @@ Carefully read and work through this check list in order to prevent the most com
 -->
 
 - [ ] I'm reporting a broken site support
-- [ ] I've verified that I'm running yt-dlp version **2021.01.16**
+- [ ] I've verified that I'm running yt-dlp version **2021.01.29**
 - [ ] I've checked that all provided URLs are alive and playable in a browser
 - [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped
 - [ ] I've searched the bugtracker for similar issues including closed ones
@@ -44,7 +44,7 @@ Add the `-v` flag to your command line you run youtube-dlc with (`youtube-dlc -v
  [debug] User config: []
  [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
  [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
- [debug] yt-dlp version 2021.01.16
+ [debug] yt-dlp version 2021.01.29
  [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
  [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
  [debug] Proxy map: {}

.github/ISSUE_TEMPLATE/2_site_support_request.md

@@ -21,7 +21,7 @@ assignees: ''
 
 <!--
 Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dlc:
-- First of, make sure you are using the latest version of yt-dlp. Run `youtube-dlc --version` and ensure your version is 2021.01.16. If it's not, see https://github.com/pukkandan/yt-dlp on how to update. Issues with outdated version will be REJECTED.
+- First of, make sure you are using the latest version of yt-dlp. Run `youtube-dlc --version` and ensure your version is 2021.01.29. If it's not, see https://github.com/pukkandan/yt-dlp on how to update. Issues with outdated version will be REJECTED.
 - Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser.
 - Make sure that site you are requesting is not dedicated to copyright infringement, see https://github.com/pukkandan/yt-dlp. yt-dlp does not support such sites. In order for site support request to be accepted all provided example URLs should not violate any copyrights.
 - Search the bugtracker for similar site support requests: https://github.com/pukkandan/yt-dlp. DO NOT post duplicates.
@@ -29,7 +29,7 @@ Carefully read and work through this check list in order to prevent the most com
 -->
 
 - [ ] I'm reporting a new site support request
-- [ ] I've verified that I'm running yt-dlp version **2021.01.16**
+- [ ] I've verified that I'm running yt-dlp version **2021.01.29**
 - [ ] I've checked that all provided URLs are alive and playable in a browser
 - [ ] I've checked that none of provided URLs violate any copyrights
 - [ ] I've searched the bugtracker for similar site support requests including closed ones

.github/ISSUE_TEMPLATE/3_site_feature_request.md

@@ -21,13 +21,13 @@ assignees: ''
 
 <!--
 Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dlc:
-- First of, make sure you are using the latest version of yt-dlp. Run `youtube-dlc --version` and ensure your version is 2021.01.16. If it's not, see https://github.com/pukkandan/yt-dlp on how to update. Issues with outdated version will be REJECTED.
+- First of, make sure you are using the latest version of yt-dlp. Run `youtube-dlc --version` and ensure your version is 2021.01.29. If it's not, see https://github.com/pukkandan/yt-dlp on how to update. Issues with outdated version will be REJECTED.
 - Search the bugtracker for similar site feature requests: https://github.com/pukkandan/yt-dlp. DO NOT post duplicates.
 - Finally, put x into all relevant boxes like this [x] (Dont forget to delete the empty space)
 -->
 
 - [ ] I'm reporting a site feature request
-- [ ] I've verified that I'm running yt-dlp version **2021.01.16**
+- [ ] I've verified that I'm running yt-dlp version **2021.01.29**
 - [ ] I've searched the bugtracker for similar site feature requests including closed ones
 
 

.github/ISSUE_TEMPLATE/4_bug_report.md

@@ -21,7 +21,7 @@ assignees: ''
 
 <!--
 Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dlc:
-- First of, make sure you are using the latest version of yt-dlp. Run `youtube-dlc --version` and ensure your version is 2021.01.16. If it's not, see https://github.com/pukkandan/yt-dlp on how to update. Issues with outdated version will be REJECTED.
+- First of, make sure you are using the latest version of yt-dlp. Run `youtube-dlc --version` and ensure your version is 2021.01.29. If it's not, see https://github.com/pukkandan/yt-dlp on how to update. Issues with outdated version will be REJECTED.
 - Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser.
 - Make sure that all URLs and arguments with special characters are properly quoted or escaped as explained in https://github.com/pukkandan/yt-dlp.
 - Search the bugtracker for similar issues: https://github.com/pukkandan/yt-dlp. DO NOT post duplicates.
@@ -30,7 +30,7 @@ Carefully read and work through this check list in order to prevent the most com
 -->
 
 - [ ] I'm reporting a broken site support issue
-- [ ] I've verified that I'm running yt-dlp version **2021.01.16**
+- [ ] I've verified that I'm running yt-dlp version **2021.01.29**
 - [ ] I've checked that all provided URLs are alive and playable in a browser
 - [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped
 - [ ] I've searched the bugtracker for similar bug reports including closed ones
@@ -46,7 +46,7 @@ Add the `-v` flag to your command line you run youtube-dlc with (`youtube-dlc -v
  [debug] User config: []
  [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
  [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
- [debug] yt-dlp version 2021.01.16
+ [debug] yt-dlp version 2021.01.29
  [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
  [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
  [debug] Proxy map: {}

.github/ISSUE_TEMPLATE/5_feature_request.md

@@ -21,13 +21,13 @@ assignees: ''
 
 <!--
 Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dlc:
-- First of, make sure you are using the latest version of yt-dlp. Run `youtube-dlc --version` and ensure your version is 2021.01.16. If it's not, see https://github.com/pukkandan/yt-dlp on how to update. Issues with outdated version will be REJECTED.
+- First of, make sure you are using the latest version of yt-dlp. Run `youtube-dlc --version` and ensure your version is 2021.01.29. If it's not, see https://github.com/pukkandan/yt-dlp on how to update. Issues with outdated version will be REJECTED.
 - Search the bugtracker for similar feature requests: https://github.com/pukkandan/yt-dlp. DO NOT post duplicates.
 - Finally, put x into all relevant boxes like this [x] (Dont forget to delete the empty space)
 -->
 
 - [ ] I'm reporting a feature request
-- [ ] I've verified that I'm running yt-dlp version **2021.01.16**
+- [ ] I've verified that I'm running yt-dlp version **2021.01.29**
 - [ ] I've searched the bugtracker for similar feature requests including closed ones
 
 

.github/workflows/build.yml

@@ -25,8 +25,8 @@ jobs:
       run: sudo apt-get -y install zip pandoc man
     - name: Bump version
       id: bump_version
-      run: python scripts/update-version-workflow.py
-    - name: Check the output from My action
+      run: python devscripts/update-version.py
+    - name: Print version
       run: echo "${{ steps.bump_version.outputs.ytdlc_version }}"
     - name: Run Make
       run: make
@@ -84,11 +84,14 @@ jobs:
       with:
           python-version: '3.8'
     - name: Install Requirements
-      run: pip install pyinstaller
+      run: pip install pyinstaller mutagen
     - name: Bump version
-      run: python scripts/update-version-workflow.py
+      id: bump_version
+      run: python devscripts/update-version.py
+    - name: Print version
+      run: echo "${{ steps.bump_version.outputs.ytdlc_version }}"
     - name: Run PyInstaller Script
-      run: python pyinst.py
+      run: python devscripts/pyinst.py 64
     - name: Upload youtube-dlc.exe Windows binary
       id: upload-release-windows
       uses: actions/upload-release-asset@v1
@@ -119,11 +122,14 @@ jobs:
           python-version: '3.4.4'
           architecture: 'x86'
     - name: Install Requirements for 32 Bit
-      run: pip install pyinstaller==3.5
+      run: pip install pyinstaller==3.5 mutagen
     - name: Bump version
-      run: python scripts/update-version-workflow.py
+      id: bump_version
+      run: python devscripts/update-version.py
+    - name: Print version
+      run: echo "${{ steps.bump_version.outputs.ytdlc_version }}"
     - name: Run PyInstaller Script for 32 Bit
-      run: python pyinst32.py
+      run: python devscripts/pyinst.py 32
     - name: Upload Executable youtube-dlc_x86.exe
       id: upload-release-windows32
       uses: actions/upload-release-asset@v1
@@ -162,18 +168,15 @@ jobs:
         asset_name: SHA2-256SUMS
         asset_content_type: text/plain
 
-  update_version_badge:
-
-    runs-on: ubuntu-latest
-
-    needs: build_unix
-
-    steps:
-    - name: Create Version Badge
-      uses: schneegans/dynamic-badges-action@v1.0.0
-      with:
-        auth: ${{ secrets.GIST_TOKEN }}
-        gistID: c69cb23c3c5b3316248e52022790aa57
-        filename: version.json
-        label: Version
-        message: ${{ needs.build_unix.outputs.ytdlc_version }}
+#  update_version_badge:
+#    runs-on: ubuntu-latest
+#    needs: build_unix
+#    steps:
+#    - name: Create Version Badge
+#      uses: schneegans/dynamic-badges-action@v1.0.0
+#      with:
+#        auth: ${{ secrets.GIST_TOKEN }}
+#        gistID: c69cb23c3c5b3316248e52022790aa57
+#        filename: version.json
+#        label: Version
+#        message: ${{ needs.build_unix.outputs.ytdlc_version }}

.github/workflows/core.yml

@@ -1,9 +1,9 @@
-name: Full Test
+name: Core Tests
 on: [push, pull_request]
 jobs:
   tests:
-    name: Tests
-    if: "!contains(github.event.head_commit.message, 'skip ci')"
+    name: Core Tests
+    if: "!contains(github.event.head_commit.message, 'ci skip all')"
     runs-on: ${{ matrix.os }}
     strategy:
       fail-fast: true
@@ -12,7 +12,7 @@ jobs:
         # TODO: python 2.6
         python-version: [2.7, 3.3, 3.4, 3.5, 3.6, 3.7, 3.8, 3.9, pypy-2.7, pypy-3.6, pypy-3.7]
         python-impl: [cpython]
-        ytdl-test-set: [core, download]
+        ytdl-test-set: [core]
         run-tests-ext: [sh]
         include:
         # python 3.2 is only available on windows via setup-python
@@ -21,20 +21,11 @@ jobs:
           python-impl: cpython
           ytdl-test-set: core
           run-tests-ext: bat
-        - os: windows-latest
-          python-version: 3.2
-          python-impl: cpython
-          ytdl-test-set: download
-          run-tests-ext: bat
         # jython
         - os: ubuntu-latest
           python-impl: jython
           ytdl-test-set: core
           run-tests-ext: sh
-        - os: ubuntu-latest
-          python-impl: jython
-          ytdl-test-set: download
-          run-tests-ext: sh
     steps:
     - uses: actions/checkout@v2
     - name: Set up Python ${{ matrix.python-version }}
@@ -60,4 +51,4 @@ jobs:
       env:
         YTDL_TEST_SET: ${{ matrix.ytdl-test-set }}
       run: ./devscripts/run_tests.${{ matrix.run-tests-ext }}
-  # flake8 has been moved to quick-test
+  # Linter is in quick-test

.github/workflows/download.yml

@@ -0,0 +1,53 @@
+name: Download Tests
+on: [push, pull_request]
+jobs:
+  tests:
+    name: Download Tests
+    if: "!contains(github.event.head_commit.message, 'ci skip dl') && !contains(github.event.head_commit.message, 'ci skip all')"
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: true
+      matrix:
+        os: [ubuntu-18.04]
+        # TODO: python 2.6
+        python-version: [2.7, 3.3, 3.4, 3.5, 3.6, 3.7, 3.8, 3.9, pypy-2.7, pypy-3.6, pypy-3.7]
+        python-impl: [cpython]
+        ytdl-test-set: [download]
+        run-tests-ext: [sh]
+        include:
+        # python 3.2 is only available on windows via setup-python
+        - os: windows-latest
+          python-version: 3.2
+          python-impl: cpython
+          ytdl-test-set: download
+          run-tests-ext: bat
+        # jython - disable for now since it takes too long to complete
+        # - os: ubuntu-latest
+        #   python-impl: jython
+        #   ytdl-test-set: download
+        #   run-tests-ext: sh
+    steps:
+    - uses: actions/checkout@v2
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v2
+      if: ${{ matrix.python-impl == 'cpython' }}
+      with:
+        python-version: ${{ matrix.python-version }}
+    - name: Set up Java 8
+      if: ${{ matrix.python-impl == 'jython' }}
+      uses: actions/setup-java@v1
+      with:
+        java-version: 8
+    - name: Install Jython
+      if: ${{ matrix.python-impl == 'jython' }}
+      run: |
+        wget http://search.maven.org/remotecontent?filepath=org/python/jython-installer/2.7.1/jython-installer-2.7.1.jar -O jython-installer.jar
+        java -jar jython-installer.jar -s -d "$HOME/jython"
+        echo "$HOME/jython/bin" >> $GITHUB_PATH
+    - name: Install nose
+      run: pip install nose
+    - name: Run tests
+      continue-on-error: ${{ matrix.ytdl-test-set == 'download' || matrix.python-impl == 'jython' }}
+      env:
+        YTDL_TEST_SET: ${{ matrix.ytdl-test-set }}
+      run: ./devscripts/run_tests.${{ matrix.run-tests-ext }}

.github/workflows/quick-test.yml

@@ -1,13 +1,13 @@
-name: Core Test
+name: Quick Test
 on: [push, pull_request]
 jobs:
   tests:
-    name: Core Tests
-    if: "!contains(github.event.head_commit.message, 'skip ci all')"
+    name: Core Test
+    if: "!contains(github.event.head_commit.message, 'ci skip all')"
     runs-on: ubuntu-latest
     steps:
     - uses: actions/checkout@v2
-    - name: Set up Python 3.9
+    - name: Set up Python
       uses: actions/setup-python@v2
       with:
         python-version: 3.9
@@ -19,7 +19,7 @@ jobs:
       run: ./devscripts/run_tests.sh
   flake8:
     name: Linter
-    if: "!contains(github.event.head_commit.message, 'skip ci all')"
+    if: "!contains(github.event.head_commit.message, 'ci skip all')"
     runs-on: ubuntu-latest
     steps:
     - uses: actions/checkout@v2

.gitignore

@@ -1,35 +1,43 @@
+# Python
 *.pyc
 *.pyo
-*.class
-*~
-*.DS_Store
 wine-py2exe/
 py2exe.log
-*.kate-swp
 build/
 dist/
 zip/
+tmp/
+venv/
+
+# Misc
+*~
+*.DS_Store
+*.kate-swp
 MANIFEST
-README.txt
-youtube-dl.1
-youtube-dlc.1
-youtube-dl.bash-completion
-youtube-dlc.bash-completion
-youtube-dl.fish
-youtube-dlc.fish
-youtube_dl/extractor/lazy_extractors.py
-youtube_dlc/extractor/lazy_extractors.py
-youtube-dl
-youtube-dlc
-youtube-dl.exe
-youtube-dlc.exe
-youtube-dl.tar.gz
-youtube-dlc.tar.gz
-youtube-dlc.spec
+test/local_parameters.json
 .coverage
 cover/
 updates_key.pem
 *.egg-info
+.tox
+*.class
+
+# Generated
+README.txt
+*.1
+*.bash-completion
+*.fish
+*.exe
+*.tar.gz
+*.zsh
+*.spec
+
+# Binary
+youtube-dl
+youtube-dlc
+*.exe
+
+# Downloaded
 *.srt
 *.ttml
 *.sbv
@@ -46,25 +54,33 @@ updates_key.pem
 *.swf
 *.part
 *.ytdl
-*.conf
 *.swp
+*.ogg
+*.opus
+*.info.json
+*.annotations.xml
+*.description
+
+# Config
+*.conf
 *.spec
-*.exe
-test/local_parameters.json
-.tox
-youtube-dl.zsh
-youtube-dlc.zsh
-
-# IntelliJ related files
-.idea
-*.iml
-
-tmp/
-venv/
-
-# VS Code related files
-.vscode
-
+cookies
 cookies.txt
 
-*.sublime-workspace
+
+
+# Text Editor / IDE
+.idea
+*.iml
+.vscode
+*.sublime-workspace
+*.sublime-project
+!yt-dlp.sublime-project
+
+# Lazy extractors
+*/extractor/lazy_extractors.py
+
+# Plugins
+ytdlp_plugins/extractor/*
+!ytdlp_plugins/extractor/__init__.py
+!ytdlp_plugins/extractor/sample.py

AUTHORS

@@ -1,248 +0,0 @@
-Ricardo Garcia Gonzalez
-Danny Colligan
-Benjamin Johnson
-Vasyl' Vavrychuk
-Witold Baryluk
-Paweł Paprota
-Gergely Imreh
-Rogério Brito
-Philipp Hagemeister
-Sören Schulze
-Kevin Ngo
-Ori Avtalion
-shizeeg
-Filippo Valsorda
-Christian Albrecht
-Dave Vasilevsky
-Jaime Marquínez Ferrándiz
-Jeff Crouse
-Osama Khalid
-Michael Walter
-M. Yasoob Ullah Khalid
-Julien Fraichard
-Johny Mo Swag
-Axel Noack
-Albert Kim
-Pierre Rudloff
-Huarong Huo
-Ismael Mejía
-Steffan Donal
-Andras Elso
-Jelle van der Waa
-Marcin Cieślak
-Anton Larionov
-Takuya Tsuchida
-Sergey M.
-Michael Orlitzky
-Chris Gahan
-Saimadhav Heblikar
-Mike Col
-Oleg Prutz
-pulpe
-Andreas Schmitz
-Michael Kaiser
-Niklas Laxström
-David Triendl
-Anthony Weems
-David Wagner
-Juan C. Olivares
-Mattias Harrysson
-phaer
-Sainyam Kapoor
-Nicolas Évrard
-Jason Normore
-Hoje Lee
-Adam Thalhammer
-Georg Jähnig
-Ralf Haring
-Koki Takahashi
-Ariset Llerena
-Adam Malcontenti-Wilson
-Tobias Bell
-Naglis Jonaitis
-Charles Chen
-Hassaan Ali
-Dobrosław Żybort
-David Fabijan
-Sebastian Haas
-Alexander Kirk
-Erik Johnson
-Keith Beckman
-Ole Ernst
-Aaron McDaniel (mcd1992)
-Magnus Kolstad
-Hari Padmanaban
-Carlos Ramos
-5moufl
-lenaten
-Dennis Scheiba
-Damon Timm
-winwon
-Xavier Beynon
-Gabriel Schubiner
-xantares
-Jan Matějka
-Mauroy Sébastien
-William Sewell
-Dao Hoang Son
-Oskar Jauch
-Matthew Rayfield
-t0mm0
-Tithen-Firion
-Zack Fernandes
-cryptonaut
-Adrian Kretz
-Mathias Rav
-Petr Kutalek
-Will Glynn
-Max Reimann
-Cédric Luthi
-Thijs Vermeir
-Joel Leclerc
-Christopher Krooss
-Ondřej Caletka
-Dinesh S
-Johan K. Jensen
-Yen Chi Hsuan
-Enam Mijbah Noor
-David Luhmer
-Shaya Goldberg
-Paul Hartmann
-Frans de Jonge
-Robin de Rooij
-Ryan Schmidt
-Leslie P. Polzer
-Duncan Keall
-Alexander Mamay
-Devin J. Pohly
-Eduardo Ferro Aldama
-Jeff Buchbinder
-Amish Bhadeshia
-Joram Schrijver
-Will W.
-Mohammad Teimori Pabandi
-Roman Le Négrate
-Matthias Küch
-Julian Richen
-Ping O.
-Mister Hat
-Peter Ding
-jackyzy823
-George Brighton
-Remita Amine
-Aurélio A. Heckert
-Bernhard Minks
-sceext
-Zach Bruggeman
-Tjark Saul
-slangangular
-Behrouz Abbasi
-ngld
-nyuszika7h
-Shaun Walbridge
-Lee Jenkins
-Anssi Hannula
-Lukáš Lalinský
-Qijiang Fan
-Rémy Léone
-Marco Ferragina
-reiv
-Muratcan Simsek
-Evan Lu
-flatgreen
-Brian Foley
-Vignesh Venkat
-Tom Gijselinck
-Founder Fang
-Andrew Alexeyew
-Saso Bezlaj
-Erwin de Haan
-Jens Wille
-Robin Houtevelts
-Patrick Griffis
-Aidan Rowe
-mutantmonkey
-Ben Congdon
-Kacper Michajłow
-José Joaquín Atria
-Viťas Strádal
-Kagami Hiiragi
-Philip Huppert
-blahgeek
-Kevin Deldycke
-inondle
-Tomáš Čech
-Déstin Reed
-Roman Tsiupa
-Artur Krysiak
-Jakub Adam Wieczorek
-Aleksandar Topuzović
-Nehal Patel
-Rob van Bekkum
-Petr Zvoníček
-Pratyush Singh
-Aleksander Nitecki
-Sebastian Blunt
-Matěj Cepl
-Xie Yanbo
-Philip Xu
-John Hawkinson
-Rich Leeper
-Zhong Jianxin
-Thor77
-Mattias Wadman
-Arjan Verwer
-Costy Petrisor
-Logan B
-Alex Seiler
-Vijay Singh
-Paul Hartmann
-Stephen Chen
-Fabian Stahl
-Bagira
-Odd Stråbø
-Philip Herzog
-Thomas Christlieb
-Marek Rusinowski
-Tobias Gruetzmacher
-Olivier Bilodeau
-Lars Vierbergen
-Juanjo Benages
-Xiao Di Guan
-Thomas Winant
-Daniel Twardowski
-Jeremie Jarosh
-Gerard Rovira
-Marvin Ewald
-Frédéric Bournival
-Timendum
-gritstub
-Adam Voss
-Mike Fährmann
-Jan Kundrát
-Giuseppe Fabiano
-Örn Guðjónsson
-Parmjit Virk
-Genki Sky
-Ľuboš Katrinec
-Corey Nicholson
-Ashutosh Chaudhary
-John Dong
-Tatsuyuki Ishi
-Daniel Weber
-Kay Bouché
-Yang Hongbo
-Lei Wang
-Petr Novák
-Leonardo Taccari
-Martin Weinelt
-Surya Oktafendri
-TingPing
-Alexandre Macabies
-Bastian de Groot
-Niklas Haas
-András Veres-Szentkirályi
-Enes Solak
-Nathan Rossi
-Thomas van der Berg
-Luca Cherubin

CONTRIBUTORS

@@ -15,4 +15,5 @@ ohnonot
 samiksome
 alxnull
 FelixFrog
-Zocker1999NET
+Zocker1999NET
+nao20010128nao

Changelog.md

@@ -4,25 +4,101 @@
 # Instuctions for creating release
 
 * Run `make doc`
-* Update Changelog.md and Authors-Fork
+* Update Changelog.md and CONTRIBUTORS
+* Change "Merged with youtube-dl" version in Readme.md if needed
 * Commit to master as `Release <version>`
 * Push to origin/release - build task will now run
-* Update version.py and run `make issuetemplates`
-* Commit to master as `[version] update`
+* Update version.py using devscripts\update-version.py (be wary of timezones)
+* Run `make issuetemplates`
+* Commit to master as `[version] update :ci skip all`
 * Push to origin/master
 * Update changelog in /releases
 
 -->
 
 
+### 2021.02.04
+* **Merge youtube-dl:** Upto [2021.02.04.1](https://github.com/ytdl-org/youtube-dl/releases/tag/2021.02.04.1)
+* **Date/time formatting in output template:** You can now use [`strftime`](https://docs.python.org/3/library/datetime.html#strftime-and-strptime-format-codes) to format date/time fields. Example: `%(upload_date>%Y-%m-%d)s`
+* **Multiple output templates:**
+    * Seperate output templates can be given for the different metadata files by using `-o TYPE:TEMPLATE`
+    * The alowed types are: `subtitle|thumbnail|description|annotation|infojson|pl_description|pl_infojson`
+* [youtube] More metadata extraction for channel/playlist URLs (channel, uploader, thumbnail, tags)
+* New option `--no-write-playlist-metafiles` to prevent writing playlist metadata files
+* [audius] Fix extractor
+* [youtube_live_chat] Fix `parse_yt_initial_data` and add `fragment_retries`
+* [postprocessor] Raise errors correctly
+* [metadatafromtitle] Fix bug when extracting data from numeric fields
+* Fix issue with overwriting files
+* Fix "Default format spec" appearing in quiet mode
+* [FormatSort] Allow user to prefer av01 over vp9 (The default is still vp9)
+* [FormatSort] fix bug where `quality` had more priority than `hasvid`
+* [pyinst] Automatically detect python architecture and working directory
+* Strip out internal fields such as `_filename` from infojson
+
+
+### 2021.01.29
+* **Features from [animelover1984/youtube-dl](https://github.com/animelover1984/youtube-dl)**: Co-authored by @animelover1984 and @bbepis
+    * Add `--get-comments`
+    * [youtube] Extract comments
+    * [billibilli] Added BiliBiliSearchIE, BilibiliChannelIE
+    * [billibilli] Extract comments
+    * [billibilli] Better video extraction
+    * Write playlist data to infojson
+    * [FFmpegMetadata] Embed infojson inside the video
+    * [EmbedThumbnail] Try embedding in mp4 using ffprobe and `-disposition`
+    * [EmbedThumbnail] Treat mka like mkv and mov like mp4
+    * [EmbedThumbnail] Embed in ogg/opus
+    * [VideoRemuxer] Conditionally remux video
+    * [VideoRemuxer] Add `-movflags +faststart` when remuxing to mp4
+    * [ffmpeg] Print entire stderr in verbose when there is error
+    * [EmbedSubtitle] Warn when embedding ass in mp4
+    * [anvato] Use NFLTokenGenerator if possible
+* **Parse additional metadata**: New option `--parse-metadata` to extract additional metadata from existing fields
+    * The extracted fields can be used in `--output`
+    * Deprecated `--metadata-from-title`
+* [Audius] Add extractor
+* [youtube] Extract playlist description and write it to `.description` file
+* Detect existing files even when using `recode`/`remux` (`extract-audio` is partially fixed)
+* Fix wrong user config from v2021.01.24
+* [youtube] Report error message from youtube as error instead of warning
+* [FormatSort] Fix some fields not sorting from v2021.01.24
+* [postprocessor] Deprecate `avconv`/`avprobe`.  All current functionality is left untouched. But don't expect any new features to work with avconv
+* [postprocessor] fix `write_debug` to not throw error when there is no `_downloader`
+* [movefiles] Don't give "cant find" warning when move is unnecessary
+* Refactor `update-version`, `pyinst.py` and related files
+* [ffmpeg] Document more formats that are supported for remux/recode
+
+
+### 2021.01.24
+* **Merge youtube-dl:** Upto [2021.01.24](https://github.com/ytdl-org/youtube-dl/releases/tag/2021.01.16)
+* Plugin support ([documentation](https://github.com/pukkandan/yt-dlp#plugins))
+* **Multiple paths**: New option `-P`/`--paths` to give different paths for different types of files
+    * The syntax is `-P "type:path" -P "type:path"` ([documentation](https://github.com/pukkandan/yt-dlp#:~:text=-P,%20--paths%20TYPE:PATH))
+    * Valid types are: home, temp, description, annotation, subtitle, infojson, thumbnail
+    * Additionally, configuration file is taken from home directory or current directory ([documentation](https://github.com/pukkandan/yt-dlp#:~:text=Home%20Configuration))
+* Allow passing different arguments to different external downloaders ([documentation](https://github.com/pukkandan/yt-dlp#:~:text=--downloader-args%20NAME:ARGS))
+* [mildom] Add extractor by @nao20010128nao
+* Warn when using old style `--external-downloader-args` and `--post-processor-args`
+* Fix `--no-overwrite` when using `--write-link`
+* [sponskrub] Output `unrecognized argument` error message correctly
+* [cbs] Make failure to extract title non-fatal
+* Fix typecasting when pre-checking archive
+* Fix issue with setting title on UNIX
+* Deprecate redundant aliases in `formatSort`. The aliases remain functional for backward compatibility, but will be left undocumented
+* [tests] Fix test_post_hooks
+* [tests] Split core and download tests
+
+
 ### 2021.01.20
 * [TrovoLive] Add extractor (only VODs)
-* [pokemon] Add `/#/player` URLs (Closes #24)
+* [pokemon] Add `/#/player` URLs
 * Improved parsing of multiple postprocessor-args, add `--ppa` as alias
 * [EmbedThumbnail] Simplify embedding in mkv
 * [sponskrub] Encode filenames correctly, better debug output and error message
 * [readme] Cleanup options
 
+
 ### 2021.01.16
 * **Merge youtube-dl:** Upto [2021.01.16](https://github.com/ytdl-org/youtube-dl/releases/tag/2021.01.16)
 * **Configuration files:**
@@ -118,7 +194,7 @@
     * Added `--no-ignore-dynamic-mpd`, `--no-allow-dynamic-mpd`, `--allow-dynamic-mpd`, `--youtube-include-hls-manifest`, `--no-youtube-include-hls-manifest`, `--no-youtube-skip-hls-manifest`, `--no-download`, `--no-download-archive`, `--resize-buffer`, `--part`, `--mtime`, `--no-keep-fragments`, `--no-cookies`, `--no-write-annotations`, `--no-write-info-json`, `--no-write-description`, `--no-write-thumbnail`, `--youtube-include-dash-manifest`, `--post-overwrites`, `--no-keep-video`, `--no-embed-subs`, `--no-embed-thumbnail`, `--no-add-metadata`, `--no-include-ads`, `--no-write-sub`, `--no-write-auto-sub`, `--no-playlist-reverse`, `--no-restrict-filenames`, `--youtube-include-dash-manifest`, `--no-format-sort-force`, `--flat-videos`, `--no-list-formats-as-table`, `--no-sponskrub`, `--no-sponskrub-cut`, `--no-sponskrub-force`
     * Renamed: `--write-subs`, `--no-write-subs`, `--no-write-auto-subs`, `--write-auto-subs`. Note that these can still be used without the ending "s"
 * Relaxed validation for format filters so that any arbitrary field can be used
-* Fix for embedding thumbnail in mp3 by @pauldubois98
+* Fix for embedding thumbnail in mp3 by @pauldubois98 ([ytdl-org/youtube-dl#21569](https://github.com/ytdl-org/youtube-dl/pull/21569))
 * Make Twitch Video ID output from Playlist and VOD extractor same. This is only a temporary fix
 * **Merge youtube-dl:** Upto [2021.01.03](https://github.com/ytdl-org/youtube-dl/commit/8e953dcbb10a1a42f4e12e4e132657cb0100a1f8) - See [blackjack4494/yt-dlc#280](https://github.com/blackjack4494/yt-dlc/pull/280) for details
     * Extractors [tiktok](https://github.com/ytdl-org/youtube-dl/commit/fb626c05867deab04425bad0c0b16b55473841a2) and [hotstar](https://github.com/ytdl-org/youtube-dl/commit/bb38a1215718cdf36d73ff0a7830a64cd9fa37cc) have not been merged

README.md

@@ -1,10 +1,12 @@
 # YT-DLP
 
-<!-- See: https://github.com/marketplace/actions/dynamic-badges -->
-[![Release Version](https://img.shields.io/endpoint?url=https://gist.githubusercontent.com/pukkandan/c69cb23c3c5b3316248e52022790aa57/raw/version.json&color=brightgreen)](https://github.com/pukkandan/yt-dlp/releases/latest)
-[![License: Unlicense](https://img.shields.io/badge/License-Unlicense-blue.svg)](https://github.com/pukkandan/yt-dlp/blob/master/LICENSE)
-[![Core Status](https://github.com/pukkandan/yt-dlp/workflows/Core%20Test/badge.svg?branch=master)](https://github.com/pukkandan/yt-dlp/actions?query=workflow%3ACore)
-[![CI Status](https://github.com/pukkandan/yt-dlp/workflows/Full%20Test/badge.svg?branch=master)](https://github.com/pukkandan/yt-dlp/actions?query=workflow%3AFull)
+[![Release version](https://img.shields.io/github/v/release/pukkandan/yt-dlp?color=brightgreen&label=Release)](https://github.com/pukkandan/yt-dlp/releases/latest)
+[![License: Unlicense](https://img.shields.io/badge/License-Unlicense-blue.svg)](LICENSE)
+[![CI Status](https://github.com/pukkandan/yt-dlp/workflows/Core%20Tests/badge.svg?branch=master)](https://github.com/pukkandan/yt-dlp/actions)  
+[![Commits](https://img.shields.io/github/commit-activity/m/pukkandan/yt-dlp?label=commits)](https://github.com/pukkandan/yt-dlp/commits)
+[![Last Commit](https://img.shields.io/github/last-commit/pukkandan/yt-dlp/master)](https://github.com/pukkandan/yt-dlp/commits)
+[![Downloads](https://img.shields.io/github/downloads/pukkandan/yt-dlp/total)](https://github.com/pukkandan/yt-dlp/releases/latest)
+[![PyPi Downloads](https://img.shields.io/pypi/dm/yt-dlp?label=PyPi)](https://pypi.org/project/yt-dlp)
 
 A command-line program to download videos from youtube.com and many other [video platforms](docs/supportedsites.md)
 
@@ -41,6 +43,7 @@ This is a fork of [youtube-dlc](https://github.com/blackjack4494/yt-dlc) which i
     * [Filtering Formats](#filtering-formats)
     * [Sorting Formats](#sorting-formats)
     * [Format Selection examples](#format-selection-examples)
+* [PLUGINS](#plugins)
 * [MORE](#more)
 
 
@@ -51,20 +54,31 @@ The major new features from the latest release of [blackjack4494/yt-dlc](https:/
 
 * **[Format Sorting](#sorting-formats)**: The default format sorting options have been changed so that higher resolution and better codecs will be now preferred instead of simply using larger bitrate. Furthermore, you can now specify the sort order using `-S`. This allows for much easier format selection that what is possible by simply using `--format` ([examples](#format-selection-examples))
 
-* **Merged with youtube-dl v2021.01.16**: You get all the latest features and patches of [youtube-dl](https://github.com/ytdl-org/youtube-dl) in addition to all the features of [youtube-dlc](https://github.com/blackjack4494/yt-dlc)
+* **Merged with youtube-dl v2021.02.04.1**: You get all the latest features and patches of [youtube-dl](https://github.com/ytdl-org/youtube-dl) in addition to all the features of [youtube-dlc](https://github.com/blackjack4494/yt-dlc)
+
+* **Merged with animelover1984/youtube-dl**: You get most of the features and improvements from [animelover1984/youtube-dl](https://github.com/animelover1984/youtube-dl) including `--get-comments`, `BiliBiliSearch`, `BilibiliChannel`, Embedding thumbnail in mp4/ogg/opus, Playlist infojson etc. Note that the NicoNico improvements are not available. See [#31](https://github.com/pukkandan/yt-dlp/pull/31) for details.
 
 * **Youtube improvements**:
     * All Youtube Feeds (`:ytfav`, `:ytwatchlater`, `:ytsubs`, `:ythistory`, `:ytrec`) works correctly and support downloading multiple pages of content
     * Youtube search works correctly (`ytsearch:`, `ytsearchdate:`) along with Search URLs
     * Redirect channel's home URL automatically to `/video` to preserve the old behaviour
 
-* **New extractors**: Trovo.live, AnimeLab, Philo MSO, Rcs, Gedi, bitwave.tv
+* **New extractors**: AnimeLab, Philo MSO, Rcs, Gedi, bitwave.tv, mildom, audius
 
 * **Fixed extractors**: archive.org, roosterteeth.com, skyit, instagram, itv, SouthparkDe, spreaker, Vlive, tiktok, akamai, ina
 
-* **New options**: `--list-formats-as-table`, `--write-link`, `--force-download-archive`, `--force-overwrites`, `--break-on-reject` etc
+* **Plugin support**: Extractors can be loaded from an external file. See [plugins](#plugins) for details
+
+* **Multiple paths and output templates**: You can give different [output templates](#output-template) and download paths for different types of files. You can also set a temporary path where intermediary files are downloaded to. See [`--paths`](https://github.com/pukkandan/yt-dlp/#:~:text=-P,%20--paths%20TYPE:PATH) for details
+
+<!-- Relative link doesn't work for "#:~:text=" -->
+
+* **Portable Configuration**: Configuration files are automatically loaded from the home and root directories. See [configuration](#configuration) for details
+
+* **Other new options**: `--parse-metadata`, `--list-formats-as-table`, `--write-link`, `--force-download-archive`, `--force-overwrites`, `--break-on-reject` etc
+
+* **Improvements**: Multiple `--postprocessor-args` and `--external-downloader-args`, Date/time formatting in `-o`, faster archive checking, more [format selection options](#format-selection) etc
 
-* **Improvements**: Multiple `--postprocessor-args`, `%(duration_string)s` in `-o`, faster archive checking, more [format selection options](#format-selection) etc
 
 See [changelog](Changelog.md) or [commits](https://github.com/pukkandan/yt-dlp/commits) for the full list of changes
 
@@ -77,7 +91,7 @@ If you are coming from [youtube-dl](https://github.com/ytdl-org/youtube-dl), the
 # INSTALLATION
 
 You can install yt-dlp using one of the following methods:
-* Use [PyPI package](https://pypi.org/project/yt-dlp/): `python -m pip install --upgrade yt-dlp`
+* Use [PyPI package](https://pypi.org/project/yt-dlp): `python -m pip install --upgrade yt-dlp`
 * Download the binary from the [latest release](https://github.com/pukkandan/yt-dlp/releases/latest)
 * Use pip+git: `python -m pip install --upgrade git+https://github.com/pukkandan/yt-dlp.git@release`
 * Install master branch: `python -m pip install --upgrade git+https://github.com/pukkandan/yt-dlp`
@@ -88,16 +102,15 @@ You can install yt-dlp using one of the following methods:
 ### COMPILE
 
 **For Windows**:
-To build the Windows executable yourself (without version info!)
+To build the Windows executable, you must have pyinstaller (and optionally mutagen for embedding thumbnail in opus/ogg files)
+
+    python -m pip install --upgrade pyinstaller mutagen
+
+Once you have all the necessary dependancies installed, just run `py devscripts\pyinst.py`. The executable will be built for the same architecture (32/64 bit) as the python used to build it. It is strongly reccomended to use python3 although python2.6+ is supported.
+
+You can also build the executable without any version info or metadata by using:
 
-    python -m pip install --upgrade pyinstaller
     pyinstaller.exe youtube_dlc\__main__.py --onefile --name youtube-dlc
-    
-Or simply execute the `make_win.bat` if pyinstaller is installed.
-There will be a `youtube-dlc.exe` in `/dist`  
-
-New way to build Windows is to use `python pyinst.py` (please use python3 64Bit)  
-For 32Bit Version use a 32Bit Version of python (3 preferred here as well) and run `python pyinst32.py`  
 
 **For Unix**:
 You will need the required build tools  
@@ -106,6 +119,7 @@ Then simply type this
 
     make
 
+**Note**: In either platform, `devscripts\update-version.py` can be used to automatically update the version number
 
 # DESCRIPTION
 **youtube-dlc** is a command-line program to download videos from youtube.com many other [video platforms](docs/supportedsites.md). It requires the Python interpreter, version 2.6, 2.7, or 3.2+, and it is not platform specific. It should work on your Unix box, on Windows or on macOS. It is released to the public domain, which means you can modify it, redistribute it or use it however you like.
@@ -151,9 +165,9 @@ Then simply type this
                                      compatibility) if this option is found
                                      inside the system configuration file, the
                                      user configuration is not loaded
-    --config-location PATH           Location of the configuration file; either
-                                     the path to the config or its containing
-                                     directory
+    --config-location PATH           Location of the main configuration file;
+                                     either the path to the config or its
+                                     containing directory
     --flat-playlist                  Do not extract the videos of a playlist,
                                      only list them
     --flat-videos                    Do not resolve the video urls
@@ -303,19 +317,36 @@ Then simply type this
                                      allowing to play the video while
                                      downloading (some players may not be able
                                      to play it)
-    --external-downloader COMMAND    Use the specified external downloader.
-                                     Currently supports
-                                     aria2c,avconv,axel,curl,ffmpeg,httpie,wget
-    --external-downloader-args ARGS  Give these arguments to the external
-                                     downloader
+    --external-downloader NAME       Use the specified external downloader.
+                                     Currently supports aria2c, avconv, axel,
+                                     curl, ffmpeg, httpie, wget
+    --downloader-args NAME:ARGS      Give these arguments to the external
+                                     downloader. Specify the downloader name and
+                                     the arguments separated by a colon ":". You
+                                     can use this option multiple times
+                                     (Alias: --external-downloader-args)
 
 ## Filesystem Options:
     -a, --batch-file FILE            File containing URLs to download ('-' for
                                      stdin), one URL per line. Lines starting
                                      with '#', ';' or ']' are considered as
                                      comments and ignored
-    -o, --output TEMPLATE            Output filename template, see "OUTPUT
+    -P, --paths TYPE:PATH            The paths where the files should be
+                                     downloaded. Specify the type of file and
+                                     the path separated by a colon ":". All the
+                                     same types as --output are supported.
+                                     Additionally, you can also provide "home"
+                                     and "temp" paths. All intermediary files
+                                     are first downloaded to the temp path and
+                                     then the final files are moved over to the
+                                     home path after download is finished. This
+                                     option is ignored if --output is an
+                                     absolute path
+    -o, --output [TYPE:]TEMPLATE     Output filename template, see "OUTPUT
                                      TEMPLATE" for details
+    --output-na-placeholder TEXT     Placeholder value for unavailable meta
+                                     fields in output filename template
+                                     (default: "NA")
     --autonumber-start NUMBER        Specify the start value for %(autonumber)s
                                      (default is 1)
     --restrict-filenames             Restrict filenames to only ASCII
@@ -328,9 +359,11 @@ Then simply type this
                                      This option includes --no-continue
     --no-force-overwrites            Do not overwrite the video, but overwrite
                                      related files (default)
-    -c, --continue                   Resume partially downloaded files (default)
-    --no-continue                    Restart download of partially downloaded
-                                     files from beginning
+    -c, --continue                   Resume partially downloaded files/fragments
+                                     (default)
+    --no-continue                    Do not resume partially downloaded
+                                     fragments. If the file is unfragmented,
+                                     restart download of the entire file
     --part                           Use .part files instead of writing directly
                                      into output file (default)
     --no-part                        Do not use .part files - write directly
@@ -343,10 +376,18 @@ Then simply type this
                                      file
     --no-write-description           Do not write video description (default)
     --write-info-json                Write video metadata to a .info.json file
+                                     (this may contain personal information)
     --no-write-info-json             Do not write video metadata (default)
     --write-annotations              Write video annotations to a
                                      .annotations.xml file
     --no-write-annotations           Do not write video annotations (default)
+    --write-playlist-metafiles       Write playlist metadata in addition to the
+                                     video metadata when using --write-info-json,
+                                     --write-description etc. (default)
+    --no-write-playlist-metafiles    Do not write playlist metadata when using
+                                     --write-info-json, --write-description etc.
+    --get-comments                   Retrieve video comments to be placed in the
+                                     .info.json file
     --load-info-json FILE            JSON file containing the video information
                                      (created with the "--write-info-json"
                                      option)
@@ -435,7 +476,7 @@ Then simply type this
     --referer URL                    Specify a custom referer, use if the video
                                      access is restricted to one domain
     --add-header FIELD:VALUE         Specify a custom HTTP header and its value,
-                                     separated by a colon ':'. You can use this
+                                     separated by a colon ":". You can use this
                                      option multiple times
     --bidi-workaround                Work around terminals that lack
                                      bidirectional text support. Requires bidiv
@@ -481,17 +522,17 @@ Then simply type this
     --list-formats-old               Present the output of -F in the old form
                                      (Alias: --no-list-formats-as-table)
     --youtube-include-dash-manifest  Download the DASH manifests and related
-                                     data on YouTube videos (default) (Alias:
-                                     --no-youtube-skip-dash-manifest)
+                                     data on YouTube videos (default)
+                                     (Alias: --no-youtube-skip-dash-manifest)
     --youtube-skip-dash-manifest     Do not download the DASH manifests and
-                                     related data on YouTube videos (Alias:
-                                     --no-youtube-include-dash-manifest)
+                                     related data on YouTube videos
+                                     (Alias: --no-youtube-include-dash-manifest)
     --youtube-include-hls-manifest   Download the HLS manifests and related data
-                                     on YouTube videos (default) (Alias:
-                                    --no-youtube-skip-hls-manifest)
+                                     on YouTube videos (default)
+                                     (Alias: --no-youtube-skip-hls-manifest)
     --youtube-skip-hls-manifest      Do not download the HLS manifests and
-                                     related data on YouTube videos (Alias:
-                                     --no-youtube-include-hls-manifest)
+                                     related data on YouTube videos
+                                     (Alias: --no-youtube-include-hls-manifest)
     --merge-output-format FORMAT     If a merge is required (e.g.
                                      bestvideo+bestaudio), output to given
                                      container format. One of mkv, mp4, ogg,
@@ -535,27 +576,30 @@ Then simply type this
 
 ## Post-Processing Options:
     -x, --extract-audio              Convert video files to audio-only files
-                                     (requires ffmpeg or avconv and ffprobe or
-                                     avprobe)
+                                     (requires ffmpeg and ffprobe)
     --audio-format FORMAT            Specify audio format: "best", "aac",
                                      "flac", "mp3", "m4a", "opus", "vorbis", or
                                      "wav"; "best" by default; No effect without
                                      -x
-    --audio-quality QUALITY          Specify ffmpeg/avconv audio quality, insert
-                                     a value between 0 (better) and 9 (worse)
-                                     for VBR or a specific bitrate like 128K
+    --audio-quality QUALITY          Specify ffmpeg audio quality, insert a
+                                     value between 0 (better) and 9 (worse) for
+                                     VBR or a specific bitrate like 128K
                                      (default 5)
     --remux-video FORMAT             Remux the video into another container if
-                                     necessary (currently supported: mp4|mkv).
-                                     If target container does not support the
-                                     video/audio codec, remuxing will fail
+                                     necessary (currently supported: mp4|mkv|flv
+                                     |webm|mov|avi|mp3|mka|m4a|ogg|opus). If
+                                     target container does not support the
+                                     video/audio codec, remuxing will fail. You
+                                     can specify multiple rules; eg.
+                                     "aac>m4a/mov>mp4/mkv" will remux aac to
+                                     m4a, mov to mp4 and anything else to mkv.
     --recode-video FORMAT            Re-encode the video into another format if
-                                     re-encoding is necessary (currently
-                                     supported: mp4|flv|ogg|webm|mkv|avi)
+                                     re-encoding is necessary. The supported
+                                     formats are the same as --remux-video
     --postprocessor-args NAME:ARGS   Give these arguments to the postprocessors.
                                      Specify the postprocessor/executable name
-                                     and the arguments separated by a colon ':'
-                                     to give the argument to only the specified
+                                     and the arguments separated by a colon ":"
+                                     to give the argument to the specified
                                      postprocessor/executable. Supported
                                      postprocessors are: SponSkrub,
                                      ExtractAudio, VideoRemuxer, VideoConvertor,
@@ -563,14 +607,14 @@ Then simply type this
                                      FixupStretched, FixupM4a, FixupM3u8,
                                      SubtitlesConvertor and EmbedThumbnail. The
                                      supported executables are: SponSkrub,
-                                     FFmpeg, FFprobe, avconf, avprobe and
-                                     AtomicParsley. You can use this option
-                                     multiple times to give different arguments
-                                     to different postprocessors. You can also
-                                     specify "PP+EXE:ARGS" to give the arguments
-                                     to the specified executable only when being
-                                     used by the specified postprocessor (Alias:
-                                     --ppa)
+                                     FFmpeg, FFprobe, and AtomicParsley. You can
+                                     use this option multiple times to give
+                                     different arguments to different
+                                     postprocessors. You can also specify
+                                     "PP+EXE:ARGS" to give the arguments to the
+                                     specified executable only when being used
+                                     by the specified postprocessor. You can use
+                                     this option multiple times (Alias: --ppa)
     -k, --keep-video                 Keep the intermediate video file on disk
                                      after post-processing
     --no-keep-video                  Delete the intermediate video file after
@@ -584,16 +628,20 @@ Then simply type this
     --no-embed-thumbnail             Do not embed thumbnail (default)
     --add-metadata                   Write metadata to the video file
     --no-add-metadata                Do not write metadata (default)
-    --metadata-from-title FORMAT     Parse additional metadata like song title /
-                                     artist from the video title. The format
-                                     syntax is the same as --output. Regular
-                                     expression with named capture groups may
+    --parse-metadata FIELD:FORMAT    Parse additional metadata like title/artist
+                                     from other fields. Give field name to
+                                     extract data from, and format of the field
+                                     seperated by a ":". Either regular
+                                     expression with named capture groups or a
+                                     similar syntax to the output template can
                                      also be used. The parsed parameters replace
-                                     existing values. Example: --metadata-from-
-                                     title "%(artist)s - %(title)s" matches a
+                                     any existing values and can be use in
+                                     output templateThis option can be used
+                                     multiple times. Example: --parse-metadata
+                                     "title:%(artist)s - %(title)s" matches a
                                      title like "Coldplay - Paradise". Example
-                                     (regex): --metadata-from-title
-                                     "(?P<artist>.+?) - (?P<title>.+)"
+                                     (regex): --parse-metadata
+                                     "description:Artist - (?P<artist>.+?)"
     --xattrs                         Write metadata to the video file's xattrs
                                      (using dublin core and xdg standards)
     --fixup POLICY                   Automatically correct known faults of the
@@ -601,15 +649,9 @@ Then simply type this
                                      emit a warning), detect_or_warn (the
                                      default; fix file if we can, warn
                                      otherwise)
-    --prefer-avconv                  Prefer avconv over ffmpeg for running the
-                                     postprocessors (Alias: --no-prefer-ffmpeg)
-    --prefer-ffmpeg                  Prefer ffmpeg over avconv for running the
-                                     postprocessors (default)
-                                     (Alias: --no-prefer-avconv)
-    --ffmpeg-location PATH           Location of the ffmpeg/avconv binary;
-                                     either the path to the binary or its
-                                     containing directory
-                                     (Alias: --avconv-location)
+    --ffmpeg-location PATH           Location of the ffmpeg binary; either the
+                                     path to the binary or its containing
+                                     directory
     --exec CMD                       Execute a command on the file after
                                      downloading and post-processing, similar to
                                      find's -exec syntax. Example: --exec 'adb
@@ -648,8 +690,9 @@ Then simply type this
 
 You can configure youtube-dlc by placing any supported command line option to a configuration file. The configuration is loaded from the following locations:
 
-1. The file given by `--config-location`
+1. **Main Configuration**: The file given by `--config-location`
 1. **Portable Configuration**: `yt-dlp.conf` or `youtube-dlc.conf` in the same directory as the bundled binary. If you are running from source-code (`<root dir>/youtube_dlc/__main__.py`), the root directory is used instead.
+1. **Home Configuration**: `yt-dlp.conf` or `youtube-dlc.conf` in the home path given by `-P "home:<path>"`, or in the current directory if no such path is given
 1. **User Configuration**:
     * `%XDG_CONFIG_HOME%/yt-dlp/config` (recommended on Linux/macOS)
     * `%XDG_CONFIG_HOME%/yt-dlp.conf`
@@ -707,11 +750,15 @@ set HOME=%USERPROFILE%
 
 # OUTPUT TEMPLATE
 
-The `-o` option allows users to indicate a template for the output file names.
+The `-o` option is used to indicate a template for the output file names while `-P` option is used to specify the path each type of file should be saved to.
 
 **tl;dr:** [navigate me to examples](#output-template-examples).
 
-The basic usage is not to set any template arguments when downloading a single file, like in `youtube-dlc -o funny_video.flv "https://some/video"`. However, it may contain special sequences that will be replaced when downloading each video. The special sequences may be formatted according to [python string formatting operations](https://docs.python.org/2/library/stdtypes.html#string-formatting). For example, `%(NAME)s` or `%(NAME)05d`. To clarify, that is a percent symbol followed by a name in parentheses, followed by formatting operations. Allowed names along with sequence type are:
+The basic usage of `-o` is not to set any template arguments when downloading a single file, like in `youtube-dlc -o funny_video.flv "https://some/video"`. However, it may contain special sequences that will be replaced when downloading each video. The special sequences may be formatted according to [python string formatting operations](https://docs.python.org/2/library/stdtypes.html#string-formatting). For example, `%(NAME)s` or `%(NAME)05d`. To clarify, that is a percent symbol followed by a name in parentheses, followed by formatting operations. Date/time fields can also be formatted according to [strftime formatting](https://docs.python.org/3/library/datetime.html#strftime-and-strptime-format-codes) by specifying it inside the parantheses seperated from the field name using a `>`. For example, `%(duration>%H-%M-%S)s`.
+
+Additionally, you can set different output templates for the various metadata files seperately from the general output template by specifying the type of file followed by the template seperated by a colon ":". The different filetypes supported are `subtitle|thumbnail|description|annotation|infojson|pl_description|pl_infojson`. For example, `-o '%(title)s.%(ext)s' -o 'thumbnail:%(title)s\%(title)s.%(ext)s'`  will put the thumbnails in a folder with the same name as the video.
+
+The available fields are:
 
  - `id` (string): Video identifier
  - `title` (string): Video title
@@ -741,7 +788,7 @@ The basic usage is not to set any template arguments when downloading a single f
  - `is_live` (boolean): Whether this video is a live stream or a fixed-length video
  - `start_time` (numeric): Time in seconds where the reproduction should start, as specified in the URL
  - `end_time` (numeric): Time in seconds where the reproduction should end, as specified in the URL
- - `format` (string): A human-readable description of the format 
+ - `format` (string): A human-readable description of the format
  - `format_id` (string): Format code specified by `--format`
  - `format_note` (string): Additional info about the format
  - `width` (numeric): Width of the video
@@ -798,7 +845,7 @@ Available for the media that is a track or a part of a music album:
  - `disc_number` (numeric): Number of the disc or other physical medium the track belongs to
  - `release_year` (numeric): Year (YYYY) when the album was released
 
-Each aforementioned sequence when referenced in an output template will be replaced by the actual value corresponding to the sequence name. Note that some of the sequences are not guaranteed to be present since they depend on the metadata obtained by a particular extractor. Such sequences will be replaced with `NA`.
+Each aforementioned sequence when referenced in an output template will be replaced by the actual value corresponding to the sequence name. Note that some of the sequences are not guaranteed to be present since they depend on the metadata obtained by a particular extractor. Such sequences will be replaced with placeholder value provided with `--output-na-placeholder` (`NA` by default).
 
 For example for `-o %(title)s-%(id)s.%(ext)s` and an mp4 video with title `youtube-dlc test video` and id `BaW_jenozKcj`, this will result in a `youtube-dlc test video-BaW_jenozKcj.mp4` file created in the current directory.
 
@@ -818,7 +865,7 @@ If you are using an output template inside a Windows batch file then you must es
 
 #### Output template examples
 
-Note that on Windows you may need to use double quotes instead of single.
+Note that on Windows you need to use double quotes instead of single.
 
 ```bash
 $ youtube-dlc --get-filename -o '%(title)s.%(ext)s' BaW_jenozKc
@@ -830,14 +877,17 @@ youtube-dlc_test_video_.mp4          # A simple file name
 # Download YouTube playlist videos in separate directory indexed by video order in a playlist
 $ youtube-dlc -o '%(playlist)s/%(playlist_index)s - %(title)s.%(ext)s' https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re
 
+# Download YouTube playlist videos in seperate directories according to their uploaded year
+$ youtube-dlc -o '%(upload_date>%Y)s/%(title)s.%(ext)s' https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re
+
 # Download all playlists of YouTube channel/user keeping each playlist in separate directory:
 $ youtube-dlc -o '%(uploader)s/%(playlist)s/%(playlist_index)s - %(title)s.%(ext)s' https://www.youtube.com/user/TheLinuxFoundation/playlists
 
 # Download Udemy course keeping each chapter in separate directory under MyVideos directory in your home
-$ youtube-dlc -u user -p password -o '~/MyVideos/%(playlist)s/%(chapter_number)s - %(chapter)s/%(title)s.%(ext)s' https://www.udemy.com/java-tutorial/
+$ youtube-dlc -u user -p password -P '~/MyVideos' -o '%(playlist)s/%(chapter_number)s - %(chapter)s/%(title)s.%(ext)s' https://www.udemy.com/java-tutorial/
 
 # Download entire series season keeping each series and each season in separate directory under C:/MyVideos
-$ youtube-dlc -o "C:/MyVideos/%(series)s/%(season_number)s - %(season)s/%(episode_number)s - %(episode)s.%(ext)s" https://videomore.ru/kino_v_detalayah/5_sezon/367617
+$ youtube-dlc -P "C:/MyVideos" -o "%(series)s/%(season_number)s - %(season)s/%(episode_number)s - %(episode)s.%(ext)s" https://videomore.ru/kino_v_detalayah/5_sezon/367617
 
 # Stream the video being downloaded to stdout
 $ youtube-dlc -o - BaW_jenozKc
@@ -846,7 +896,7 @@ $ youtube-dlc -o - BaW_jenozKc
 # FORMAT SELECTION
 
 By default, youtube-dlc tries to download the best available quality if you **don't** pass any options.
-This is generally equivalent to using `-f bestvideo*+bestaudio/best`. However, if multiple audiostreams is enabled (`--audio-multistreams`), the default format changes to `-f bestvideo+bestaudio/best`. Similarly, if ffmpeg and avconv are unavailable, or if you use youtube-dlc to stream to `stdout` (`-o -`), the default becomes `-f best/bestvideo+bestaudio`.
+This is generally equivalent to using `-f bestvideo*+bestaudio/best`. However, if multiple audiostreams is enabled (`--audio-multistreams`), the default format changes to `-f bestvideo+bestaudio/best`. Similarly, if ffmpeg is unavailable, or if you use youtube-dlc to stream to `stdout` (`-o -`), the default becomes `-f best/bestvideo+bestaudio`.
 
 The general syntax for format selection is `--f FORMAT` (or `--format FORMAT`) where `FORMAT` is a *selector expression*, i.e. an expression that describes format or formats you would like to download.
 
@@ -877,7 +927,7 @@ If you want to download multiple videos and they don't have the same formats ava
 
 If you want to download several formats of the same video use a comma as a separator, e.g. `-f 22,17,18` will download all these three formats, of course if they are available. Or a more sophisticated example combined with the precedence feature: `-f 136/137/mp4/bestvideo,140/m4a/bestaudio`.
 
-You can merge the video and audio of multiple formats into a single file using `-f <format1>+<format2>+...` (requires ffmpeg or avconv installed), for example `-f bestvideo+bestaudio` will download the best video-only format, the best audio-only format and mux them together with ffmpeg/avconv. If `--no-video-multistreams` is used, all formats with a video stream except the first one are ignored. Similarly, if `--no-audio-multistreams` is used, all formats with an audio stream except the first one are ignored. For example, `-f bestvideo+best+bestaudio` will download and merge all 3 given formats. The resulting file will have 2 video streams and 2 audio streams. But `-f bestvideo+best+bestaudio --no-video-multistreams` will download and merge only `bestvideo` and `bestaudio`. `best` is ignored since another format containing a video stream (`bestvideo`) has already been selected. The order of the formats is therefore important. `-f best+bestaudio --no-audio-multistreams` will download and merge both formats while `-f bestaudio+best --no-audio-multistreams` will ignore `best` and download only `bestaudio`.
+You can merge the video and audio of multiple formats into a single file using `-f <format1>+<format2>+...` (requires ffmpeg installed), for example `-f bestvideo+bestaudio` will download the best video-only format, the best audio-only format and mux them together with ffmpeg. If `--no-video-multistreams` is used, all formats with a video stream except the first one are ignored. Similarly, if `--no-audio-multistreams` is used, all formats with an audio stream except the first one are ignored. For example, `-f bestvideo+best+bestaudio` will download and merge all 3 given formats. The resulting file will have 2 video streams and 2 audio streams. But `-f bestvideo+best+bestaudio --no-video-multistreams` will download and merge only `bestvideo` and `bestaudio`. `best` is ignored since another format containing a video stream (`bestvideo`) has already been selected. The order of the formats is therefore important. `-f best+bestaudio --no-audio-multistreams` will download and merge both formats while `-f bestaudio+best --no-audio-multistreams` will ignore `best` and download only `bestaudio`.
 
 ## Filtering Formats
 
@@ -916,35 +966,35 @@ Format selectors can also be grouped using parentheses, for example if you want
 
 You can change the criteria for being considered the `best` by using `-S` (`--format-sort`). The general format for this is `--format-sort field1,field2...`. The available fields are:
 
- - `video`, `has_video`: Gives priority to formats that has a video stream
- - `audio`, `has_audio`: Gives priority to formats that has a audio stream
- - `extractor`, `preference`, `extractor_preference`: The format preference as given by the extractor
- - `lang`, `language_preference`: Language preference as given by the extractor
+ - `hasvid`: Gives priority to formats that has a video stream
+ - `hasaud`: Gives priority to formats that has a audio stream
+ - `ie_pref`: The format preference as given by the extractor
+ - `lang`: Language preference as given by the extractor
  - `quality`: The quality of the format. This is a metadata field available in some websites
- - `source`, `source_preference`: Preference of the source as given by the extractor
- - `proto`, `protocol`: Protocol used for download (`https`/`ftps` > `http`/`ftp` > `m3u8-native` > `m3u8` > `http-dash-segments` > other > `mms`/`rtsp` > unknown > `f4f`/`f4m`)
- - `vcodec`, `video_codec`: Video Codec (`vp9` > `h265` > `h264` > `vp8` > `h263` > `theora` > other > unknown)
- - `acodec`, `audio_codec`: Audio Codec (`opus` > `vorbis` > `aac` > `mp4a` > `mp3` > `ac3` > `dts` > other > unknown)
+ - `source`: Preference of the source as given by the extractor
+ - `proto`: Protocol used for download (`https`/`ftps` > `http`/`ftp` > `m3u8-native` > `m3u8` > `http-dash-segments` > other > `mms`/`rtsp` > unknown > `f4f`/`f4m`)
+ - `vcodec`: Video Codec (`av01` > `vp9` > `h265` > `h264` > `vp8` > `h263` > `theora` > other > unknown)
+ - `acodec`: Audio Codec (`opus` > `vorbis` > `aac` > `mp4a` > `mp3` > `ac3` > `dts` > other > unknown)
  - `codec`: Equivalent to `vcodec,acodec`
- - `vext`, `video_ext`: Video Extension (`mp4` > `webm` > `flv` > other > unknown). If `--prefer-free-formats` is used, `webm` is prefered.
- - `aext`, `audio_ext`: Audio Extension (`m4a` > `aac` > `mp3` > `ogg` > `opus` > `webm` > other > unknown). If `--prefer-free-formats` is used, the order changes to `opus` > `ogg` > `webm` > `m4a` > `mp3` > `aac`.
- - `ext`, `extension`: Equivalent to `vext,aext`
+ - `vext`: Video Extension (`mp4` > `webm` > `flv` > other > unknown). If `--prefer-free-formats` is used, `webm` is prefered.
+ - `aext`: Audio Extension (`m4a` > `aac` > `mp3` > `ogg` > `opus` > `webm` > other > unknown). If `--prefer-free-formats` is used, the order changes to `opus` > `ogg` > `webm` > `m4a` > `mp3` > `aac`.
+ - `ext`: Equivalent to `vext,aext`
  - `filesize`: Exact filesize, if know in advance. This will be unavailable for mu38 and DASH formats.
- - `filesize_approx`: Approximate filesize calculated from the manifests
- - `size`, `filesize_estimate`: Exact filesize if available, otherwise approximate filesize
+ - `fs_approx`: Approximate filesize calculated from the manifests
+ - `size`: Exact filesize if available, otherwise approximate filesize
  - `height`: Height of video
  - `width`: Width of video
- - `res`, `dimension`: Video resolution, calculated as the smallest dimension.
- - `fps`, `framerate`: Framerate of video
- - `tbr`, `total_bitrate`: Total average bitrate in KBit/s
- - `vbr`, `video_bitrate`: Average video bitrate in KBit/s
- - `abr`, `audio_bitrate`: Average audio bitrate in KBit/s
- - `br`, `bitrate`: Equivalent to using `tbr,vbr,abr`
- - `samplerate`, `asr`: Audio sample rate in Hz
+ - `res`: Video resolution, calculated as the smallest dimension.
+ - `fps`: Framerate of video
+ - `tbr`: Total average bitrate in KBit/s
+ - `vbr`: Average video bitrate in KBit/s
+ - `abr`: Average audio bitrate in KBit/s
+ - `br`: Equivalent to using `tbr,vbr,abr`
+ - `asr`: Audio sample rate in Hz
 
 Note that any other **numerical** field made available by the extractor can also be used. All fields, unless specified otherwise, are sorted in decending order. To reverse this, prefix the field with a `+`. Eg: `+res` prefers format with the smallest resolution. Additionally, you can suffix a prefered value for the fields, seperated by a `:`. Eg: `res:720` prefers larger videos, but no larger than 720p and the smallest video if there are no videos less than 720p. For `codec` and `ext`, you can provide two prefered values, the first for video and the second for audio. Eg: `+codec:avc:m4a` (equivalent to `+vcodec:avc,+acodec:m4a`) sets the video codec preference to `h264` > `h265` > `vp9` > `vp8` > `h263` > `theora` and audio codec preference to `mp4a` > `aac` > `vorbis` > `opus` > `mp3` > `ac3` > `dts`. You can also make the sorting prefer the nearest values to the provided by using `~` as the delimiter. Eg: `filesize~1G` prefers the format with filesize closest to 1 GiB.
 
-The fields `has_video`, `extractor`, `lang`, `quality` are always given highest priority in sorting, irrespective of the user-defined order. This behaviour can be changed by using `--force-format-sort`. Apart from these, the default order used is: `res,fps,codec,size,br,asr,proto,ext,has_audio,source,format_id`. Note that the extractors may override this default order, but they cannot override the user-provided order.
+The fields `hasvid`, `ie_pref`, `lang`, `quality` are always given highest priority in sorting, irrespective of the user-defined order. This behaviour can be changed by using `--force-format-sort`. Apart from these, the default order used is: `res,fps,codec:vp9,size,br,asr,proto,ext,hasaud,source,id`. Note that the extractors may override this default order, but they cannot override the user-provided order.
 
 If your format selector is `worst`, the last item is selected after sorting. This means it will select the format that is worst in all repects. Most of the time, what you actually want is the video with the smallest filesize instead. So it is generally better to use `-f best -S +size,+br,+res,+fps`.
 
@@ -983,7 +1033,7 @@ $ youtube-dlc -f 'wv*+wa/w'
 $ youtube-dlc -S '+res'
 
 # Download the smallest video available
-$ youtube-dlc -S '+size,+bitrate'
+$ youtube-dlc -S '+size,+br'
 
 
 
@@ -1031,7 +1081,7 @@ $ youtube-dlc -f '(bv*+ba/b)[protocol^=http][protocol!*=dash] / (bv*+ba/b)'
 
 # Download best video available via the best protocol
 # (https/ftps > http/ftp > m3u8_native > m3u8 > http_dash_segments ...)
-$ youtube-dlc -S 'protocol'
+$ youtube-dlc -S 'proto'
 
 
 
@@ -1067,9 +1117,11 @@ $ youtube-dlc -S 'res:720,fps'
 $ youtube-dlc -S '+res:480,codec,br'
 ```
 
+# PLUGINS
 
+Plugins are loaded from `<root-dir>/ytdlp_plugins/<type>/__init__.py`. Currently only `extractor` plugins are supported. Support for `downloader` and `postprocessor` plugins may be added in the future. See [ytdlp_plugins](ytdlp_plugins) for example.
 
-
+**Note**: `<root-dir>` is the directory of the binary (`<root-dir>/youtube-dlc`), or the root directory of the module if you are running directly from source-code (`<root dir>/youtube_dlc/__main__.py`)
 
 # MORE
-For FAQ, Developer Instructions etc., see the [original README](https://github.com/ytdl-org/youtube-dl)
+For FAQ, Developer Instructions etc., see the [original README](https://github.com/ytdl-org/youtube-dl#faq)

devscripts/pyinst.py

@@ -0,0 +1,78 @@
+#!/usr/bin/env python
+# coding: utf-8
+
+from __future__ import unicode_literals
+import sys
+import os
+import platform
+
+from PyInstaller.utils.win32.versioninfo import (
+    VarStruct, VarFileInfo, StringStruct, StringTable,
+    StringFileInfo, FixedFileInfo, VSVersionInfo, SetVersion,
+)
+import PyInstaller.__main__
+
+arch = sys.argv[1] if len(sys.argv) > 1 else platform.architecture()[0][:2]
+assert arch in ('32', '64')
+print('Building %sbit version' % arch)
+_x86 = '_x86' if arch == '32' else ''
+
+FILE_DESCRIPTION = 'Media Downloader%s' % (' (32 Bit)' if _x86 else '')
+SHORT_URLS = {'32': 'git.io/JUGsM', '64': 'git.io/JLh7K'}
+
+root_dir = os.path.abspath(os.path.join(os.path.dirname(__file__), '..'))
+print('Changing working directory to %s' % root_dir)
+os.chdir(root_dir)
+
+exec(compile(open('youtube_dlc/version.py').read(), 'youtube_dlc/version.py', 'exec'))
+VERSION = locals()['__version__']
+
+VERSION_LIST = VERSION.replace('-', '.').split('.')
+VERSION_LIST = list(map(int, VERSION_LIST)) + [0] * (4 - len(VERSION_LIST))
+
+print('Version: %s%s' % (VERSION, _x86))
+print('Remember to update the version using devscipts\\update-version.py')
+
+VERSION_FILE = VSVersionInfo(
+    ffi=FixedFileInfo(
+        filevers=VERSION_LIST,
+        prodvers=VERSION_LIST,
+        mask=0x3F,
+        flags=0x0,
+        OS=0x4,
+        fileType=0x1,
+        subtype=0x0,
+        date=(0, 0),
+    ),
+    kids=[
+        StringFileInfo([
+            StringTable(
+                '040904B0', [
+                    StringStruct('Comments', 'Youtube-dlc%s Command Line Interface.' % _x86),
+                    StringStruct('CompanyName', 'pukkandan@gmail.com'),
+                    StringStruct('FileDescription', FILE_DESCRIPTION),
+                    StringStruct('FileVersion', VERSION),
+                    StringStruct('InternalName', 'youtube-dlc%s' % _x86),
+                    StringStruct(
+                        'LegalCopyright',
+                        'pukkandan@gmail.com | UNLICENSE',
+                    ),
+                    StringStruct('OriginalFilename', 'youtube-dlc%s.exe' % _x86),
+                    StringStruct('ProductName', 'Youtube-dlc%s' % _x86),
+                    StringStruct('ProductVersion', '%s%s | %s' % (VERSION, _x86, SHORT_URLS[arch])),
+                ])]),
+        VarFileInfo([VarStruct('Translation', [0, 1200])])
+    ]
+)
+
+PyInstaller.__main__.run([
+    '--name=youtube-dlc%s' % _x86,
+    '--onefile',
+    '--icon=devscripts/cloud.ico',
+    '--exclude-module=youtube_dl',
+    '--exclude-module=test',
+    '--exclude-module=ytdlp_plugins',
+    '--hidden-import=mutagen',
+    'youtube_dlc/__main__.py',
+])
+SetVersion('dist/youtube-dlc%s.exe' % _x86, VERSION_FILE)

devscripts/update-version.py

@@ -0,0 +1,31 @@
+from __future__ import unicode_literals
+from datetime import datetime
+# import urllib.request
+
+# response = urllib.request.urlopen('https://blackjack4494.github.io/youtube-dlc/update/LATEST_VERSION')
+# old_version = response.read().decode('utf-8')
+
+exec(compile(open('youtube_dlc/version.py').read(), 'youtube_dlc/version.py', 'exec'))
+old_version = locals()['__version__']
+
+old_version_list = old_version.replace('-', '.').split(".", 4)
+
+old_ver = '.'.join(old_version_list[:3])
+old_rev = old_version_list[3] if len(old_version_list) > 3 else ''
+
+ver = datetime.now().strftime("%Y.%m.%d")
+rev = str(int(old_rev or 0) + 1) if old_ver == ver else ''
+
+VERSION = '.'.join((ver, rev)) if rev else ver
+# VERSION_LIST = [(int(v) for v in ver.split(".") + [rev or 0])]
+
+print('::set-output name=ytdlc_version::' + VERSION)
+
+file_version_py = open('youtube_dlc/version.py', 'rt')
+data = file_version_py.read()
+data = data.replace(old_version, VERSION)
+file_version_py.close()
+
+file_version_py = open('youtube_dlc/version.py', 'wt')
+file_version_py.write(data)
+file_version_py.close()

docs/supportedsites.md

@@ -47,12 +47,13 @@
  - **Amara**
  - **AMCNetworks**
  - **AmericasTestKitchen**
+ - **AmericasTestKitchenSeason**
  - **anderetijden**: npo.nl, ntr.nl, omroepwnl.nl, zapp.nl and npo3.nl
  - **AnimeLab**
  - **AnimeLabShows**
  - **AnimeOnDemand**
  - **Anvato**
- - **aol.com**
+ - **aol.com**: Yahoo screen and movies
  - **APA**
  - **Aparat**
  - **AppleConnect**
@@ -79,6 +80,9 @@
  - **AudioBoom**
  - **audiomack**
  - **audiomack:album**
+ - **Audius**: Audius.co
+ - **audius:playlist**: Audius.co playlists
+ - **audius:track**: Audius track ID or API link. Prepend with "audius:"
  - **AWAAN**
  - **awaan:live**
  - **awaan:season**
@@ -111,7 +115,9 @@
  - **BiliBili**
  - **BilibiliAudio**
  - **BilibiliAudioAlbum**
+ - **BilibiliChannel**
  - **BiliBiliPlayer**
+ - **BiliBiliSearch**: Bilibili video search, "bilisearch" keyword
  - **BioBioChileTV**
  - **Biography**
  - **BIQLE**
@@ -197,8 +203,6 @@
  - **CNNArticle**
  - **CNNBlogs**
  - **ComedyCentral**
- - **ComedyCentralFullEpisodes**
- - **ComedyCentralShortname**
  - **ComedyCentralTV**
  - **CondeNast**: Condé Nast media group: Allure, Architectural Digest, Ars Technica, Bon Appétit, Brides, Condé Nast, Condé Nast Traveler, Details, Epicurious, GQ, Glamour, Golf Digest, SELF, Teen Vogue, The New Yorker, Vanity Fair, Vogue, W Magazine, WIRED
  - **CONtv**
@@ -520,6 +524,12 @@
  - **Mgoon**
  - **MGTV**: 芒果TV
  - **MiaoPai**
+ - **mildom**: Record ongoing live by specific user in Mildom
+ - **mildom:user:vod**: Download all VODs from specific user in Mildom
+ - **mildom:vod**: Download a VOD in Mildom
+ - **minds**
+ - **minds:channel**
+ - **minds:group**
  - **MinistryGrid**
  - **Minoto**
  - **miomio.tv**
@@ -549,6 +559,7 @@
  - **mtv:video**
  - **mtvjapan**
  - **mtvservices:embedded**
+ - **MTVUutisetArticle**
  - **MuenchenTV**: münchen.tv
  - **mva**: Microsoft Virtual Academy videos
  - **mva:course**: Microsoft Virtual Academy courses
@@ -880,6 +891,8 @@
  - **Sport5**
  - **SportBox**
  - **SportDeutschland**
+ - **spotify**
+ - **spotify:show**
  - **Spreaker**
  - **SpreakerPage**
  - **SpreakerShow**
@@ -962,13 +975,13 @@
  - **TNAFlixNetworkEmbed**
  - **toggle**
  - **ToonGoggles**
- - **Tosh**: Tosh.0
  - **tou.tv**
  - **Toypics**: Toypics video
  - **ToypicsUser**: Toypics user profile
  - **TrailerAddict** (Currently broken)
  - **Trilulilu**
- - **TrovoLive**
+ - **Trovo**
+ - **TrovoVod**
  - **TruNews**
  - **TruTV**
  - **Tube8**
@@ -1078,7 +1091,6 @@
  - **vidme**
  - **vidme:user**
  - **vidme:user:likes**
- - **Vidzi**
  - **vier**: vier.be and vijf.be
  - **vier:videos**
  - **viewlift**
@@ -1123,6 +1135,7 @@
  - **vrv**
  - **vrv:series**
  - **VShare**
+ - **VTM**
  - **VTXTV**
  - **vube**: Vube.com
  - **VuClip**

make_win.bat

@@ -1 +0,0 @@
-py -m PyInstaller youtube_dlc\__main__.py --onefile --name youtube-dlc --version-file win\ver.txt --icon win\icon\cloud.ico --upx-exclude=vcruntime140.dll

pyinst.py

@@ -1,92 +0,0 @@
-from __future__ import unicode_literals
-from PyInstaller.utils.win32.versioninfo import (
-    VarStruct, VarFileInfo, StringStruct, StringTable,
-    StringFileInfo, FixedFileInfo, VSVersionInfo, SetVersion,
-)
-import PyInstaller.__main__
-
-from datetime import datetime
-
-FILE_DESCRIPTION = 'Media Downloader'
-
-exec(compile(open('youtube_dlc/version.py').read(), 'youtube_dlc/version.py', 'exec'))
-
-_LATEST_VERSION = locals()['__version__']
-
-_OLD_VERSION = _LATEST_VERSION.rsplit("-", 1)
-
-if len(_OLD_VERSION) > 0:
-    old_ver = _OLD_VERSION[0]
-
-old_rev = ''
-if len(_OLD_VERSION) > 1:
-    old_rev = _OLD_VERSION[1]
-
-now = datetime.now()
-# ver = f'{datetime.today():%Y.%m.%d}'
-ver = now.strftime("%Y.%m.%d")
-rev = ''
-
-if old_ver == ver:
-    if old_rev:
-        rev = int(old_rev) + 1
-    else:
-        rev = 1
-
-_SEPARATOR = '-'
-
-version = _SEPARATOR.join(filter(None, [ver, str(rev)]))
-
-print(version)
-
-version_list = ver.split(".")
-_year, _month, _day = [int(value) for value in version_list]
-_rev = 0
-if rev:
-    _rev = rev
-_ver_tuple = _year, _month, _day, _rev
-
-version_file = VSVersionInfo(
-    ffi=FixedFileInfo(
-        filevers=_ver_tuple,
-        prodvers=_ver_tuple,
-        mask=0x3F,
-        flags=0x0,
-        OS=0x4,
-        fileType=0x1,
-        subtype=0x0,
-        date=(0, 0),
-    ),
-    kids=[
-        StringFileInfo(
-            [
-                StringTable(
-                    "040904B0",
-                    [
-                        StringStruct("Comments", "Youtube-dlc Command Line Interface."),
-                        StringStruct("CompanyName", "theidel@uni-bremen.de"),
-                        StringStruct("FileDescription", FILE_DESCRIPTION),
-                        StringStruct("FileVersion", version),
-                        StringStruct("InternalName", "youtube-dlc"),
-                        StringStruct(
-                            "LegalCopyright",
-                            "theidel@uni-bremen.de | UNLICENSE",
-                        ),
-                        StringStruct("OriginalFilename", "youtube-dlc.exe"),
-                        StringStruct("ProductName", "Youtube-dlc"),
-                        StringStruct("ProductVersion", version + " | git.io/JLh7K"),
-                    ],
-                )
-            ]
-        ),
-        VarFileInfo([VarStruct("Translation", [0, 1200])])
-    ]
-)
-
-PyInstaller.__main__.run([
-    '--name=youtube-dlc',
-    '--onefile',
-    '--icon=win/icon/cloud.ico',
-    'youtube_dlc/__main__.py',
-])
-SetVersion('dist/youtube-dlc.exe', version_file)

pyinst32.py

@@ -1,92 +0,0 @@
-from __future__ import unicode_literals
-from PyInstaller.utils.win32.versioninfo import (
-    VarStruct, VarFileInfo, StringStruct, StringTable,
-    StringFileInfo, FixedFileInfo, VSVersionInfo, SetVersion,
-)
-import PyInstaller.__main__
-
-from datetime import datetime
-
-FILE_DESCRIPTION = 'Media Downloader 32 Bit Version'
-
-exec(compile(open('youtube_dlc/version.py').read(), 'youtube_dlc/version.py', 'exec'))
-
-_LATEST_VERSION = locals()['__version__']
-
-_OLD_VERSION = _LATEST_VERSION.rsplit("-", 1)
-
-if len(_OLD_VERSION) > 0:
-    old_ver = _OLD_VERSION[0]
-
-old_rev = ''
-if len(_OLD_VERSION) > 1:
-    old_rev = _OLD_VERSION[1]
-
-now = datetime.now()
-# ver = f'{datetime.today():%Y.%m.%d}'
-ver = now.strftime("%Y.%m.%d")
-rev = ''
-
-if old_ver == ver:
-    if old_rev:
-        rev = int(old_rev) + 1
-    else:
-        rev = 1
-
-_SEPARATOR = '-'
-
-version = _SEPARATOR.join(filter(None, [ver, str(rev)]))
-
-print(version)
-
-version_list = ver.split(".")
-_year, _month, _day = [int(value) for value in version_list]
-_rev = 0
-if rev:
-    _rev = rev
-_ver_tuple = _year, _month, _day, _rev
-
-version_file = VSVersionInfo(
-    ffi=FixedFileInfo(
-        filevers=_ver_tuple,
-        prodvers=_ver_tuple,
-        mask=0x3F,
-        flags=0x0,
-        OS=0x4,
-        fileType=0x1,
-        subtype=0x0,
-        date=(0, 0),
-    ),
-    kids=[
-        StringFileInfo(
-            [
-                StringTable(
-                    "040904B0",
-                    [
-                        StringStruct("Comments", "Youtube-dlc_x86 Command Line Interface."),
-                        StringStruct("CompanyName", "theidel@uni-bremen.de"),
-                        StringStruct("FileDescription", FILE_DESCRIPTION),
-                        StringStruct("FileVersion", version),
-                        StringStruct("InternalName", "youtube-dlc_x86"),
-                        StringStruct(
-                            "LegalCopyright",
-                            "theidel@uni-bremen.de | UNLICENSE",
-                        ),
-                        StringStruct("OriginalFilename", "youtube-dlc_x86.exe"),
-                        StringStruct("ProductName", "Youtube-dlc_x86"),
-                        StringStruct("ProductVersion", version + "_x86 | git.io/JUGsM"),
-                    ],
-                )
-            ]
-        ),
-        VarFileInfo([VarStruct("Translation", [0, 1200])])
-    ]
-)
-
-PyInstaller.__main__.run([
-    '--name=youtube-dlc_x86',
-    '--onefile',
-    '--icon=win/icon/cloud.ico',
-    'youtube_dlc/__main__.py',
-])
-SetVersion('dist/youtube-dlc_x86.exe', version_file)

requirements.txt

@@ -0,0 +1 @@
+mutagen

scripts/update-version-workflow.py

@@ -1,44 +0,0 @@
-from __future__ import unicode_literals
-from datetime import datetime
-# import urllib.request
-
-# response = urllib.request.urlopen('https://blackjack4494.github.io/youtube-dlc/update/LATEST_VERSION')
-# _LATEST_VERSION = response.read().decode('utf-8')
-
-exec(compile(open('youtube_dlc/version.py').read(), 'youtube_dlc/version.py', 'exec'))
-
-_LATEST_VERSION = locals()['__version__']
-
-_OLD_VERSION = _LATEST_VERSION.rsplit("-", 1)
-
-if len(_OLD_VERSION) > 0:
-    old_ver = _OLD_VERSION[0]
-
-old_rev = ''
-if len(_OLD_VERSION) > 1:
-    old_rev = _OLD_VERSION[1]
-
-now = datetime.now()
-# ver = f'{datetime.today():%Y.%m.%d}'
-ver = now.strftime("%Y.%m.%d")
-rev = ''
-
-if old_ver == ver:
-    if old_rev:
-        rev = int(old_rev) + 1
-    else:
-        rev = 1
-
-_SEPARATOR = '-'
-
-version = _SEPARATOR.join(filter(None, [ver, str(rev)]))
-
-print('::set-output name=ytdlc_version::' + version)
-
-file_version_py = open('youtube_dlc/version.py', 'rt')
-data = file_version_py.read()
-data = data.replace(locals()['__version__'], version)
-file_version_py.close()
-file_version_py = open('youtube_dlc/version.py', 'wt')
-file_version_py.write(data)
-file_version_py.close()

scripts/update-version.py

@@ -1,33 +0,0 @@
-# Unused
-
-from __future__ import unicode_literals
-from datetime import datetime
-import urllib.request
-
-response = urllib.request.urlopen('https://blackjack4494.github.io/youtube-dlc/update/LATEST_VERSION')
-
-_LATEST_VERSION = response.read().decode('utf-8')
-
-_OLD_VERSION = _LATEST_VERSION.rsplit("-", 1)
-
-if len(_OLD_VERSION) > 0:
-    old_ver = _OLD_VERSION[0]
-
-old_rev = ''
-if len(_OLD_VERSION) > 1:
-    old_rev = _OLD_VERSION[1]
-
-now = datetime.now()
-# ver = f'{datetime.today():%Y.%m.%d}'
-ver = now.strftime("%Y.%m.%d")
-rev = ''
-
-if old_ver == ver:
-    if old_rev:
-        rev = int(old_rev) + 1
-    else:
-        rev = 1
-
-_SEPARATOR = '-'
-
-version = _SEPARATOR.join(filter(None, [ver, str(rev)]))

setup.cfg

@@ -2,5 +2,5 @@
 universal = True
 
 [flake8]
-exclude = youtube_dlc/extractor/__init__.py,devscripts/buildserver.py,devscripts/lazy_load_template.py,devscripts/make_issue_template.py,setup.py,build,.git,venv,devscripts/create-github-release.py,devscripts/release.sh,devscripts/show-downloads-statistics.py,scripts/update-version.py
+exclude = youtube_dlc/extractor/__init__.py,devscripts/buildserver.py,devscripts/lazy_load_template.py,devscripts/make_issue_template.py,setup.py,build,.git,venv,devscripts/create-github-release.py,devscripts/release.sh,devscripts/show-downloads-statistics.py
 ignore = E402,E501,E731,E741,W503

setup.py

@@ -7,10 +7,12 @@ import warnings
 import sys
 from distutils.spawn import spawn
 
+
 # Get the version from youtube_dlc/version.py without importing the package
 exec(compile(open('youtube_dlc/version.py').read(),
              'youtube_dlc/version.py', 'exec'))
 
+
 DESCRIPTION = 'Command-line program to download videos from YouTube.com and many other other video platforms.'
 
 LONG_DESCRIPTION = '\n\n'.join((
@@ -18,6 +20,9 @@ LONG_DESCRIPTION = '\n\n'.join((
     '**PS**: Many links in this document will not work since this is a copy of the README.md from Github',
     open("README.md", "r", encoding="utf-8").read()))
 
+REQUIREMENTS = ['mutagen']
+
+
 if len(sys.argv) >= 2 and sys.argv[1] == 'py2exe':
     print("inv")
 else:
@@ -41,10 +46,8 @@ else:
     params = {
         'data_files': data_files,
     }
-    #if setuptools_available:
     params['entry_points'] = {'console_scripts': ['youtube-dlc = youtube_dlc:main']}
-    #else:
-    #    params['scripts'] = ['bin/youtube-dlc']
+
 
 class build_lazy_extractors(Command):
     description = 'Build the extractor lazy loading module'
@@ -62,6 +65,9 @@ class build_lazy_extractors(Command):
             dry_run=self.dry_run,
         )
 
+
+packages = find_packages(exclude=("youtube_dl", "test", "ytdlp_plugins"))
+
 setup(
     name="yt-dlp",
     version=__version__,
@@ -71,7 +77,8 @@ setup(
     long_description=LONG_DESCRIPTION,
     long_description_content_type="text/markdown",
     url="https://github.com/pukkandan/yt-dlp",
-    packages=find_packages(exclude=("youtube_dl","test",)),
+    packages=packages,
+    install_requires=REQUIREMENTS,
     project_urls={
         'Documentation': 'https://github.com/pukkandan/yt-dlp#yt-dlp',
         'Source': 'https://github.com/pukkandan/yt-dlp',

test/test_YoutubeDL.py

@@ -637,13 +637,20 @@ class TestYoutubeDL(unittest.TestCase):
             'title2': '%PATH%',
         }
 
-        def fname(templ):
-            ydl = YoutubeDL({'outtmpl': templ})
+        def fname(templ, na_placeholder='NA'):
+            params = {'outtmpl': templ}
+            if na_placeholder != 'NA':
+                params['outtmpl_na_placeholder'] = na_placeholder
+            ydl = YoutubeDL(params)
             return ydl.prepare_filename(info)
         self.assertEqual(fname('%(id)s.%(ext)s'), '1234.mp4')
         self.assertEqual(fname('%(id)s-%(width)s.%(ext)s'), '1234-NA.mp4')
-        # Replace missing fields with 'NA'
-        self.assertEqual(fname('%(uploader_date)s-%(id)s.%(ext)s'), 'NA-1234.mp4')
+        NA_TEST_OUTTMPL = '%(uploader_date)s-%(width)d-%(id)s.%(ext)s'
+        # Replace missing fields with 'NA' by default
+        self.assertEqual(fname(NA_TEST_OUTTMPL), 'NA-NA-1234.mp4')
+        # Or by provided placeholder
+        self.assertEqual(fname(NA_TEST_OUTTMPL, na_placeholder='none'), 'none-none-1234.mp4')
+        self.assertEqual(fname(NA_TEST_OUTTMPL, na_placeholder=''), '--1234.mp4')
         self.assertEqual(fname('%(height)d.%(ext)s'), '1080.mp4')
         self.assertEqual(fname('%(height)6d.%(ext)s'), '  1080.mp4')
         self.assertEqual(fname('%(height)-6d.%(ext)s'), '1080  .mp4')

test/test_post_hooks.py

@@ -8,11 +8,11 @@ import unittest
 sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
 from test.helper import get_params, try_rm
-import youtube_dl.YoutubeDL
-from youtube_dl.utils import DownloadError
+import youtube_dlc.YoutubeDL
+from youtube_dlc.utils import DownloadError
 
 
-class YoutubeDL(youtube_dl.YoutubeDL):
+class YoutubeDL(youtube_dlc.YoutubeDL):
     def __init__(self, *args, **kwargs):
         super(YoutubeDL, self).__init__(*args, **kwargs)
         self.to_stderr = self.to_screen

test/test_postprocessors.py

@@ -8,10 +8,16 @@ import sys
 import unittest
 sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
-from youtube_dlc.postprocessor import MetadataFromTitlePP
+from youtube_dlc.postprocessor import MetadataFromFieldPP, MetadataFromTitlePP
+
+
+class TestMetadataFromField(unittest.TestCase):
+    def test_format_to_regex(self):
+        pp = MetadataFromFieldPP(None, ['title:%(title)s - %(artist)s'])
+        self.assertEqual(pp._data[0]['regex'], r'(?P<title>[^\r\n]+)\ \-\ (?P<artist>[^\r\n]+)')
 
 
 class TestMetadataFromTitle(unittest.TestCase):
     def test_format_to_regex(self):
         pp = MetadataFromTitlePP(None, '%(title)s - %(artist)s')
-        self.assertEqual(pp._titleregex, r'(?P<title>.+)\ \-\ (?P<artist>.+)')
+        self.assertEqual(pp._titleregex, r'(?P<title>[^\r\n]+)\ \-\ (?P<artist>[^\r\n]+)')

test/test_unicode_literals.py

@@ -15,8 +15,6 @@ IGNORED_FILES = [
     'setup.py',  # http://bugs.python.org/issue13943
     'conf.py',
     'buildserver.py',
-    'pyinst.py',
-    'pyinst32.py',
 ]
 
 IGNORED_DIRS = [

test/test_youtube_chapters.py

@@ -1,275 +0,0 @@
-#!/usr/bin/env python
-# coding: utf-8
-from __future__ import unicode_literals
-
-# Allow direct execution
-import os
-import sys
-import unittest
-sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
-
-from test.helper import expect_value
-from youtube_dlc.extractor import YoutubeIE
-
-
-class TestYoutubeChapters(unittest.TestCase):
-
-    _TEST_CASES = [
-        (
-            # https://www.youtube.com/watch?v=A22oy8dFjqc
-            # pattern: 00:00 - <title>
-            '''This is the absolute ULTIMATE experience of Queen's set at LIVE AID, this is the best video mixed to the absolutely superior stereo radio broadcast. This vastly superior audio mix takes a huge dump on all of the official mixes. Best viewed in 1080p. ENJOY! ***MAKE SURE TO READ THE DESCRIPTION***<br /><a href="#" onclick="yt.www.watch.player.seekTo(00*60+36);return false;">00:36</a> - Bohemian Rhapsody<br /><a href="#" onclick="yt.www.watch.player.seekTo(02*60+42);return false;">02:42</a> - Radio Ga Ga<br /><a href="#" onclick="yt.www.watch.player.seekTo(06*60+53);return false;">06:53</a> - Ay Oh!<br /><a href="#" onclick="yt.www.watch.player.seekTo(07*60+34);return false;">07:34</a> - Hammer To Fall<br /><a href="#" onclick="yt.www.watch.player.seekTo(12*60+08);return false;">12:08</a> - Crazy Little Thing Called Love<br /><a href="#" onclick="yt.www.watch.player.seekTo(16*60+03);return false;">16:03</a> - We Will Rock You<br /><a href="#" onclick="yt.www.watch.player.seekTo(17*60+18);return false;">17:18</a> - We Are The Champions<br /><a href="#" onclick="yt.www.watch.player.seekTo(21*60+12);return false;">21:12</a> - Is This The World We Created...?<br /><br />Short song analysis:<br /><br />- "Bohemian Rhapsody": Although it's a short medley version, it's one of the best performances of the ballad section, with Freddie nailing the Bb4s with the correct studio phrasing (for the first time ever!).<br /><br />- "Radio Ga Ga": Although it's missing one chorus, this is one of - if not the best - the best versions ever, Freddie nails all the Bb4s and sounds very clean! Spike Edney's Roland Jupiter 8 also really shines through on this mix, compared to the DVD releases!<br /><br />- "Audience Improv": A great improv, Freddie sounds strong and confident. You gotta love when he sustains that A4 for 4 seconds!<br /><br />- "Hammer To Fall": Despite missing a verse and a chorus, it's a strong version (possibly the best ever). Freddie sings the song amazingly, and even ad-libs a C#5 and a C5! Also notice how heavy Brian's guitar sounds compared to the thin DVD mixes - it roars!<br /><br />- "Crazy Little Thing Called Love": A great version, the crowd loves the song, the jam is great as well! Only downside to this is the slight feedback issues.<br /><br />- "We Will Rock You": Although cut down to the 1st verse and chorus, Freddie sounds strong. He nails the A4, and the solo from Dr. May is brilliant!<br /><br />- "We Are the Champions": Perhaps the high-light of the performance - Freddie is very daring on this version, he sustains the pre-chorus Bb4s, nails the 1st C5, belts great A4s, but most importantly: He nails the chorus Bb4s, in all 3 choruses! This is the only time he has ever done so! It has to be said though, the last one sounds a bit rough, but that's a side effect of belting high notes for the past 18 minutes, with nodules AND laryngitis!<br /><br />- "Is This The World We Created... ?": Freddie and Brian perform a beautiful version of this, and it is one of the best versions ever. It's both sad and hilarious that a couple of BBC engineers are talking over the song, one of them being completely oblivious of the fact that he is interrupting the performance, on live television... Which was being televised to almost 2 billion homes.<br /><br /><br />All rights go to their respective owners!<br />-----Copyright Disclaimer Under Section 107 of the Copyright Act 1976, allowance is made for fair use for purposes such as criticism, comment, news reporting, teaching, scholarship, and research. Fair use is a use permitted by copyright statute that might otherwise be infringing. Non-profit, educational or personal use tips the balance in favor of fair use''',
-            1477,
-            [{
-                'start_time': 36,
-                'end_time': 162,
-                'title': 'Bohemian Rhapsody',
-            }, {
-                'start_time': 162,
-                'end_time': 413,
-                'title': 'Radio Ga Ga',
-            }, {
-                'start_time': 413,
-                'end_time': 454,
-                'title': 'Ay Oh!',
-            }, {
-                'start_time': 454,
-                'end_time': 728,
-                'title': 'Hammer To Fall',
-            }, {
-                'start_time': 728,
-                'end_time': 963,
-                'title': 'Crazy Little Thing Called Love',
-            }, {
-                'start_time': 963,
-                'end_time': 1038,
-                'title': 'We Will Rock You',
-            }, {
-                'start_time': 1038,
-                'end_time': 1272,
-                'title': 'We Are The Champions',
-            }, {
-                'start_time': 1272,
-                'end_time': 1477,
-                'title': 'Is This The World We Created...?',
-            }]
-        ),
-        (
-            # https://www.youtube.com/watch?v=ekYlRhALiRQ
-            # pattern: <num>. <title> 0:00
-            '1.  Those Beaten Paths of Confusion <a href="#" onclick="yt.www.watch.player.seekTo(0*60+00);return false;">0:00</a><br />2.  Beyond the Shadows of Emptiness & Nothingness <a href="#" onclick="yt.www.watch.player.seekTo(11*60+47);return false;">11:47</a><br />3.  Poison Yourself...With Thought <a href="#" onclick="yt.www.watch.player.seekTo(26*60+30);return false;">26:30</a><br />4.  The Agents of Transformation <a href="#" onclick="yt.www.watch.player.seekTo(35*60+57);return false;">35:57</a><br />5.  Drowning in the Pain of Consciousness <a href="#" onclick="yt.www.watch.player.seekTo(44*60+32);return false;">44:32</a><br />6.  Deny the Disease of Life <a href="#" onclick="yt.www.watch.player.seekTo(53*60+07);return false;">53:07</a><br /><br />More info/Buy: http://crepusculonegro.storenvy.com/products/257645-cn-03-arizmenda-within-the-vacuum-of-infinity<br /><br />No copyright is intended. The rights to this video are assumed by the owner and its affiliates.',
-            4009,
-            [{
-                'start_time': 0,
-                'end_time': 707,
-                'title': '1. Those Beaten Paths of Confusion',
-            }, {
-                'start_time': 707,
-                'end_time': 1590,
-                'title': '2. Beyond the Shadows of Emptiness & Nothingness',
-            }, {
-                'start_time': 1590,
-                'end_time': 2157,
-                'title': '3. Poison Yourself...With Thought',
-            }, {
-                'start_time': 2157,
-                'end_time': 2672,
-                'title': '4. The Agents of Transformation',
-            }, {
-                'start_time': 2672,
-                'end_time': 3187,
-                'title': '5. Drowning in the Pain of Consciousness',
-            }, {
-                'start_time': 3187,
-                'end_time': 4009,
-                'title': '6. Deny the Disease of Life',
-            }]
-        ),
-        (
-            # https://www.youtube.com/watch?v=WjL4pSzog9w
-            # pattern: 00:00 <title>
-            '<a href="https://arizmenda.bandcamp.com/merch/despairs-depths-descended-cd" class="yt-uix-servicelink  " data-target-new-window="True" data-servicelink="CDAQ6TgYACITCNf1raqT2dMCFdRjGAod_o0CBSj4HQ" data-url="https://arizmenda.bandcamp.com/merch/despairs-depths-descended-cd" rel="nofollow noopener" target="_blank">https://arizmenda.bandcamp.com/merch/...</a><br /><br /><a href="#" onclick="yt.www.watch.player.seekTo(00*60+00);return false;">00:00</a> Christening Unborn Deformities <br /><a href="#" onclick="yt.www.watch.player.seekTo(07*60+08);return false;">07:08</a> Taste of Purity<br /><a href="#" onclick="yt.www.watch.player.seekTo(16*60+16);return false;">16:16</a> Sculpting Sins of a Universal Tongue<br /><a href="#" onclick="yt.www.watch.player.seekTo(24*60+45);return false;">24:45</a> Birth<br /><a href="#" onclick="yt.www.watch.player.seekTo(31*60+24);return false;">31:24</a> Neves<br /><a href="#" onclick="yt.www.watch.player.seekTo(37*60+55);return false;">37:55</a> Libations in Limbo',
-            2705,
-            [{
-                'start_time': 0,
-                'end_time': 428,
-                'title': 'Christening Unborn Deformities',
-            }, {
-                'start_time': 428,
-                'end_time': 976,
-                'title': 'Taste of Purity',
-            }, {
-                'start_time': 976,
-                'end_time': 1485,
-                'title': 'Sculpting Sins of a Universal Tongue',
-            }, {
-                'start_time': 1485,
-                'end_time': 1884,
-                'title': 'Birth',
-            }, {
-                'start_time': 1884,
-                'end_time': 2275,
-                'title': 'Neves',
-            }, {
-                'start_time': 2275,
-                'end_time': 2705,
-                'title': 'Libations in Limbo',
-            }]
-        ),
-        (
-            # https://www.youtube.com/watch?v=o3r1sn-t3is
-            # pattern: <title> 00:00 <note>
-            'Download this show in MP3: <a href="http://sh.st/njZKK" class="yt-uix-servicelink  " data-url="http://sh.st/njZKK" data-target-new-window="True" data-servicelink="CDAQ6TgYACITCK3j8_6o2dMCFVDCGAoduVAKKij4HQ" rel="nofollow noopener" target="_blank">http://sh.st/njZKK</a><br /><br />Setlist:<br />I-E-A-I-A-I-O <a href="#" onclick="yt.www.watch.player.seekTo(00*60+45);return false;">00:45</a><br />Suite-Pee <a href="#" onclick="yt.www.watch.player.seekTo(4*60+26);return false;">4:26</a>  (Incomplete)<br />Attack <a href="#" onclick="yt.www.watch.player.seekTo(5*60+31);return false;">5:31</a> (First live performance since 2011)<br />Prison Song <a href="#" onclick="yt.www.watch.player.seekTo(8*60+42);return false;">8:42</a><br />Know <a href="#" onclick="yt.www.watch.player.seekTo(12*60+32);return false;">12:32</a> (First live performance since 2011)<br />Aerials <a href="#" onclick="yt.www.watch.player.seekTo(15*60+32);return false;">15:32</a><br />Soldier Side - Intro <a href="#" onclick="yt.www.watch.player.seekTo(19*60+13);return false;">19:13</a><br />B.Y.O.B. <a href="#" onclick="yt.www.watch.player.seekTo(20*60+09);return false;">20:09</a><br />Soil <a href="#" onclick="yt.www.watch.player.seekTo(24*60+32);return false;">24:32</a><br />Darts <a href="#" onclick="yt.www.watch.player.seekTo(27*60+48);return false;">27:48</a><br />Radio/Video <a href="#" onclick="yt.www.watch.player.seekTo(30*60+38);return false;">30:38</a><br />Hypnotize <a href="#" onclick="yt.www.watch.player.seekTo(35*60+05);return false;">35:05</a><br />Temper <a href="#" onclick="yt.www.watch.player.seekTo(38*60+08);return false;">38:08</a> (First live performance since 1999)<br />CUBErt <a href="#" onclick="yt.www.watch.player.seekTo(41*60+00);return false;">41:00</a><br />Needles <a href="#" onclick="yt.www.watch.player.seekTo(42*60+57);return false;">42:57</a><br />Deer Dance <a href="#" onclick="yt.www.watch.player.seekTo(46*60+27);return false;">46:27</a><br />Bounce <a href="#" onclick="yt.www.watch.player.seekTo(49*60+38);return false;">49:38</a><br />Suggestions <a href="#" onclick="yt.www.watch.player.seekTo(51*60+25);return false;">51:25</a><br />Psycho <a href="#" onclick="yt.www.watch.player.seekTo(53*60+52);return false;">53:52</a><br />Chop Suey! <a href="#" onclick="yt.www.watch.player.seekTo(58*60+13);return false;">58:13</a><br />Lonely Day <a href="#" onclick="yt.www.watch.player.seekTo(1*3600+01*60+15);return false;">1:01:15</a><br />Question! <a href="#" onclick="yt.www.watch.player.seekTo(1*3600+04*60+14);return false;">1:04:14</a><br />Lost in Hollywood <a href="#" onclick="yt.www.watch.player.seekTo(1*3600+08*60+10);return false;">1:08:10</a><br />Vicinity of Obscenity  <a href="#" onclick="yt.www.watch.player.seekTo(1*3600+13*60+40);return false;">1:13:40</a>(First live performance since 2012)<br />Forest <a href="#" onclick="yt.www.watch.player.seekTo(1*3600+16*60+17);return false;">1:16:17</a><br />Cigaro <a href="#" onclick="yt.www.watch.player.seekTo(1*3600+20*60+02);return false;">1:20:02</a><br />Toxicity <a href="#" onclick="yt.www.watch.player.seekTo(1*3600+23*60+57);return false;">1:23:57</a>(with Chino Moreno)<br />Sugar <a href="#" onclick="yt.www.watch.player.seekTo(1*3600+27*60+53);return false;">1:27:53</a>',
-            5640,
-            [{
-                'start_time': 45,
-                'end_time': 266,
-                'title': 'I-E-A-I-A-I-O',
-            }, {
-                'start_time': 266,
-                'end_time': 331,
-                'title': 'Suite-Pee (Incomplete)',
-            }, {
-                'start_time': 331,
-                'end_time': 522,
-                'title': 'Attack (First live performance since 2011)',
-            }, {
-                'start_time': 522,
-                'end_time': 752,
-                'title': 'Prison Song',
-            }, {
-                'start_time': 752,
-                'end_time': 932,
-                'title': 'Know (First live performance since 2011)',
-            }, {
-                'start_time': 932,
-                'end_time': 1153,
-                'title': 'Aerials',
-            }, {
-                'start_time': 1153,
-                'end_time': 1209,
-                'title': 'Soldier Side - Intro',
-            }, {
-                'start_time': 1209,
-                'end_time': 1472,
-                'title': 'B.Y.O.B.',
-            }, {
-                'start_time': 1472,
-                'end_time': 1668,
-                'title': 'Soil',
-            }, {
-                'start_time': 1668,
-                'end_time': 1838,
-                'title': 'Darts',
-            }, {
-                'start_time': 1838,
-                'end_time': 2105,
-                'title': 'Radio/Video',
-            }, {
-                'start_time': 2105,
-                'end_time': 2288,
-                'title': 'Hypnotize',
-            }, {
-                'start_time': 2288,
-                'end_time': 2460,
-                'title': 'Temper (First live performance since 1999)',
-            }, {
-                'start_time': 2460,
-                'end_time': 2577,
-                'title': 'CUBErt',
-            }, {
-                'start_time': 2577,
-                'end_time': 2787,
-                'title': 'Needles',
-            }, {
-                'start_time': 2787,
-                'end_time': 2978,
-                'title': 'Deer Dance',
-            }, {
-                'start_time': 2978,
-                'end_time': 3085,
-                'title': 'Bounce',
-            }, {
-                'start_time': 3085,
-                'end_time': 3232,
-                'title': 'Suggestions',
-            }, {
-                'start_time': 3232,
-                'end_time': 3493,
-                'title': 'Psycho',
-            }, {
-                'start_time': 3493,
-                'end_time': 3675,
-                'title': 'Chop Suey!',
-            }, {
-                'start_time': 3675,
-                'end_time': 3854,
-                'title': 'Lonely Day',
-            }, {
-                'start_time': 3854,
-                'end_time': 4090,
-                'title': 'Question!',
-            }, {
-                'start_time': 4090,
-                'end_time': 4420,
-                'title': 'Lost in Hollywood',
-            }, {
-                'start_time': 4420,
-                'end_time': 4577,
-                'title': 'Vicinity of Obscenity (First live performance since 2012)',
-            }, {
-                'start_time': 4577,
-                'end_time': 4802,
-                'title': 'Forest',
-            }, {
-                'start_time': 4802,
-                'end_time': 5037,
-                'title': 'Cigaro',
-            }, {
-                'start_time': 5037,
-                'end_time': 5273,
-                'title': 'Toxicity (with Chino Moreno)',
-            }, {
-                'start_time': 5273,
-                'end_time': 5640,
-                'title': 'Sugar',
-            }]
-        ),
-        (
-            # https://www.youtube.com/watch?v=PkYLQbsqCE8
-            # pattern: <num> - <title> [<latinized title>] 0:00:00
-            '''Затемно (Zatemno) is an Obscure Black Metal Band from Russia.<br /><br />"Во прах (Vo prakh)'' Into The Ashes", Debut mini-album released may 6, 2016, by Death Knell Productions<br />Released on 6 panel digipak CD, limited to 100 copies only<br />And digital format on Bandcamp<br /><br />Tracklist<br /><br />1 - Во прах [Vo prakh] <a href="#" onclick="yt.www.watch.player.seekTo(0*3600+00*60+00);return false;">0:00:00</a><br />2 - Искупление [Iskupleniye] <a href="#" onclick="yt.www.watch.player.seekTo(0*3600+08*60+10);return false;">0:08:10</a><br />3 - Из серпов луны...[Iz serpov luny] <a href="#" onclick="yt.www.watch.player.seekTo(0*3600+14*60+30);return false;">0:14:30</a><br /><br />Links:<br /><a href="https://deathknellprod.bandcamp.com/album/--2" class="yt-uix-servicelink  " data-target-new-window="True" data-url="https://deathknellprod.bandcamp.com/album/--2" data-servicelink="CC8Q6TgYACITCNP234Kr2dMCFcNxGAodQqsIwSj4HQ" target="_blank" rel="nofollow noopener">https://deathknellprod.bandcamp.com/a...</a><br /><a href="https://www.facebook.com/DeathKnellProd/" class="yt-uix-servicelink  " data-target-new-window="True" data-url="https://www.facebook.com/DeathKnellProd/" data-servicelink="CC8Q6TgYACITCNP234Kr2dMCFcNxGAodQqsIwSj4HQ" target="_blank" rel="nofollow noopener">https://www.facebook.com/DeathKnellProd/</a><br /><br /><br />I don't have any right about this artifact, my only intention is to spread the music of the band, all rights are reserved to the Затемно (Zatemno) and his producers, Death Knell Productions.<br /><br />------------------------------------------------------------------<br /><br />Subscribe for more videos like this.<br />My link: <a href="https://web.facebook.com/AttackOfTheDragons" class="yt-uix-servicelink  " data-target-new-window="True" data-url="https://web.facebook.com/AttackOfTheDragons" data-servicelink="CC8Q6TgYACITCNP234Kr2dMCFcNxGAodQqsIwSj4HQ" target="_blank" rel="nofollow noopener">https://web.facebook.com/AttackOfTheD...</a>''',
-            1138,
-            [{
-                'start_time': 0,
-                'end_time': 490,
-                'title': '1 - Во прах [Vo prakh]',
-            }, {
-                'start_time': 490,
-                'end_time': 870,
-                'title': '2 - Искупление [Iskupleniye]',
-            }, {
-                'start_time': 870,
-                'end_time': 1138,
-                'title': '3 - Из серпов луны...[Iz serpov luny]',
-            }]
-        ),
-        (
-            # https://www.youtube.com/watch?v=xZW70zEasOk
-            # time point more than duration
-            '''● LCS Spring finals: Saturday and Sunday from <a href="#" onclick="yt.www.watch.player.seekTo(13*60+30);return false;">13:30</a> outside the venue! <br />● PAX East: Fri, Sat & Sun - more info in tomorrows video on the main channel!''',
-            283,
-            []
-        ),
-    ]
-
-    def test_youtube_chapters(self):
-        for description, duration, expected_chapters in self._TEST_CASES:
-            ie = YoutubeIE()
-            expect_value(
-                self, ie._extract_chapters_from_description(description, duration),
-                expected_chapters, None)
-
-
-if __name__ == '__main__':
-    unittest.main()

test/test_youtube_signature.py

@@ -86,13 +86,9 @@ class TestPlayerInfo(unittest.TestCase):
             ('https://www.youtube.com/yts/jsbin/player-en_US-vflaxXRn1/base.js', 'vflaxXRn1'),
             ('https://s.ytimg.com/yts/jsbin/html5player-en_US-vflXGBaUN.js', 'vflXGBaUN'),
             ('https://s.ytimg.com/yts/jsbin/html5player-en_US-vflKjOTVq/html5player.js', 'vflKjOTVq'),
-            ('http://s.ytimg.com/yt/swfbin/watch_as3-vflrEm9Nq.swf', 'vflrEm9Nq'),
-            ('https://s.ytimg.com/yts/swfbin/player-vflenCdZL/watch_as3.swf', 'vflenCdZL'),
         )
         for player_url, expected_player_id in PLAYER_URLS:
-            expected_player_type = player_url.split('.')[-1]
-            player_type, player_id = YoutubeIE._extract_player_info(player_url)
-            self.assertEqual(player_type, expected_player_type)
+            player_id = YoutubeIE._extract_player_info(player_url)
             self.assertEqual(player_id, expected_player_id)
 
 

win/ver.txt

@@ -1,45 +0,0 @@
-# UTF-8
-#
-# For more details about fixed file info 'ffi' see:
-# http://msdn.microsoft.com/en-us/library/ms646997.aspx
-VSVersionInfo(
-  ffi=FixedFileInfo(
-    # filevers and prodvers should be always a tuple with four items: (1, 2, 3, 4)
-    # Set not needed items to zero 0.
-    filevers=(16, 9, 2020, 0),
-    prodvers=(16, 9, 2020, 0),
-    # Contains a bitmask that specifies the valid bits 'flags'r
-    mask=0x3f,
-    # Contains a bitmask that specifies the Boolean attributes of the file.
-    flags=0x0,
-    # The operating system for which this file was designed.
-    # 0x4 - NT and there is no need to change it.
-    # OS=0x40004,
-	OS=0x4,
-    # The general type of file.
-    # 0x1 - the file is an application.
-    fileType=0x1,
-    # The function of the file.
-    # 0x0 - the function is not defined for this fileType
-    subtype=0x0,
-    # Creation date and time stamp.
-    date=(0, 0)
-    ),
-  kids=[
-    StringFileInfo(
-      [
-      StringTable(
-        u'040904B0',
-        [StringStruct(u'Comments', u'Youtube-dlc Command Line Interface.'),
-	StringStruct(u'CompanyName', u'theidel@uni-bremen.de'),
-        StringStruct(u'FileDescription', u'Media Downloader'),
-        StringStruct(u'FileVersion', u'16.9.2020.0'),
-        StringStruct(u'InternalName', u'youtube-dlc'),
-        StringStruct(u'LegalCopyright', u'theidel@uni-bremen.de | UNLICENSE'),
-        StringStruct(u'OriginalFilename', u'youtube-dlc.exe'),
-        StringStruct(u'ProductName', u'Youtube-dlc'),
-        StringStruct(u'ProductVersion', u'16.9.2020.0 | git.io/JUGsM')])
-      ]), 
-    VarFileInfo([VarStruct(u'Translation', [0, 1200])])
-  ]
-)

youtube_dlc/YoutubeDL.py

@@ -49,6 +49,7 @@ from .utils import (
     date_from_str,
     DateRange,
     DEFAULT_OUTTMPL,
+    OUTTMPL_TYPES,
     determine_ext,
     determine_protocol,
     DOT_DESKTOP_LINK_TEMPLATE,
@@ -61,6 +62,7 @@ from .utils import (
     ExistingVideoReached,
     expand_path,
     ExtractorError,
+    float_or_none,
     format_bytes,
     format_field,
     formatSeconds,
@@ -69,6 +71,7 @@ from .utils import (
     iri_to_uri,
     ISO3166Utils,
     locked_file,
+    make_dir,
     make_HTTPS_handler,
     MaxDownloadsReached,
     orderedSet,
@@ -90,6 +93,7 @@ from .utils import (
     sanitized_Request,
     std_headers,
     str_or_none,
+    strftime_or_none,
     subtitles_filename,
     to_high_limit_path,
     UnavailableVideoError,
@@ -104,7 +108,7 @@ from .utils import (
     process_communicate_or_kill,
 )
 from .cache import Cache
-from .extractor import get_info_extractor, gen_extractor_classes, _LAZY_LOADER
+from .extractor import get_info_extractor, gen_extractor_classes, _LAZY_LOADER, _PLUGIN_CLASSES
 from .extractor.openload import PhantomJSwrapper
 from .downloader import get_suitable_downloader
 from .downloader.rtmp import rtmpdump_version
@@ -114,8 +118,9 @@ from .postprocessor import (
     FFmpegFixupStretchedPP,
     FFmpegMergerPP,
     FFmpegPostProcessor,
-    FFmpegSubtitlesConvertorPP,
+    # FFmpegSubtitlesConvertorPP,
     get_postprocessor,
+    MoveFilesAfterDownloadPP,
 )
 from .version import __version__
 
@@ -170,18 +175,26 @@ class YoutubeDL(object):
     forcejson:         Force printing info_dict as JSON.
     dump_single_json:  Force printing the info_dict of the whole playlist
                        (or video) as a single JSON line.
-    force_write_download_archive: Force writing download archive regardless of
-                       'skip_download' or 'simulate'.
+    force_write_download_archive: Force writing download archive regardless
+                       of 'skip_download' or 'simulate'.
     simulate:          Do not download the video files.
     format:            Video format code. see "FORMAT SELECTION" for more details.
-    format_sort:       How to sort the video formats. see "Sorting Formats" for more details.
-    format_sort_force: Force the given format_sort. see "Sorting Formats" for more details.
-    allow_multiple_video_streams:   Allow multiple video streams to be merged into a single file
-    allow_multiple_audio_streams:   Allow multiple audio streams to be merged into a single file
-    outtmpl:           Template for output names.
-    restrictfilenames: Do not allow "&" and spaces in file names.
-    trim_file_name:    Limit length of filename (extension excluded).
-    ignoreerrors:      Do not stop on download errors. (Default True when running youtube-dlc, but False when directly accessing YoutubeDL class)
+    format_sort:       How to sort the video formats. see "Sorting Formats"
+                       for more details.
+    format_sort_force: Force the given format_sort. see "Sorting Formats"
+                       for more details.
+    allow_multiple_video_streams:   Allow multiple video streams to be merged
+                       into a single file
+    allow_multiple_audio_streams:   Allow multiple audio streams to be merged
+                       into a single file
+    outtmpl:           Dictionary of templates for output names. Allowed keys
+                       are 'default' and the keys of OUTTMPL_TYPES (in utils.py)
+    outtmpl_na_placeholder: Placeholder for unavailable meta fields.
+    restrictfilenames: Do not allow "&" and spaces in file names
+    trim_file_name:    Limit length of filename (extension excluded)
+    ignoreerrors:      Do not stop on download errors
+                       (Default True when running youtube-dlc,
+                       but False when directly accessing YoutubeDL class)
     force_generic_extractor: Force downloader to use the generic extractor
     overwrites:        Overwrite all video and metadata files if True,
                        overwrite only non-video files if None
@@ -197,8 +210,12 @@ class YoutubeDL(object):
     logtostderr:       Log messages to stderr instead of stdout.
     writedescription:  Write the video description to a .description file
     writeinfojson:     Write the video description to a .info.json file
+    writecomments:     Extract video comments. This will not be written to disk
+                       unless writeinfojson is also given
     writeannotations:  Write the video annotations to a .annotations.xml file
     writethumbnail:    Write the thumbnail image to a file
+    allow_playlist_files: Whether to write playlists' description, infojson etc
+                       also to disk when using the 'write*' options
     write_all_thumbnails:  Write all thumbnail formats to files
     writelink:         Write an internet shortcut file, depending on the
                        current platform (.url/.webloc/.desktop)
@@ -257,6 +274,8 @@ class YoutubeDL(object):
     postprocessors:    A list of dictionaries, each with an entry
                        * key:  The name of the postprocessor. See
                                youtube_dlc/postprocessor/__init__.py for a list.
+                       * _after_move: Optional. If True, run this post_processor
+                               after 'MoveFilesAfterDownload'
                        as well as any further keyword arguments for the
                        postprocessor.
     post_hooks:        A list of functions that get called as the final step
@@ -287,6 +306,9 @@ class YoutubeDL(object):
                        Progress hooks are guaranteed to be called at least once
                        (with status "finished") if the download is successful.
     merge_output_format: Extension to use when merging formats.
+    final_ext:         Expected final extension; used to detect when the file was
+                       already downloaded and converted. "merge_output_format" is
+                       replaced by this extension when given
     fixup:             Automatically correct known faults of the file.
                        One of:
                        - "never": do nothing
@@ -340,7 +362,7 @@ class YoutubeDL(object):
 
     The following options are used by the post processors:
     prefer_ffmpeg:     If False, use avconv instead of ffmpeg if both are available,
-                       otherwise prefer ffmpeg.
+                       otherwise prefer ffmpeg. (avconv support is deprecated)
     ffmpeg_location:   Location of the ffmpeg/avconv binary; either the path
                        to the binary or its containing directory.
     postprocessor_args: A dictionary of postprocessor/executable keys (in lower case)
@@ -368,7 +390,8 @@ class YoutubeDL(object):
 
     params = None
     _ies = []
-    _pps = []
+    _pps = {'beforedl': [], 'aftermove': [], 'normal': []}
+    __prepare_filename_warned = False
     _download_retcode = None
     _num_downloads = None
     _playlist_level = 0
@@ -381,7 +404,8 @@ class YoutubeDL(object):
             params = {}
         self._ies = []
         self._ies_instances = {}
-        self._pps = []
+        self._pps = {'beforedl': [], 'aftermove': [], 'normal': []}
+        self.__prepare_filename_warned = False
         self._post_hooks = []
         self._progress_hooks = []
         self._download_retcode = 0
@@ -427,6 +451,14 @@ class YoutubeDL(object):
             if self.params.get('geo_verification_proxy') is None:
                 self.params['geo_verification_proxy'] = self.params['cn_verification_proxy']
 
+        if self.params.get('final_ext'):
+            if self.params.get('merge_output_format'):
+                self.report_warning('--merge-output-format will be ignored since --remux-video or --recode-video is given')
+            self.params['merge_output_format'] = self.params['final_ext']
+
+        if 'overwrites' in self.params and self.params['overwrites'] is None:
+            del self.params['overwrites']
+
         check_deprecated('autonumber_size', '--autonumber-size', 'output template with %(autonumber)0Nd, where N in the number of digits')
         check_deprecated('autonumber', '--auto-number', '-o "%(autonumber)s-%(title)s.%(ext)s"')
         check_deprecated('usetitle', '--title', '-o "%(title)s-%(id)s.%(ext)s"')
@@ -468,10 +500,7 @@ class YoutubeDL(object):
                 'Set the LC_ALL environment variable to fix this.')
             self.params['restrictfilenames'] = True
 
-        if isinstance(params.get('outtmpl'), bytes):
-            self.report_warning(
-                'Parameter outtmpl is bytes, but should be a unicode string. '
-                'Put  from __future__ import unicode_literals  at the top of your code file or consider switching to Python 3.x.')
+        self.outtmpl_dict = self.parse_outtmpl()
 
         self._setup_opener()
 
@@ -483,8 +512,13 @@ class YoutubeDL(object):
             pp_class = get_postprocessor(pp_def_raw['key'])
             pp_def = dict(pp_def_raw)
             del pp_def['key']
+            if 'when' in pp_def:
+                when = pp_def['when']
+                del pp_def['when']
+            else:
+                when = 'normal'
             pp = pp_class(self, **compat_kwargs(pp_def))
-            self.add_post_processor(pp)
+            self.add_post_processor(pp, when=when)
 
         for ph in self.params.get('post_hooks', []):
             self.add_post_hook(ph)
@@ -536,9 +570,9 @@ class YoutubeDL(object):
         for ie in gen_extractor_classes():
             self.add_info_extractor(ie)
 
-    def add_post_processor(self, pp):
+    def add_post_processor(self, pp, when='normal'):
         """Add a PostProcessor object to the end of the chain."""
-        self._pps.append(pp)
+        self._pps[when].append(pp)
         pp.set_downloader(self)
 
     def add_post_hook(self, ph):
@@ -599,7 +633,7 @@ class YoutubeDL(object):
                 # already of type unicode()
                 ctypes.windll.kernel32.SetConsoleTitleW(ctypes.c_wchar_p(message))
         elif 'TERM' in os.environ:
-            self._write_string('\033[0;%s\007' % message, self._screen_file)
+            self._write_string('\033]0;%s\007' % message, self._screen_file)
 
     def save_console_title(self):
         if not self.params.get('consoletitle', False):
@@ -698,15 +732,33 @@ class YoutubeDL(object):
     def report_file_delete(self, file_name):
         """Report that existing file will be deleted."""
         try:
-            self.to_screen('Deleting already existent file %s' % file_name)
+            self.to_screen('Deleting existing file %s' % file_name)
         except UnicodeEncodeError:
-            self.to_screen('Deleting already existent file')
+            self.to_screen('Deleting existing file')
 
-    def prepare_filename(self, info_dict):
-        """Generate the output filename."""
+    def parse_outtmpl(self):
+        outtmpl_dict = self.params.get('outtmpl', {})
+        if not isinstance(outtmpl_dict, dict):
+            outtmpl_dict = {'default': outtmpl_dict}
+        outtmpl_dict.update({
+            k: v for k, v in DEFAULT_OUTTMPL.items()
+            if not outtmpl_dict.get(k)})
+        for key, val in outtmpl_dict.items():
+            if isinstance(val, bytes):
+                self.report_warning(
+                    'Parameter outtmpl is bytes, but should be a unicode string. '
+                    'Put  from __future__ import unicode_literals  at the top of your code file or consider switching to Python 3.x.')
+        return outtmpl_dict
+
+    def _prepare_filename(self, info_dict, tmpl_type='default'):
         try:
             template_dict = dict(info_dict)
 
+            template_dict['duration_string'] = (  # %(duration>%H-%M-%S)s is wrong if duration > 24hrs
+                formatSeconds(info_dict['duration'], '-')
+                if info_dict.get('duration', None) is not None
+                else None)
+
             template_dict['epoch'] = int(time.time())
             autonumber_size = self.params.get('autonumber_size')
             if autonumber_size is None:
@@ -727,9 +779,11 @@ class YoutubeDL(object):
             template_dict = dict((k, v if isinstance(v, compat_numeric_types) else sanitize(k, v))
                                  for k, v in template_dict.items()
                                  if v is not None and not isinstance(v, (list, tuple, dict)))
-            template_dict = collections.defaultdict(lambda: 'NA', template_dict)
+            na = self.params.get('outtmpl_na_placeholder', 'NA')
+            template_dict = collections.defaultdict(lambda: na, template_dict)
 
-            outtmpl = self.params.get('outtmpl', DEFAULT_OUTTMPL)
+            outtmpl = self.outtmpl_dict.get(tmpl_type, self.outtmpl_dict['default'])
+            force_ext = OUTTMPL_TYPES.get(tmpl_type)
 
             # For fields playlist_index and autonumber convert all occurrences
             # of %(field)s to %(field)0Nd for backward compatibility
@@ -745,27 +799,45 @@ class YoutubeDL(object):
                     r'%%(\1)0%dd' % field_size_compat_map[mobj.group('field')],
                     outtmpl)
 
+            # As of [1] format syntax is:
+            #  %[mapping_key][conversion_flags][minimum_width][.precision][length_modifier]type
+            # 1. https://docs.python.org/2/library/stdtypes.html#string-formatting
+            FORMAT_RE = r'''(?x)
+                (?<!%)
+                %
+                \({0}\)  # mapping key
+                (?:[#0\-+ ]+)?  # conversion flags (optional)
+                (?:\d+)?  # minimum field width (optional)
+                (?:\.\d+)?  # precision (optional)
+                [hlL]?  # length modifier (optional)
+                (?P<type>[diouxXeEfFgGcrs%])  # conversion type
+            '''
+
+            numeric_fields = list(self._NUMERIC_FIELDS)
+
+            # Format date
+            FORMAT_DATE_RE = FORMAT_RE.format(r'(?P<key>(?P<field>\w+)>(?P<format>.+?))')
+            for mobj in re.finditer(FORMAT_DATE_RE, outtmpl):
+                conv_type, field, frmt, key = mobj.group('type', 'field', 'format', 'key')
+                if key in template_dict:
+                    continue
+                value = strftime_or_none(template_dict.get(field), frmt, na)
+                if conv_type in 'crs':  # string
+                    value = sanitize(field, value)
+                else:  # number
+                    numeric_fields.append(key)
+                    value = float_or_none(value, default=None)
+                if value is not None:
+                    template_dict[key] = value
+
             # Missing numeric fields used together with integer presentation types
             # in format specification will break the argument substitution since
-            # string 'NA' is returned for missing fields. We will patch output
-            # template for missing fields to meet string presentation type.
-            for numeric_field in self._NUMERIC_FIELDS:
+            # string NA placeholder is returned for missing fields. We will patch
+            # output template for missing fields to meet string presentation type.
+            for numeric_field in numeric_fields:
                 if numeric_field not in template_dict:
-                    # As of [1] format syntax is:
-                    #  %[mapping_key][conversion_flags][minimum_width][.precision][length_modifier]type
-                    # 1. https://docs.python.org/2/library/stdtypes.html#string-formatting
-                    FORMAT_RE = r'''(?x)
-                        (?<!%)
-                        %
-                        \({0}\)  # mapping key
-                        (?:[#0\-+ ]+)?  # conversion flags (optional)
-                        (?:\d+)?  # minimum field width (optional)
-                        (?:\.\d+)?  # precision (optional)
-                        [hlL]?  # length modifier (optional)
-                        [diouxXeEfFgGcrs%]  # conversion type
-                    '''
                     outtmpl = re.sub(
-                        FORMAT_RE.format(numeric_field),
+                        FORMAT_RE.format(re.escape(numeric_field)),
                         r'%({0})s'.format(numeric_field), outtmpl)
 
             # expand_path translates '%%' into '%' and '$$' into '$'
@@ -781,6 +853,9 @@ class YoutubeDL(object):
             # title "Hello $PATH", we don't want `$PATH` to be expanded.
             filename = expand_path(outtmpl).replace(sep, '') % template_dict
 
+            if force_ext is not None:
+                filename = replace_extension(filename, force_ext, template_dict.get('ext'))
+
             # https://github.com/blackjack4494/youtube-dlc/issues/85
             trim_file_name = self.params.get('trim_file_name', False)
             if trim_file_name:
@@ -796,11 +871,36 @@ class YoutubeDL(object):
             # to workaround encoding issues with subprocess on python2 @ Windows
             if sys.version_info < (3, 0) and sys.platform == 'win32':
                 filename = encodeFilename(filename, True).decode(preferredencoding())
-            return sanitize_path(filename)
+            filename = sanitize_path(filename)
+
+            return filename
         except ValueError as err:
             self.report_error('Error in output template: ' + str(err) + ' (encoding: ' + repr(preferredencoding()) + ')')
             return None
 
+    def prepare_filename(self, info_dict, dir_type='', warn=False):
+        """Generate the output filename."""
+        paths = self.params.get('paths', {})
+        assert isinstance(paths, dict)
+        filename = self._prepare_filename(info_dict, dir_type or 'default')
+
+        if warn and not self.__prepare_filename_warned:
+            if not paths:
+                pass
+            elif filename == '-':
+                self.report_warning('--paths is ignored when an outputting to stdout')
+            elif os.path.isabs(filename):
+                self.report_warning('--paths is ignored since an absolute path is given in output template')
+            self.__prepare_filename_warned = True
+        if filename == '-' or not filename:
+            return filename
+
+        homepath = expand_path(paths.get('home', '').strip())
+        assert isinstance(homepath, compat_str)
+        subdir = expand_path(paths.get(dir_type, '').strip()) if dir_type else ''
+        assert isinstance(subdir, compat_str)
+        return sanitize_path(os.path.join(homepath, subdir, filename))
+
     def _match_entry(self, info_dict, incomplete):
         """ Returns None if the file should be downloaded """
 
@@ -885,16 +985,16 @@ class YoutubeDL(object):
                                     'and will probably not work.')
 
             try:
-                temp_id = ie.extract_id(url) if callable(getattr(ie, 'extract_id', None)) else ie._match_id(url)
+                temp_id = str_or_none(
+                    ie.extract_id(url) if callable(getattr(ie, 'extract_id', None))
+                    else ie._match_id(url))
             except (AssertionError, IndexError, AttributeError):
                 temp_id = None
             if temp_id is not None and self.in_download_archive({'id': temp_id, 'ie_key': ie_key}):
                 self.to_screen("[%s] %s: has already been recorded in archive" % (
                                ie_key, temp_id))
                 break
-
             return self.__extract_info(url, ie, download, extra_info, process, info_dict)
-
         else:
             self.report_error('no suitable InfoExtractor for URL %s' % url)
 
@@ -946,10 +1046,6 @@ class YoutubeDL(object):
         self.add_extra_info(ie_result, {
             'extractor': ie.IE_NAME,
             'webpage_url': url,
-            'duration_string': (
-                formatSeconds(ie_result['duration'], '-')
-                if ie_result.get('duration', None) is not None
-                else None),
             'webpage_url_basename': url_basename(url),
             'extractor_key': ie.ie_key(),
         })
@@ -969,9 +1065,7 @@ class YoutubeDL(object):
             extract_flat = self.params.get('extract_flat', False)
             if ((extract_flat == 'in_playlist' and 'playlist' in extra_info)
                     or extract_flat is True):
-                self.__forced_printings(
-                    ie_result, self.prepare_filename(ie_result),
-                    incomplete=True)
+                self.__forced_printings(ie_result, self.prepare_filename(ie_result), incomplete=True)
                 return ie_result
 
         if result_type == 'video':
@@ -1062,6 +1156,53 @@ class YoutubeDL(object):
         playlist = ie_result.get('title') or ie_result.get('id')
         self.to_screen('[download] Downloading playlist: %s' % playlist)
 
+        if self.params.get('allow_playlist_files', True):
+            ie_copy = {
+                'playlist': playlist,
+                'playlist_id': ie_result.get('id'),
+                'playlist_title': ie_result.get('title'),
+                'playlist_uploader': ie_result.get('uploader'),
+                'playlist_uploader_id': ie_result.get('uploader_id'),
+                'playlist_index': 0
+            }
+            ie_copy.update(dict(ie_result))
+
+            def ensure_dir_exists(path):
+                return make_dir(path, self.report_error)
+
+            if self.params.get('writeinfojson', False):
+                infofn = self.prepare_filename(ie_copy, 'pl_infojson')
+                if not ensure_dir_exists(encodeFilename(infofn)):
+                    return
+                if not self.params.get('overwrites', True) and os.path.exists(encodeFilename(infofn)):
+                    self.to_screen('[info] Playlist metadata is already present')
+                else:
+                    playlist_info = dict(ie_result)
+                    # playlist_info['entries'] = list(playlist_info['entries'])  # Entries is a generator which shouldnot be resolved here
+                    del playlist_info['entries']
+                    self.to_screen('[info] Writing playlist metadata as JSON to: ' + infofn)
+                    try:
+                        write_json_file(self.filter_requested_info(playlist_info), infofn)
+                    except (OSError, IOError):
+                        self.report_error('Cannot write playlist metadata to JSON file ' + infofn)
+
+            if self.params.get('writedescription', False):
+                descfn = self.prepare_filename(ie_copy, 'pl_description')
+                if not ensure_dir_exists(encodeFilename(descfn)):
+                    return
+                if not self.params.get('overwrites', True) and os.path.exists(encodeFilename(descfn)):
+                    self.to_screen('[info] Playlist description is already present')
+                elif ie_result.get('description') is None:
+                    self.report_warning('There\'s no playlist description to write.')
+                else:
+                    try:
+                        self.to_screen('[info] Writing playlist description to: ' + descfn)
+                        with io.open(encodeFilename(descfn), 'w', encoding='utf-8') as descfile:
+                            descfile.write(ie_result['description'])
+                    except (OSError, IOError):
+                        self.report_error('Cannot write playlist description file ' + descfn)
+                        return
+
         playlist_results = []
 
         playliststart = self.params.get('playliststart', 1) - 1
@@ -1246,7 +1387,7 @@ class YoutubeDL(object):
             and (
                 not can_merge()
                 or info_dict.get('is_live', False)
-                or self.params.get('outtmpl', DEFAULT_OUTTMPL) == '-'))
+                or self.outtmpl_dict['default'] == '-'))
 
         return (
             'best/bestvideo+bestaudio'
@@ -1757,7 +1898,7 @@ class YoutubeDL(object):
         if req_format is None:
             req_format = self._default_format_spec(info_dict, download=download)
             if self.params.get('verbose'):
-                self._write_string('[debug] Default format spec: %s\n' % req_format)
+                self.to_screen('[debug] Default format spec: %s' % req_format)
 
         format_selector = self.build_format_selector(req_format)
 
@@ -1888,6 +2029,8 @@ class YoutubeDL(object):
 
         assert info_dict.get('_type', 'video') == 'video'
 
+        info_dict.setdefault('__postprocessors', [])
+
         max_downloads = self.params.get('max_downloads')
         if max_downloads is not None:
             if self._num_downloads >= int(max_downloads):
@@ -1904,10 +2047,15 @@ class YoutubeDL(object):
 
         self._num_downloads += 1
 
-        info_dict['_filename'] = filename = self.prepare_filename(info_dict)
+        info_dict = self.pre_process(info_dict)
+
+        info_dict['_filename'] = full_filename = self.prepare_filename(info_dict, warn=True)
+        temp_filename = self.prepare_filename(info_dict, 'temp')
+        files_to_move = {}
+        skip_dl = self.params.get('skip_download', False)
 
         # Forced printings
-        self.__forced_printings(info_dict, filename, incomplete=False)
+        self.__forced_printings(info_dict, full_filename, incomplete=False)
 
         if self.params.get('simulate', False):
             if self.params.get('force_write_download_archive', False):
@@ -1916,24 +2064,21 @@ class YoutubeDL(object):
             # Do nothing else if in simulate mode
             return
 
-        if filename is None:
+        if full_filename is None:
             return
 
         def ensure_dir_exists(path):
-            try:
-                dn = os.path.dirname(path)
-                if dn and not os.path.exists(dn):
-                    os.makedirs(dn)
-                return True
-            except (OSError, IOError) as err:
-                self.report_error('unable to create directory ' + error_to_compat_str(err))
-                return False
+            return make_dir(path, self.report_error)
 
-        if not ensure_dir_exists(sanitize_path(encodeFilename(filename))):
+        if not ensure_dir_exists(encodeFilename(full_filename)):
+            return
+        if not ensure_dir_exists(encodeFilename(temp_filename)):
             return
 
         if self.params.get('writedescription', False):
-            descfn = replace_extension(filename, 'description', info_dict.get('ext'))
+            descfn = self.prepare_filename(info_dict, 'description')
+            if not ensure_dir_exists(encodeFilename(descfn)):
+                return
             if not self.params.get('overwrites', True) and os.path.exists(encodeFilename(descfn)):
                 self.to_screen('[info] Video description is already present')
             elif info_dict.get('description') is None:
@@ -1948,7 +2093,9 @@ class YoutubeDL(object):
                     return
 
         if self.params.get('writeannotations', False):
-            annofn = replace_extension(filename, 'annotations.xml', info_dict.get('ext'))
+            annofn = self.prepare_filename(info_dict, 'annotation')
+            if not ensure_dir_exists(encodeFilename(annofn)):
+                return
             if not self.params.get('overwrites', True) and os.path.exists(encodeFilename(annofn)):
                 self.to_screen('[info] Video annotations are already present')
             elif not info_dict.get('annotations'):
@@ -1982,9 +2129,14 @@ class YoutubeDL(object):
             # ie = self.get_info_extractor(info_dict['extractor_key'])
             for sub_lang, sub_info in subtitles.items():
                 sub_format = sub_info['ext']
-                sub_filename = subtitles_filename(filename, sub_lang, sub_format, info_dict.get('ext'))
+                sub_fn = self.prepare_filename(info_dict, 'subtitle')
+                sub_filename = subtitles_filename(
+                     temp_filename if not skip_dl else sub_fn,
+                    sub_lang, sub_format, info_dict.get('ext'))
+                sub_filename_final = subtitles_filename(sub_fn, sub_lang, sub_format, info_dict.get('ext'))
                 if not self.params.get('overwrites', True) and os.path.exists(encodeFilename(sub_filename)):
                     self.to_screen('[info] Video subtitle %s.%s is already present' % (sub_lang, sub_format))
+                    files_to_move[sub_filename] = sub_filename_final
                 else:
                     self.to_screen('[info] Writing video subtitles to: ' + sub_filename)
                     if sub_info.get('data') is not None:
@@ -1993,6 +2145,7 @@ class YoutubeDL(object):
                             # See https://github.com/ytdl-org/youtube-dl/issues/10268
                             with io.open(encodeFilename(sub_filename), 'w', encoding='utf-8', newline='') as subfile:
                                 subfile.write(sub_info['data'])
+                            files_to_move[sub_filename] = sub_filename_final
                         except (OSError, IOError):
                             self.report_error('Cannot write subtitles file ' + sub_filename)
                             return
@@ -2008,47 +2161,55 @@ class YoutubeDL(object):
                                 with io.open(encodeFilename(sub_filename), 'wb') as subfile:
                                     subfile.write(sub_data)
                             '''
+                            files_to_move[sub_filename] = sub_filename_final
                         except (ExtractorError, IOError, OSError, ValueError, compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
                             self.report_warning('Unable to download subtitle for "%s": %s' %
                                                 (sub_lang, error_to_compat_str(err)))
                             continue
 
-        if self.params.get('skip_download', False):
+        if skip_dl:
             if self.params.get('convertsubtitles', False):
-                subconv = FFmpegSubtitlesConvertorPP(self, format=self.params.get('convertsubtitles'))
-                filename_real_ext = os.path.splitext(filename)[1][1:]
+                # subconv = FFmpegSubtitlesConvertorPP(self, format=self.params.get('convertsubtitles'))
+                filename_real_ext = os.path.splitext(full_filename)[1][1:]
                 filename_wo_ext = (
-                    os.path.splitext(filename)[0]
+                    os.path.splitext(full_filename)[0]
                     if filename_real_ext == info_dict['ext']
-                    else filename)
+                    else full_filename)
                 afilename = '%s.%s' % (filename_wo_ext, self.params.get('convertsubtitles'))
-                if subconv.available:
-                    info_dict.setdefault('__postprocessors', [])
-                    # info_dict['__postprocessors'].append(subconv)
+                # if subconv.available:
+                #     info_dict['__postprocessors'].append(subconv)
                 if os.path.exists(encodeFilename(afilename)):
                     self.to_screen(
                         '[download] %s has already been downloaded and '
                         'converted' % afilename)
                 else:
                     try:
-                        self.post_process(filename, info_dict)
-                    except (PostProcessingError) as err:
-                        self.report_error('postprocessing: %s' % str(err))
+                        self.post_process(full_filename, info_dict, files_to_move)
+                    except PostProcessingError as err:
+                        self.report_error('Postprocessing: %s' % str(err))
                         return
 
         if self.params.get('writeinfojson', False):
-            infofn = replace_extension(filename, 'info.json', info_dict.get('ext'))
+            infofn = self.prepare_filename(info_dict, 'infojson')
+            if not ensure_dir_exists(encodeFilename(infofn)):
+                return
             if not self.params.get('overwrites', True) and os.path.exists(encodeFilename(infofn)):
-                self.to_screen('[info] Video description metadata is already present')
+                self.to_screen('[info] Video metadata is already present')
             else:
-                self.to_screen('[info] Writing video description metadata as JSON to: ' + infofn)
+                self.to_screen('[info] Writing video metadata as JSON to: ' + infofn)
                 try:
                     write_json_file(self.filter_requested_info(info_dict), infofn)
                 except (OSError, IOError):
-                    self.report_error('Cannot write metadata to JSON file ' + infofn)
+                    self.report_error('Cannot write video metadata to JSON file ' + infofn)
                     return
+            info_dict['__infojson_filename'] = infofn
 
-        self._write_thumbnails(info_dict, filename)
+        thumbfn = self.prepare_filename(info_dict, 'thumbnail')
+        thumb_fn_temp = temp_filename if not skip_dl else thumbfn
+        for thumb_ext in self._write_thumbnails(info_dict, thumb_fn_temp):
+            thumb_filename_temp = replace_extension(thumb_fn_temp, thumb_ext, info_dict.get('ext'))
+            thumb_filename = replace_extension(thumbfn, thumb_ext, info_dict.get('ext'))
+            files_to_move[thumb_filename_temp] = info_dict['__thumbnail_filename'] = thumb_filename
 
         # Write internet shortcut files
         url_link = webloc_link = desktop_link = False
@@ -2073,8 +2234,8 @@ class YoutubeDL(object):
             ascii_url = iri_to_uri(info_dict['webpage_url'])
 
         def _write_link_file(extension, template, newline, embed_filename):
-            linkfn = replace_extension(filename, extension, info_dict.get('ext'))
-            if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(linkfn)):
+            linkfn = replace_extension(full_filename, extension, info_dict.get('ext'))
+            if self.params.get('overwrites', True) and os.path.exists(encodeFilename(linkfn)):
                 self.to_screen('[info] Internet shortcut is already present')
             else:
                 try:
@@ -2101,16 +2262,39 @@ class YoutubeDL(object):
 
         # Download
         must_record_download_archive = False
-        if not self.params.get('skip_download', False):
+        if not skip_dl:
             try:
+
+                def existing_file(*filepaths):
+                    ext = info_dict.get('ext')
+                    final_ext = self.params.get('final_ext', ext)
+                    existing_files = []
+                    for file in orderedSet(filepaths):
+                        if final_ext != ext:
+                            converted = replace_extension(file, final_ext, ext)
+                            if os.path.exists(encodeFilename(converted)):
+                                existing_files.append(converted)
+                        if os.path.exists(encodeFilename(file)):
+                            existing_files.append(file)
+
+                    if not existing_files or self.params.get('overwrites', False):
+                        for file in orderedSet(existing_files):
+                            self.report_file_delete(file)
+                            os.remove(encodeFilename(file))
+                        return None
+
+                    self.report_file_already_downloaded(existing_files[0])
+                    info_dict['ext'] = os.path.splitext(existing_files[0])[1][1:]
+                    return existing_files[0]
+
+                success = True
                 if info_dict.get('requested_formats') is not None:
                     downloaded = []
-                    success = True
                     merger = FFmpegMergerPP(self)
                     if not merger.available:
                         postprocessors = []
                         self.report_warning('You have requested multiple '
-                                            'formats but ffmpeg or avconv are not installed.'
+                                            'formats but ffmpeg is not installed.'
                                             ' The formats won\'t be merged.')
                     else:
                         postprocessors = [merger]
@@ -2134,32 +2318,31 @@ class YoutubeDL(object):
                         # TODO: Check acodec/vcodec
                         return False
 
-                    filename_real_ext = os.path.splitext(filename)[1][1:]
-                    filename_wo_ext = (
-                        os.path.splitext(filename)[0]
-                        if filename_real_ext == info_dict['ext']
-                        else filename)
                     requested_formats = info_dict['requested_formats']
+                    old_ext = info_dict['ext']
                     if self.params.get('merge_output_format') is None and not compatible_formats(requested_formats):
                         info_dict['ext'] = 'mkv'
                         self.report_warning(
                             'Requested formats are incompatible for merge and will be merged into mkv.')
+
+                    def correct_ext(filename):
+                        filename_real_ext = os.path.splitext(filename)[1][1:]
+                        filename_wo_ext = (
+                            os.path.splitext(filename)[0]
+                            if filename_real_ext == old_ext
+                            else filename)
+                        return '%s.%s' % (filename_wo_ext, info_dict['ext'])
+
                     # Ensure filename always has a correct extension for successful merge
-                    filename = '%s.%s' % (filename_wo_ext, info_dict['ext'])
-                    file_exists = os.path.exists(encodeFilename(filename))
-                    if not self.params.get('overwrites', False) and file_exists:
-                        self.to_screen(
-                            '[download] %s has already been downloaded and '
-                            'merged' % filename)
-                    else:
-                        if file_exists:
-                            self.report_file_delete(filename)
-                            os.remove(encodeFilename(filename))
+                    full_filename = correct_ext(full_filename)
+                    temp_filename = correct_ext(temp_filename)
+                    dl_filename = existing_file(full_filename, temp_filename)
+                    if dl_filename is None:
                         for f in requested_formats:
                             new_info = dict(info_dict)
                             new_info.update(f)
                             fname = prepend_extension(
-                                self.prepare_filename(new_info),
+                                self.prepare_filename(new_info, 'temp'),
                                 'f%s' % f['format_id'], new_info['ext'])
                             if not ensure_dir_exists(fname):
                                 return
@@ -2171,14 +2354,15 @@ class YoutubeDL(object):
                         # Even if there were no downloads, it is being merged only now
                         info_dict['__real_download'] = True
                 else:
-                    # Delete existing file with --yes-overwrites
-                    if self.params.get('overwrites', False):
-                        if os.path.exists(encodeFilename(filename)):
-                            self.report_file_delete(filename)
-                            os.remove(encodeFilename(filename))
                     # Just a single file
-                    success, real_download = dl(filename, info_dict)
-                    info_dict['__real_download'] = real_download
+                    dl_filename = existing_file(full_filename, temp_filename)
+                    if dl_filename is None:
+                        success, real_download = dl(temp_filename, info_dict)
+                        info_dict['__real_download'] = real_download
+
+                dl_filename = dl_filename or temp_filename
+                info_dict['__finaldir'] = os.path.dirname(os.path.abspath(encodeFilename(full_filename)))
+
             except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
                 self.report_error('unable to download video data: %s' % error_to_compat_str(err))
                 return
@@ -2188,13 +2372,13 @@ class YoutubeDL(object):
                 self.report_error('content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded))
                 return
 
-            if success and filename != '-':
+            if success and full_filename != '-':
                 # Fixup content
                 fixup_policy = self.params.get('fixup')
                 if fixup_policy is None:
                     fixup_policy = 'detect_or_warn'
 
-                INSTALL_FFMPEG_MESSAGE = 'Install ffmpeg or avconv to fix this automatically.'
+                INSTALL_FFMPEG_MESSAGE = 'Install ffmpeg to fix this automatically.'
 
                 stretched_ratio = info_dict.get('stretched_ratio')
                 if stretched_ratio is not None and stretched_ratio != 1:
@@ -2204,7 +2388,6 @@ class YoutubeDL(object):
                     elif fixup_policy == 'detect_or_warn':
                         stretched_pp = FFmpegFixupStretchedPP(self)
                         if stretched_pp.available:
-                            info_dict.setdefault('__postprocessors', [])
                             info_dict['__postprocessors'].append(stretched_pp)
                         else:
                             self.report_warning(
@@ -2214,7 +2397,8 @@ class YoutubeDL(object):
                         assert fixup_policy in ('ignore', 'never')
 
                 if (info_dict.get('requested_formats') is None
-                        and info_dict.get('container') == 'm4a_dash'):
+                        and info_dict.get('container') == 'm4a_dash'
+                        and info_dict.get('ext') == 'm4a'):
                     if fixup_policy == 'warn':
                         self.report_warning(
                             '%s: writing DASH m4a. '
@@ -2223,7 +2407,6 @@ class YoutubeDL(object):
                     elif fixup_policy == 'detect_or_warn':
                         fixup_pp = FFmpegFixupM4aPP(self)
                         if fixup_pp.available:
-                            info_dict.setdefault('__postprocessors', [])
                             info_dict['__postprocessors'].append(fixup_pp)
                         else:
                             self.report_warning(
@@ -2242,7 +2425,6 @@ class YoutubeDL(object):
                     elif fixup_policy == 'detect_or_warn':
                         fixup_pp = FFmpegFixupM3u8PP(self)
                         if fixup_pp.available:
-                            info_dict.setdefault('__postprocessors', [])
                             info_dict['__postprocessors'].append(fixup_pp)
                         else:
                             self.report_warning(
@@ -2252,13 +2434,13 @@ class YoutubeDL(object):
                         assert fixup_policy in ('ignore', 'never')
 
                 try:
-                    self.post_process(filename, info_dict)
-                except (PostProcessingError) as err:
-                    self.report_error('postprocessing: %s' % str(err))
+                    self.post_process(dl_filename, info_dict, files_to_move)
+                except PostProcessingError as err:
+                    self.report_error('Postprocessing: %s' % str(err))
                     return
                 try:
                     for ph in self._post_hooks:
-                        ph(filename)
+                        ph(full_filename)
                 except Exception as err:
                     self.report_error('post hooks: %s' % str(err))
                     return
@@ -2272,7 +2454,7 @@ class YoutubeDL(object):
 
     def download(self, url_list):
         """Download a given list of URLs."""
-        outtmpl = self.params.get('outtmpl', DEFAULT_OUTTMPL)
+        outtmpl = self.outtmpl_dict['default']
         if (len(url_list) > 1
                 and outtmpl != '-'
                 and '%' not in outtmpl
@@ -2320,31 +2502,48 @@ class YoutubeDL(object):
 
     @staticmethod
     def filter_requested_info(info_dict):
+        fields_to_remove = ('requested_formats', 'requested_subtitles')
         return dict(
             (k, v) for k, v in info_dict.items()
-            if k not in ['requested_formats', 'requested_subtitles'])
+            if (k[0] != '_' or k == '_type') and k not in fields_to_remove)
 
-    def post_process(self, filename, ie_info):
+    def run_pp(self, pp, infodict, files_to_move={}):
+        files_to_delete = []
+        files_to_delete, infodict = pp.run(infodict)
+        if not files_to_delete:
+            return files_to_move, infodict
+
+        if self.params.get('keepvideo', False):
+            for f in files_to_delete:
+                files_to_move.setdefault(f, '')
+        else:
+            for old_filename in set(files_to_delete):
+                self.to_screen('Deleting original file %s (pass -k to keep)' % old_filename)
+                try:
+                    os.remove(encodeFilename(old_filename))
+                except (IOError, OSError):
+                    self.report_warning('Unable to remove downloaded original file')
+                if old_filename in files_to_move:
+                    del files_to_move[old_filename]
+        return files_to_move, infodict
+
+    def pre_process(self, ie_info):
+        info = dict(ie_info)
+        for pp in self._pps['beforedl']:
+            info = self.run_pp(pp, info)[1]
+        return info
+
+    def post_process(self, filename, ie_info, files_to_move={}):
         """Run all the postprocessors on the given file."""
         info = dict(ie_info)
         info['filepath'] = filename
-        pps_chain = []
-        if ie_info.get('__postprocessors') is not None:
-            pps_chain.extend(ie_info['__postprocessors'])
-        pps_chain.extend(self._pps)
-        for pp in pps_chain:
-            files_to_delete = []
-            try:
-                files_to_delete, info = pp.run(info)
-            except PostProcessingError as e:
-                self.report_error(e.msg)
-            if files_to_delete and not self.params.get('keepvideo', False):
-                for old_filename in set(files_to_delete):
-                    self.to_screen('Deleting original file %s (pass -k to keep)' % old_filename)
-                    try:
-                        os.remove(encodeFilename(old_filename))
-                    except (IOError, OSError):
-                        self.report_warning('Unable to remove downloaded original file')
+        info['__files_to_move'] = {}
+
+        for pp in ie_info.get('__postprocessors', []) + self._pps['normal']:
+            files_to_move, info = self.run_pp(pp, info, files_to_move)
+        info = self.run_pp(MoveFilesAfterDownloadPP(self, files_to_move), info)[1]
+        for pp in self._pps['aftermove']:
+            info = self.run_pp(pp, info, {})[1]
 
     def _make_archive_id(self, info_dict):
         video_id = info_dict.get('id')
@@ -2364,7 +2563,7 @@ class YoutubeDL(object):
                     break
             else:
                 return
-        return extractor.lower() + ' ' + video_id
+        return '%s %s' % (extractor.lower(), video_id)
 
     def in_download_archive(self, info_dict):
         fn = self.params.get('download_archive')
@@ -2565,9 +2764,12 @@ class YoutubeDL(object):
                 self.get_encoding()))
         write_string(encoding_str, encoding=None)
 
-        self._write_string('[debug] yt-dlp version ' + __version__ + '\n')
+        self._write_string('[debug] yt-dlp version %s\n' % __version__)
         if _LAZY_LOADER:
-            self._write_string('[debug] Lazy loading extractors enabled' + '\n')
+            self._write_string('[debug] Lazy loading extractors enabled\n')
+        if _PLUGIN_CLASSES:
+            self._write_string(
+                '[debug] Plugin Extractors: %s\n' % [ie.ie_key() for ie in _PLUGIN_CLASSES])
         try:
             sp = subprocess.Popen(
                 ['git', 'rev-parse', '--short', 'HEAD'],
@@ -2576,7 +2778,7 @@ class YoutubeDL(object):
             out, err = process_communicate_or_kill(sp)
             out = out.decode().strip()
             if re.match('[0-9a-f]+', out):
-                self._write_string('[debug] Git HEAD: ' + out + '\n')
+                self._write_string('[debug] Git HEAD: %s\n' % out)
         except Exception:
             try:
                 sys.exc_clear()
@@ -2692,27 +2894,25 @@ class YoutubeDL(object):
             encoding = preferredencoding()
         return encoding
 
-    def _write_thumbnails(self, info_dict, filename):
+    def _write_thumbnails(self, info_dict, filename):  # return the extensions
         if self.params.get('writethumbnail', False):
             thumbnails = info_dict.get('thumbnails')
             if thumbnails:
                 thumbnails = [thumbnails[-1]]
         elif self.params.get('write_all_thumbnails', False):
-            thumbnails = info_dict.get('thumbnails')
+            thumbnails = info_dict.get('thumbnails') or []
         else:
-            return
-
-        if not thumbnails:
-            # No thumbnails present, so return immediately
-            return
+            thumbnails = []
 
+        ret = []
         for t in thumbnails:
             thumb_ext = determine_ext(t['url'], 'jpg')
-            suffix = '_%s' % t['id'] if len(thumbnails) > 1 else ''
+            suffix = '%s.' % t['id'] if len(thumbnails) > 1 else ''
             thumb_display_id = '%s ' % t['id'] if len(thumbnails) > 1 else ''
-            t['filename'] = thumb_filename = replace_extension(filename + suffix, thumb_ext, info_dict.get('ext'))
+            t['filename'] = thumb_filename = replace_extension(filename, suffix + thumb_ext, info_dict.get('ext'))
 
             if not self.params.get('overwrites', True) and os.path.exists(encodeFilename(thumb_filename)):
+                ret.append(suffix + thumb_ext)
                 self.to_screen('[%s] %s: Thumbnail %sis already present' %
                                (info_dict['extractor'], info_dict['id'], thumb_display_id))
             else:
@@ -2722,8 +2922,10 @@ class YoutubeDL(object):
                     uf = self.urlopen(t['url'])
                     with open(encodeFilename(thumb_filename), 'wb') as thumbf:
                         shutil.copyfileobj(uf, thumbf)
+                    ret.append(suffix + thumb_ext)
                     self.to_screen('[%s] %s: Writing thumbnail %sto: %s' %
                                    (info_dict['extractor'], info_dict['id'], thumb_display_id, thumb_filename))
                 except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
                     self.report_warning('Unable to download thumbnail "%s": %s' %
                                         (t['url'], error_to_compat_str(err)))
+        return ret

youtube_dlc/__init__.py

@@ -15,10 +15,10 @@ import sys
 
 from .options import (
     parseOpts,
+    _remux_formats,
 )
 from .compat import (
     compat_getpass,
-    compat_shlex_split,
     workaround_optparse_bug9161,
 )
 from .utils import (
@@ -46,6 +46,7 @@ from .downloader import (
 from .extractor import gen_extractors, list_extractors
 from .extractor.common import InfoExtractor
 from .extractor.adobepass import MSO_INFO
+from .postprocessor.metadatafromfield import MetadataFromFieldPP
 from .YoutubeDL import YoutubeDL
 
 
@@ -70,14 +71,7 @@ def _real_main(argv=None):
         std_headers['Referer'] = opts.referer
 
     # Custom HTTP headers
-    if opts.headers is not None:
-        for h in opts.headers:
-            if ':' not in h:
-                parser.error('wrong header formatting, it should be key:value, not "%s"' % h)
-            key, value = h.split(':', 1)
-            if opts.verbose:
-                write_string('[debug] Adding header from command line option %s:%s\n' % (key, value))
-            std_headers[key] = value
+    std_headers.update(opts.headers)
 
     # Dump user agent
     if opts.dump_user_agent:
@@ -216,12 +210,15 @@ def _real_main(argv=None):
         opts.audioquality = opts.audioquality.strip('k').strip('K')
         if not opts.audioquality.isdigit():
             parser.error('invalid audio quality specified')
-    if opts.remuxvideo is not None:
-        if opts.remuxvideo not in ['mp4', 'mkv']:
-            parser.error('invalid video container format specified')
     if opts.recodevideo is not None:
-        if opts.recodevideo not in ['mp4', 'flv', 'webm', 'ogg', 'mkv', 'avi']:
+        if opts.recodevideo not in _remux_formats:
             parser.error('invalid video recode format specified')
+    if opts.remuxvideo and opts.recodevideo:
+        opts.remuxvideo = None
+        write_string('WARNING: --remux-video is ignored since --recode-video was given\n', out=sys.stderr)
+    if opts.remuxvideo is not None:
+        if opts.remuxvideo not in _remux_formats:
+            parser.error('invalid video remux format specified')
     if opts.convertsubtitles is not None:
         if opts.convertsubtitles not in ['srt', 'vtt', 'ass', 'lrc']:
             parser.error('invalid subtitle format specified')
@@ -240,32 +237,45 @@ def _real_main(argv=None):
     if opts.allsubtitles and not opts.writeautomaticsub:
         opts.writesubtitles = True
 
-    outtmpl = ((opts.outtmpl is not None and opts.outtmpl)
-               or (opts.format == '-1' and opts.usetitle and '%(title)s-%(id)s-%(format)s.%(ext)s')
-               or (opts.format == '-1' and '%(id)s-%(format)s.%(ext)s')
-               or (opts.usetitle and opts.autonumber and '%(autonumber)s-%(title)s-%(id)s.%(ext)s')
-               or (opts.usetitle and '%(title)s-%(id)s.%(ext)s')
-               or (opts.useid and '%(id)s.%(ext)s')
-               or (opts.autonumber and '%(autonumber)s-%(id)s.%(ext)s')
-               or DEFAULT_OUTTMPL)
-    if not os.path.splitext(outtmpl)[1] and opts.extractaudio:
+    outtmpl = opts.outtmpl
+    if not outtmpl:
+        outtmpl = {'default': (
+            '%(title)s-%(id)s-%(format)s.%(ext)s' if opts.format == '-1' and opts.usetitle
+            else '%(id)s-%(format)s.%(ext)s' if opts.format == '-1'
+            else '%(autonumber)s-%(title)s-%(id)s.%(ext)s' if opts.usetitle and opts.autonumber
+            else '%(title)s-%(id)s.%(ext)s' if opts.usetitle
+            else '%(id)s.%(ext)s' if opts.useid
+            else '%(autonumber)s-%(id)s.%(ext)s' if opts.autonumber
+            else None)}
+    outtmpl_default = outtmpl.get('default')
+    if outtmpl_default is not None and not os.path.splitext(outtmpl_default)[1] and opts.extractaudio:
         parser.error('Cannot download a video and extract audio into the same'
                      ' file! Use "{0}.%(ext)s" instead of "{0}" as the output'
-                     ' template'.format(outtmpl))
+                     ' template'.format(outtmpl_default))
+
     for f in opts.format_sort:
         if re.match(InfoExtractor.FormatSort.regex, f) is None:
             parser.error('invalid format sort string "%s" specified' % f)
 
+    if opts.metafromfield is None:
+        opts.metafromfield = []
+    if opts.metafromtitle is not None:
+        opts.metafromfield.append('title:%s' % opts.metafromtitle)
+    for f in opts.metafromfield:
+        if re.match(MetadataFromFieldPP.regex, f) is None:
+            parser.error('invalid format string "%s" specified for --parse-metadata' % f)
+
     any_getting = opts.geturl or opts.gettitle or opts.getid or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat or opts.getduration or opts.dumpjson or opts.dump_single_json
     any_printing = opts.print_json
     download_archive_fn = expand_path(opts.download_archive) if opts.download_archive is not None else opts.download_archive
 
     # PostProcessors
     postprocessors = []
-    if opts.metafromtitle:
+    if opts.metafromfield:
         postprocessors.append({
-            'key': 'MetadataFromTitle',
-            'titleformat': opts.metafromtitle
+            'key': 'MetadataFromField',
+            'formats': opts.metafromfield,
+            'when': 'beforedl'
         })
     if opts.extractaudio:
         postprocessors.append({
@@ -326,32 +336,24 @@ def _real_main(argv=None):
             'force': opts.sponskrub_force,
             'ignoreerror': opts.sponskrub is None,
         })
-    # Please keep ExecAfterDownload towards the bottom as it allows the user to modify the final file in any way.
-    # So if the user is able to remove the file before your postprocessor runs it might cause a few problems.
+    # ExecAfterDownload must be the last PP
     if opts.exec_cmd:
         postprocessors.append({
             'key': 'ExecAfterDownload',
             'exec_cmd': opts.exec_cmd,
+            'when': 'aftermove'
         })
-    external_downloader_args = None
-    if opts.external_downloader_args:
-        external_downloader_args = compat_shlex_split(opts.external_downloader_args)
 
-    postprocessor_args = {}
-    if opts.postprocessor_args is not None:
-        for string in opts.postprocessor_args:
-            mobj = re.match(r'(?P<pp>\w+(?:\+\w+)?):(?P<args>.*)$', string)
-            if mobj is None:
-                if 'sponskrub' not in postprocessor_args:  # for backward compatibility
-                    postprocessor_args['sponskrub'] = []
-                    if opts.verbose:
-                        write_string('[debug] Adding postprocessor args from command line option sponskrub: \n')
-                pp_key, pp_args = 'default', string
-            else:
-                pp_key, pp_args = mobj.group('pp').lower(), mobj.group('args')
-            if opts.verbose:
-                write_string('[debug] Adding postprocessor args from command line option %s: %s\n' % (pp_key, pp_args))
-            postprocessor_args[pp_key] = compat_shlex_split(pp_args)
+    _args_compat_warning = 'WARNING: %s given without specifying name. The arguments will be given to all %s\n'
+    if 'default' in opts.external_downloader_args:
+        write_string(_args_compat_warning % ('--external-downloader-args', 'external downloaders'), out=sys.stderr),
+
+    if 'default-compat' in opts.postprocessor_args and 'default' not in opts.postprocessor_args:
+        write_string(_args_compat_warning % ('--post-processor-args', 'post-processors'), out=sys.stderr),
+        opts.postprocessor_args.setdefault('sponskrub', [])
+        opts.postprocessor_args['default'] = opts.postprocessor_args['default-compat']
+
+    audio_ext = opts.audioformat if (opts.extractaudio and opts.audioformat != 'best') else None
 
     match_filter = (
         None if opts.match_filter is None
@@ -390,6 +392,8 @@ def _real_main(argv=None):
         'listformats': opts.listformats,
         'listformats_table': opts.listformats_table,
         'outtmpl': outtmpl,
+        'outtmpl_na_placeholder': opts.outtmpl_na_placeholder,
+        'paths': opts.paths,
         'autonumber_size': opts.autonumber_size,
         'autonumber_start': opts.autonumber_start,
         'restrictfilenames': opts.restrictfilenames,
@@ -412,13 +416,14 @@ def _real_main(argv=None):
         'playlistreverse': opts.playlist_reverse,
         'playlistrandom': opts.playlist_random,
         'noplaylist': opts.noplaylist,
-        'logtostderr': opts.outtmpl == '-',
+        'logtostderr': outtmpl_default == '-',
         'consoletitle': opts.consoletitle,
         'nopart': opts.nopart,
         'updatetime': opts.updatetime,
         'writedescription': opts.writedescription,
         'writeannotations': opts.writeannotations,
-        'writeinfojson': opts.writeinfojson,
+        'writeinfojson': opts.writeinfojson or opts.getcomments,
+        'getcomments': opts.getcomments,
         'writethumbnail': opts.writethumbnail,
         'write_all_thumbnails': opts.write_all_thumbnails,
         'writelink': opts.writelink,
@@ -469,6 +474,7 @@ def _real_main(argv=None):
         'extract_flat': opts.extract_flat,
         'mark_watched': opts.mark_watched,
         'merge_output_format': opts.merge_output_format,
+        'final_ext': opts.recodevideo or opts.remuxvideo or audio_ext,
         'postprocessors': postprocessors,
         'fixup': opts.fixup,
         'source_address': opts.source_address,
@@ -485,8 +491,8 @@ def _real_main(argv=None):
         'ffmpeg_location': opts.ffmpeg_location,
         'hls_prefer_native': opts.hls_prefer_native,
         'hls_use_mpegts': opts.hls_use_mpegts,
-        'external_downloader_args': external_downloader_args,
-        'postprocessor_args': postprocessor_args,
+        'external_downloader_args': opts.external_downloader_args,
+        'postprocessor_args': opts.postprocessor_args,
         'cn_verification_proxy': opts.cn_verification_proxy,
         'geo_verification_proxy': opts.geo_verification_proxy,
         'config_location': opts.config_location,

youtube_dlc/downloader/common.py

@@ -332,7 +332,7 @@ class FileDownloader(object):
         """
 
         nooverwrites_and_exists = (
-            not self.params.get('overwrites', True)
+            not self.params.get('overwrites', subtitle)
             and os.path.exists(encodeFilename(filename))
         )
 

youtube_dlc/downloader/external.py

@@ -95,7 +95,8 @@ class ExternalFD(FileDownloader):
         return cli_valueless_option(self.params, command_option, param, expected_value)
 
     def _configuration_args(self, default=[]):
-        return cli_configuration_args(self.params, 'external_downloader_args', default)
+        return cli_configuration_args(
+            self.params, 'external_downloader_args', self.get_basename(), default)[0]
 
     def _call_downloader(self, tmpfilename, info_dict):
         """ Either overwrite this or implement _make_cmd """
@@ -232,7 +233,7 @@ class FFmpegFD(ExternalFD):
         url = info_dict['url']
         ffpp = FFmpegPostProcessor(downloader=self)
         if not ffpp.available:
-            self.report_error('m3u8 download detected but ffmpeg or avconv could not be found. Please install one.')
+            self.report_error('m3u8 download detected but ffmpeg could not be found. Please install')
             return False
         ffpp.check_version()
 

youtube_dlc/downloader/youtube_live_chat.py

@@ -4,6 +4,9 @@ import re
 import json
 
 from .fragment import FragmentFD
+from ..compat import compat_urllib_error
+from ..utils import try_get
+from ..extractor.youtube import YoutubeBaseInfoExtractor as YT_BaseIE
 
 
 class YoutubeLiveChatReplayFD(FragmentFD):
@@ -15,6 +18,7 @@ class YoutubeLiveChatReplayFD(FragmentFD):
         video_id = info_dict['video_id']
         self.to_screen('[%s] Downloading live chat' % self.FD_NAME)
 
+        fragment_retries = self.params.get('fragment_retries', 0)
         test = self.params.get('test', False)
 
         ctx = {
@@ -28,15 +32,52 @@ class YoutubeLiveChatReplayFD(FragmentFD):
             return self._download_fragment(ctx, url, info_dict, headers)
 
         def parse_yt_initial_data(data):
-            window_patt = b'window\\["ytInitialData"\\]\\s*=\\s*(.*?)(?<=});'
-            var_patt = b'var\\s+ytInitialData\\s*=\\s*(.*?)(?<=});'
-            for patt in window_patt, var_patt:
+            patterns = (
+                r'%s\\s*%s' % (YT_BaseIE._YT_INITIAL_DATA_RE, YT_BaseIE._YT_INITIAL_BOUNDARY_RE),
+                r'%s' % YT_BaseIE._YT_INITIAL_DATA_RE)
+            data = data.decode('utf-8', 'replace')
+            for patt in patterns:
                 try:
                     raw_json = re.search(patt, data).group(1)
                     return json.loads(raw_json)
                 except AttributeError:
                     continue
 
+        def download_and_parse_fragment(url, frag_index):
+            count = 0
+            while count <= fragment_retries:
+                try:
+                    success, raw_fragment = dl_fragment(url)
+                    if not success:
+                        return False, None, None
+                    data = parse_yt_initial_data(raw_fragment) or json.loads(raw_fragment)['response']
+
+                    live_chat_continuation = try_get(
+                        data,
+                        lambda x: x['continuationContents']['liveChatContinuation'], dict) or {}
+                    offset = continuation_id = None
+                    processed_fragment = bytearray()
+                    for action in live_chat_continuation.get('actions', []):
+                        if 'replayChatItemAction' in action:
+                            replay_chat_item_action = action['replayChatItemAction']
+                            offset = int(replay_chat_item_action['videoOffsetTimeMsec'])
+                        processed_fragment.extend(
+                            json.dumps(action, ensure_ascii=False).encode('utf-8') + b'\n')
+                    if offset is not None:
+                        continuation_id = try_get(
+                            live_chat_continuation,
+                            lambda x: x['continuations'][0]['liveChatReplayContinuationData']['continuation'])
+                    self._append_fragment(ctx, processed_fragment)
+
+                    return True, continuation_id, offset
+                except compat_urllib_error.HTTPError as err:
+                    count += 1
+                    if count <= fragment_retries:
+                        self.report_retry_fragment(err, frag_index, count, fragment_retries)
+            if count > fragment_retries:
+                self.report_error('giving up after %s fragment retries' % fragment_retries)
+                return False, None, None
+
         self._prepare_and_start_frag_download(ctx)
 
         success, raw_fragment = dl_fragment(
@@ -44,54 +85,25 @@ class YoutubeLiveChatReplayFD(FragmentFD):
         if not success:
             return False
         data = parse_yt_initial_data(raw_fragment)
-        continuation_id = data['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation']
+        continuation_id = try_get(
+            data,
+            lambda x: x['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation'])
         # no data yet but required to call _append_fragment
         self._append_fragment(ctx, b'')
 
-        first = True
-        offset = None
+        frag_index = offset = 0
         while continuation_id is not None:
-            data = None
-            if first:
-                url = 'https://www.youtube.com/live_chat_replay?continuation={}'.format(continuation_id)
-                success, raw_fragment = dl_fragment(url)
-                if not success:
-                    return False
-                data = parse_yt_initial_data(raw_fragment)
-            else:
-                url = ('https://www.youtube.com/live_chat_replay/get_live_chat_replay'
-                       + '?continuation={}'.format(continuation_id)
-                       + '&playerOffsetMs={}'.format(max(offset - 5000, 0))
-                       + '&hidden=false'
-                       + '&pbj=1')
-                success, raw_fragment = dl_fragment(url)
-                if not success:
-                    return False
-                data = json.loads(raw_fragment)['response']
-
-            first = False
-            continuation_id = None
-
-            live_chat_continuation = data['continuationContents']['liveChatContinuation']
-            offset = None
-            processed_fragment = bytearray()
-            if 'actions' in live_chat_continuation:
-                for action in live_chat_continuation['actions']:
-                    if 'replayChatItemAction' in action:
-                        replay_chat_item_action = action['replayChatItemAction']
-                        offset = int(replay_chat_item_action['videoOffsetTimeMsec'])
-                    processed_fragment.extend(
-                        json.dumps(action, ensure_ascii=False).encode('utf-8') + b'\n')
-                try:
-                    continuation_id = live_chat_continuation['continuations'][0]['liveChatReplayContinuationData']['continuation']
-                except KeyError:
-                    continuation_id = None
-
-            self._append_fragment(ctx, processed_fragment)
-
-            if test or offset is None:
+            frag_index += 1
+            url = ''.join((
+                'https://www.youtube.com/live_chat_replay',
+                '/get_live_chat_replay' if frag_index > 1 else '',
+                '?continuation=%s' % continuation_id,
+                '&playerOffsetMs=%d&hidden=false&pbj=1' % max(offset - 5000, 0) if frag_index > 1 else ''))
+            success, continuation_id, offset = download_and_parse_fragment(url, frag_index)
+            if not success:
+                return False
+            if test:
                 break
 
         self._finish_frag_download(ctx)
-
         return True

youtube_dlc/extractor/__init__.py

@@ -1,13 +1,20 @@
 from __future__ import unicode_literals
 
+from ..utils import load_plugins
+
 try:
     from .lazy_extractors import *
     from .lazy_extractors import _ALL_CLASSES
     _LAZY_LOADER = True
+    _PLUGIN_CLASSES = []
 except ImportError:
     _LAZY_LOADER = False
+
+if not _LAZY_LOADER:
     from .extractors import *
 
+    _PLUGIN_CLASSES = load_plugins('extractor', 'IE', globals())
+
     _ALL_CLASSES = [
         klass
         for name, klass in globals().items()

youtube_dlc/extractor/abcnews.py

@@ -1,14 +1,15 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import calendar
 import re
-import time
 
 from .amp import AMPIE
 from .common import InfoExtractor
-from .youtube import YoutubeIE
-from ..compat import compat_urlparse
+from ..utils import (
+    parse_duration,
+    parse_iso8601,
+    try_get,
+)
 
 
 class AbcNewsVideoIE(AMPIE):
@@ -18,8 +19,8 @@ class AbcNewsVideoIE(AMPIE):
                         (?:
                             abcnews\.go\.com/
                             (?:
-                                [^/]+/video/(?P<display_id>[0-9a-z-]+)-|
-                                video/embed\?.*?\bid=
+                                (?:[^/]+/)*video/(?P<display_id>[0-9a-z-]+)-|
+                                video/(?:embed|itemfeed)\?.*?\bid=
                             )|
                             fivethirtyeight\.abcnews\.go\.com/video/embed/\d+/
                         )
@@ -36,6 +37,8 @@ class AbcNewsVideoIE(AMPIE):
             'description': 'George Stephanopoulos goes one-on-one with Iranian Foreign Minister Dr. Javad Zarif.',
             'duration': 180,
             'thumbnail': r're:^https?://.*\.jpg$',
+            'timestamp': 1380454200,
+            'upload_date': '20130929',
         },
         'params': {
             # m3u8 download
@@ -47,6 +50,12 @@ class AbcNewsVideoIE(AMPIE):
     }, {
         'url': 'http://abcnews.go.com/2020/video/2020-husband-stands-teacher-jail-student-affairs-26119478',
         'only_matching': True,
+    }, {
+        'url': 'http://abcnews.go.com/video/itemfeed?id=46979033',
+        'only_matching': True,
+    }, {
+        'url': 'https://abcnews.go.com/GMA/News/video/history-christmas-story-67894761',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
@@ -67,28 +76,23 @@ class AbcNewsIE(InfoExtractor):
     _VALID_URL = r'https?://abcnews\.go\.com/(?:[^/]+/)+(?P<display_id>[0-9a-z-]+)/story\?id=(?P<id>\d+)'
 
     _TESTS = [{
-        'url': 'http://abcnews.go.com/Blotter/News/dramatic-video-rare-death-job-america/story?id=10498713#.UIhwosWHLjY',
+        # Youtube Embeds
+        'url': 'https://abcnews.go.com/Entertainment/peter-billingsley-child-actor-christmas-story-hollywood-power/story?id=51286501',
         'info_dict': {
-            'id': '10505354',
-            'ext': 'flv',
-            'display_id': 'dramatic-video-rare-death-job-america',
-            'title': 'Occupational Hazards',
-            'description': 'Nightline investigates the dangers that lurk at various jobs.',
-            'thumbnail': r're:^https?://.*\.jpg$',
-            'upload_date': '20100428',
-            'timestamp': 1272412800,
+            'id': '51286501',
+            'title': "Peter Billingsley: From child actor in 'A Christmas Story' to Hollywood power player",
+            'description': 'Billingsley went from a child actor to Hollywood power player.',
         },
-        'add_ie': ['AbcNewsVideo'],
+        'playlist_count': 5,
     }, {
         'url': 'http://abcnews.go.com/Entertainment/justin-timberlake-performs-stop-feeling-eurovision-2016/story?id=39125818',
         'info_dict': {
             'id': '38897857',
             'ext': 'mp4',
-            'display_id': 'justin-timberlake-performs-stop-feeling-eurovision-2016',
             'title': 'Justin Timberlake Drops Hints For Secret Single',
             'description': 'Lara Spencer reports the buzziest stories of the day in "GMA" Pop News.',
-            'upload_date': '20160515',
-            'timestamp': 1463329500,
+            'upload_date': '20160505',
+            'timestamp': 1462442280,
         },
         'params': {
             # m3u8 download
@@ -100,49 +104,55 @@ class AbcNewsIE(InfoExtractor):
     }, {
         'url': 'http://abcnews.go.com/Technology/exclusive-apple-ceo-tim-cook-iphone-cracking-software/story?id=37173343',
         'only_matching': True,
+    }, {
+        # inline.type == 'video'
+        'url': 'http://abcnews.go.com/Technology/exclusive-apple-ceo-tim-cook-iphone-cracking-software/story?id=37173343',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        display_id = mobj.group('display_id')
-        video_id = mobj.group('id')
+        story_id = self._match_id(url)
+        webpage = self._download_webpage(url, story_id)
+        story = self._parse_json(self._search_regex(
+            r"window\['__abcnews__'\]\s*=\s*({.+?});",
+            webpage, 'data'), story_id)['page']['content']['story']['everscroll'][0]
+        article_contents = story.get('articleContents') or {}
 
-        webpage = self._download_webpage(url, video_id)
-        video_url = self._search_regex(
-            r'window\.abcnvideo\.url\s*=\s*"([^"]+)"', webpage, 'video URL')
-        full_video_url = compat_urlparse.urljoin(url, video_url)
+        def entries():
+            featured_video = story.get('featuredVideo') or {}
+            feed = try_get(featured_video, lambda x: x['video']['feed'])
+            if feed:
+                yield {
+                    '_type': 'url',
+                    'id': featured_video.get('id'),
+                    'title': featured_video.get('name'),
+                    'url': feed,
+                    'thumbnail': featured_video.get('images'),
+                    'description': featured_video.get('description'),
+                    'timestamp': parse_iso8601(featured_video.get('uploadDate')),
+                    'duration': parse_duration(featured_video.get('duration')),
+                    'ie_key': AbcNewsVideoIE.ie_key(),
+                }
 
-        youtube_url = YoutubeIE._extract_url(webpage)
+            for inline in (article_contents.get('inlines') or []):
+                inline_type = inline.get('type')
+                if inline_type == 'iframe':
+                    iframe_url = try_get(inline, lambda x: x['attrs']['src'])
+                    if iframe_url:
+                        yield self.url_result(iframe_url)
+                elif inline_type == 'video':
+                    video_id = inline.get('id')
+                    if video_id:
+                        yield {
+                            '_type': 'url',
+                            'id': video_id,
+                            'url': 'http://abcnews.go.com/video/embed?id=' + video_id,
+                            'thumbnail': inline.get('imgSrc') or inline.get('imgDefault'),
+                            'description': inline.get('description'),
+                            'duration': parse_duration(inline.get('duration')),
+                            'ie_key': AbcNewsVideoIE.ie_key(),
+                        }
 
-        timestamp = None
-        date_str = self._html_search_regex(
-            r'<span[^>]+class="timestamp">([^<]+)</span>',
-            webpage, 'timestamp', fatal=False)
-        if date_str:
-            tz_offset = 0
-            if date_str.endswith(' ET'):  # Eastern Time
-                tz_offset = -5
-                date_str = date_str[:-3]
-            date_formats = ['%b. %d, %Y', '%b %d, %Y, %I:%M %p']
-            for date_format in date_formats:
-                try:
-                    timestamp = calendar.timegm(time.strptime(date_str.strip(), date_format))
-                except ValueError:
-                    continue
-            if timestamp is not None:
-                timestamp -= tz_offset * 3600
-
-        entry = {
-            '_type': 'url_transparent',
-            'ie_key': AbcNewsVideoIE.ie_key(),
-            'url': full_video_url,
-            'id': video_id,
-            'display_id': display_id,
-            'timestamp': timestamp,
-        }
-
-        if youtube_url:
-            entries = [entry, self.url_result(youtube_url, ie=YoutubeIE.ie_key())]
-            return self.playlist_result(entries)
-
-        return entry
+        return self.playlist_result(
+            entries(), story_id, article_contents.get('headline'),
+            article_contents.get('subHead'))

youtube_dlc/extractor/adn.py

@@ -26,6 +26,7 @@ from ..utils import (
     strip_or_none,
     try_get,
     unified_strdate,
+    urlencode_postdata,
 )
 
 
@@ -51,9 +52,12 @@ class ADNIE(InfoExtractor):
         }
     }
 
+    _NETRC_MACHINE = 'animedigitalnetwork'
     _BASE_URL = 'http://animedigitalnetwork.fr'
     _API_BASE_URL = 'https://gw.api.animedigitalnetwork.fr/'
     _PLAYER_BASE_URL = _API_BASE_URL + 'player/'
+    _HEADERS = {}
+    _LOGIN_ERR_MESSAGE = 'Unable to log in'
     _RSA_KEY = (0x9B42B08905199A5CCE2026274399CA560ECB209EE9878A708B1C0812E1BB8CB5D1FB7441861147C1A1F2F3A0476DD63A9CAC20D3E983613346850AA6CB38F16DC7D720FD7D86FC6E5B3D5BBC72E14CD0BF9E869F2CEA2CCAD648F1DCE38F1FF916CEFB2D339B64AA0264372344BC775E265E8A852F88144AB0BD9AA06C1A4ABB, 65537)
     _POS_ALIGN_MAP = {
         'start': 1,
@@ -129,19 +133,42 @@ Format: Marked,Start,End,Style,Name,MarginL,MarginR,MarginV,Effect,Text'''
             }])
         return subtitles
 
+    def _real_initialize(self):
+        username, password = self._get_login_info()
+        if not username:
+            return
+        try:
+            access_token = (self._download_json(
+                self._API_BASE_URL + 'authentication/login', None,
+                'Logging in', self._LOGIN_ERR_MESSAGE, fatal=False,
+                data=urlencode_postdata({
+                    'password': password,
+                    'rememberMe': False,
+                    'source': 'Web',
+                    'username': username,
+                })) or {}).get('accessToken')
+            if access_token:
+                self._HEADERS = {'authorization': 'Bearer ' + access_token}
+        except ExtractorError as e:
+            message = None
+            if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
+                resp = self._parse_json(
+                    e.cause.read().decode(), None, fatal=False) or {}
+                message = resp.get('message') or resp.get('code')
+            self.report_warning(message or self._LOGIN_ERR_MESSAGE)
+
     def _real_extract(self, url):
         video_id = self._match_id(url)
         video_base_url = self._PLAYER_BASE_URL + 'video/%s/' % video_id
         player = self._download_json(
             video_base_url + 'configuration', video_id,
-            'Downloading player config JSON metadata')['player']
+            'Downloading player config JSON metadata',
+            headers=self._HEADERS)['player']
         options = player['options']
 
         user = options['user']
         if not user.get('hasAccess'):
-            raise ExtractorError(
-                'This video is only available for paying users', expected=True)
-            # self.raise_login_required() # FIXME: Login is not implemented
+            self.raise_login_required()
 
         token = self._download_json(
             user.get('refreshTokenUrl') or (self._PLAYER_BASE_URL + 'refresh/token'),
@@ -188,8 +215,7 @@ Format: Marked,Start,End,Style,Name,MarginL,MarginR,MarginV,Effect,Text'''
                 message = error.get('message')
                 if e.cause.code == 403 and error.get('code') == 'player-bad-geolocation-country':
                     self.raise_geo_restricted(msg=message)
-                else:
-                    raise ExtractorError(message)
+                raise ExtractorError(message)
         else:
             raise ExtractorError('Giving up retrying')
 

youtube_dlc/extractor/aenetworks.py

@@ -252,11 +252,11 @@ class AENetworksShowIE(AENetworksListBaseIE):
     _TESTS = [{
         'url': 'http://www.history.com/shows/ancient-aliens',
         'info_dict': {
-            'id': 'SH012427480000',
+            'id': 'SERIES1574',
             'title': 'Ancient Aliens',
             'description': 'md5:3f6d74daf2672ff3ae29ed732e37ea7f',
         },
-        'playlist_mincount': 168,
+        'playlist_mincount': 150,
     }]
     _RESOURCE = 'series'
     _ITEMS_KEY = 'episodes'

youtube_dlc/extractor/aljazeera.py

@@ -1,13 +1,16 @@
 from __future__ import unicode_literals
 
+import json
+import re
+
 from .common import InfoExtractor
 
 
 class AlJazeeraIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?aljazeera\.com/(?:programmes|video)/.*?/(?P<id>[^/]+)\.html'
+    _VALID_URL = r'https?://(?:www\.)?aljazeera\.com/(?P<type>program/[^/]+|(?:feature|video)s)/\d{4}/\d{1,2}/\d{1,2}/(?P<id>[^/?&#]+)'
 
     _TESTS = [{
-        'url': 'http://www.aljazeera.com/programmes/the-slum/2014/08/deliverance-201482883754237240.html',
+        'url': 'https://www.aljazeera.com/program/episode/2014/9/19/deliverance',
         'info_dict': {
             'id': '3792260579001',
             'ext': 'mp4',
@@ -20,14 +23,34 @@ class AlJazeeraIE(InfoExtractor):
         'add_ie': ['BrightcoveNew'],
         'skip': 'Not accessible from Travis CI server',
     }, {
-        'url': 'http://www.aljazeera.com/video/news/2017/05/sierra-leone-709-carat-diamond-auctioned-170511100111930.html',
+        'url': 'https://www.aljazeera.com/videos/2017/5/11/sierra-leone-709-carat-diamond-to-be-auctioned-off',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.aljazeera.com/features/2017/8/21/transforming-pakistans-buses-into-art',
         'only_matching': True,
     }]
-    BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/665003303001/default_default/index.html?videoId=%s'
+    BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/%s/%s_default/index.html?videoId=%s'
 
     def _real_extract(self, url):
-        program_name = self._match_id(url)
-        webpage = self._download_webpage(url, program_name)
-        brightcove_id = self._search_regex(
-            r'RenderPagesVideo\(\'(.+?)\'', webpage, 'brightcove id')
-        return self.url_result(self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id, 'BrightcoveNew', brightcove_id)
+        post_type, name = re.match(self._VALID_URL, url).groups()
+        post_type = {
+            'features': 'post',
+            'program': 'episode',
+            'videos': 'video',
+        }[post_type.split('/')[0]]
+        video = self._download_json(
+            'https://www.aljazeera.com/graphql', name, query={
+                'operationName': 'SingleArticleQuery',
+                'variables': json.dumps({
+                    'name': name,
+                    'postType': post_type,
+                }),
+            }, headers={
+                'wp-site': 'aje',
+            })['data']['article']['video']
+        video_id = video['id']
+        account_id = video.get('accountId') or '665003303001'
+        player_id = video.get('playerId') or 'BkeSH5BDb'
+        return self.url_result(
+            self.BRIGHTCOVE_URL_TEMPLATE % (account_id, player_id, video_id),
+            'BrightcoveNew', video_id)

youtube_dlc/extractor/americastestkitchen.py

@@ -1,13 +1,16 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import json
 import re
 
 from .common import InfoExtractor
 from ..utils import (
     clean_html,
+    int_or_none,
     try_get,
     unified_strdate,
+    unified_timestamp,
 )
 
 
@@ -22,8 +25,8 @@ class AmericasTestKitchenIE(InfoExtractor):
             'ext': 'mp4',
             'description': 'md5:64e606bfee910627efc4b5f050de92b3',
             'thumbnail': r're:^https?://',
-            'timestamp': 1523664000,
-            'upload_date': '20180414',
+            'timestamp': 1523318400,
+            'upload_date': '20180410',
             'release_date': '20180410',
             'series': "America's Test Kitchen",
             'season_number': 18,
@@ -33,6 +36,27 @@ class AmericasTestKitchenIE(InfoExtractor):
         'params': {
             'skip_download': True,
         },
+    }, {
+        # Metadata parsing behaves differently for newer episodes (705) as opposed to older episodes (582 above)
+        'url': 'https://www.americastestkitchen.com/episode/705-simple-chicken-dinner',
+        'md5': '06451608c57651e985a498e69cec17e5',
+        'info_dict': {
+            'id': '5fbe8c61bda2010001c6763b',
+            'title': 'Simple Chicken Dinner',
+            'ext': 'mp4',
+            'description': 'md5:eb68737cc2fd4c26ca7db30139d109e7',
+            'thumbnail': r're:^https?://',
+            'timestamp': 1610755200,
+            'upload_date': '20210116',
+            'release_date': '20210116',
+            'series': "America's Test Kitchen",
+            'season_number': 21,
+            'episode': 'Simple Chicken Dinner',
+            'episode_number': 3,
+        },
+        'params': {
+            'skip_download': True,
+        },
     }, {
         'url': 'https://www.americastestkitchen.com/videos/3420-pan-seared-salmon',
         'only_matching': True,
@@ -60,7 +84,76 @@ class AmericasTestKitchenIE(InfoExtractor):
             'url': 'https://player.zype.com/embed/%s.js?api_key=jZ9GUhRmxcPvX7M3SlfejB6Hle9jyHTdk2jVxG7wOHPLODgncEKVdPYBhuz9iWXQ' % video['zypeId'],
             'ie_key': 'Zype',
             'description': clean_html(video.get('description')),
+            'timestamp': unified_timestamp(video.get('publishDate')),
             'release_date': unified_strdate(video.get('publishDate')),
+            'episode_number': int_or_none(episode.get('number')),
+            'season_number': int_or_none(episode.get('season')),
             'series': try_get(episode, lambda x: x['show']['title']),
             'episode': episode.get('title'),
         }
+
+
+class AmericasTestKitchenSeasonIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?(?P<show>americastestkitchen|cookscountry)\.com/episodes/browse/season_(?P<id>\d+)'
+    _TESTS = [{
+        # ATK Season
+        'url': 'https://www.americastestkitchen.com/episodes/browse/season_1',
+        'info_dict': {
+            'id': 'season_1',
+            'title': 'Season 1',
+        },
+        'playlist_count': 13,
+    }, {
+        # Cooks Country Season
+        'url': 'https://www.cookscountry.com/episodes/browse/season_12',
+        'info_dict': {
+            'id': 'season_12',
+            'title': 'Season 12',
+        },
+        'playlist_count': 13,
+    }]
+
+    def _real_extract(self, url):
+        show_name, season_number = re.match(self._VALID_URL, url).groups()
+        season_number = int(season_number)
+
+        slug = 'atk' if show_name == 'americastestkitchen' else 'cco'
+
+        season = 'Season %d' % season_number
+
+        season_search = self._download_json(
+            'https://y1fnzxui30-dsn.algolia.net/1/indexes/everest_search_%s_season_desc_production' % slug,
+            season, headers={
+                'Origin': 'https://www.%s.com' % show_name,
+                'X-Algolia-API-Key': '8d504d0099ed27c1b73708d22871d805',
+                'X-Algolia-Application-Id': 'Y1FNZXUI30',
+            }, query={
+                'facetFilters': json.dumps([
+                    'search_season_list:' + season,
+                    'search_document_klass:episode',
+                    'search_show_slug:' + slug,
+                ]),
+                'attributesToRetrieve': 'description,search_%s_episode_number,search_document_date,search_url,title' % slug,
+                'attributesToHighlight': '',
+                'hitsPerPage': 1000,
+            })
+
+        def entries():
+            for episode in (season_search.get('hits') or []):
+                search_url = episode.get('search_url')
+                if not search_url:
+                    continue
+                yield {
+                    '_type': 'url',
+                    'url': 'https://www.%s.com%s' % (show_name, search_url),
+                    'id': try_get(episode, lambda e: e['objectID'].split('_')[-1]),
+                    'title': episode.get('title'),
+                    'description': episode.get('description'),
+                    'timestamp': unified_timestamp(episode.get('search_document_date')),
+                    'season_number': season_number,
+                    'episode_number': int_or_none(episode.get('search_%s_episode_number' % slug)),
+                    'ie_key': AmericasTestKitchenIE.ie_key(),
+                }
+
+        return self.playlist_result(
+            entries(), 'season_%d' % season_number, season)

youtube_dlc/extractor/amp.py

@@ -8,6 +8,7 @@ from ..utils import (
     int_or_none,
     mimetype2ext,
     parse_iso8601,
+    unified_timestamp,
     url_or_none,
 )
 
@@ -88,7 +89,7 @@ class AMPIE(InfoExtractor):
 
         self._sort_formats(formats)
 
-        timestamp = parse_iso8601(item.get('pubDate'), ' ') or parse_iso8601(item.get('dc-date'))
+        timestamp = unified_timestamp(item.get('pubDate'), ' ') or parse_iso8601(item.get('dc-date'))
 
         return {
             'id': video_id,

youtube_dlc/extractor/anvato.py

@@ -21,6 +21,16 @@ from ..utils import (
     unsmuggle_url,
 )
 
+# This import causes a ModuleNotFoundError on some systems for unknown reason.
+# See issues:
+# https://github.com/pukkandan/yt-dlp/issues/35
+# https://github.com/ytdl-org/youtube-dl/issues/27449
+# https://github.com/animelover1984/youtube-dl/issues/17
+try:
+    from .anvato_token_generator import NFLTokenGenerator
+except ImportError:
+    NFLTokenGenerator = None
+
 
 def md5_text(s):
     if not isinstance(s, compat_str):
@@ -203,6 +213,10 @@ class AnvatoIE(InfoExtractor):
         'telemundo': 'anvato_mcp_telemundo_web_prod_c5278d51ad46fda4b6ca3d0ea44a7846a054f582'
     }
 
+    _TOKEN_GENERATORS = {
+        'GXvEgwyJeWem8KCYXfeoHWknwP48Mboj': NFLTokenGenerator,
+    }
+
     _API_KEY = '3hwbSuqqT690uxjNYBktSQpa5ZrpYYR0Iofx7NcJHyA'
 
     _ANVP_RE = r'<script[^>]+\bdata-anvp\s*=\s*(["\'])(?P<anvp>(?:(?!\1).)+)\1'
@@ -262,9 +276,12 @@ class AnvatoIE(InfoExtractor):
             'anvrid': anvrid,
             'anvts': server_time,
         }
-        api['anvstk'] = md5_text('%s|%s|%d|%s' % (
-            access_key, anvrid, server_time,
-            self._ANVACK_TABLE.get(access_key, self._API_KEY)))
+        if self._TOKEN_GENERATORS.get(access_key) is not None:
+            api['anvstk2'] = self._TOKEN_GENERATORS[access_key].generate(self, access_key, video_id)
+        else:
+            api['anvstk'] = md5_text('%s|%s|%d|%s' % (
+                access_key, anvrid, server_time,
+                self._ANVACK_TABLE.get(access_key, self._API_KEY)))
 
         return self._download_json(
             video_data_url, video_id, transform_source=strip_jsonp,

youtube_dlc/extractor/aol.py

@@ -3,7 +3,7 @@ from __future__ import unicode_literals
 
 import re
 
-from .common import InfoExtractor
+from .yahoo import YahooIE
 from ..compat import (
     compat_parse_qs,
     compat_urllib_parse_urlparse,
@@ -15,9 +15,9 @@ from ..utils import (
 )
 
 
-class AolIE(InfoExtractor):
+class AolIE(YahooIE):
     IE_NAME = 'aol.com'
-    _VALID_URL = r'(?:aol-video:|https?://(?:www\.)?aol\.(?:com|ca|co\.uk|de|jp)/video/(?:[^/]+/)*)(?P<id>[0-9a-f]+)'
+    _VALID_URL = r'(?:aol-video:|https?://(?:www\.)?aol\.(?:com|ca|co\.uk|de|jp)/video/(?:[^/]+/)*)(?P<id>\d{9}|[0-9a-f]{24}|[0-9a-f]{8}-(?:[0-9a-f]{4}-){3}[0-9a-f]{12})'
 
     _TESTS = [{
         # video with 5min ID
@@ -76,10 +76,16 @@ class AolIE(InfoExtractor):
     }, {
         'url': 'https://www.aol.jp/video/playlist/5a28e936a1334d000137da0c/5a28f3151e642219fde19831/',
         'only_matching': True,
+    }, {
+        # Yahoo video
+        'url': 'https://www.aol.com/video/play/991e6700-ac02-11ea-99ff-357400036f61/24bbc846-3e30-3c46-915e-fe8ccd7fcc46/',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
+        if '-' in video_id:
+            return self._extract_yahoo_video(video_id, 'us')
 
         response = self._download_json(
             'https://feedapi.b2c.on.aol.com/v1.0/app/videos/aolon/%s/details' % video_id,

youtube_dlc/extractor/ard.py

@@ -226,13 +226,13 @@ class ARDMediathekIE(ARDMediathekBaseIE):
             if doc.tag == 'rss':
                 return GenericIE()._extract_rss(url, video_id, doc)
 
-        title = self._html_search_regex(
+        title = self._og_search_title(webpage, default=None) or self._html_search_regex(
             [r'<h1(?:\s+class="boxTopHeadline")?>(.*?)</h1>',
              r'<meta name="dcterms\.title" content="(.*?)"/>',
              r'<h4 class="headline">(.*?)</h4>',
              r'<title[^>]*>(.*?)</title>'],
             webpage, 'title')
-        description = self._html_search_meta(
+        description = self._og_search_description(webpage, default=None) or self._html_search_meta(
             'dcterms.abstract', webpage, 'description', default=None)
         if description is None:
             description = self._html_search_meta(
@@ -289,18 +289,18 @@ class ARDMediathekIE(ARDMediathekBaseIE):
 
 
 class ARDIE(InfoExtractor):
-    _VALID_URL = r'(?P<mainurl>https?://(www\.)?daserste\.de/[^?#]+/videos(?:extern)?/(?P<display_id>[^/?#]+)-(?P<id>[0-9]+))\.html'
+    _VALID_URL = r'(?P<mainurl>https?://(?:www\.)?daserste\.de/[^?#]+/videos(?:extern)?/(?P<display_id>[^/?#]+)-(?:video-?)?(?P<id>[0-9]+))\.html'
     _TESTS = [{
-        # available till 14.02.2019
-        'url': 'http://www.daserste.de/information/talk/maischberger/videos/das-groko-drama-zerlegen-sich-die-volksparteien-video-102.html',
-        'md5': '8e4ec85f31be7c7fc08a26cdbc5a1f49',
+        # available till 7.01.2022
+        'url': 'https://www.daserste.de/information/talk/maischberger/videos/maischberger-die-woche-video100.html',
+        'md5': '867d8aa39eeaf6d76407c5ad1bb0d4c1',
         'info_dict': {
-            'display_id': 'das-groko-drama-zerlegen-sich-die-volksparteien-video',
-            'id': '102',
+            'display_id': 'maischberger-die-woche',
+            'id': '100',
             'ext': 'mp4',
-            'duration': 4435.0,
-            'title': 'Das GroKo-Drama: Zerlegen sich die Volksparteien?',
-            'upload_date': '20180214',
+            'duration': 3687.0,
+            'title': 'maischberger. die woche vom 7. Januar 2021',
+            'upload_date': '20210107',
             'thumbnail': r're:^https?://.*\.jpg$',
         },
     }, {
@@ -355,17 +355,17 @@ class ARDIE(InfoExtractor):
 class ARDBetaMediathekIE(ARDMediathekBaseIE):
     _VALID_URL = r'https://(?:(?:beta|www)\.)?ardmediathek\.de/(?P<client>[^/]+)/(?P<mode>player|live|video|sendung|sammlung)/(?P<display_id>(?:[^/]+/)*)(?P<video_id>[a-zA-Z0-9]+)'
     _TESTS = [{
-        'url': 'https://ardmediathek.de/ard/video/die-robuste-roswita/Y3JpZDovL2Rhc2Vyc3RlLmRlL3RhdG9ydC9mYmM4NGM1NC0xNzU4LTRmZGYtYWFhZS0wYzcyZTIxNGEyMDE',
-        'md5': 'dfdc87d2e7e09d073d5a80770a9ce88f',
+        'url': 'https://www.ardmediathek.de/mdr/video/die-robuste-roswita/Y3JpZDovL21kci5kZS9iZWl0cmFnL2Ntcy84MWMxN2MzZC0wMjkxLTRmMzUtODk4ZS0wYzhlOWQxODE2NGI/',
+        'md5': 'a1dc75a39c61601b980648f7c9f9f71d',
         'info_dict': {
             'display_id': 'die-robuste-roswita',
-            'id': '70153354',
+            'id': '78566716',
             'title': 'Die robuste Roswita',
-            'description': r're:^Der Mord.*trüber ist als die Ilm.',
+            'description': r're:^Der Mord.*totgeglaubte Ehefrau Roswita',
             'duration': 5316,
-            'thumbnail': 'https://img.ardmediathek.de/standard/00/70/15/33/90/-1852531467/16x9/960?mandant=ard',
-            'timestamp': 1577047500,
-            'upload_date': '20191222',
+            'thumbnail': 'https://img.ardmediathek.de/standard/00/78/56/67/84/575672121/16x9/960?mandant=ard',
+            'timestamp': 1596658200,
+            'upload_date': '20200805',
             'ext': 'mp4',
         },
     }, {

youtube_dlc/extractor/audius.py

@@ -0,0 +1,247 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import random
+import re
+
+from .common import InfoExtractor
+from ..utils import ExtractorError, try_get, compat_str, str_or_none
+from ..compat import compat_urllib_parse_unquote
+
+
+class AudiusBaseIE(InfoExtractor):
+    _API_BASE = None
+    _API_V = '/v1'
+
+    def _get_response_data(self, response):
+        if isinstance(response, dict):
+            response_data = response.get('data')
+            if response_data is not None:
+                return response_data
+            if len(response) == 1 and 'message' in response:
+                raise ExtractorError('API error: %s' % response['message'],
+                                     expected=True)
+        raise ExtractorError('Unexpected API response')
+
+    def _select_api_base(self):
+        """Selecting one of the currently available API hosts"""
+        response = super(AudiusBaseIE, self)._download_json(
+            'https://api.audius.co/', None,
+            note='Requesting available API hosts',
+            errnote='Unable to request available API hosts')
+        hosts = self._get_response_data(response)
+        if isinstance(hosts, list):
+            self._API_BASE = random.choice(hosts)
+            return
+        raise ExtractorError('Unable to get available API hosts')
+
+    @staticmethod
+    def _prepare_url(url, title):
+        """
+        Audius removes forward slashes from the uri, but leaves backslashes.
+        The problem is that the current version of Chrome replaces backslashes
+        in the address bar with a forward slashes, so if you copy the link from
+        there and paste it into youtube-dl, you won't be able to download
+        anything from this link, since the Audius API won't be able to resolve
+        this url
+        """
+        url = compat_urllib_parse_unquote(url)
+        title = compat_urllib_parse_unquote(title)
+        if '/' in title or '%2F' in title:
+            fixed_title = title.replace('/', '%5C').replace('%2F', '%5C')
+            return url.replace(title, fixed_title)
+        return url
+
+    def _api_request(self, path, item_id=None, note='Downloading JSON metadata',
+                     errnote='Unable to download JSON metadata',
+                     expected_status=None):
+        if self._API_BASE is None:
+            self._select_api_base()
+        try:
+            response = super(AudiusBaseIE, self)._download_json(
+                '%s%s%s' % (self._API_BASE, self._API_V, path), item_id, note=note,
+                errnote=errnote, expected_status=expected_status)
+        except ExtractorError as exc:
+            # some of Audius API hosts may not work as expected and return HTML
+            if 'Failed to parse JSON' in compat_str(exc):
+                raise ExtractorError('An error occurred while receiving data. Try again',
+                                     expected=True)
+            raise exc
+        return self._get_response_data(response)
+
+    def _resolve_url(self, url, item_id):
+        return self._api_request('/resolve?url=%s' % url, item_id,
+                                 expected_status=404)
+
+
+class AudiusIE(AudiusBaseIE):
+    _VALID_URL = r'''(?x)https?://(?:www\.)?(?:audius\.co/(?P<uploader>[\w\d-]+)(?!/album|/playlist)/(?P<title>\S+))'''
+    IE_DESC = 'Audius.co'
+    _TESTS = [
+        {
+            # URL from Chrome address bar which replace backslash to forward slash
+            'url': 'https://audius.co/test_acc/t%D0%B5%D0%B5%D0%B5est-1.%5E_%7B%7D/%22%3C%3E.%E2%84%96~%60-198631',
+            'md5': '92c35d3e754d5a0f17eef396b0d33582',
+            'info_dict': {
+                'id': 'xd8gY',
+                'title': '''Tеееest/ 1.!@#$%^&*()_+=[]{};'\\\":<>,.?/№~`''',
+                'ext': 'mp3',
+                'description': 'Description',
+                'duration': 30,
+                'track': '''Tеееest/ 1.!@#$%^&*()_+=[]{};'\\\":<>,.?/№~`''',
+                'artist': 'test',
+                'genre': 'Electronic',
+                'thumbnail': r're:https?://.*\.jpg',
+                'view_count': int,
+                'like_count': int,
+                'repost_count': int,
+            }
+        },
+        {
+            # Regular track
+            'url': 'https://audius.co/voltra/radar-103692',
+            'md5': '491898a0a8de39f20c5d6a8a80ab5132',
+            'info_dict': {
+                'id': 'KKdy2',
+                'title': 'RADAR',
+                'ext': 'mp3',
+                'duration': 318,
+                'track': 'RADAR',
+                'artist': 'voltra',
+                'genre': 'Trance',
+                'thumbnail': r're:https?://.*\.jpg',
+                'view_count': int,
+                'like_count': int,
+                'repost_count': int,
+            }
+        },
+    ]
+
+    _ARTWORK_MAP = {
+        "150x150": 150,
+        "480x480": 480,
+        "1000x1000": 1000
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        track_id = try_get(mobj, lambda x: x.group('track_id'))
+        if track_id is None:
+            title = mobj.group('title')
+            # uploader = mobj.group('uploader')
+            url = self._prepare_url(url, title)
+            track_data = self._resolve_url(url, title)
+        else:  # API link
+            title = None
+            # uploader = None
+            track_data = self._api_request('/tracks/%s' % track_id, track_id)
+
+        if not isinstance(track_data, dict):
+            raise ExtractorError('Unexpected API response')
+
+        track_id = track_data.get('id')
+        if track_id is None:
+            raise ExtractorError('Unable to get ID of the track')
+
+        artworks_data = track_data.get('artwork')
+        thumbnails = []
+        if isinstance(artworks_data, dict):
+            for quality_key, thumbnail_url in artworks_data.items():
+                thumbnail = {
+                    "url": thumbnail_url
+                }
+                quality_code = self._ARTWORK_MAP.get(quality_key)
+                if quality_code is not None:
+                    thumbnail['preference'] = quality_code
+                thumbnails.append(thumbnail)
+
+        return {
+            'id': track_id,
+            'title': track_data.get('title', title),
+            'url': '%s/v1/tracks/%s/stream' % (self._API_BASE, track_id),
+            'ext': 'mp3',
+            'description': track_data.get('description'),
+            'duration': track_data.get('duration'),
+            'track': track_data.get('title'),
+            'artist': try_get(track_data, lambda x: x['user']['name'], compat_str),
+            'genre': track_data.get('genre'),
+            'thumbnails': thumbnails,
+            'view_count': track_data.get('play_count'),
+            'like_count': track_data.get('favorite_count'),
+            'repost_count': track_data.get('repost_count'),
+        }
+
+
+class AudiusTrackIE(AudiusIE):
+    _VALID_URL = r'''(?x)(?:audius:)(?:https?://(?:www\.)?.+/v1/tracks/)?(?P<track_id>\w+)'''
+    IE_NAME = 'audius:track'
+    IE_DESC = 'Audius track ID or API link. Prepend with "audius:"'
+    _TESTS = [
+        {
+            'url': 'audius:9RWlo',
+            'only_matching': True
+        },
+        {
+            'url': 'audius:http://discoveryprovider.audius.prod-us-west-2.staked.cloud/v1/tracks/9RWlo',
+            'only_matching': True
+        },
+    ]
+
+
+class AudiusPlaylistIE(AudiusBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?audius\.co/(?P<uploader>[\w\d-]+)/(?:album|playlist)/(?P<title>\S+)'
+    IE_NAME = 'audius:playlist'
+    IE_DESC = 'Audius.co playlists'
+    _TEST = {
+        'url': 'https://audius.co/test_acc/playlist/test-playlist-22910',
+        'info_dict': {
+            'id': 'DNvjN',
+            'title': 'test playlist',
+            'description': 'Test description\n\nlol',
+        },
+        'playlist_count': 175,
+    }
+
+    def _build_playlist(self, tracks):
+        entries = []
+        for track in tracks:
+            if not isinstance(track, dict):
+                raise ExtractorError('Unexpected API response')
+            track_id = str_or_none(track.get('id'))
+            if not track_id:
+                raise ExtractorError('Unable to get track ID from playlist')
+            entries.append(self.url_result(
+                'audius:%s' % track_id,
+                ie=AudiusTrackIE.ie_key(), video_id=track_id))
+        return entries
+
+    def _real_extract(self, url):
+        self._select_api_base()
+        mobj = re.match(self._VALID_URL, url)
+        title = mobj.group('title')
+        # uploader = mobj.group('uploader')
+        url = self._prepare_url(url, title)
+        playlist_response = self._resolve_url(url, title)
+
+        if not isinstance(playlist_response, list) or len(playlist_response) != 1:
+            raise ExtractorError('Unexpected API response')
+
+        playlist_data = playlist_response[0]
+        if not isinstance(playlist_data, dict):
+            raise ExtractorError('Unexpected API response')
+
+        playlist_id = playlist_data.get('id')
+        if playlist_id is None:
+            raise ExtractorError('Unable to get playlist ID')
+
+        playlist_tracks = self._api_request(
+            '/playlists/%s/tracks' % playlist_id,
+            title, note='Downloading playlist tracks metadata',
+            errnote='Unable to download playlist tracks metadata')
+        if not isinstance(playlist_tracks, list):
+            raise ExtractorError('Unexpected API response')
+
+        entries = self._build_playlist(playlist_tracks)
+        return self.playlist_result(entries, playlist_id,
+                                    playlist_data.get('playlist_name', title),
+                                    playlist_data.get('description'))

youtube_dlc/extractor/awaan.py

@@ -48,6 +48,7 @@ class AWAANBaseIE(InfoExtractor):
             'duration': int_or_none(video_data.get('duration')),
             'timestamp': parse_iso8601(video_data.get('create_time'), ' '),
             'is_live': is_live,
+            'uploader_id': video_data.get('user_id'),
         }
 
 
@@ -107,6 +108,7 @@ class AWAANLiveIE(AWAANBaseIE):
             'title': 're:Dubai Al Oula [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
             'upload_date': '20150107',
             'timestamp': 1420588800,
+            'uploader_id': '71',
         },
         'params': {
             # m3u8 download

youtube_dlc/extractor/azmedien.py

@@ -47,7 +47,7 @@ class AZMedienIE(InfoExtractor):
         'url': 'https://www.telebaern.tv/telebaern-news/montag-1-oktober-2018-ganze-sendung-133531189#video=0_7xjo9lf1',
         'only_matching': True
     }]
-    _API_TEMPL = 'https://www.%s/api/pub/gql/%s/NewsArticleTeaser/cb9f2f81ed22e9b47f4ca64ea3cc5a5d13e88d1d'
+    _API_TEMPL = 'https://www.%s/api/pub/gql/%s/NewsArticleTeaser/a4016f65fe62b81dc6664dd9f4910e4ab40383be'
     _PARTNER_ID = '1719221'
 
     def _real_extract(self, url):

youtube_dlc/extractor/bilibili.py

@@ -2,9 +2,10 @@
 from __future__ import unicode_literals
 
 import hashlib
+import json
 import re
 
-from .common import InfoExtractor
+from .common import InfoExtractor, SearchInfoExtractor
 from ..compat import (
     compat_parse_qs,
     compat_urlparse,
@@ -32,13 +33,14 @@ class BiliBiliIE(InfoExtractor):
                             (?:
                                 video/[aA][vV]|
                                 anime/(?P<anime_id>\d+)/play\#
-                            )(?P<id_bv>\d+)|
-                            video/[bB][vV](?P<id>[^/?#&]+)
+                            )(?P<id>\d+)|
+                            video/[bB][vV](?P<id_bv>[^/?#&]+)
                         )
+                        (?:/?\?p=(?P<page>\d+))?
                     '''
 
     _TESTS = [{
-        'url': 'http://www.bilibili.tv/video/av1074402/',
+        'url': 'http://www.bilibili.com/video/av1074402/',
         'md5': '5f7d29e1a2872f3df0cf76b1f87d3788',
         'info_dict': {
             'id': '1074402',
@@ -56,6 +58,10 @@ class BiliBiliIE(InfoExtractor):
         # Tested in BiliBiliBangumiIE
         'url': 'http://bangumi.bilibili.com/anime/1869/play#40062',
         'only_matching': True,
+    }, {
+        # bilibili.tv
+        'url': 'http://www.bilibili.tv/video/av1074402/',
+        'only_matching': True,
     }, {
         'url': 'http://bangumi.bilibili.com/anime/5802/play#100643',
         'md5': '3f721ad1e75030cc06faf73587cfec57',
@@ -124,12 +130,20 @@ class BiliBiliIE(InfoExtractor):
         url, smuggled_data = unsmuggle_url(url, {})
 
         mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id') or mobj.group('id_bv')
+        video_id = mobj.group('id_bv') or mobj.group('id')
+
+        av_id, bv_id = self._get_video_id_set(video_id, mobj.group('id_bv') is not None)
+        video_id = av_id
+
         anime_id = mobj.group('anime_id')
+        page_id = mobj.group('page')
         webpage = self._download_webpage(url, video_id)
 
         if 'anime/' not in url:
             cid = self._search_regex(
+                r'\bcid(?:["\']:|=)(\d+),["\']page(?:["\']:|=)' + str(page_id), webpage, 'cid',
+                default=None
+            ) or self._search_regex(
                 r'\bcid(?:["\']:|=)(\d+)', webpage, 'cid',
                 default=None
             ) or compat_parse_qs(self._search_regex(
@@ -207,9 +221,9 @@ class BiliBiliIE(InfoExtractor):
             break
 
         title = self._html_search_regex(
-            ('<h1[^>]+\btitle=(["\'])(?P<title>(?:(?!\1).)+)\1',
-             '(?s)<h1[^>]*>(?P<title>.+?)</h1>'), webpage, 'title',
-            group='title')
+            (r'<h1[^>]+\btitle=(["\'])(?P<title>(?:(?!\1).)+)\1',
+             r'(?s)<h1[^>]*>(?P<title>.+?)</h1>'), webpage, 'title',
+            group='title') + ('_p' + str(page_id) if page_id is not None else '')
         description = self._html_search_meta('description', webpage)
         timestamp = unified_timestamp(self._html_search_regex(
             r'<time[^>]+datetime="([^"]+)"', webpage, 'upload time',
@@ -219,7 +233,8 @@ class BiliBiliIE(InfoExtractor):
 
         # TODO 'view_count' requires deobfuscating Javascript
         info = {
-            'id': video_id,
+            'id': str(video_id) if page_id is None else '%s_p%s' % (video_id, page_id),
+            'cid': cid,
             'title': title,
             'description': description,
             'timestamp': timestamp,
@@ -235,27 +250,134 @@ class BiliBiliIE(InfoExtractor):
                 'uploader': uploader_mobj.group('name'),
                 'uploader_id': uploader_mobj.group('id'),
             })
+
         if not info.get('uploader'):
             info['uploader'] = self._html_search_meta(
                 'author', webpage, 'uploader', default=None)
 
+        comments = None
+        if self._downloader.params.get('getcomments', False):
+            comments = self._get_all_comment_pages(video_id)
+
+        raw_danmaku = self._get_raw_danmaku(video_id, cid)
+
+        raw_tags = self._get_tags(video_id)
+        tags = list(map(lambda x: x['tag_name'], raw_tags))
+
+        top_level_info = {
+            'raw_danmaku': raw_danmaku,
+            'comments': comments,
+            'comment_count': len(comments) if comments is not None else None,
+            'tags': tags,
+            'raw_tags': raw_tags,
+        }
+
+        '''
+        # Requires https://github.com/m13253/danmaku2ass which is licenced under GPL3
+        # See https://github.com/animelover1984/youtube-dl
+        danmaku = NiconicoIE.CreateDanmaku(raw_danmaku, commentType='Bilibili', x=1024, y=576)
+        entries[0]['subtitles'] = {
+            'danmaku': [{
+                'ext': 'ass',
+                'data': danmaku
+            }]
+        }
+        '''
+
         for entry in entries:
             entry.update(info)
 
         if len(entries) == 1:
+            entries[0].update(top_level_info)
             return entries[0]
         else:
             for idx, entry in enumerate(entries):
                 entry['id'] = '%s_part%d' % (video_id, (idx + 1))
 
-            return {
+            global_info = {
                 '_type': 'multi_video',
                 'id': video_id,
+                'bv_id': bv_id,
                 'title': title,
                 'description': description,
                 'entries': entries,
             }
 
+            global_info.update(info)
+            global_info.update(top_level_info)
+
+            return global_info
+
+    def _get_video_id_set(self, id, is_bv):
+        query = {'bvid': id} if is_bv else {'aid': id}
+        response = self._download_json(
+            "http://api.bilibili.cn/x/web-interface/view",
+            id, query=query,
+            note='Grabbing original ID via API')
+
+        if response['code'] == -400:
+            raise ExtractorError('Video ID does not exist', expected=True, video_id=id)
+        elif response['code'] != 0:
+            raise ExtractorError('Unknown error occurred during API check (code %s)' % response['code'], expected=True, video_id=id)
+        return (response['data']['aid'], response['data']['bvid'])
+
+    # recursive solution to getting every page of comments for the video
+    # we can stop when we reach a page without any comments
+    def _get_all_comment_pages(self, video_id, commentPageNumber=0):
+        comment_url = "https://api.bilibili.com/x/v2/reply?jsonp=jsonp&pn=%s&type=1&oid=%s&sort=2&_=1567227301685" % (commentPageNumber, video_id)
+        json_str = self._download_webpage(
+            comment_url, video_id,
+            note='Extracting comments from page %s' % (commentPageNumber))
+        replies = json.loads(json_str)['data']['replies']
+        if replies is None:
+            return []
+        return self._get_all_children(replies) + self._get_all_comment_pages(video_id, commentPageNumber + 1)
+
+    # extracts all comments in the tree
+    def _get_all_children(self, replies):
+        if replies is None:
+            return []
+
+        ret = []
+        for reply in replies:
+            author = reply['member']['uname']
+            author_id = reply['member']['mid']
+            id = reply['rpid']
+            text = reply['content']['message']
+            timestamp = reply['ctime']
+            parent = reply['parent'] if reply['parent'] != 0 else 'root'
+
+            comment = {
+                "author": author,
+                "author_id": author_id,
+                "id": id,
+                "text": text,
+                "timestamp": timestamp,
+                "parent": parent,
+            }
+            ret.append(comment)
+
+            # from the JSON, the comment structure seems arbitrarily deep, but I could be wrong.
+            # Regardless, this should work.
+            ret += self._get_all_children(reply['replies'])
+
+        return ret
+
+    def _get_raw_danmaku(self, video_id, cid):
+        # This will be useful if I decide to scrape all pages instead of doing them individually
+        # cid_url = "https://www.bilibili.com/widget/getPageList?aid=%s" % (video_id)
+        # cid_str = self._download_webpage(cid_url, video_id, note=False)
+        # cid = json.loads(cid_str)[0]['cid']
+
+        danmaku_url = "https://comment.bilibili.com/%s.xml" % (cid)
+        danmaku = self._download_webpage(danmaku_url, video_id, note='Downloading danmaku comments')
+        return danmaku
+
+    def _get_tags(self, video_id):
+        tags_url = "https://api.bilibili.com/x/tag/archive/tags?aid=%s" % (video_id)
+        tags_json = self._download_json(tags_url, video_id, note='Downloading tags')
+        return tags_json['data']
+
 
 class BiliBiliBangumiIE(InfoExtractor):
     _VALID_URL = r'https?://bangumi\.bilibili\.com/anime/(?P<id>\d+)'
@@ -324,6 +446,73 @@ class BiliBiliBangumiIE(InfoExtractor):
             season_info.get('bangumi_title'), season_info.get('evaluate'))
 
 
+class BilibiliChannelIE(InfoExtractor):
+    _VALID_URL = r'https?://space.bilibili\.com/(?P<id>\d+)'
+    # May need to add support for pagination? Need to find a user with many video uploads to test
+    _API_URL = "https://api.bilibili.com/x/space/arc/search?mid=%s&pn=1&ps=25&jsonp=jsonp"
+    _TEST = {}  # TODO: Add tests
+
+    def _real_extract(self, url):
+        list_id = self._match_id(url)
+        json_str = self._download_webpage(self._API_URL % list_id, "None")
+
+        json_parsed = json.loads(json_str)
+        entries = [{
+            '_type': 'url',
+            'ie_key': BiliBiliIE.ie_key(),
+            'url': ('https://www.bilibili.com/video/%s' %
+                    entry['bvid']),
+            'id': entry['bvid'],
+        } for entry in json_parsed['data']['list']['vlist']]
+
+        return {
+            '_type': 'playlist',
+            'id': list_id,
+            'entries': entries
+        }
+
+
+class BiliBiliSearchIE(SearchInfoExtractor):
+    IE_DESC = 'Bilibili video search, "bilisearch" keyword'
+    _MAX_RESULTS = 100000
+    _SEARCH_KEY = 'bilisearch'
+    MAX_NUMBER_OF_RESULTS = 1000
+
+    def _get_n_results(self, query, n):
+        """Get a specified number of results for a query"""
+
+        entries = []
+        pageNumber = 0
+        while True:
+            pageNumber += 1
+            # FIXME
+            api_url = "https://api.bilibili.com/x/web-interface/search/type?context=&page=%s&order=pubdate&keyword=%s&duration=0&tids_2=&__refresh__=true&search_type=video&tids=0&highlight=1" % (pageNumber, query)
+            json_str = self._download_webpage(
+                api_url, "None", query={"Search_key": query},
+                note='Extracting results from page %s' % pageNumber)
+            data = json.loads(json_str)['data']
+
+            # FIXME: this is hideous
+            if "result" not in data:
+                return {
+                    '_type': 'playlist',
+                    'id': query,
+                    'entries': entries[:n]
+                }
+
+            videos = data['result']
+            for video in videos:
+                e = self.url_result(video['arcurl'], 'BiliBili', str(video['aid']))
+                entries.append(e)
+
+            if(len(entries) >= n or len(videos) >= BiliBiliSearchIE.MAX_NUMBER_OF_RESULTS):
+                return {
+                    '_type': 'playlist',
+                    'id': query,
+                    'entries': entries[:n]
+                }
+
+
 class BilibiliAudioBaseIE(InfoExtractor):
     def _call_api(self, path, sid, query=None):
         if not query:

youtube_dlc/extractor/bleacherreport.py

@@ -90,13 +90,19 @@ class BleacherReportCMSIE(AMPIE):
     _VALID_URL = r'https?://(?:www\.)?bleacherreport\.com/video_embed\?id=(?P<id>[0-9a-f-]{36}|\d{5})'
     _TESTS = [{
         'url': 'http://bleacherreport.com/video_embed?id=8fd44c2f-3dc5-4821-9118-2c825a98c0e1&library=video-cms',
-        'md5': '2e4b0a997f9228ffa31fada5c53d1ed1',
+        'md5': '670b2d73f48549da032861130488c681',
         'info_dict': {
             'id': '8fd44c2f-3dc5-4821-9118-2c825a98c0e1',
-            'ext': 'flv',
+            'ext': 'mp4',
             'title': 'Cena vs. Rollins Would Expose the Heavyweight Division',
             'description': 'md5:984afb4ade2f9c0db35f3267ed88b36e',
+            'upload_date': '20150723',
+            'timestamp': 1437679032,
+
         },
+        'expected_warnings': [
+            'Unable to download f4m manifest'
+        ]
     }]
 
     def _real_extract(self, url):

youtube_dlc/extractor/bravotv.py

@@ -12,7 +12,7 @@ from ..utils import (
 
 
 class BravoTVIE(AdobePassIE):
-    _VALID_URL = r'https?://(?:www\.)?bravotv\.com/(?:[^/]+/)+(?P<id>[^/?#]+)'
+    _VALID_URL = r'https?://(?:www\.)?(?P<req_id>bravotv|oxygen)\.com/(?:[^/]+/)+(?P<id>[^/?#]+)'
     _TESTS = [{
         'url': 'https://www.bravotv.com/top-chef/season-16/episode-15/videos/the-top-chef-season-16-winner-is',
         'md5': 'e34684cfea2a96cd2ee1ef3a60909de9',
@@ -28,10 +28,13 @@ class BravoTVIE(AdobePassIE):
     }, {
         'url': 'http://www.bravotv.com/below-deck/season-3/ep-14-reunion-part-1',
         'only_matching': True,
+    }, {
+        'url': 'https://www.oxygen.com/in-ice-cold-blood/season-2/episode-16/videos/handling-the-horwitz-house-after-the-murder-season-2',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
-        display_id = self._match_id(url)
+        site, display_id = re.match(self._VALID_URL, url).groups()
         webpage = self._download_webpage(url, display_id)
         settings = self._parse_json(self._search_regex(
             r'<script[^>]+data-drupal-selector="drupal-settings-json"[^>]*>({.+?})</script>', webpage, 'drupal settings'),
@@ -53,11 +56,14 @@ class BravoTVIE(AdobePassIE):
                 tp_path = release_pid = tve['release_pid']
             if tve.get('entitlement') == 'auth':
                 adobe_pass = settings.get('tve_adobe_auth', {})
+                if site == 'bravotv':
+                    site = 'bravo'
                 resource = self._get_mvpd_resource(
-                    adobe_pass.get('adobePassResourceId', 'bravo'),
+                    adobe_pass.get('adobePassResourceId') or site,
                     tve['title'], release_pid, tve.get('rating'))
                 query['auth'] = self._extract_mvpd_auth(
-                    url, release_pid, adobe_pass.get('adobePassRequestorId', 'bravo'), resource)
+                    url, release_pid,
+                    adobe_pass.get('adobePassRequestorId') or site, resource)
         else:
             shared_playlist = settings['ls_playlist']
             account_pid = shared_playlist['account_pid']

youtube_dlc/extractor/cbs.py

@@ -59,7 +59,7 @@ class CBSIE(CBSBaseIE):
             'http://can.cbs.com/thunder/player/videoPlayerService.php',
             content_id, query={'partner': site, 'contentId': content_id})
         video_data = xpath_element(items_data, './/item')
-        title = xpath_text(video_data, 'videoTitle', 'title', True)
+        title = xpath_text(video_data, 'videoTitle', 'title') or xpath_text(video_data, 'videotitle', 'title')
         tp_path = 'dJ5BDC/media/guid/%d/%s' % (mpx_acc, content_id)
         tp_release_url = 'http://link.theplatform.com/s/' + tp_path
 

youtube_dlc/extractor/ccma.py

@@ -1,6 +1,7 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import datetime
 import re
 
 from .common import InfoExtractor
@@ -8,8 +9,8 @@ from ..utils import (
     clean_html,
     int_or_none,
     parse_duration,
-    parse_iso8601,
     parse_resolution,
+    try_get,
     url_or_none,
 )
 
@@ -24,8 +25,9 @@ class CCMAIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'L\'espot de La Marató de TV3',
             'description': 'md5:f12987f320e2f6e988e9908e4fe97765',
-            'timestamp': 1470918540,
-            'upload_date': '20160811',
+            'timestamp': 1478608140,
+            'upload_date': '20161108',
+            'age_limit': 0,
         }
     }, {
         'url': 'http://www.ccma.cat/catradio/alacarta/programa/el-consell-de-savis-analitza-el-derbi/audio/943685/',
@@ -35,8 +37,24 @@ class CCMAIE(InfoExtractor):
             'ext': 'mp3',
             'title': 'El Consell de Savis analitza el derbi',
             'description': 'md5:e2a3648145f3241cb9c6b4b624033e53',
-            'upload_date': '20171205',
-            'timestamp': 1512507300,
+            'upload_date': '20170512',
+            'timestamp': 1494622500,
+            'vcodec': 'none',
+            'categories': ['Esports'],
+        }
+    }, {
+        'url': 'http://www.ccma.cat/tv3/alacarta/crims/crims-josep-tallada-lespereu-me-capitol-1/video/6031387/',
+        'md5': 'b43c3d3486f430f3032b5b160d80cbc3',
+        'info_dict': {
+            'id': '6031387',
+            'ext': 'mp4',
+            'title': 'Crims - Josep Talleda, l\'"Espereu-me" (capítol 1)',
+            'description': 'md5:7cbdafb640da9d0d2c0f62bad1e74e60',
+            'timestamp': 1582577700,
+            'upload_date': '20200224',
+            'subtitles': 'mincount:4',
+            'age_limit': 16,
+            'series': 'Crims',
         }
     }]
 
@@ -72,17 +90,27 @@ class CCMAIE(InfoExtractor):
 
         informacio = media['informacio']
         title = informacio['titol']
-        durada = informacio.get('durada', {})
+        durada = informacio.get('durada') or {}
         duration = int_or_none(durada.get('milisegons'), 1000) or parse_duration(durada.get('text'))
-        timestamp = parse_iso8601(informacio.get('data_emissio', {}).get('utc'))
+        tematica = try_get(informacio, lambda x: x['tematica']['text'])
+
+        timestamp = None
+        data_utc = try_get(informacio, lambda x: x['data_emissio']['utc'])
+        try:
+            timestamp = datetime.datetime.strptime(
+                data_utc, '%Y-%d-%mT%H:%M:%S%z').timestamp()
+        except TypeError:
+            pass
 
         subtitles = {}
-        subtitols = media.get('subtitols', {})
-        if subtitols:
-            sub_url = subtitols.get('url')
+        subtitols = media.get('subtitols') or []
+        if isinstance(subtitols, dict):
+            subtitols = [subtitols]
+        for st in subtitols:
+            sub_url = st.get('url')
             if sub_url:
                 subtitles.setdefault(
-                    subtitols.get('iso') or subtitols.get('text') or 'ca', []).append({
+                    st.get('iso') or st.get('text') or 'ca', []).append({
                         'url': sub_url,
                     })
 
@@ -97,6 +125,16 @@ class CCMAIE(InfoExtractor):
                     'height': int_or_none(imatges.get('alcada')),
                 }]
 
+        age_limit = None
+        codi_etic = try_get(informacio, lambda x: x['codi_etic']['id'])
+        if codi_etic:
+            codi_etic_s = codi_etic.split('_')
+            if len(codi_etic_s) == 2:
+                if codi_etic_s[1] == 'TP':
+                    age_limit = 0
+                else:
+                    age_limit = int_or_none(codi_etic_s[1])
+
         return {
             'id': media_id,
             'title': title,
@@ -106,4 +144,9 @@ class CCMAIE(InfoExtractor):
             'thumbnails': thumbnails,
             'subtitles': subtitles,
             'formats': formats,
+            'age_limit': age_limit,
+            'alt_title': informacio.get('titol_complet'),
+            'episode_number': int_or_none(informacio.get('capitol')),
+            'categories': [tematica] if tematica else None,
+            'series': informacio.get('programa'),
         }

youtube_dlc/extractor/cda.py

@@ -96,7 +96,7 @@ class CDAIE(InfoExtractor):
             raise ExtractorError('This video is only available for premium users.', expected=True)
 
         need_confirm_age = False
-        if self._html_search_regex(r'(<form[^>]+action="/a/validatebirth")',
+        if self._html_search_regex(r'(<form[^>]+action="[^"]*/a/validatebirth[^"]*")',
                                    webpage, 'birthday validate form', default=None):
             webpage = self._download_age_confirm_page(
                 url, video_id, note='Confirming age')

youtube_dlc/extractor/comedycentral.py

@@ -1,142 +1,51 @@
 from __future__ import unicode_literals
 
 from .mtv import MTVServicesInfoExtractor
-from .common import InfoExtractor
 
 
 class ComedyCentralIE(MTVServicesInfoExtractor):
-    _VALID_URL = r'''(?x)https?://(?:www\.)?cc\.com/
-        (video-clips|episodes|cc-studios|video-collections|shows(?=/[^/]+/(?!full-episodes)))
-        /(?P<title>.*)'''
+    _VALID_URL = r'https?://(?:www\.)?cc\.com/(?:episodes|video(?:-clips)?)/(?P<id>[0-9a-z]{6})'
     _FEED_URL = 'http://comedycentral.com/feeds/mrss/'
 
     _TESTS = [{
-        'url': 'http://www.cc.com/video-clips/kllhuv/stand-up-greg-fitzsimmons--uncensored---too-good-of-a-mother',
-        'md5': 'c4f48e9eda1b16dd10add0744344b6d8',
+        'url': 'http://www.cc.com/video-clips/5ke9v2/the-daily-show-with-trevor-noah-doc-rivers-and-steve-ballmer---the-nba-player-strike',
+        'md5': 'b8acb347177c680ff18a292aa2166f80',
         'info_dict': {
-            'id': 'cef0cbb3-e776-4bc9-b62e-8016deccb354',
+            'id': '89ccc86e-1b02-4f83-b0c9-1d9592ecd025',
             'ext': 'mp4',
-            'title': 'CC:Stand-Up|August 18, 2013|1|0101|Uncensored - Too Good of a Mother',
-            'description': 'After a certain point, breastfeeding becomes c**kblocking.',
-            'timestamp': 1376798400,
-            'upload_date': '20130818',
+            'title': 'The Daily Show with Trevor Noah|August 28, 2020|25|25149|Doc Rivers and Steve Ballmer - The NBA Player Strike',
+            'description': 'md5:5334307c433892b85f4f5e5ac9ef7498',
+            'timestamp': 1598670000,
+            'upload_date': '20200829',
         },
     }, {
-        'url': 'http://www.cc.com/shows/the-daily-show-with-trevor-noah/interviews/6yx39d/exclusive-rand-paul-extended-interview',
+        'url': 'http://www.cc.com/episodes/pnzzci/drawn-together--american-idol--parody-clip-show-season-3-ep-314',
         'only_matching': True,
-    }]
-
-
-class ComedyCentralFullEpisodesIE(MTVServicesInfoExtractor):
-    _VALID_URL = r'''(?x)https?://(?:www\.)?cc\.com/
-        (?:full-episodes|shows(?=/[^/]+/full-episodes))
-        /(?P<id>[^?]+)'''
-    _FEED_URL = 'http://comedycentral.com/feeds/mrss/'
-
-    _TESTS = [{
-        'url': 'http://www.cc.com/full-episodes/pv391a/the-daily-show-with-trevor-noah-november-28--2016---ryan-speedo-green-season-22-ep-22028',
-        'info_dict': {
-            'description': 'Donald Trump is accused of exploiting his president-elect status for personal gain, Cuban leader Fidel Castro dies, and Ryan Speedo Green discusses "Sing for Your Life."',
-            'title': 'November 28, 2016 - Ryan Speedo Green',
-        },
-        'playlist_count': 4,
     }, {
-        'url': 'http://www.cc.com/shows/the-daily-show-with-trevor-noah/full-episodes',
-        'only_matching': True,
-    }]
-
-    def _real_extract(self, url):
-        playlist_id = self._match_id(url)
-        webpage = self._download_webpage(url, playlist_id)
-        mgid = self._extract_mgid(webpage, url, data_zone='t2_lc_promo1')
-        videos_info = self._get_videos_info(mgid)
-        return videos_info
-
-
-class ToshIE(MTVServicesInfoExtractor):
-    IE_DESC = 'Tosh.0'
-    _VALID_URL = r'^https?://tosh\.cc\.com/video-(?:clips|collections)/[^/]+/(?P<videotitle>[^/?#]+)'
-    _FEED_URL = 'http://tosh.cc.com/feeds/mrss'
-
-    _TESTS = [{
-        'url': 'http://tosh.cc.com/video-clips/68g93d/twitter-users-share-summer-plans',
-        'info_dict': {
-            'description': 'Tosh asked fans to share their summer plans.',
-            'title': 'Twitter Users Share Summer Plans',
-        },
-        'playlist': [{
-            'md5': 'f269e88114c1805bb6d7653fecea9e06',
-            'info_dict': {
-                'id': '90498ec2-ed00-11e0-aca6-0026b9414f30',
-                'ext': 'mp4',
-                'title': 'Tosh.0|June 9, 2077|2|211|Twitter Users Share Summer Plans',
-                'description': 'Tosh asked fans to share their summer plans.',
-                'thumbnail': r're:^https?://.*\.jpg',
-                # It's really reported to be published on year 2077
-                'upload_date': '20770610',
-                'timestamp': 3390510600,
-                'subtitles': {
-                    'en': 'mincount:3',
-                },
-            },
-        }]
-    }, {
-        'url': 'http://tosh.cc.com/video-collections/x2iz7k/just-plain-foul/m5q4fp',
+        'url': 'https://www.cc.com/video/k3sdvm/the-daily-show-with-jon-stewart-exclusive-the-fourth-estate',
         'only_matching': True,
     }]
 
 
 class ComedyCentralTVIE(MTVServicesInfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?comedycentral\.tv/(?:staffeln|shows)/(?P<id>[^/?#&]+)'
+    _VALID_URL = r'https?://(?:www\.)?comedycentral\.tv/folgen/(?P<id>[0-9a-z]{6})'
     _TESTS = [{
-        'url': 'http://www.comedycentral.tv/staffeln/7436-the-mindy-project-staffel-4',
+        'url': 'https://www.comedycentral.tv/folgen/pxdpec/josh-investigates-klimawandel-staffel-1-ep-1',
         'info_dict': {
-            'id': 'local_playlist-f99b626bdfe13568579a',
-            'ext': 'flv',
-            'title': 'Episode_the-mindy-project_shows_season-4_episode-3_full-episode_part1',
+            'id': '15907dc3-ec3c-11e8-a442-0e40cf2fc285',
+            'ext': 'mp4',
+            'title': 'Josh Investigates',
+            'description': 'Steht uns das Ende der Welt bevor?',
         },
-        'params': {
-            # rtmp download
-            'skip_download': True,
-        },
-    }, {
-        'url': 'http://www.comedycentral.tv/shows/1074-workaholics',
-        'only_matching': True,
-    }, {
-        'url': 'http://www.comedycentral.tv/shows/1727-the-mindy-project/bonus',
-        'only_matching': True,
     }]
+    _FEED_URL = 'http://feeds.mtvnservices.com/od/feed/intl-mrss-player-feed'
+    _GEO_COUNTRIES = ['DE']
 
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-
-        webpage = self._download_webpage(url, video_id)
-
-        mrss_url = self._search_regex(
-            r'data-mrss=(["\'])(?P<url>(?:(?!\1).)+)\1',
-            webpage, 'mrss url', group='url')
-
-        return self._get_videos_info_from_url(mrss_url, video_id)
-
-
-class ComedyCentralShortnameIE(InfoExtractor):
-    _VALID_URL = r'^:(?P<id>tds|thedailyshow|theopposition)$'
-    _TESTS = [{
-        'url': ':tds',
-        'only_matching': True,
-    }, {
-        'url': ':thedailyshow',
-        'only_matching': True,
-    }, {
-        'url': ':theopposition',
-        'only_matching': True,
-    }]
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-        shortcut_map = {
-            'tds': 'http://www.cc.com/shows/the-daily-show-with-trevor-noah/full-episodes',
-            'thedailyshow': 'http://www.cc.com/shows/the-daily-show-with-trevor-noah/full-episodes',
-            'theopposition': 'http://www.cc.com/shows/the-opposition-with-jordan-klepper/full-episodes',
+    def _get_feed_query(self, uri):
+        return {
+            'accountOverride': 'intl.mtvi.com',
+            'arcEp': 'web.cc.tv',
+            'ep': 'b9032c3a',
+            'imageEp': 'web.cc.tv',
+            'mgid': uri,
         }
-        return self.url_result(shortcut_map[video_id])

youtube_dlc/extractor/common.py

@@ -336,9 +336,8 @@ class InfoExtractor(object):
     There must be a key "entries", which is a list, an iterable, or a PagedList
     object, each element of which is a valid dictionary by this specification.
 
-    Additionally, playlists can have "id", "title", "description", "uploader",
-    "uploader_id", "uploader_url", "duration" attributes with the same semantics
-    as videos (see above).
+    Additionally, playlists can have "id", "title", and any other relevent
+    attributes with the same semantics as videos (see above).
 
 
     _type "multi_video" indicates that there are multiple videos that
@@ -967,10 +966,11 @@ class InfoExtractor(object):
             urls, playlist_id=playlist_id, playlist_title=playlist_title)
 
     @staticmethod
-    def playlist_result(entries, playlist_id=None, playlist_title=None, playlist_description=None):
+    def playlist_result(entries, playlist_id=None, playlist_title=None, playlist_description=None, **kwargs):
         """Returns a playlist"""
         video_info = {'_type': 'playlist',
                       'entries': entries}
+        video_info.update(kwargs)
         if playlist_id:
             video_info['id'] = playlist_id
         if playlist_title:
@@ -1366,17 +1366,17 @@ class InfoExtractor(object):
     class FormatSort:
         regex = r' *((?P<reverse>\+)?(?P<field>[a-zA-Z0-9_]+)((?P<seperator>[~:])(?P<limit>.*?))?)? *$'
 
-        default = ('hidden', 'has_video', 'extractor', 'lang', 'quality',
-                   'res', 'fps', 'codec', 'size', 'br', 'asr',
-                   'proto', 'ext', 'has_audio', 'source', 'format_id')
+        default = ('hidden', 'hasvid', 'ie_pref', 'lang', 'quality',
+                   'res', 'fps', 'codec:vp9', 'size', 'br', 'asr',
+                   'proto', 'ext', 'has_audio', 'source', 'format_id')  # These must not be aliases
 
         settings = {
             'vcodec': {'type': 'ordered', 'regex': True,
-                       'order': ['vp9', '(h265|he?vc?)', '(h264|avc)', 'vp8', '(mp4v|h263)', 'theora', '', None, 'none']},
+                       'order': ['av0?1', 'vp9', '(h265|he?vc?)', '(h264|avc)', 'vp8', '(mp4v|h263)', 'theora', '', None, 'none']},
             'acodec': {'type': 'ordered', 'regex': True,
                        'order': ['opus', 'vorbis', 'aac', 'mp?4a?', 'mp3', 'e?a?c-?3', 'dts', '', None, 'none']},
-            'protocol': {'type': 'ordered', 'regex': True,
-                         'order': ['(ht|f)tps', '(ht|f)tp$', 'm3u8.+', 'm3u8', '.*dash', '', 'mms|rtsp', 'none', 'f4']},
+            'proto': {'type': 'ordered', 'regex': True, 'field': 'protocol',
+                      'order': ['(ht|f)tps', '(ht|f)tp$', 'm3u8.+', 'm3u8', '.*dash', '', 'mms|rtsp', 'none', 'f4']},
             'vext': {'type': 'ordered', 'field': 'video_ext',
                      'order': ('mp4', 'webm', 'flv', '', 'none'),
                      'order_free': ('webm', 'mp4', 'flv', '', 'none')},
@@ -1384,14 +1384,14 @@ class InfoExtractor(object):
                      'order': ('m4a', 'aac', 'mp3', 'ogg', 'opus', 'webm', '', 'none'),
                      'order_free': ('opus', 'ogg', 'webm', 'm4a', 'mp3', 'aac', '', 'none')},
             'hidden': {'visible': False, 'forced': True, 'type': 'extractor', 'max': -1000},
-            'extractor_preference': {'priority': True, 'type': 'extractor'},
-            'has_video': {'priority': True, 'field': 'vcodec', 'type': 'boolean', 'not_in_list': ('none',)},
-            'has_audio': {'field': 'acodec', 'type': 'boolean', 'not_in_list': ('none',)},
-            'language_preference': {'priority': True, 'convert': 'ignore'},
+            'ie_pref': {'priority': True, 'type': 'extractor', 'field': 'extractor_preference'},
+            'hasvid': {'priority': True, 'field': 'vcodec', 'type': 'boolean', 'not_in_list': ('none',)},
+            'hasaud': {'field': 'acodec', 'type': 'boolean', 'not_in_list': ('none',)},
+            'lang': {'priority': True, 'convert': 'ignore', 'field': 'language_preference'},
             'quality': {'priority': True, 'convert': 'float_none'},
             'filesize': {'convert': 'bytes'},
-            'filesize_approx': {'convert': 'bytes'},
-            'format_id': {'convert': 'string'},
+            'fs_approx': {'convert': 'bytes', 'field': 'filesize_approx'},
+            'id': {'convert': 'string', 'field': 'format_id'},
             'height': {'convert': 'float_none'},
             'width': {'convert': 'float_none'},
             'fps': {'convert': 'float_none'},
@@ -1399,32 +1399,42 @@ class InfoExtractor(object):
             'vbr': {'convert': 'float_none'},
             'abr': {'convert': 'float_none'},
             'asr': {'convert': 'float_none'},
-            'source_preference': {'convert': 'ignore'},
+            'source': {'convert': 'ignore', 'field': 'source_preference'},
+
             'codec': {'type': 'combined', 'field': ('vcodec', 'acodec')},
-            'bitrate': {'type': 'combined', 'field': ('tbr', 'vbr', 'abr'), 'same_limit': True},
-            'filesize_estimate': {'type': 'combined', 'same_limit': True, 'field': ('filesize', 'filesize_approx')},
-            'extension': {'type': 'combined', 'field': ('vext', 'aext')},
-            'dimension': {'type': 'multiple', 'field': ('height', 'width'), 'function': min},  # not named as 'resolution' because such a field exists
-            'res': {'type': 'alias', 'field': 'dimension'},
-            'ext': {'type': 'alias', 'field': 'extension'},
-            'br': {'type': 'alias', 'field': 'bitrate'},
+            'br': {'type': 'combined', 'field': ('tbr', 'vbr', 'abr'), 'same_limit': True},
+            'size': {'type': 'combined', 'same_limit': True, 'field': ('filesize', 'fs_approx')},
+            'ext': {'type': 'combined', 'field': ('vext', 'aext')},
+            'res': {'type': 'multiple', 'field': ('height', 'width'), 'function': min},
+
+            # Most of these exist only for compatibility reasons
+            'dimension': {'type': 'alias', 'field': 'res'},
+            'resolution': {'type': 'alias', 'field': 'res'},
+            'extension': {'type': 'alias', 'field': 'ext'},
+            'bitrate': {'type': 'alias', 'field': 'br'},
             'total_bitrate': {'type': 'alias', 'field': 'tbr'},
             'video_bitrate': {'type': 'alias', 'field': 'vbr'},
             'audio_bitrate': {'type': 'alias', 'field': 'abr'},
             'framerate': {'type': 'alias', 'field': 'fps'},
-            'lang': {'type': 'alias', 'field': 'language_preference'},  # not named as 'language' because such a field exists
-            'proto': {'type': 'alias', 'field': 'protocol'},
-            'source': {'type': 'alias', 'field': 'source_preference'},
-            'size': {'type': 'alias', 'field': 'filesize_estimate'},
+            'language_preference': {'type': 'alias', 'field': 'lang'},  # not named as 'language' because such a field exists
+            'protocol': {'type': 'alias', 'field': 'proto'},
+            'source_preference': {'type': 'alias', 'field': 'source'},
+            'filesize_approx': {'type': 'alias', 'field': 'fs_approx'},
+            'filesize_estimate': {'type': 'alias', 'field': 'size'},
             'samplerate': {'type': 'alias', 'field': 'asr'},
             'video_ext': {'type': 'alias', 'field': 'vext'},
             'audio_ext': {'type': 'alias', 'field': 'aext'},
             'video_codec': {'type': 'alias', 'field': 'vcodec'},
             'audio_codec': {'type': 'alias', 'field': 'acodec'},
-            'video': {'type': 'alias', 'field': 'has_video'},
-            'audio': {'type': 'alias', 'field': 'has_audio'},
-            'extractor': {'type': 'alias', 'field': 'extractor_preference'},
-            'preference': {'type': 'alias', 'field': 'extractor_preference'}}
+            'video': {'type': 'alias', 'field': 'hasvid'},
+            'has_video': {'type': 'alias', 'field': 'hasvid'},
+            'audio': {'type': 'alias', 'field': 'hasaud'},
+            'has_audio': {'type': 'alias', 'field': 'hasaud'},
+            'extractor': {'type': 'alias', 'field': 'ie_pref'},
+            'preference': {'type': 'alias', 'field': 'ie_pref'},
+            'extractor_preference': {'type': 'alias', 'field': 'ie_pref'},
+            'format_id': {'type': 'alias', 'field': 'id'},
+        }
 
         _order = []
 
@@ -2254,7 +2264,7 @@ class InfoExtractor(object):
             })
         return entries
 
-    def _extract_mpd_formats(self, mpd_url, video_id, mpd_id=None, note=None, errnote=None, fatal=True, formats_dict={}, data=None, headers={}, query={}):
+    def _extract_mpd_formats(self, mpd_url, video_id, mpd_id=None, note=None, errnote=None, fatal=True, data=None, headers={}, query={}):
         res = self._download_xml_handle(
             mpd_url, video_id,
             note=note or 'Downloading MPD manifest',
@@ -2268,10 +2278,9 @@ class InfoExtractor(object):
         mpd_base_url = base_url(urlh.geturl())
 
         return self._parse_mpd_formats(
-            mpd_doc, mpd_id=mpd_id, mpd_base_url=mpd_base_url,
-            formats_dict=formats_dict, mpd_url=mpd_url)
+            mpd_doc, mpd_id, mpd_base_url, mpd_url)
 
-    def _parse_mpd_formats(self, mpd_doc, mpd_id=None, mpd_base_url='', formats_dict={}, mpd_url=None):
+    def _parse_mpd_formats(self, mpd_doc, mpd_id=None, mpd_base_url='', mpd_url=None):
         """
         Parse formats from MPD manifest.
         References:
@@ -2550,15 +2559,7 @@ class InfoExtractor(object):
                         else:
                             # Assuming direct URL to unfragmented media.
                             f['url'] = base_url
-
-                        # According to [1, 5.3.5.2, Table 7, page 35] @id of Representation
-                        # is not necessarily unique within a Period thus formats with
-                        # the same `format_id` are quite possible. There are numerous examples
-                        # of such manifests (see https://github.com/ytdl-org/youtube-dl/issues/15111,
-                        # https://github.com/ytdl-org/youtube-dl/issues/13919)
-                        full_info = formats_dict.get(representation_id, {}).copy()
-                        full_info.update(f)
-                        formats.append(full_info)
+                        formats.append(f)
                     else:
                         self.report_warning('Unknown MIME type %s in DASH manifest' % mime_type)
         return formats

youtube_dlc/extractor/egghead.py

@@ -12,7 +12,14 @@ from ..utils import (
 )
 
 
-class EggheadCourseIE(InfoExtractor):
+class EggheadBaseIE(InfoExtractor):
+    def _call_api(self, path, video_id, resource, fatal=True):
+        return self._download_json(
+            'https://app.egghead.io/api/v1/' + path,
+            video_id, 'Downloading %s JSON' % resource, fatal=fatal)
+
+
+class EggheadCourseIE(EggheadBaseIE):
     IE_DESC = 'egghead.io course'
     IE_NAME = 'egghead:course'
     _VALID_URL = r'https://egghead\.io/courses/(?P<id>[^/?#&]+)'
@@ -28,10 +35,9 @@ class EggheadCourseIE(InfoExtractor):
 
     def _real_extract(self, url):
         playlist_id = self._match_id(url)
-
-        lessons = self._download_json(
-            'https://egghead.io/api/v1/series/%s/lessons' % playlist_id,
-            playlist_id, 'Downloading course lessons JSON')
+        series_path = 'series/' + playlist_id
+        lessons = self._call_api(
+            series_path + '/lessons', playlist_id, 'course lessons')
 
         entries = []
         for lesson in lessons:
@@ -44,9 +50,8 @@ class EggheadCourseIE(InfoExtractor):
             entries.append(self.url_result(
                 lesson_url, ie=EggheadLessonIE.ie_key(), video_id=lesson_id))
 
-        course = self._download_json(
-            'https://egghead.io/api/v1/series/%s' % playlist_id,
-            playlist_id, 'Downloading course JSON', fatal=False) or {}
+        course = self._call_api(
+            series_path, playlist_id, 'course', False) or {}
 
         playlist_id = course.get('id')
         if playlist_id:
@@ -57,7 +62,7 @@ class EggheadCourseIE(InfoExtractor):
             course.get('description'))
 
 
-class EggheadLessonIE(InfoExtractor):
+class EggheadLessonIE(EggheadBaseIE):
     IE_DESC = 'egghead.io lesson'
     IE_NAME = 'egghead:lesson'
     _VALID_URL = r'https://egghead\.io/(?:api/v1/)?lessons/(?P<id>[^/?#&]+)'
@@ -74,7 +79,7 @@ class EggheadLessonIE(InfoExtractor):
             'upload_date': '20161209',
             'duration': 304,
             'view_count': 0,
-            'tags': ['javascript', 'free'],
+            'tags': 'count:2',
         },
         'params': {
             'skip_download': True,
@@ -88,8 +93,8 @@ class EggheadLessonIE(InfoExtractor):
     def _real_extract(self, url):
         display_id = self._match_id(url)
 
-        lesson = self._download_json(
-            'https://egghead.io/api/v1/lessons/%s' % display_id, display_id)
+        lesson = self._call_api(
+            'lessons/' + display_id, display_id, 'lesson')
 
         lesson_id = compat_str(lesson['id'])
         title = lesson['title']

youtube_dlc/extractor/extractors.py

@@ -50,7 +50,10 @@ from .animelab import (
     AnimeLabIE,
     AnimeLabShowsIE,
 )
-from .americastestkitchen import AmericasTestKitchenIE
+from .americastestkitchen import (
+    AmericasTestKitchenIE,
+    AmericasTestKitchenSeasonIE,
+)
 from .animeondemand import AnimeOnDemandIE
 from .anvato import AnvatoIE
 from .aol import AolIE
@@ -87,6 +90,11 @@ from .atvat import ATVAtIE
 from .audimedia import AudiMediaIE
 from .audioboom import AudioBoomIE
 from .audiomack import AudiomackIE, AudiomackAlbumIE
+from .audius import (
+    AudiusIE,
+    AudiusTrackIE,
+    AudiusPlaylistIE
+)
 from .awaan import (
     AWAANIE,
     AWAANVideoIE,
@@ -119,10 +127,12 @@ from .bigflix import BigflixIE
 from .bild import BildIE
 from .bilibili import (
     BiliBiliIE,
+    BiliBiliSearchIE,
     BiliBiliBangumiIE,
     BilibiliAudioIE,
     BilibiliAudioAlbumIE,
     BiliBiliPlayerIE,
+    BilibiliChannelIE,
 )
 from .biobiochiletv import BioBioChileTVIE
 from .bitchute import (
@@ -244,11 +254,8 @@ from .cnn import (
 )
 from .coub import CoubIE
 from .comedycentral import (
-    ComedyCentralFullEpisodesIE,
     ComedyCentralIE,
-    ComedyCentralShortnameIE,
     ComedyCentralTVIE,
-    ToshIE,
 )
 from .commonmistakes import CommonMistakesIE, UnicodeBOMIE
 from .commonprotocols import (
@@ -677,6 +684,16 @@ from .microsoftvirtualacademy import (
     MicrosoftVirtualAcademyIE,
     MicrosoftVirtualAcademyCourseIE,
 )
+from .mildom import (
+    MildomIE,
+    MildomVodIE,
+    MildomUserVodIE,
+)
+from .minds import (
+    MindsIE,
+    MindsChannelIE,
+    MindsGroupIE,
+)
 from .ministrygrid import MinistryGridIE
 from .minoto import MinotoIE
 from .miomio import MioMioIE
@@ -1157,6 +1174,10 @@ from .stitcher import StitcherIE
 from .sport5 import Sport5IE
 from .sportbox import SportBoxIE
 from .sportdeutschland import SportDeutschlandIE
+from .spotify import (
+    SpotifyIE,
+    SpotifyShowIE,
+)
 from .spreaker import (
     SpreakerIE,
     SpreakerPageIE,
@@ -1265,7 +1286,10 @@ from .toutv import TouTvIE
 from .toypics import ToypicsUserIE, ToypicsIE
 from .traileraddict import TrailerAddictIE
 from .trilulilu import TriluliluIE
-from .trovolive import TrovoLiveIE
+from .trovo import (
+    TrovoIE,
+    TrovoVodIE,
+)
 from .trunews import TruNewsIE
 from .trutv import TruTVIE
 from .tube8 import Tube8IE
@@ -1284,6 +1308,7 @@ from .tv2 import (
     TV2IE,
     TV2ArticleIE,
     KatsomoIE,
+    MTVUutisetArticleIE,
 )
 from .tv2dk import (
     TV2DKIE,
@@ -1424,7 +1449,6 @@ from .vidme import (
     VidmeUserIE,
     VidmeUserLikesIE,
 )
-from .vidzi import VidziIE
 from .vier import VierIE, VierVideosIE
 from .viewlift import (
     ViewLiftIE,
@@ -1484,6 +1508,7 @@ from .vrv import (
     VRVSeriesIE,
 )
 from .vshare import VShareIE
+from .vtm import VTMIE
 from .medialaan import MedialaanIE
 from .vube import VubeIE
 from .vuclip import VuClipIE

youtube_dlc/extractor/franceculture.py

@@ -11,7 +11,7 @@ from ..utils import (
 
 class FranceCultureIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?franceculture\.fr/emissions/(?:[^/]+/)*(?P<id>[^/?#&]+)'
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.franceculture.fr/emissions/carnet-nomade/rendez-vous-au-pays-des-geeks',
         'info_dict': {
             'id': 'rendez-vous-au-pays-des-geeks',
@@ -20,10 +20,14 @@ class FranceCultureIE(InfoExtractor):
             'title': 'Rendez-vous au pays des geeks',
             'thumbnail': r're:^https?://.*\.jpg$',
             'upload_date': '20140301',
-            'timestamp': 1393642916,
+            'timestamp': 1393700400,
             'vcodec': 'none',
         }
-    }
+    }, {
+        # no thumbnail
+        'url': 'https://www.franceculture.fr/emissions/la-recherche-montre-en-main/la-recherche-montre-en-main-du-mercredi-10-octobre-2018',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         display_id = self._match_id(url)
@@ -36,19 +40,19 @@ class FranceCultureIE(InfoExtractor):
                     </h1>|
                     <div[^>]+class="[^"]*?(?:title-zone-diffusion|heading-zone-(?:wrapper|player-button))[^"]*?"[^>]*>
                 ).*?
-                (<button[^>]+data-asset-source="[^"]+"[^>]+>)
+                (<button[^>]+data-(?:url|asset-source)="[^"]+"[^>]+>)
             ''',
             webpage, 'video data'))
 
-        video_url = video_data['data-asset-source']
-        title = video_data.get('data-asset-title') or self._og_search_title(webpage)
+        video_url = video_data.get('data-url') or video_data['data-asset-source']
+        title = video_data.get('data-asset-title') or video_data.get('data-diffusion-title') or self._og_search_title(webpage)
 
         description = self._html_search_regex(
             r'(?s)<div[^>]+class="intro"[^>]*>.*?<h2>(.+?)</h2>',
             webpage, 'description', default=None)
         thumbnail = self._search_regex(
             r'(?s)<figure[^>]+itemtype="https://schema.org/ImageObject"[^>]*>.*?<img[^>]+(?:data-dejavu-)?src="([^"]+)"',
-            webpage, 'thumbnail', fatal=False)
+            webpage, 'thumbnail', default=None)
         uploader = self._html_search_regex(
             r'(?s)<span class="author">(.*?)</span>',
             webpage, 'uploader', default=None)
@@ -64,6 +68,6 @@ class FranceCultureIE(InfoExtractor):
             'ext': ext,
             'vcodec': 'none' if ext == 'mp3' else None,
             'uploader': uploader,
-            'timestamp': int_or_none(video_data.get('data-asset-created-date')),
+            'timestamp': int_or_none(video_data.get('data-start-time')) or int_or_none(video_data.get('data-asset-created-date')),
             'duration': int_or_none(video_data.get('data-duration')),
         }

youtube_dlc/extractor/generic.py

@@ -131,6 +131,7 @@ from .gedi import GediEmbedsIE
 from .rcs import RCSEmbedsIE
 from .bitchute import BitChuteIE
 from .arcpublishing import ArcPublishingIE
+from .medialaan import MedialaanIE
 
 
 class GenericIE(InfoExtractor):
@@ -2224,6 +2225,20 @@ class GenericIE(InfoExtractor):
                 'duration': 1581,
             },
         },
+        {
+            # MyChannels SDK embed
+            # https://www.24kitchen.nl/populair/deskundige-dit-waarom-sommigen-gevoelig-zijn-voor-voedselallergieen
+            'url': 'https://www.demorgen.be/nieuws/burgemeester-rotterdam-richt-zich-in-videoboodschap-tot-relschoppers-voelt-het-goed~b0bcfd741/',
+            'md5': '90c0699c37006ef18e198c032d81739c',
+            'info_dict': {
+                'id': '194165',
+                'ext': 'mp4',
+                'title': 'Burgemeester Aboutaleb spreekt relschoppers toe',
+                'timestamp': 1611740340,
+                'upload_date': '20210127',
+                'duration': 159,
+            },
+        },
     ]
 
     def report_following_redirect(self, new_url):
@@ -2463,6 +2478,9 @@ class GenericIE(InfoExtractor):
         webpage = self._webpage_read_content(
             full_response, url, video_id, prefix=first_bytes)
 
+        if '<title>DPG Media Privacy Gate</title>' in webpage:
+            webpage = self._download_webpage(url, video_id)
+
         self.report_extraction(video_id)
 
         # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
@@ -2594,6 +2612,11 @@ class GenericIE(InfoExtractor):
         if arc_urls:
             return self.playlist_from_matches(arc_urls, video_id, video_title, ie=ArcPublishingIE.ie_key())
 
+        mychannels_urls = MedialaanIE._extract_urls(webpage)
+        if mychannels_urls:
+            return self.playlist_from_matches(
+                mychannels_urls, video_id, video_title, ie=MedialaanIE.ie_key())
+
         # Look for embedded rtl.nl player
         matches = re.findall(
             r'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',

youtube_dlc/extractor/googledrive.py

@@ -7,6 +7,7 @@ from ..compat import compat_parse_qs
 from ..utils import (
     determine_ext,
     ExtractorError,
+    get_element_by_class,
     int_or_none,
     lowercase_escape,
     try_get,
@@ -237,7 +238,7 @@ class GoogleDriveIE(InfoExtractor):
                 if confirmation_webpage:
                     confirm = self._search_regex(
                         r'confirm=([^&"\']+)', confirmation_webpage,
-                        'confirmation code', fatal=False)
+                        'confirmation code', default=None)
                     if confirm:
                         confirmed_source_url = update_url_query(source_url, {
                             'confirm': confirm,
@@ -245,6 +246,11 @@ class GoogleDriveIE(InfoExtractor):
                         urlh = request_source_file(confirmed_source_url, 'confirmed source')
                         if urlh and urlh.headers.get('Content-Disposition'):
                             add_source_format(urlh)
+                    else:
+                        self.report_warning(
+                            get_element_by_class('uc-error-subcaption', confirmation_webpage)
+                            or get_element_by_class('uc-error-caption', confirmation_webpage)
+                            or 'unable to extract confirmation code')
 
         if not formats and reason:
             raise ExtractorError(reason, expected=True)

youtube_dlc/extractor/lbry.py

@@ -5,7 +5,10 @@ import functools
 import json
 
 from .common import InfoExtractor
-from ..compat import compat_str
+from ..compat import (
+    compat_str,
+    compat_urllib_parse_unquote,
+)
 from ..utils import (
     determine_ext,
     ExtractorError,
@@ -131,6 +134,9 @@ class LBRYIE(LBRYBaseIE):
     }, {
         'url': 'https://lbry.tv/$/download/Episode-1/e7d93d772bd87e2b62d5ab993c1c3ced86ebb396',
         'only_matching': True,
+    }, {
+        'url': 'https://lbry.tv/@lacajadepandora:a/TRUMP-EST%C3%81-BIEN-PUESTO-con-Pilar-Baselga,-Carlos-Senra,-Luis-Palacios-(720p_30fps_H264-192kbit_AAC):1',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
@@ -139,6 +145,7 @@ class LBRYIE(LBRYBaseIE):
             display_id = display_id.split('/', 2)[-1].replace('/', ':')
         else:
             display_id = display_id.replace(':', '#')
+        display_id = compat_urllib_parse_unquote(display_id)
         uri = 'lbry://' + display_id
         result = self._resolve_url(uri, display_id, 'stream')
         result_value = result['value']

youtube_dlc/extractor/medialaan.py

@@ -2,268 +2,113 @@ from __future__ import unicode_literals
 
 import re
 
-from .gigya import GigyaBaseIE
-
-from ..compat import compat_str
+from .common import InfoExtractor
 from ..utils import (
+    extract_attributes,
     int_or_none,
-    parse_duration,
-    try_get,
-    unified_timestamp,
+    mimetype2ext,
+    parse_iso8601,
 )
 
 
-class MedialaanIE(GigyaBaseIE):
+class MedialaanIE(InfoExtractor):
     _VALID_URL = r'''(?x)
                     https?://
-                        (?:www\.|nieuws\.)?
                         (?:
-                            (?P<site_id>vtm|q2|vtmkzoom)\.be/
-                            (?:
-                                video(?:/[^/]+/id/|/?\?.*?\baid=)|
-                                (?:[^/]+/)*
-                            )
+                            (?:embed\.)?mychannels.video/embed/|
+                            embed\.mychannels\.video/(?:s(?:dk|cript)/)?production/|
+                            (?:www\.)?(?:
+                                (?:
+                                    7sur7|
+                                    demorgen|
+                                    hln|
+                                    joe|
+                                    qmusic
+                                )\.be|
+                                (?:
+                                    [abe]d|
+                                    bndestem|
+                                    destentor|
+                                    gelderlander|
+                                    pzc|
+                                    tubantia|
+                                    volkskrant
+                                )\.nl
+                            )/video/(?:[^/]+/)*[^/?&#]+~p
                         )
-                        (?P<id>[^/?#&]+)
+                        (?P<id>\d+)
                     '''
-    _NETRC_MACHINE = 'medialaan'
-    _APIKEY = '3_HZ0FtkMW_gOyKlqQzW5_0FHRC7Nd5XpXJZcDdXY4pk5eES2ZWmejRW5egwVm4ug-'
-    _SITE_TO_APP_ID = {
-        'vtm': 'vtm_watch',
-        'q2': 'q2',
-        'vtmkzoom': 'vtmkzoom',
-    }
     _TESTS = [{
-        # vod
-        'url': 'http://vtm.be/video/volledige-afleveringen/id/vtm_20170219_VM0678361_vtmwatch',
+        'url': 'https://www.bndestem.nl/video/de-terugkeer-van-ally-de-aap-en-wie-vertrekt-er-nog-bij-nac~p193993',
         'info_dict': {
-            'id': 'vtm_20170219_VM0678361_vtmwatch',
+            'id': '193993',
             'ext': 'mp4',
-            'title': 'Allemaal Chris afl. 6',
-            'description': 'md5:4be86427521e7b07e0adb0c9c554ddb2',
-            'timestamp': 1487533280,
-            'upload_date': '20170219',
-            'duration': 2562,
-            'series': 'Allemaal Chris',
-            'season': 'Allemaal Chris',
-            'season_number': 1,
-            'season_id': '256936078124527',
-            'episode': 'Allemaal Chris afl. 6',
-            'episode_number': 6,
-            'episode_id': '256936078591527',
+            'title': 'De terugkeer van Ally de Aap en wie vertrekt er nog bij NAC?',
+            'timestamp': 1611663540,
+            'upload_date': '20210126',
+            'duration': 238,
         },
         'params': {
             'skip_download': True,
         },
-        'skip': 'Requires account credentials',
     }, {
-        # clip
-        'url': 'http://vtm.be/video?aid=168332',
-        'info_dict': {
-            'id': '168332',
-            'ext': 'mp4',
-            'title': '"Veronique liegt!"',
-            'description': 'md5:1385e2b743923afe54ba4adc38476155',
-            'timestamp': 1489002029,
-            'upload_date': '20170308',
-            'duration': 96,
-        },
-    }, {
-        # vod
-        'url': 'http://vtm.be/video/volledige-afleveringen/id/257107153551000',
+        'url': 'https://www.gelderlander.nl/video/kanalen/degelderlander~c320/series/snel-nieuws~s984/noodbevel-in-doetinchem-politie-stuurt-mensen-centrum-uit~p194093',
         'only_matching': True,
     }, {
-        # vod
-        'url': 'http://vtm.be/video?aid=163157',
+        'url': 'https://embed.mychannels.video/sdk/production/193993?options=TFTFF_default',
         'only_matching': True,
     }, {
-        # vod
-        'url': 'http://www.q2.be/video/volledige-afleveringen/id/2be_20170301_VM0684442_q2',
+        'url': 'https://embed.mychannels.video/script/production/193993',
         'only_matching': True,
     }, {
-        # clip
-        'url': 'http://vtmkzoom.be/k3-dansstudio/een-nieuw-seizoen-van-k3-dansstudio',
+        'url': 'https://embed.mychannels.video/production/193993',
         'only_matching': True,
     }, {
-        # http/s redirect
-        'url': 'https://vtmkzoom.be/video?aid=45724',
-        'info_dict': {
-            'id': '257136373657000',
-            'ext': 'mp4',
-            'title': 'K3 Dansstudio Ushuaia afl.6',
-        },
-        'params': {
-            'skip_download': True,
-        },
-        'skip': 'Requires account credentials',
+        'url': 'https://mychannels.video/embed/193993',
+        'only_matching': True,
     }, {
-        # nieuws.vtm.be
-        'url': 'https://nieuws.vtm.be/stadion/stadion/genk-nog-moeilijk-programma',
+        'url': 'https://embed.mychannels.video/embed/193993',
         'only_matching': True,
     }]
 
-    def _real_initialize(self):
-        self._logged_in = False
-
-    def _login(self):
-        username, password = self._get_login_info()
-        if username is None:
-            self.raise_login_required()
-
-        auth_data = {
-            'APIKey': self._APIKEY,
-            'sdk': 'js_6.1',
-            'format': 'json',
-            'loginID': username,
-            'password': password,
-        }
-
-        auth_info = self._gigya_login(auth_data)
-
-        self._uid = auth_info['UID']
-        self._uid_signature = auth_info['UIDSignature']
-        self._signature_timestamp = auth_info['signatureTimestamp']
-
-        self._logged_in = True
+    @staticmethod
+    def _extract_urls(webpage):
+        entries = []
+        for element in re.findall(r'(<div[^>]+data-mychannels-type="video"[^>]*>)', webpage):
+            mychannels_id = extract_attributes(element).get('data-mychannels-id')
+            if mychannels_id:
+                entries.append('https://mychannels.video/embed/' + mychannels_id)
+        return entries
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id, site_id = mobj.group('id', 'site_id')
+        production_id = self._match_id(url)
+        production = self._download_json(
+            'https://embed.mychannels.video/sdk/production/' + production_id,
+            production_id, query={'options': 'UUUU_default'})['productions'][0]
+        title = production['title']
 
-        webpage = self._download_webpage(url, video_id)
-
-        config = self._parse_json(
-            self._search_regex(
-                r'videoJSConfig\s*=\s*JSON\.parse\(\'({.+?})\'\);',
-                webpage, 'config', default='{}'), video_id,
-            transform_source=lambda s: s.replace(
-                '\\\\', '\\').replace(r'\"', '"').replace(r"\'", "'"))
-
-        vod_id = config.get('vodId') or self._search_regex(
-            (r'\\"vodId\\"\s*:\s*\\"(.+?)\\"',
-             r'"vodId"\s*:\s*"(.+?)"',
-             r'<[^>]+id=["\']vod-(\d+)'),
-            webpage, 'video_id', default=None)
-
-        # clip, no authentication required
-        if not vod_id:
-            player = self._parse_json(
-                self._search_regex(
-                    r'vmmaplayer\(({.+?})\);', webpage, 'vmma player',
-                    default=''),
-                video_id, transform_source=lambda s: '[%s]' % s, fatal=False)
-            if player:
-                video = player[-1]
-                if video['videoUrl'] in ('http', 'https'):
-                    return self.url_result(video['url'], MedialaanIE.ie_key())
-                info = {
-                    'id': video_id,
-                    'url': video['videoUrl'],
-                    'title': video['title'],
-                    'thumbnail': video.get('imageUrl'),
-                    'timestamp': int_or_none(video.get('createdDate')),
-                    'duration': int_or_none(video.get('duration')),
-                }
+        formats = []
+        for source in (production.get('sources') or []):
+            src = source.get('src')
+            if not src:
+                continue
+            ext = mimetype2ext(source.get('type'))
+            if ext == 'm3u8':
+                formats.extend(self._extract_m3u8_formats(
+                    src, production_id, 'mp4', 'm3u8_native',
+                    m3u8_id='hls', fatal=False))
             else:
-                info = self._parse_html5_media_entries(
-                    url, webpage, video_id, m3u8_id='hls')[0]
-                info.update({
-                    'id': video_id,
-                    'title': self._html_search_meta('description', webpage),
-                    'duration': parse_duration(self._html_search_meta('duration', webpage)),
+                formats.append({
+                    'ext': ext,
+                    'url': src,
                 })
-        # vod, authentication required
-        else:
-            if not self._logged_in:
-                self._login()
+        self._sort_formats(formats)
 
-            settings = self._parse_json(
-                self._search_regex(
-                    r'jQuery\.extend\(Drupal\.settings\s*,\s*({.+?})\);',
-                    webpage, 'drupal settings', default='{}'),
-                video_id)
-
-            def get(container, item):
-                return try_get(
-                    settings, lambda x: x[container][item],
-                    compat_str) or self._search_regex(
-                    r'"%s"\s*:\s*"([^"]+)' % item, webpage, item,
-                    default=None)
-
-            app_id = get('vod', 'app_id') or self._SITE_TO_APP_ID.get(site_id, 'vtm_watch')
-            sso = get('vod', 'gigyaDatabase') or 'vtm-sso'
-
-            data = self._download_json(
-                'http://vod.medialaan.io/api/1.0/item/%s/video' % vod_id,
-                video_id, query={
-                    'app_id': app_id,
-                    'user_network': sso,
-                    'UID': self._uid,
-                    'UIDSignature': self._uid_signature,
-                    'signatureTimestamp': self._signature_timestamp,
-                })
-
-            formats = self._extract_m3u8_formats(
-                data['response']['uri'], video_id, entry_protocol='m3u8_native',
-                ext='mp4', m3u8_id='hls')
-
-            self._sort_formats(formats)
-
-            info = {
-                'id': vod_id,
-                'formats': formats,
-            }
-
-            api_key = get('vod', 'apiKey')
-            channel = get('medialaanGigya', 'channel')
-
-            if api_key:
-                videos = self._download_json(
-                    'http://vod.medialaan.io/vod/v2/videos', video_id, fatal=False,
-                    query={
-                        'channels': channel,
-                        'ids': vod_id,
-                        'limit': 1,
-                        'apikey': api_key,
-                    })
-                if videos:
-                    video = try_get(
-                        videos, lambda x: x['response']['videos'][0], dict)
-                    if video:
-                        def get(container, item, expected_type=None):
-                            return try_get(
-                                video, lambda x: x[container][item], expected_type)
-
-                        def get_string(container, item):
-                            return get(container, item, compat_str)
-
-                        info.update({
-                            'series': get_string('program', 'title'),
-                            'season': get_string('season', 'title'),
-                            'season_number': int_or_none(get('season', 'number')),
-                            'season_id': get_string('season', 'id'),
-                            'episode': get_string('episode', 'title'),
-                            'episode_number': int_or_none(get('episode', 'number')),
-                            'episode_id': get_string('episode', 'id'),
-                            'duration': int_or_none(
-                                video.get('duration')) or int_or_none(
-                                video.get('durationMillis'), scale=1000),
-                            'title': get_string('episode', 'title'),
-                            'description': get_string('episode', 'text'),
-                            'timestamp': unified_timestamp(get_string(
-                                'publication', 'begin')),
-                        })
-
-            if not info.get('title'):
-                info['title'] = try_get(
-                    config, lambda x: x['videoConfig']['title'],
-                    compat_str) or self._html_search_regex(
-                    r'\\"title\\"\s*:\s*\\"(.+?)\\"', webpage, 'title',
-                    default=None) or self._og_search_title(webpage)
-
-        if not info.get('description'):
-            info['description'] = self._html_search_regex(
-                r'<div[^>]+class="field-item\s+even">\s*<p>(.+?)</p>',
-                webpage, 'description', default=None)
-
-        return info
+        return {
+            'id': production_id,
+            'title': title,
+            'formats': formats,
+            'thumbnail': production.get('posterUrl'),
+            'timestamp': parse_iso8601(production.get('publicationDate'), ' '),
+            'duration': int_or_none(production.get('duration')) or None,
+        }

youtube_dlc/extractor/mildom.py

@@ -0,0 +1,284 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from datetime import datetime
+import itertools
+import json
+import base64
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError, std_headers,
+    update_url_query,
+    random_uuidv4,
+    try_get,
+)
+from ..compat import (
+    compat_urlparse,
+    compat_urllib_parse_urlencode,
+    compat_str,
+)
+
+
+class MildomBaseIE(InfoExtractor):
+    _GUEST_ID = None
+    _DISPATCHER_CONFIG = None
+
+    def _call_api(self, url, video_id, query={}, note='Downloading JSON metadata', init=False):
+        url = update_url_query(url, self._common_queries(query, init=init))
+        return self._download_json(url, video_id, note=note)['body']
+
+    def _common_queries(self, query={}, init=False):
+        dc = self._fetch_dispatcher_config()
+        r = {
+            'timestamp': self.iso_timestamp(),
+            '__guest_id': '' if init else self.guest_id(),
+            '__location': dc['location'],
+            '__country': dc['country'],
+            '__cluster': dc['cluster'],
+            '__platform': 'web',
+            '__la': self.lang_code(),
+            '__pcv': 'v2.9.44',
+            'sfr': 'pc',
+            'accessToken': '',
+        }
+        r.update(query)
+        return r
+
+    def _fetch_dispatcher_config(self):
+        if not self._DISPATCHER_CONFIG:
+            try:
+                tmp = self._download_json(
+                    'https://disp.mildom.com/serverListV2', 'initialization',
+                    note='Downloading dispatcher_config', data=json.dumps({
+                        'protover': 0,
+                        'data': base64.b64encode(json.dumps({
+                            'fr': 'web',
+                            'sfr': 'pc',
+                            'devi': 'Windows',
+                            'la': 'ja',
+                            'gid': None,
+                            'loc': '',
+                            'clu': '',
+                            'wh': '1919*810',
+                            'rtm': self.iso_timestamp(),
+                            'ua': std_headers['User-Agent'],
+                        }).encode('utf8')).decode('utf8').replace('\n', ''),
+                    }).encode('utf8'))
+                self._DISPATCHER_CONFIG = self._parse_json(base64.b64decode(tmp['data']), 'initialization')
+            except ExtractorError:
+                self._DISPATCHER_CONFIG = self._download_json(
+                    'https://bookish-octo-barnacle.vercel.app/api/dispatcher_config', 'initialization',
+                    note='Downloading dispatcher_config fallback')
+        return self._DISPATCHER_CONFIG
+
+    @staticmethod
+    def iso_timestamp():
+        'new Date().toISOString()'
+        return datetime.utcnow().isoformat()[0:-3] + 'Z'
+
+    def guest_id(self):
+        'getGuestId'
+        if self._GUEST_ID:
+            return self._GUEST_ID
+        self._GUEST_ID = try_get(
+            self, (
+                lambda x: x._call_api(
+                    'https://cloudac.mildom.com/nonolive/gappserv/guest/h5init', 'initialization',
+                    note='Downloading guest token', init=True)['guest_id'] or None,
+                lambda x: x._get_cookies('https://www.mildom.com').get('gid').value,
+                lambda x: x._get_cookies('https://m.mildom.com').get('gid').value,
+            ), compat_str) or ''
+        return self._GUEST_ID
+
+    def lang_code(self):
+        'getCurrentLangCode'
+        return 'ja'
+
+
+class MildomIE(MildomBaseIE):
+    IE_NAME = 'mildom'
+    IE_DESC = 'Record ongoing live by specific user in Mildom'
+    _VALID_URL = r'https?://(?:(?:www|m)\.)mildom\.com/(?P<id>\d+)'
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        url = 'https://www.mildom.com/%s' % video_id
+
+        webpage = self._download_webpage(url, video_id)
+
+        enterstudio = self._call_api(
+            'https://cloudac.mildom.com/nonolive/gappserv/live/enterstudio', video_id,
+            note='Downloading live metadata', query={'user_id': video_id})
+
+        title = try_get(
+            enterstudio, (
+                lambda x: self._html_search_meta('twitter:description', webpage),
+                lambda x: x['anchor_intro'],
+            ), compat_str)
+        description = try_get(
+            enterstudio, (
+                lambda x: x['intro'],
+                lambda x: x['live_intro'],
+            ), compat_str)
+        uploader = try_get(
+            enterstudio, (
+                lambda x: self._html_search_meta('twitter:title', webpage),
+                lambda x: x['loginname'],
+            ), compat_str)
+
+        servers = self._call_api(
+            'https://cloudac.mildom.com/nonolive/gappserv/live/liveserver', video_id,
+            note='Downloading live server list', query={
+                'user_id': video_id,
+                'live_server_type': 'hls',
+            })
+
+        stream_query = self._common_queries({
+            'streamReqId': random_uuidv4(),
+            'is_lhls': '0',
+        })
+        m3u8_url = update_url_query(servers['stream_server'] + '/%s_master.m3u8' % video_id, stream_query)
+        formats = self._extract_m3u8_formats(m3u8_url, video_id, 'mp4', headers={
+            'Referer': 'https://www.mildom.com/',
+            'Origin': 'https://www.mildom.com',
+        }, note='Downloading m3u8 information')
+        del stream_query['streamReqId'], stream_query['timestamp']
+        for fmt in formats:
+            # Uses https://github.com/nao20010128nao/bookish-octo-barnacle by @nao20010128nao as a proxy
+            parsed = compat_urlparse.urlparse(fmt['url'])
+            parsed = parsed._replace(
+                netloc='bookish-octo-barnacle.vercel.app',
+                query=compat_urllib_parse_urlencode(stream_query, True),
+                path='/api' + parsed.path)
+            fmt['url'] = compat_urlparse.urlunparse(parsed)
+
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'uploader': uploader,
+            'uploader_id': video_id,
+            'formats': formats,
+            'is_live': True,
+        }
+
+
+class MildomVodIE(MildomBaseIE):
+    IE_NAME = 'mildom:vod'
+    IE_DESC = 'Download a VOD in Mildom'
+    _VALID_URL = r'https?://(?:(?:www|m)\.)mildom\.com/playback/(?P<user_id>\d+)/(?P<id>(?P=user_id)-[a-zA-Z0-9]+)'
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        m = self._VALID_URL_RE.match(url)
+        user_id = m.group('user_id')
+        url = 'https://www.mildom.com/playback/%s/%s' % (user_id, video_id)
+
+        webpage = self._download_webpage(url, video_id)
+
+        autoplay = self._call_api(
+            'https://cloudac.mildom.com/nonolive/videocontent/playback/getPlaybackDetail', video_id,
+            note='Downloading playback metadata', query={
+                'v_id': video_id,
+            })['playback']
+
+        title = try_get(
+            autoplay, (
+                lambda x: self._html_search_meta('og:description', webpage),
+                lambda x: x['title'],
+            ), compat_str)
+        description = try_get(
+            autoplay, (
+                lambda x: x['video_intro'],
+            ), compat_str)
+        uploader = try_get(
+            autoplay, (
+                lambda x: x['author_info']['login_name'],
+            ), compat_str)
+
+        audio_formats = [{
+            'url': autoplay['audio_url'],
+            'format_id': 'audio',
+            'protocol': 'm3u8_native',
+            'vcodec': 'none',
+            'acodec': 'aac',
+        }]
+        video_formats = []
+        for fmt in autoplay['video_link']:
+            video_formats.append({
+                'format_id': 'video-%s' % fmt['name'],
+                'url': fmt['url'],
+                'protocol': 'm3u8_native',
+                'width': fmt['level'] * autoplay['video_width'] // autoplay['video_height'],
+                'height': fmt['level'],
+                'vcodec': 'h264',
+                'acodec': 'aac',
+            })
+
+        stream_query = self._common_queries({
+            'is_lhls': '0',
+        })
+        del stream_query['timestamp']
+        formats = audio_formats + video_formats
+        for fmt in formats:
+            fmt['ext'] = 'mp4'
+            parsed = compat_urlparse.urlparse(fmt['url'])
+            stream_query['path'] = parsed.path[5:]
+            parsed = parsed._replace(
+                netloc='bookish-octo-barnacle.vercel.app',
+                query=compat_urllib_parse_urlencode(stream_query, True),
+                path='/api/vod2/proxy')
+            fmt['url'] = compat_urlparse.urlunparse(parsed)
+
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'uploader': uploader,
+            'uploader_id': user_id,
+            'formats': formats,
+        }
+
+
+class MildomUserVodIE(MildomBaseIE):
+    IE_NAME = 'mildom:user:vod'
+    IE_DESC = 'Download all VODs from specific user in Mildom'
+    _VALID_URL = r'https?://(?:(?:www|m)\.)mildom\.com/profile/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://www.mildom.com/profile/10093333',
+        'info_dict': {
+            'id': '10093333',
+            'title': 'Uploads from ねこばたけ',
+        },
+        'playlist_mincount': 351,
+    }]
+
+    def _real_extract(self, url):
+        user_id = self._match_id(url)
+
+        self._downloader.report_warning('To download ongoing live, please use "https://www.mildom.com/%s" instead. This will list up VODs belonging to user.' % user_id)
+
+        profile = self._call_api(
+            'https://cloudac.mildom.com/nonolive/gappserv/user/profileV2', user_id,
+            query={'user_id': user_id}, note='Downloading user profile')['user_info']
+
+        results = []
+        for page in itertools.count(1):
+            reply = self._call_api(
+                'https://cloudac.mildom.com/nonolive/videocontent/profile/playbackList',
+                user_id, note='Downloading page %d' % page, query={
+                    'user_id': user_id,
+                    'page': page,
+                    'limit': '30',
+                })
+            if not reply:
+                break
+            results.extend('https://www.mildom.com/playback/%s/%s' % (user_id, x['v_id']) for x in reply)
+        return self.playlist_result([
+            self.url_result(u, ie=MildomVodIE.ie_key()) for u in results
+        ], user_id, 'Uploads from %s' % profile['loginname'])

youtube_dlc/extractor/minds.py

@@ -0,0 +1,196 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..compat import compat_str
+from ..utils import (
+    clean_html,
+    int_or_none,
+    str_or_none,
+    strip_or_none,
+)
+
+
+class MindsBaseIE(InfoExtractor):
+    _VALID_URL_BASE = r'https?://(?:www\.)?minds\.com/'
+
+    def _call_api(self, path, video_id, resource, query=None):
+        api_url = 'https://www.minds.com/api/' + path
+        token = self._get_cookies(api_url).get('XSRF-TOKEN')
+        return self._download_json(
+            api_url, video_id, 'Downloading %s JSON metadata' % resource, headers={
+                'Referer': 'https://www.minds.com/',
+                'X-XSRF-TOKEN': token.value if token else '',
+            }, query=query)
+
+
+class MindsIE(MindsBaseIE):
+    IE_NAME = 'minds'
+    _VALID_URL = MindsBaseIE._VALID_URL_BASE + r'(?:media|newsfeed|archive/view)/(?P<id>[0-9]+)'
+    _TESTS = [{
+        'url': 'https://www.minds.com/media/100000000000086822',
+        'md5': '215a658184a419764852239d4970b045',
+        'info_dict': {
+            'id': '100000000000086822',
+            'ext': 'mp4',
+            'title': 'Minds intro sequence',
+            'thumbnail': r're:https?://.+\.png',
+            'uploader_id': 'ottman',
+            'upload_date': '20130524',
+            'timestamp': 1369404826,
+            'uploader': 'Bill Ottman',
+            'view_count': int,
+            'like_count': int,
+            'dislike_count': int,
+            'tags': ['animation'],
+            'comment_count': int,
+            'license': 'attribution-cc',
+        },
+    }, {
+        # entity.type == 'activity' and empty title
+        'url': 'https://www.minds.com/newsfeed/798025111988506624',
+        'md5': 'b2733a74af78d7fd3f541c4cbbaa5950',
+        'info_dict': {
+            'id': '798022190320226304',
+            'ext': 'mp4',
+            'title': '798022190320226304',
+            'uploader': 'ColinFlaherty',
+            'upload_date': '20180111',
+            'timestamp': 1515639316,
+            'uploader_id': 'ColinFlaherty',
+        },
+    }, {
+        'url': 'https://www.minds.com/archive/view/715172106794442752',
+        'only_matching': True,
+    }, {
+        # youtube perma_url
+        'url': 'https://www.minds.com/newsfeed/1197131838022602752',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        entity_id = self._match_id(url)
+        entity = self._call_api(
+            'v1/entities/entity/' + entity_id, entity_id, 'entity')['entity']
+        if entity.get('type') == 'activity':
+            if entity.get('custom_type') == 'video':
+                video_id = entity['entity_guid']
+            else:
+                return self.url_result(entity['perma_url'])
+        else:
+            assert(entity['subtype'] == 'video')
+            video_id = entity_id
+        # 1080p and webm formats available only on the sources array
+        video = self._call_api(
+            'v2/media/video/' + video_id, video_id, 'video')
+
+        formats = []
+        for source in (video.get('sources') or []):
+            src = source.get('src')
+            if not src:
+                continue
+            formats.append({
+                'format_id': source.get('label'),
+                'height': int_or_none(source.get('size')),
+                'url': src,
+            })
+        self._sort_formats(formats)
+
+        entity = video.get('entity') or entity
+        owner = entity.get('ownerObj') or {}
+        uploader_id = owner.get('username')
+
+        tags = entity.get('tags')
+        if tags and isinstance(tags, compat_str):
+            tags = [tags]
+
+        thumbnail = None
+        poster = video.get('poster') or entity.get('thumbnail_src')
+        if poster:
+            urlh = self._request_webpage(poster, video_id, fatal=False)
+            if urlh:
+                thumbnail = urlh.geturl()
+
+        return {
+            'id': video_id,
+            'title': entity.get('title') or video_id,
+            'formats': formats,
+            'description': clean_html(entity.get('description')) or None,
+            'license': str_or_none(entity.get('license')),
+            'timestamp': int_or_none(entity.get('time_created')),
+            'uploader': strip_or_none(owner.get('name')),
+            'uploader_id': uploader_id,
+            'uploader_url': 'https://www.minds.com/' + uploader_id if uploader_id else None,
+            'view_count': int_or_none(entity.get('play:count')),
+            'like_count': int_or_none(entity.get('thumbs:up:count')),
+            'dislike_count': int_or_none(entity.get('thumbs:down:count')),
+            'tags': tags,
+            'comment_count': int_or_none(entity.get('comments:count')),
+            'thumbnail': thumbnail,
+        }
+
+
+class MindsFeedBaseIE(MindsBaseIE):
+    _PAGE_SIZE = 150
+
+    def _entries(self, feed_id):
+        query = {'limit': self._PAGE_SIZE, 'sync': 1}
+        i = 1
+        while True:
+            data = self._call_api(
+                'v2/feeds/container/%s/videos' % feed_id,
+                feed_id, 'page %s' % i, query)
+            entities = data.get('entities') or []
+            for entity in entities:
+                guid = entity.get('guid')
+                if not guid:
+                    continue
+                yield self.url_result(
+                    'https://www.minds.com/newsfeed/' + guid,
+                    MindsIE.ie_key(), guid)
+            query['from_timestamp'] = data['load-next']
+            if not (query['from_timestamp'] and len(entities) == self._PAGE_SIZE):
+                break
+            i += 1
+
+    def _real_extract(self, url):
+        feed_id = self._match_id(url)
+        feed = self._call_api(
+            'v1/%s/%s' % (self._FEED_PATH, feed_id),
+            feed_id, self._FEED_TYPE)[self._FEED_TYPE]
+
+        return self.playlist_result(
+            self._entries(feed['guid']), feed_id,
+            strip_or_none(feed.get('name')),
+            feed.get('briefdescription'))
+
+
+class MindsChannelIE(MindsFeedBaseIE):
+    _FEED_TYPE = 'channel'
+    IE_NAME = 'minds:' + _FEED_TYPE
+    _VALID_URL = MindsBaseIE._VALID_URL_BASE + r'(?!(?:newsfeed|media|api|archive|groups)/)(?P<id>[^/?&#]+)'
+    _FEED_PATH = 'channel'
+    _TEST = {
+        'url': 'https://www.minds.com/ottman',
+        'info_dict': {
+            'id': 'ottman',
+            'title': 'Bill Ottman',
+            'description': 'Co-creator & CEO @minds',
+        },
+        'playlist_mincount': 54,
+    }
+
+
+class MindsGroupIE(MindsFeedBaseIE):
+    _FEED_TYPE = 'group'
+    IE_NAME = 'minds:' + _FEED_TYPE
+    _VALID_URL = MindsBaseIE._VALID_URL_BASE + r'groups/profile/(?P<id>[0-9]+)'
+    _FEED_PATH = 'groups/group'
+    _TEST = {
+        'url': 'https://www.minds.com/groups/profile/785582576369672204/feed/videos',
+        'info_dict': {
+            'id': '785582576369672204',
+            'title': 'Cooking Videos',
+        },
+        'playlist_mincount': 1,
+    }

youtube_dlc/extractor/mtv.py

@@ -255,6 +255,10 @@ class MTVServicesInfoExtractor(InfoExtractor):
 
         return try_get(feed, lambda x: x['result']['data']['id'], compat_str)
 
+    @staticmethod
+    def _extract_child_with_type(parent, t):
+        return next(c for c in parent['children'] if c.get('type') == t)
+
     def _extract_new_triforce_mgid(self, webpage, url='', video_id=None):
         if url == '':
             return
@@ -332,6 +336,13 @@ class MTVServicesInfoExtractor(InfoExtractor):
         if not mgid:
             mgid = self._extract_triforce_mgid(webpage, data_zone)
 
+        if not mgid:
+            data = self._parse_json(self._search_regex(
+                r'__DATA__\s*=\s*({.+?});', webpage, 'data'), None)
+            main_container = self._extract_child_with_type(data, 'MainContainer')
+            video_player = self._extract_child_with_type(main_container, 'VideoPlayer')
+            mgid = video_player['props']['media']['video']['config']['uri']
+
         return mgid
 
     def _real_extract(self, url):
@@ -403,18 +414,6 @@ class MTVIE(MTVServicesInfoExtractor):
         'only_matching': True,
     }]
 
-    @staticmethod
-    def extract_child_with_type(parent, t):
-        children = parent['children']
-        return next(c for c in children if c.get('type') == t)
-
-    def _extract_mgid(self, webpage):
-        data = self._parse_json(self._search_regex(
-            r'__DATA__\s*=\s*({.+?});', webpage, 'data'), None)
-        main_container = self.extract_child_with_type(data, 'MainContainer')
-        video_player = self.extract_child_with_type(main_container, 'VideoPlayer')
-        return video_player['props']['media']['video']['config']['uri']
-
 
 class MTVJapanIE(MTVServicesInfoExtractor):
     IE_NAME = 'mtvjapan'

youtube_dlc/extractor/ninegag.py

@@ -1,104 +1,125 @@
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
-from ..utils import str_to_int
+from ..utils import (
+    determine_ext,
+    ExtractorError,
+    int_or_none,
+    try_get,
+    url_or_none,
+)
 
 
 class NineGagIE(InfoExtractor):
     IE_NAME = '9gag'
-    _VALID_URL = r'https?://(?:www\.)?9gag(?:\.com/tv|\.tv)/(?:p|embed)/(?P<id>[a-zA-Z0-9]+)(?:/(?P<display_id>[^?#/]+))?'
+    _VALID_URL = r'https?://(?:www\.)?9gag\.com/gag/(?P<id>[^/?&#]+)'
 
-    _TESTS = [{
-        'url': 'http://9gag.com/tv/p/Kk2X5/people-are-awesome-2013-is-absolutely-awesome',
+    _TEST = {
+        'url': 'https://9gag.com/gag/ae5Ag7B',
         'info_dict': {
-            'id': 'kXzwOKyGlSA',
+            'id': 'ae5Ag7B',
             'ext': 'mp4',
-            'description': 'This 3-minute video will make you smile and then make you feel untalented and insignificant. Anyway, you should share this awesomeness. (Thanks, Dino!)',
-            'title': '\"People Are Awesome 2013\" Is Absolutely Awesome',
-            'uploader_id': 'UCdEH6EjDKwtTe-sO2f0_1XA',
-            'uploader': 'CompilationChannel',
-            'upload_date': '20131110',
-            'view_count': int,
-        },
-        'add_ie': ['Youtube'],
-    }, {
-        'url': 'http://9gag.com/tv/p/aKolP3',
-        'info_dict': {
-            'id': 'aKolP3',
-            'ext': 'mp4',
-            'title': 'This Guy Travelled 11 countries In 44 days Just To Make This Amazing Video',
-            'description': "I just saw more in 1 minute than I've seen in 1 year. This guy's video is epic!!",
-            'uploader_id': 'rickmereki',
-            'uploader': 'Rick Mereki',
-            'upload_date': '20110803',
-            'view_count': int,
-        },
-        'add_ie': ['Vimeo'],
-    }, {
-        'url': 'http://9gag.com/tv/p/KklwM',
-        'only_matching': True,
-    }, {
-        'url': 'http://9gag.tv/p/Kk2X5',
-        'only_matching': True,
-    }, {
-        'url': 'http://9gag.com/tv/embed/a5Dmvl',
-        'only_matching': True,
-    }]
-
-    _EXTERNAL_VIDEO_PROVIDER = {
-        '1': {
-            'url': '%s',
-            'ie_key': 'Youtube',
-        },
-        '2': {
-            'url': 'http://player.vimeo.com/video/%s',
-            'ie_key': 'Vimeo',
-        },
-        '3': {
-            'url': 'http://instagram.com/p/%s',
-            'ie_key': 'Instagram',
-        },
-        '4': {
-            'url': 'http://vine.co/v/%s',
-            'ie_key': 'Vine',
-        },
+            'title': 'Capybara Agility Training',
+            'upload_date': '20191108',
+            'timestamp': 1573237208,
+            'categories': ['Awesome'],
+            'tags': ['Weimaraner', 'American Pit Bull Terrier'],
+            'duration': 44,
+            'like_count': int,
+            'dislike_count': int,
+            'comment_count': int,
+        }
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-        display_id = mobj.group('display_id') or video_id
+        post_id = self._match_id(url)
+        post = self._download_json(
+            'https://9gag.com/v1/post', post_id, query={
+                'id': post_id
+            })['data']['post']
 
-        webpage = self._download_webpage(url, display_id)
+        if post.get('type') != 'Animated':
+            raise ExtractorError(
+                'The given url does not contain a video',
+                expected=True)
 
-        post_view = self._parse_json(
-            self._search_regex(
-                r'var\s+postView\s*=\s*new\s+app\.PostView\({\s*post:\s*({.+?})\s*,\s*posts:\s*prefetchedCurrentPost',
-                webpage, 'post view'),
-            display_id)
+        title = post['title']
 
-        ie_key = None
-        source_url = post_view.get('sourceUrl')
-        if not source_url:
-            external_video_id = post_view['videoExternalId']
-            external_video_provider = post_view['videoExternalProvider']
-            source_url = self._EXTERNAL_VIDEO_PROVIDER[external_video_provider]['url'] % external_video_id
-            ie_key = self._EXTERNAL_VIDEO_PROVIDER[external_video_provider]['ie_key']
-        title = post_view['title']
-        description = post_view.get('description')
-        view_count = str_to_int(post_view.get('externalView'))
-        thumbnail = post_view.get('thumbnail_700w') or post_view.get('ogImageUrl') or post_view.get('thumbnail_300w')
+        duration = None
+        formats = []
+        thumbnails = []
+        for key, image in (post.get('images') or {}).items():
+            image_url = url_or_none(image.get('url'))
+            if not image_url:
+                continue
+            ext = determine_ext(image_url)
+            image_id = key.strip('image')
+            common = {
+                'url': image_url,
+                'width': int_or_none(image.get('width')),
+                'height': int_or_none(image.get('height')),
+            }
+            if ext in ('jpg', 'png'):
+                webp_url = image.get('webpUrl')
+                if webp_url:
+                    t = common.copy()
+                    t.update({
+                        'id': image_id + '-webp',
+                        'url': webp_url,
+                    })
+                    thumbnails.append(t)
+                common.update({
+                    'id': image_id,
+                    'ext': ext,
+                })
+                thumbnails.append(common)
+            elif ext in ('webm', 'mp4'):
+                if not duration:
+                    duration = int_or_none(image.get('duration'))
+                common['acodec'] = 'none' if image.get('hasAudio') == 0 else None
+                for vcodec in ('vp8', 'vp9', 'h265'):
+                    c_url = image.get(vcodec + 'Url')
+                    if not c_url:
+                        continue
+                    c_f = common.copy()
+                    c_f.update({
+                        'format_id': image_id + '-' + vcodec,
+                        'url': c_url,
+                        'vcodec': vcodec,
+                    })
+                    formats.append(c_f)
+                common.update({
+                    'ext': ext,
+                    'format_id': image_id,
+                })
+                formats.append(common)
+        self._sort_formats(formats)
+
+        section = try_get(post, lambda x: x['postSection']['name'])
+
+        tags = None
+        post_tags = post.get('tags')
+        if post_tags:
+            tags = []
+            for tag in post_tags:
+                tag_key = tag.get('key')
+                if not tag_key:
+                    continue
+                tags.append(tag_key)
+
+        get_count = lambda x: int_or_none(post.get(x + 'Count'))
 
         return {
-            '_type': 'url_transparent',
-            'url': source_url,
-            'ie_key': ie_key,
-            'id': video_id,
-            'display_id': display_id,
+            'id': post_id,
             'title': title,
-            'description': description,
-            'view_count': view_count,
-            'thumbnail': thumbnail,
+            'timestamp': int_or_none(post.get('creationTs')),
+            'duration': duration,
+            'formats': formats,
+            'thumbnails': thumbnails,
+            'like_count': get_count('upVote'),
+            'dislike_count': get_count('downVote'),
+            'comment_count': get_count('comments'),
+            'age_limit': 18 if post.get('nsfw') == 1 else None,
+            'categories': [section] if section else None,
+            'tags': tags,
         }

youtube_dlc/extractor/njpwworld.py

@@ -6,30 +6,40 @@ import re
 from .common import InfoExtractor
 from ..compat import compat_urlparse
 from ..utils import (
-    extract_attributes,
     get_element_by_class,
     urlencode_postdata,
 )
 
 
 class NJPWWorldIE(InfoExtractor):
-    _VALID_URL = r'https?://njpwworld\.com/p/(?P<id>[a-z0-9_]+)'
+    _VALID_URL = r'https?://(front\.)?njpwworld\.com/p/(?P<id>[a-z0-9_]+)'
     IE_DESC = '新日本プロレスワールド'
     _NETRC_MACHINE = 'njpwworld'
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://njpwworld.com/p/s_series_00155_1_9/',
         'info_dict': {
             'id': 's_series_00155_1_9',
             'ext': 'mp4',
-            'title': '第9試合　ランディ・サベージ　vs　リック・スタイナー',
+            'title': '闘強導夢2000 2000年1月4日 東京ドーム 第9試合 ランディ・サベージ VS リック・スタイナー',
             'tags': list,
         },
         'params': {
             'skip_download': True,  # AES-encrypted m3u8
         },
         'skip': 'Requires login',
-    }
+    }, {
+        'url': 'https://front.njpwworld.com/p/s_series_00563_16_bs',
+        'info_dict': {
+            'id': 's_series_00563_16_bs',
+            'ext': 'mp4',
+            'title': 'WORLD TAG LEAGUE 2020 & BEST OF THE SUPER Jr.27 2020年12月6日 福岡・福岡国際センター バックステージコメント（字幕あり）',
+            'tags': ["福岡・福岡国際センター", "バックステージコメント", "2020", "20年代"],
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }]
 
     _LOGIN_URL = 'https://front.njpwworld.com/auth/login'
 
@@ -64,35 +74,27 @@ class NJPWWorldIE(InfoExtractor):
         webpage = self._download_webpage(url, video_id)
 
         formats = []
-        for mobj in re.finditer(r'<a[^>]+\bhref=(["\'])/player.+?[^>]*>', webpage):
-            player = extract_attributes(mobj.group(0))
-            player_path = player.get('href')
-            if not player_path:
-                continue
-            kind = self._search_regex(
-                r'(low|high)$', player.get('class') or '', 'kind',
-                default='low')
+        for kind, vid in re.findall(r'if\s+\(\s*imageQualityType\s*==\s*\'([^\']+)\'\s*\)\s*{\s*video_id\s*=\s*"(\d+)"', webpage):
+            player_path = '/intent?id=%s&type=url' % vid
             player_url = compat_urlparse.urljoin(url, player_path)
-            player_page = self._download_webpage(
-                player_url, video_id, note='Downloading player page')
-            entries = self._parse_html5_media_entries(
-                player_url, player_page, video_id, m3u8_id='hls-%s' % kind,
-                m3u8_entry_protocol='m3u8_native')
-            kind_formats = entries[0]['formats']
-            for f in kind_formats:
-                f['quality'] = 2 if kind == 'high' else 1
-            formats.extend(kind_formats)
+            formats.append({
+                'url': player_url,
+                'format_id': kind,
+                'ext': 'mp4',
+                'protocol': 'm3u8',
+                'quality': 2 if kind == 'high' else 1,
+            })
 
         self._sort_formats(formats)
 
-        post_content = get_element_by_class('post-content', webpage)
+        tag_block = get_element_by_class('tag-block', webpage)
         tags = re.findall(
-            r'<li[^>]+class="tag-[^"]+"><a[^>]*>([^<]+)</a></li>', post_content
-        ) if post_content else None
+            r'<a[^>]+class="tag-[^"]+"[^>]*>([^<]+)</a>', tag_block
+        ) if tag_block else None
 
         return {
             'id': video_id,
-            'title': self._og_search_title(webpage),
+            'title': get_element_by_class('article-title', webpage) or self._og_search_title(webpage),
             'formats': formats,
             'tags': tags,
         }

youtube_dlc/extractor/pornhub.py

@@ -22,11 +22,15 @@ from ..utils import (
     orderedSet,
     remove_quotes,
     str_to_int,
+    update_url_query,
+    urlencode_postdata,
     url_or_none,
 )
 
 
 class PornHubBaseIE(InfoExtractor):
+    _NETRC_MACHINE = 'pornhub'
+
     def _download_webpage_handle(self, *args, **kwargs):
         def dl(*args, **kwargs):
             return super(PornHubBaseIE, self)._download_webpage_handle(*args, **kwargs)
@@ -52,6 +56,66 @@ class PornHubBaseIE(InfoExtractor):
 
         return webpage, urlh
 
+    def _real_initialize(self):
+        self._logged_in = False
+
+    def _login(self, host):
+        if self._logged_in:
+            return
+
+        site = host.split('.')[0]
+
+        # Both sites pornhub and pornhubpremium have separate accounts
+        # so there should be an option to provide credentials for both.
+        # At the same time some videos are available under the same video id
+        # on both sites so that we have to identify them as the same video.
+        # For that purpose we have to keep both in the same extractor
+        # but under different netrc machines.
+        username, password = self._get_login_info(netrc_machine=site)
+        if username is None:
+            return
+
+        login_url = 'https://www.%s/%slogin' % (host, 'premium/' if 'premium' in host else '')
+        login_page = self._download_webpage(
+            login_url, None, 'Downloading %s login page' % site)
+
+        def is_logged(webpage):
+            return any(re.search(p, webpage) for p in (
+                r'class=["\']signOut',
+                r'>Sign\s+[Oo]ut\s*<'))
+
+        if is_logged(login_page):
+            self._logged_in = True
+            return
+
+        login_form = self._hidden_inputs(login_page)
+
+        login_form.update({
+            'username': username,
+            'password': password,
+        })
+
+        response = self._download_json(
+            'https://www.%s/front/authenticate' % host, None,
+            'Logging in to %s' % site,
+            data=urlencode_postdata(login_form),
+            headers={
+                'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
+                'Referer': login_url,
+                'X-Requested-With': 'XMLHttpRequest',
+            })
+
+        if response.get('success') == '1':
+            self._logged_in = True
+            return
+
+        message = response.get('message')
+        if message is not None:
+            raise ExtractorError(
+                'Unable to login: %s' % message, expected=True)
+
+        raise ExtractorError('Unable to log in')
+
 
 class PornHubIE(PornHubBaseIE):
     IE_DESC = 'PornHub and Thumbzilla'
@@ -163,12 +227,20 @@ class PornHubIE(PornHubBaseIE):
     }, {
         'url': 'https://www.pornhubpremium.com/view_video.php?viewkey=ph5e4acdae54a82',
         'only_matching': True,
+    }, {
+        # Some videos are available with the same id on both premium
+        # and non-premium sites (e.g. this and the following test)
+        'url': 'https://www.pornhub.com/view_video.php?viewkey=ph5f75b0f4b18e3',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.pornhubpremium.com/view_video.php?viewkey=ph5f75b0f4b18e3',
+        'only_matching': True,
     }]
 
     @staticmethod
     def _extract_urls(webpage):
         return re.findall(
-            r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//(?:www\.)?pornhub\.(?:com|net|org)/embed/[\da-z]+)',
+            r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//(?:www\.)?pornhub(?:premium)?\.(?:com|net|org)/embed/[\da-z]+)',
             webpage)
 
     def _extract_count(self, pattern, webpage, name):
@@ -180,12 +252,7 @@ class PornHubIE(PornHubBaseIE):
         host = mobj.group('host') or 'pornhub.com'
         video_id = mobj.group('id')
 
-        if 'premium' in host:
-            if not self._downloader.params.get('cookiefile'):
-                raise ExtractorError(
-                    'PornHub Premium requires authentication.'
-                    ' You may want to use --cookies.',
-                    expected=True)
+        self._login(host)
 
         self._set_cookie(host, 'age_verified', '1')
 
@@ -405,6 +472,10 @@ class PornHubIE(PornHubBaseIE):
 
 
 class PornHubPlaylistBaseIE(PornHubBaseIE):
+    def _extract_page(self, url):
+        return int_or_none(self._search_regex(
+            r'\bpage=(\d+)', url, 'page', default=None))
+
     def _extract_entries(self, webpage, host):
         # Only process container div with main playlist content skipping
         # drop-down menu that uses similar pattern for videos (see
@@ -422,26 +493,6 @@ class PornHubPlaylistBaseIE(PornHubBaseIE):
                 container))
         ]
 
-    def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        host = mobj.group('host')
-        playlist_id = mobj.group('id')
-
-        webpage = self._download_webpage(url, playlist_id)
-
-        entries = self._extract_entries(webpage, host)
-
-        playlist = self._parse_json(
-            self._search_regex(
-                r'(?:playlistObject|PLAYLIST_VIEW)\s*=\s*({.+?});', webpage,
-                'playlist', default='{}'),
-            playlist_id, fatal=False)
-        title = playlist.get('title') or self._search_regex(
-            r'>Videos\s+in\s+(.+?)\s+[Pp]laylist<', webpage, 'title', fatal=False)
-
-        return self.playlist_result(
-            entries, playlist_id, title, playlist.get('description'))
-
 
 class PornHubUserIE(PornHubPlaylistBaseIE):
     _VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?(?P<host>pornhub(?:premium)?\.(?:com|net|org))/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/?#&]+))(?:[?#&]|/(?!videos)|$)'
@@ -463,14 +514,27 @@ class PornHubUserIE(PornHubPlaylistBaseIE):
     }, {
         'url': 'https://www.pornhub.com/model/zoe_ph?abc=1',
         'only_matching': True,
+    }, {
+        # Unavailable via /videos page, but available with direct pagination
+        # on pornstar page (see [1]), requires premium
+        # 1. https://github.com/ytdl-org/youtube-dl/issues/27853
+        'url': 'https://www.pornhubpremium.com/pornstar/sienna-west',
+        'only_matching': True,
+    }, {
+        # Same as before, multi page
+        'url': 'https://www.pornhubpremium.com/pornstar/lily-labeau',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         user_id = mobj.group('id')
+        videos_url = '%s/videos' % mobj.group('url')
+        page = self._extract_page(url)
+        if page:
+            videos_url = update_url_query(videos_url, {'page': page})
         return self.url_result(
-            '%s/videos' % mobj.group('url'), ie=PornHubPagedVideoListIE.ie_key(),
-            video_id=user_id)
+            videos_url, ie=PornHubPagedVideoListIE.ie_key(), video_id=user_id)
 
 
 class PornHubPagedPlaylistBaseIE(PornHubPlaylistBaseIE):
@@ -483,32 +547,55 @@ class PornHubPagedPlaylistBaseIE(PornHubPlaylistBaseIE):
                 <button[^>]+\bid=["\']moreDataBtn
             ''', webpage) is not None
 
-    def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        host = mobj.group('host')
-        item_id = mobj.group('id')
+    def _entries(self, url, host, item_id):
+        page = self._extract_page(url)
 
-        page = int_or_none(self._search_regex(
-            r'\bpage=(\d+)', url, 'page', default=None))
+        VIDEOS = '/videos'
 
-        entries = []
-        for page_num in (page, ) if page is not None else itertools.count(1):
+        def download_page(base_url, num, fallback=False):
+            note = 'Downloading page %d%s' % (num, ' (switch to fallback)' if fallback else '')
+            return self._download_webpage(
+                base_url, item_id, note, query={'page': num})
+
+        def is_404(e):
+            return isinstance(e.cause, compat_HTTPError) and e.cause.code == 404
+
+        base_url = url
+        has_page = page is not None
+        first_page = page if has_page else 1
+        for page_num in (first_page, ) if has_page else itertools.count(first_page):
             try:
-                webpage = self._download_webpage(
-                    url, item_id, 'Downloading page %d' % page_num,
-                    query={'page': page_num})
+                try:
+                    webpage = download_page(base_url, page_num)
+                except ExtractorError as e:
+                    # Some sources may not be available via /videos page,
+                    # trying to fallback to main page pagination (see [1])
+                    # 1. https://github.com/ytdl-org/youtube-dl/issues/27853
+                    if is_404(e) and page_num == first_page and VIDEOS in base_url:
+                        base_url = base_url.replace(VIDEOS, '')
+                        webpage = download_page(base_url, page_num, fallback=True)
+                    else:
+                        raise
             except ExtractorError as e:
-                if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404:
+                if is_404(e) and page_num != first_page:
                     break
                 raise
             page_entries = self._extract_entries(webpage, host)
             if not page_entries:
                 break
-            entries.extend(page_entries)
+            for e in page_entries:
+                yield e
             if not self._has_more(webpage):
                 break
 
-        return self.playlist_result(orderedSet(entries), item_id)
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        host = mobj.group('host')
+        item_id = mobj.group('id')
+
+        self._login(host)
+
+        return self.playlist_result(self._entries(url, host, item_id), item_id)
 
 
 class PornHubPagedVideoListIE(PornHubPagedPlaylistBaseIE):

youtube_dlc/extractor/spike.py

@@ -20,19 +20,6 @@ class BellatorIE(MTVServicesInfoExtractor):
     _FEED_URL = 'http://www.bellator.com/feeds/mrss/'
     _GEO_COUNTRIES = ['US']
 
-    def _extract_mgid(self, webpage, url):
-        mgid = None
-
-        if not mgid:
-            mgid = self._extract_triforce_mgid(webpage)
-
-        if not mgid:
-            mgid = self._extract_new_triforce_mgid(webpage, url)
-
-        return mgid
-
-# TODO Remove - Reason: Outdated Site
-
 
 class ParamountNetworkIE(MTVServicesInfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?paramountnetwork\.com/[^/]+/[\da-z]{6}(?:[/?#&]|$)'
@@ -56,16 +43,6 @@ class ParamountNetworkIE(MTVServicesInfoExtractor):
     def _get_feed_query(self, uri):
         return {
             'arcEp': 'paramountnetwork.com',
+            'imageEp': 'paramountnetwork.com',
             'mgid': uri,
         }
-
-    def _extract_mgid(self, webpage, url):
-        root_data = self._parse_json(self._search_regex(
-            r'window\.__DATA__\s*=\s*({.+})',
-            webpage, 'data'), None)
-
-        def find_sub_data(data, data_type):
-            return next(c for c in data['children'] if c.get('type') == data_type)
-
-        c = find_sub_data(find_sub_data(root_data, 'MainContainer'), 'VideoPlayer')
-        return c['props']['media']['video']['config']['uri']

youtube_dlc/extractor/spotify.py

@@ -0,0 +1,156 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import json
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    clean_podcast_url,
+    float_or_none,
+    int_or_none,
+    strip_or_none,
+    try_get,
+    unified_strdate,
+)
+
+
+class SpotifyBaseIE(InfoExtractor):
+    _ACCESS_TOKEN = None
+    _OPERATION_HASHES = {
+        'Episode': '8276d4423d709ae9b68ec1b74cc047ba0f7479059a37820be730f125189ac2bf',
+        'MinimalShow': '13ee079672fad3f858ea45a55eb109553b4fb0969ed793185b2e34cbb6ee7cc0',
+        'ShowEpisodes': 'e0e5ce27bd7748d2c59b4d44ba245a8992a05be75d6fabc3b20753fc8857444d',
+    }
+    _VALID_URL_TEMPL = r'https?://open\.spotify\.com/%s/(?P<id>[^/?&#]+)'
+
+    def _real_initialize(self):
+        self._ACCESS_TOKEN = self._download_json(
+            'https://open.spotify.com/get_access_token', None)['accessToken']
+
+    def _call_api(self, operation, video_id, variables):
+        return self._download_json(
+            'https://api-partner.spotify.com/pathfinder/v1/query', video_id, query={
+                'operationName': 'query' + operation,
+                'variables': json.dumps(variables),
+                'extensions': json.dumps({
+                    'persistedQuery': {
+                        'sha256Hash': self._OPERATION_HASHES[operation],
+                    },
+                })
+            }, headers={'authorization': 'Bearer ' + self._ACCESS_TOKEN})['data']
+
+    def _extract_episode(self, episode, series):
+        episode_id = episode['id']
+        title = episode['name'].strip()
+
+        formats = []
+        audio_preview = episode.get('audioPreview') or {}
+        audio_preview_url = audio_preview.get('url')
+        if audio_preview_url:
+            f = {
+                'url': audio_preview_url.replace('://p.scdn.co/mp3-preview/', '://anon-podcast.scdn.co/'),
+                'vcodec': 'none',
+            }
+            audio_preview_format = audio_preview.get('format')
+            if audio_preview_format:
+                f['format_id'] = audio_preview_format
+                mobj = re.match(r'([0-9A-Z]{3})_(?:[A-Z]+_)?(\d+)', audio_preview_format)
+                if mobj:
+                    f.update({
+                        'abr': int(mobj.group(2)),
+                        'ext': mobj.group(1).lower(),
+                    })
+            formats.append(f)
+
+        for item in (try_get(episode, lambda x: x['audio']['items']) or []):
+            item_url = item.get('url')
+            if not (item_url and item.get('externallyHosted')):
+                continue
+            formats.append({
+                'url': clean_podcast_url(item_url),
+                'vcodec': 'none',
+            })
+
+        thumbnails = []
+        for source in (try_get(episode, lambda x: x['coverArt']['sources']) or []):
+            source_url = source.get('url')
+            if not source_url:
+                continue
+            thumbnails.append({
+                'url': source_url,
+                'width': int_or_none(source.get('width')),
+                'height': int_or_none(source.get('height')),
+            })
+
+        return {
+            'id': episode_id,
+            'title': title,
+            'formats': formats,
+            'thumbnails': thumbnails,
+            'description': strip_or_none(episode.get('description')),
+            'duration': float_or_none(try_get(
+                episode, lambda x: x['duration']['totalMilliseconds']), 1000),
+            'release_date': unified_strdate(try_get(
+                episode, lambda x: x['releaseDate']['isoString'])),
+            'series': series,
+        }
+
+
+class SpotifyIE(SpotifyBaseIE):
+    IE_NAME = 'spotify'
+    _VALID_URL = SpotifyBaseIE._VALID_URL_TEMPL % 'episode'
+    _TEST = {
+        'url': 'https://open.spotify.com/episode/4Z7GAJ50bgctf6uclHlWKo',
+        'md5': '74010a1e3fa4d9e1ab3aa7ad14e42d3b',
+        'info_dict': {
+            'id': '4Z7GAJ50bgctf6uclHlWKo',
+            'ext': 'mp3',
+            'title': 'From the archive: Why time management is ruining our lives',
+            'description': 'md5:b120d9c4ff4135b42aa9b6d9cde86935',
+            'duration': 2083.605,
+            'release_date': '20201217',
+            'series': "The Guardian's Audio Long Reads",
+        }
+    }
+
+    def _real_extract(self, url):
+        episode_id = self._match_id(url)
+        episode = self._call_api('Episode', episode_id, {
+            'uri': 'spotify:episode:' + episode_id
+        })['episode']
+        return self._extract_episode(
+            episode, try_get(episode, lambda x: x['podcast']['name']))
+
+
+class SpotifyShowIE(SpotifyBaseIE):
+    IE_NAME = 'spotify:show'
+    _VALID_URL = SpotifyBaseIE._VALID_URL_TEMPL % 'show'
+    _TEST = {
+        'url': 'https://open.spotify.com/show/4PM9Ke6l66IRNpottHKV9M',
+        'info_dict': {
+            'id': '4PM9Ke6l66IRNpottHKV9M',
+            'title': 'The Story from the Guardian',
+            'description': 'The Story podcast is dedicated to our finest audio documentaries, investigations and long form stories',
+        },
+        'playlist_mincount': 36,
+    }
+
+    def _real_extract(self, url):
+        show_id = self._match_id(url)
+        podcast = self._call_api('ShowEpisodes', show_id, {
+            'limit': 1000000000,
+            'offset': 0,
+            'uri': 'spotify:show:' + show_id,
+        })['podcast']
+        podcast_name = podcast.get('name')
+
+        entries = []
+        for item in (try_get(podcast, lambda x: x['episodes']['items']) or []):
+            episode = item.get('episode')
+            if not episode:
+                continue
+            entries.append(self._extract_episode(episode, podcast_name))
+
+        return self.playlist_result(
+            entries, show_id, podcast_name, podcast.get('description'))

youtube_dlc/extractor/svt.py

@@ -255,8 +255,10 @@ class SVTPlayIE(SVTPlayBaseIE):
             svt_id = self._search_regex(
                 (r'<video[^>]+data-video-id=["\']([\da-zA-Z-]+)',
                  r'["\']videoSvtId["\']\s*:\s*["\']([\da-zA-Z-]+)',
+                 r'["\']videoSvtId\\?["\']\s*:\s*\\?["\']([\da-zA-Z-]+)',
                  r'"content"\s*:\s*{.*?"id"\s*:\s*"([\da-zA-Z-]+)"',
-                 r'["\']svtId["\']\s*:\s*["\']([\da-zA-Z-]+)'),
+                 r'["\']svtId["\']\s*:\s*["\']([\da-zA-Z-]+)',
+                 r'["\']svtId\\?["\']\s*:\s*\\?["\']([\da-zA-Z-]+)'),
                 webpage, 'video id')
 
         info_dict = self._extract_by_video_id(svt_id, webpage)

youtube_dlc/extractor/trovo.py

@@ -0,0 +1,193 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import json
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    int_or_none,
+    str_or_none,
+    try_get,
+)
+
+
+class TrovoBaseIE(InfoExtractor):
+    _VALID_URL_BASE = r'https?://(?:www\.)?trovo\.live/'
+
+    def _extract_streamer_info(self, data):
+        streamer_info = data.get('streamerInfo') or {}
+        username = streamer_info.get('userName')
+        return {
+            'uploader': streamer_info.get('nickName'),
+            'uploader_id': str_or_none(streamer_info.get('uid')),
+            'uploader_url': 'https://trovo.live/' + username if username else None,
+        }
+
+
+class TrovoIE(TrovoBaseIE):
+    _VALID_URL = TrovoBaseIE._VALID_URL_BASE + r'(?!(?:clip|video)/)(?P<id>[^/?&#]+)'
+
+    def _real_extract(self, url):
+        username = self._match_id(url)
+        live_info = self._download_json(
+            'https://gql.trovo.live/', username, query={
+                'query': '''{
+  getLiveInfo(params: {userName: "%s"}) {
+    isLive
+    programInfo	{
+      coverUrl
+      id
+      streamInfo {
+        desc
+        playUrl
+      }
+      title
+    }
+    streamerInfo {
+        nickName
+        uid
+        userName
+    }
+  }
+}''' % username,
+            })['data']['getLiveInfo']
+        if live_info.get('isLive') == 0:
+            raise ExtractorError('%s is offline' % username, expected=True)
+        program_info = live_info['programInfo']
+        program_id = program_info['id']
+        title = self._live_title(program_info['title'])
+
+        formats = []
+        for stream_info in (program_info.get('streamInfo') or []):
+            play_url = stream_info.get('playUrl')
+            if not play_url:
+                continue
+            format_id = stream_info.get('desc')
+            formats.append({
+                'format_id': format_id,
+                'height': int_or_none(format_id[:-1]) if format_id else None,
+                'url': play_url,
+            })
+        self._sort_formats(formats)
+
+        info = {
+            'id': program_id,
+            'title': title,
+            'formats': formats,
+            'thumbnail': program_info.get('coverUrl'),
+            'is_live': True,
+        }
+        info.update(self._extract_streamer_info(live_info))
+        return info
+
+
+class TrovoVodIE(TrovoBaseIE):
+    _VALID_URL = TrovoBaseIE._VALID_URL_BASE + r'(?:clip|video)/(?P<id>[^/?&#]+)'
+    _TESTS = [{
+        'url': 'https://trovo.live/video/ltv-100095501_100095501_1609596043',
+        'info_dict': {
+            'id': 'ltv-100095501_100095501_1609596043',
+            'ext': 'mp4',
+            'title': 'Spontaner 12 Stunden Stream! - Ok Boomer!',
+            'uploader': 'Exsl',
+            'timestamp': 1609640305,
+            'upload_date': '20210103',
+            'uploader_id': '100095501',
+            'duration': 43977,
+            'view_count': int,
+            'like_count': int,
+            'comment_count': int,
+            'comments': 'mincount:8',
+            'categories': ['Grand Theft Auto V'],
+        },
+    }, {
+        'url': 'https://trovo.live/clip/lc-5285890810184026005',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        vid = self._match_id(url)
+        resp = self._download_json(
+            'https://gql.trovo.live/', vid, data=json.dumps([{
+                'query': '''{
+  batchGetVodDetailInfo(params: {vids: ["%s"]}) {
+    VodDetailInfos
+  }
+}''' % vid,
+            }, {
+                'query': '''{
+  getCommentList(params: {appInfo: {postID: "%s"}, pageSize: 1000000000, preview: {}}) {
+    commentList {
+      author {
+        nickName
+        uid
+      }
+      commentID
+      content
+      createdAt
+      parentID
+    }
+  }
+}''' % vid,
+            }]).encode(), headers={
+                'Content-Type': 'application/json',
+            })
+        vod_detail_info = resp[0]['data']['batchGetVodDetailInfo']['VodDetailInfos'][vid]
+        vod_info = vod_detail_info['vodInfo']
+        title = vod_info['title']
+
+        language = vod_info.get('languageName')
+        formats = []
+        for play_info in (vod_info.get('playInfos') or []):
+            play_url = play_info.get('playUrl')
+            if not play_url:
+                continue
+            format_id = play_info.get('desc')
+            formats.append({
+                'ext': 'mp4',
+                'filesize': int_or_none(play_info.get('fileSize')),
+                'format_id': format_id,
+                'height': int_or_none(format_id[:-1]) if format_id else None,
+                'language': language,
+                'protocol': 'm3u8_native',
+                'tbr': int_or_none(play_info.get('bitrate')),
+                'url': play_url,
+            })
+        self._sort_formats(formats)
+
+        category = vod_info.get('categoryName')
+        get_count = lambda x: int_or_none(vod_info.get(x + 'Num'))
+
+        comment_list = try_get(resp, lambda x: x[1]['data']['getCommentList']['commentList'], list) or []
+        comments = []
+        for comment in comment_list:
+            content = comment.get('content')
+            if not content:
+                continue
+            author = comment.get('author') or {}
+            parent = comment.get('parentID')
+            comments.append({
+                'author': author.get('nickName'),
+                'author_id': str_or_none(author.get('uid')),
+                'id': str_or_none(comment.get('commentID')),
+                'text': content,
+                'timestamp': int_or_none(comment.get('createdAt')),
+                'parent': 'root' if parent == 0 else str_or_none(parent),
+            })
+
+        info = {
+            'id': vid,
+            'title': title,
+            'formats': formats,
+            'thumbnail': vod_info.get('coverUrl'),
+            'timestamp': int_or_none(vod_info.get('publishTs')),
+            'duration': int_or_none(vod_info.get('duration')),
+            'view_count': get_count('watch'),
+            'like_count': get_count('like'),
+            'comment_count': get_count('comment'),
+            'comments': comments,
+            'categories': [category] if category else None,
+        }
+        info.update(self._extract_streamer_info(vod_detail_info))
+        return info

youtube_dlc/extractor/tv2.py

@@ -20,7 +20,7 @@ from ..utils import (
 
 class TV2IE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?tv2\.no/v/(?P<id>\d+)'
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.tv2.no/v/916509/',
         'info_dict': {
             'id': '916509',
@@ -33,7 +33,7 @@ class TV2IE(InfoExtractor):
             'view_count': int,
             'categories': list,
         },
-    }
+    }]
     _API_DOMAIN = 'sumo.tv2.no'
     _PROTOCOLS = ('HDS', 'HLS', 'DASH')
     _GEO_COUNTRIES = ['NO']
@@ -42,6 +42,12 @@ class TV2IE(InfoExtractor):
         video_id = self._match_id(url)
         api_base = 'http://%s/api/web/asset/%s' % (self._API_DOMAIN, video_id)
 
+        asset = self._download_json(
+            api_base + '.json', video_id,
+            'Downloading metadata JSON')['asset']
+        title = asset.get('subtitle') or asset['title']
+        is_live = asset.get('live') is True
+
         formats = []
         format_urls = []
         for protocol in self._PROTOCOLS:
@@ -81,7 +87,8 @@ class TV2IE(InfoExtractor):
                 elif ext == 'm3u8':
                     if not data.get('drmProtected'):
                         formats.extend(self._extract_m3u8_formats(
-                            video_url, video_id, 'mp4', entry_protocol='m3u8_native',
+                            video_url, video_id, 'mp4',
+                            'm3u8' if is_live else 'm3u8_native',
                             m3u8_id=format_id, fatal=False))
                 elif ext == 'mpd':
                     formats.extend(self._extract_mpd_formats(
@@ -99,11 +106,6 @@ class TV2IE(InfoExtractor):
             raise ExtractorError('This video is DRM protected.', expected=True)
         self._sort_formats(formats)
 
-        asset = self._download_json(
-            api_base + '.json', video_id,
-            'Downloading metadata JSON')['asset']
-        title = asset['title']
-
         thumbnails = [{
             'id': thumbnail.get('@type'),
             'url': thumbnail.get('url'),
@@ -112,7 +114,7 @@ class TV2IE(InfoExtractor):
         return {
             'id': video_id,
             'url': video_url,
-            'title': title,
+            'title': self._live_title(title) if is_live else title,
             'description': strip_or_none(asset.get('description')),
             'thumbnails': thumbnails,
             'timestamp': parse_iso8601(asset.get('createTime')),
@@ -120,6 +122,7 @@ class TV2IE(InfoExtractor):
             'view_count': int_or_none(asset.get('views')),
             'categories': asset.get('keywords', '').split(','),
             'formats': formats,
+            'is_live': is_live,
         }
 
 
@@ -168,13 +171,13 @@ class TV2ArticleIE(InfoExtractor):
 
 
 class KatsomoIE(TV2IE):
-    _VALID_URL = r'https?://(?:www\.)?(?:katsomo|mtv)\.fi/(?:#!/)?(?:[^/]+/[0-9a-z-]+-\d+/[0-9a-z-]+-|[^/]+/\d+/[^/]+/)(?P<id>\d+)'
-    _TEST = {
+    _VALID_URL = r'https?://(?:www\.)?(?:katsomo|mtv(uutiset)?)\.fi/(?:sarja/[0-9a-z-]+-\d+/[0-9a-z-]+-|(?:#!/)?jakso/(?:\d+/[^/]+/)?|video/prog)(?P<id>\d+)'
+    _TESTS = [{
         'url': 'https://www.mtv.fi/sarja/mtv-uutiset-live-33001002003/lahden-pelicans-teki-kovan-ratkaisun-ville-nieminen-pihalle-1181321',
         'info_dict': {
             'id': '1181321',
             'ext': 'mp4',
-            'title': 'MTV Uutiset Live',
+            'title': 'Lahden Pelicans teki kovan ratkaisun – Ville Nieminen pihalle',
             'description': 'Päätöksen teki Pelicansin hallitus.',
             'timestamp': 1575116484,
             'upload_date': '20191130',
@@ -186,7 +189,60 @@ class KatsomoIE(TV2IE):
             # m3u8 download
             'skip_download': True,
         },
-    }
+    }, {
+        'url': 'http://www.katsomo.fi/#!/jakso/33001005/studio55-fi/658521/jukka-kuoppamaki-tekee-yha-lauluja-vaikka-lentokoneessa',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.mtvuutiset.fi/video/prog1311159',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.katsomo.fi/#!/jakso/1311159',
+        'only_matching': True,
+    }]
     _API_DOMAIN = 'api.katsomo.fi'
     _PROTOCOLS = ('HLS', 'MPD')
     _GEO_COUNTRIES = ['FI']
+
+
+class MTVUutisetArticleIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)mtvuutiset\.fi/artikkeli/[^/]+/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://www.mtvuutiset.fi/artikkeli/tallaisia-vaurioita-viking-amorellassa-on-useamman-osaston-alla-vetta/7931384',
+        'info_dict': {
+            'id': '1311159',
+            'ext': 'mp4',
+            'title': 'Viking Amorellan matkustajien evakuointi on alkanut – tältä operaatio näyttää laivalla',
+            'description': 'Viking Amorellan matkustajien evakuointi on alkanut – tältä operaatio näyttää laivalla',
+            'timestamp': 1600608966,
+            'upload_date': '20200920',
+            'duration': 153.7886666,
+            'view_count': int,
+            'categories': list,
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }, {
+        # multiple Youtube embeds
+        'url': 'https://www.mtvuutiset.fi/artikkeli/50-vuotta-subarun-vastaiskua/6070962',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        article_id = self._match_id(url)
+        article = self._download_json(
+            'http://api.mtvuutiset.fi/mtvuutiset/api/json/' + article_id,
+            article_id)
+
+        def entries():
+            for video in (article.get('videos') or []):
+                video_type = video.get('videotype')
+                video_url = video.get('url')
+                if not (video_url and video_type in ('katsomo', 'youtube')):
+                    continue
+                yield self.url_result(
+                    video_url, video_type.capitalize(), video.get('video_id'))
+
+        return self.playlist_result(
+            entries(), article_id, article.get('title'), article.get('description'))

youtube_dlc/extractor/tv4.py

@@ -17,7 +17,7 @@ class TV4IE(InfoExtractor):
             tv4\.se/(?:[^/]+)/klipp/(?:.*)-|
             tv4play\.se/
             (?:
-                (?:program|barn)/(?:[^/]+/|(?:[^\?]+)\?video_id=)|
+                (?:program|barn)/(?:(?:[^/]+/){1,2}|(?:[^\?]+)\?video_id=)|
                 iframe/video/|
                 film/|
                 sport/|
@@ -65,6 +65,10 @@ class TV4IE(InfoExtractor):
         {
             'url': 'http://www.tv4play.se/program/farang/3922081',
             'only_matching': True,
+        },
+        {
+            'url': 'https://www.tv4play.se/program/nyheterna/avsnitt/13315940',
+            'only_matching': True,
         }
     ]
 

youtube_dlc/extractor/vidio.py

@@ -4,7 +4,13 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..utils import int_or_none
+from ..utils import (
+    int_or_none,
+    parse_iso8601,
+    str_or_none,
+    strip_or_none,
+    try_get,
+)
 
 
 class VidioIE(InfoExtractor):
@@ -21,57 +27,63 @@ class VidioIE(InfoExtractor):
             'thumbnail': r're:^https?://.*\.jpg$',
             'duration': 149,
             'like_count': int,
+            'uploader': 'TWELVE Pic',
+            'timestamp': 1444902800,
+            'upload_date': '20151015',
+            'uploader_id': 'twelvepictures',
+            'channel': 'Cover Music Video',
+            'channel_id': '280236',
+            'view_count': int,
+            'dislike_count': int,
+            'comment_count': int,
+            'tags': 'count:4',
         },
     }, {
         'url': 'https://www.vidio.com/watch/77949-south-korea-test-fires-missile-that-can-strike-all-of-the-north',
         'only_matching': True,
     }]
 
+    def _real_initialize(self):
+        self._api_key = self._download_json(
+            'https://www.vidio.com/auth', None, data=b'')['api_key']
+
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id, display_id = mobj.group('id', 'display_id')
+        video_id, display_id = re.match(self._VALID_URL, url).groups()
+        data = self._download_json(
+            'https://api.vidio.com/videos/' + video_id, display_id, headers={
+                'Content-Type': 'application/vnd.api+json',
+                'X-API-KEY': self._api_key,
+            })
+        video = data['videos'][0]
+        title = video['title'].strip()
 
-        webpage = self._download_webpage(url, display_id)
-
-        title = self._og_search_title(webpage)
-
-        m3u8_url, duration, thumbnail = [None] * 3
-
-        clips = self._parse_json(
-            self._html_search_regex(
-                r'data-json-clips\s*=\s*(["\'])(?P<data>\[.+?\])\1',
-                webpage, 'video data', default='[]', group='data'),
-            display_id, fatal=False)
-        if clips:
-            clip = clips[0]
-            m3u8_url = clip.get('sources', [{}])[0].get('file')
-            duration = clip.get('clip_duration')
-            thumbnail = clip.get('image')
-
-        m3u8_url = m3u8_url or self._search_regex(
-            r'data(?:-vjs)?-clip-hls-url=(["\'])(?P<url>(?:(?!\1).)+)\1',
-            webpage, 'hls url', group='url')
         formats = self._extract_m3u8_formats(
-            m3u8_url, display_id, 'mp4', entry_protocol='m3u8_native')
+            data['clips'][0]['hls_url'], display_id, 'mp4', 'm3u8_native')
         self._sort_formats(formats)
 
-        duration = int_or_none(duration or self._search_regex(
-            r'data-video-duration=(["\'])(?P<duration>\d+)\1', webpage,
-            'duration', fatal=False, group='duration'))
-        thumbnail = thumbnail or self._og_search_thumbnail(webpage)
-
-        like_count = int_or_none(self._search_regex(
-            (r'<span[^>]+data-comment-vote-count=["\'](\d+)',
-             r'<span[^>]+class=["\'].*?\blike(?:__|-)count\b.*?["\'][^>]*>\s*(\d+)'),
-            webpage, 'like count', fatal=False))
+        get_first = lambda x: try_get(data, lambda y: y[x + 's'][0], dict) or {}
+        channel = get_first('channel')
+        user = get_first('user')
+        username = user.get('username')
+        get_count = lambda x: int_or_none(video.get('total_' + x))
 
         return {
             'id': video_id,
             'display_id': display_id,
             'title': title,
-            'description': self._og_search_description(webpage),
-            'thumbnail': thumbnail,
-            'duration': duration,
-            'like_count': like_count,
+            'description': strip_or_none(video.get('description')),
+            'thumbnail': video.get('image_url_medium'),
+            'duration': int_or_none(video.get('duration')),
+            'like_count': get_count('likes'),
             'formats': formats,
+            'uploader': user.get('name'),
+            'timestamp': parse_iso8601(video.get('created_at')),
+            'uploader_id': username,
+            'uploader_url': 'https://www.vidio.com/@' + username if username else None,
+            'channel': channel.get('name'),
+            'channel_id': str_or_none(channel.get('id')),
+            'view_count': get_count('view_count'),
+            'dislike_count': get_count('dislikes'),
+            'comment_count': get_count('comments'),
+            'tags': video.get('tag_list'),
         }

youtube_dlc/extractor/vlive.py

@@ -125,7 +125,7 @@ class VLiveIE(VLiveBaseIE):
                 headers={'Referer': 'https://www.vlive.tv/'}, query=query)
         except ExtractorError as e:
             if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
-                self.raise_login_required(json.loads(e.cause.read().decode())['message'])
+                self.raise_login_required(json.loads(e.cause.read().decode('utf-8'))['message'])
             raise
 
     def _real_extract(self, url):

youtube_dlc/extractor/vtm.py

@@ -0,0 +1,62 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    parse_iso8601,
+    try_get,
+)
+
+
+class VTMIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?vtm\.be/([^/?&#]+)~v(?P<id>[0-9a-f]{8}(?:-[0-9a-f]{4}){3}-[0-9a-f]{12})'
+    _TEST = {
+        'url': 'https://vtm.be/gast-vernielt-genkse-hotelkamer~ve7534523-279f-4b4d-a5c9-a33ffdbe23e1',
+        'md5': '37dca85fbc3a33f2de28ceb834b071f8',
+        'info_dict': {
+            'id': '192445',
+            'ext': 'mp4',
+            'title': 'Gast vernielt Genkse hotelkamer',
+            'timestamp': 1611060180,
+            'upload_date': '20210119',
+            'duration': 74,
+            # TODO: fix url _type result processing
+            # 'series': 'Op Interventie',
+        }
+    }
+
+    def _real_extract(self, url):
+        uuid = self._match_id(url)
+        video = self._download_json(
+            'https://omc4vm23offuhaxx6hekxtzspi.appsync-api.eu-west-1.amazonaws.com/graphql',
+            uuid, query={
+                'query': '''{
+  getComponent(type: Video, uuid: "%s") {
+    ... on Video {
+      description
+      duration
+      myChannelsVideo
+      program {
+        title
+      }
+      publishedAt
+      title
+    }
+  }
+}''' % uuid,
+            }, headers={
+                'x-api-key': 'da2-lz2cab4tfnah3mve6wiye4n77e',
+            })['data']['getComponent']
+
+        return {
+            '_type': 'url',
+            'id': uuid,
+            'title': video.get('title'),
+            'url': 'http://mychannels.video/embed/%d' % video['myChannelsVideo'],
+            'description': video.get('description'),
+            'timestamp': parse_iso8601(video.get('publishedAt')),
+            'duration': int_or_none(video.get('duration')),
+            'series': try_get(video, lambda x: x['program']['title']),
+            'ie_key': 'Medialaan',
+        }

youtube_dlc/extractor/vvvvid.py

@@ -4,6 +4,7 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from .youtube import YoutubeIE
 from ..utils import (
     ExtractorError,
     int_or_none,
@@ -47,6 +48,22 @@ class VVVVIDIE(InfoExtractor):
         'params': {
             'skip_download': True,
         },
+    }, {
+        # video_type == 'video/youtube'
+        'url': 'https://www.vvvvid.it/show/404/one-punch-man/406/486683/trailer',
+        'md5': '33e0edfba720ad73a8782157fdebc648',
+        'info_dict': {
+            'id': 'RzmFKUDOUgw',
+            'ext': 'mp4',
+            'title': 'Trailer',
+            'upload_date': '20150906',
+            'description': 'md5:a5e802558d35247fee285875328c0b80',
+            'uploader_id': 'BandaiVisual',
+            'uploader': 'BANDAI NAMCO Arts Channel',
+        },
+        'params': {
+            'skip_download': True,
+        },
     }, {
         'url': 'https://www.vvvvid.it/show/434/perche-dovrei-guardarlo-di-dario-moccia/437/489048',
         'only_matching': True
@@ -154,12 +171,13 @@ class VVVVIDIE(InfoExtractor):
                     if season_number:
                         info['season_number'] = int(season_number)
 
-        for quality in ('_sd', ''):
+        video_type = video_data.get('video_type')
+        is_youtube = False
+        for quality in ('', '_sd'):
             embed_code = video_data.get('embed_info' + quality)
             if not embed_code:
                 continue
             embed_code = ds(embed_code)
-            video_type = video_data.get('video_type')
             if video_type in ('video/rcs', 'video/kenc'):
                 if video_type == 'video/kenc':
                     kenc = self._download_json(
@@ -172,19 +190,28 @@ class VVVVIDIE(InfoExtractor):
                     if kenc_message:
                         embed_code += '?' + ds(kenc_message)
                 formats.extend(self._extract_akamai_formats(embed_code, video_id))
+            elif video_type == 'video/youtube':
+                info.update({
+                    '_type': 'url_transparent',
+                    'ie_key': YoutubeIE.ie_key(),
+                    'url': embed_code,
+                })
+                is_youtube = True
+                break
             else:
                 formats.extend(self._extract_wowza_formats(
                     'http://sb.top-ix.org/videomg/_definst_/mp4:%s/playlist.m3u8' % embed_code, video_id))
             metadata_from_url(embed_code)
 
-        self._sort_formats(formats)
+        if not is_youtube:
+            self._sort_formats(formats)
+            info['formats'] = formats
 
         metadata_from_url(video_data.get('thumbnail'))
         info.update(self._extract_common_video_info(video_data))
         info.update({
             'id': video_id,
             'title': title,
-            'formats': formats,
             'duration': int_or_none(video_data.get('length')),
             'series': video_data.get('show_title'),
             'season_id': season_id,

youtube_dlc/extractor/wat.py

@@ -1,12 +1,9 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
 from ..compat import compat_str
 from ..utils import (
-    ExtractorError,
     unified_strdate,
     HEADRequest,
     int_or_none,
@@ -46,15 +43,6 @@ class WatIE(InfoExtractor):
         },
     ]
 
-    _FORMATS = (
-        (200, 416, 234),
-        (400, 480, 270),
-        (600, 640, 360),
-        (1200, 640, 360),
-        (1800, 960, 540),
-        (2500, 1280, 720),
-    )
-
     def _real_extract(self, url):
         video_id = self._match_id(url)
         video_id = video_id if video_id.isdigit() and len(video_id) > 6 else compat_str(int(video_id, 36))
@@ -97,46 +85,20 @@ class WatIE(InfoExtractor):
                     return red_url
             return None
 
-        def remove_bitrate_limit(manifest_url):
-            return re.sub(r'(?:max|min)_bitrate=\d+&?', '', manifest_url)
-
         formats = []
-        try:
-            alt_urls = lambda manifest_url: [re.sub(r'(?:wdv|ssm)?\.ism/', repl + '.ism/', manifest_url) for repl in ('', 'ssm')]
-            manifest_urls = self._download_json(
-                'http://www.wat.tv/get/webhtml/' + video_id, video_id)
-            m3u8_url = manifest_urls.get('hls')
-            if m3u8_url:
-                m3u8_url = remove_bitrate_limit(m3u8_url)
-                for m3u8_alt_url in alt_urls(m3u8_url):
-                    formats.extend(self._extract_m3u8_formats(
-                        m3u8_alt_url, video_id, 'mp4',
-                        'm3u8_native', m3u8_id='hls', fatal=False))
-                    formats.extend(self._extract_f4m_formats(
-                        m3u8_alt_url.replace('ios', 'web').replace('.m3u8', '.f4m'),
-                        video_id, f4m_id='hds', fatal=False))
-            mpd_url = manifest_urls.get('mpd')
-            if mpd_url:
-                mpd_url = remove_bitrate_limit(mpd_url)
-                for mpd_alt_url in alt_urls(mpd_url):
-                    formats.extend(self._extract_mpd_formats(
-                        mpd_alt_url, video_id, mpd_id='dash', fatal=False))
-            self._sort_formats(formats)
-        except ExtractorError:
-            abr = 64
-            for vbr, width, height in self._FORMATS:
-                tbr = vbr + abr
-                format_id = 'http-%s' % tbr
-                fmt_url = 'http://dnl.adv.tf1.fr/2/USP-0x0/%s/%s/%s/ssm/%s-%s-64k.mp4' % (video_id[-4:-2], video_id[-2:], video_id, video_id, vbr)
-                if self._is_valid_url(fmt_url, video_id, format_id):
-                    formats.append({
-                        'format_id': format_id,
-                        'url': fmt_url,
-                        'vbr': vbr,
-                        'abr': abr,
-                        'width': width,
-                        'height': height,
-                    })
+        manifest_urls = self._download_json(
+            'http://www.wat.tv/get/webhtml/' + video_id, video_id)
+        m3u8_url = manifest_urls.get('hls')
+        if m3u8_url:
+            formats.extend(self._extract_m3u8_formats(
+                m3u8_url, video_id, 'mp4',
+                'm3u8_native', m3u8_id='hls', fatal=False))
+        mpd_url = manifest_urls.get('mpd')
+        if mpd_url:
+            formats.extend(self._extract_mpd_formats(
+                mpd_url.replace('://das-q1.tf1.fr/', '://das-q1-ssl.tf1.fr/'),
+                video_id, mpd_id='dash', fatal=False))
+        self._sort_formats(formats)
 
         date_diffusion = first_chapter.get('date_diffusion') or video_data.get('configv4', {}).get('estatS4')
         upload_date = unified_strdate(date_diffusion) if date_diffusion else None

youtube_dlc/extractor/yahoo.py

@@ -177,46 +177,9 @@ class YahooIE(InfoExtractor):
         'only_matching': True,
     }]
 
-    def _real_extract(self, url):
-        url, country, display_id = re.match(self._VALID_URL, url).groups()
-        if not country:
-            country = 'us'
-        else:
-            country = country.split('-')[0]
-        api_base = 'https://%s.yahoo.com/_td/api/resource/' % country
-
-        for i, uuid in enumerate(['url=' + url, 'ymedia-alias=' + display_id]):
-            content = self._download_json(
-                api_base + 'content;getDetailView=true;uuids=["%s"]' % uuid,
-                display_id, 'Downloading content JSON metadata', fatal=i == 1)
-            if content:
-                item = content['items'][0]
-                break
-
-        if item.get('type') != 'video':
-            entries = []
-
-            cover = item.get('cover') or {}
-            if cover.get('type') == 'yvideo':
-                cover_url = cover.get('url')
-                if cover_url:
-                    entries.append(self.url_result(
-                        cover_url, 'Yahoo', cover.get('uuid')))
-
-            for e in item.get('body', []):
-                if e.get('type') == 'videoIframe':
-                    iframe_url = e.get('url')
-                    if not iframe_url:
-                        continue
-                    entries.append(self.url_result(iframe_url))
-
-            return self.playlist_result(
-                entries, item.get('uuid'),
-                item.get('title'), item.get('summary'))
-
-        video_id = item['uuid']
+    def _extract_yahoo_video(self, video_id, country):
         video = self._download_json(
-            api_base + 'VideoService.videos;view=full;video_ids=["%s"]' % video_id,
+            'https://%s.yahoo.com/_td/api/resource/VideoService.videos;view=full;video_ids=["%s"]' % (country, video_id),
             video_id, 'Downloading video JSON metadata')[0]
         title = video['title']
 
@@ -298,7 +261,6 @@ class YahooIE(InfoExtractor):
             'id': video_id,
             'title': self._live_title(title) if is_live else title,
             'formats': formats,
-            'display_id': display_id,
             'thumbnails': thumbnails,
             'description': clean_html(video.get('description')),
             'timestamp': parse_iso8601(video.get('publish_time')),
@@ -311,6 +273,44 @@ class YahooIE(InfoExtractor):
             'episode_number': int_or_none(series_info.get('episode_number')),
         }
 
+    def _real_extract(self, url):
+        url, country, display_id = re.match(self._VALID_URL, url).groups()
+        if not country:
+            country = 'us'
+        else:
+            country = country.split('-')[0]
+
+        item = self._download_json(
+            'https://%s.yahoo.com/caas/content/article' % country, display_id,
+            'Downloading content JSON metadata', query={
+                'url': url
+            })['items'][0]['data']['partnerData']
+
+        if item.get('type') != 'video':
+            entries = []
+
+            cover = item.get('cover') or {}
+            if cover.get('type') == 'yvideo':
+                cover_url = cover.get('url')
+                if cover_url:
+                    entries.append(self.url_result(
+                        cover_url, 'Yahoo', cover.get('uuid')))
+
+            for e in (item.get('body') or []):
+                if e.get('type') == 'videoIframe':
+                    iframe_url = e.get('url')
+                    if not iframe_url:
+                        continue
+                    entries.append(self.url_result(iframe_url))
+
+            return self.playlist_result(
+                entries, item.get('uuid'),
+                item.get('title'), item.get('summary'))
+
+        info = self._extract_yahoo_video(item['uuid'], country)
+        info['display_id'] = display_id
+        return info
+
 
 class YahooSearchIE(SearchInfoExtractor):
     IE_DESC = 'Yahoo screen search'

youtube_dlc/extractor/zype.py

@@ -87,11 +87,16 @@ class ZypeIE(InfoExtractor):
                 r'(["\'])(?P<url>(?:(?!\1).)+\.m3u8(?:(?!\1).)*)\1',
                 body, 'm3u8 url', group='url', default=None)
             if not m3u8_url:
-                source = self._parse_json(self._search_regex(
-                    r'(?s)sources\s*:\s*\[\s*({.+?})\s*\]', body,
-                    'source'), video_id, js_to_json)
-                if source.get('integration') == 'verizon-media':
-                    m3u8_url = 'https://content.uplynk.com/%s.m3u8' % source['id']
+                source = self._search_regex(
+                    r'(?s)sources\s*:\s*\[\s*({.+?})\s*\]', body, 'source')
+
+                def get_attr(key):
+                    return self._search_regex(
+                        r'\b%s\s*:\s*([\'"])(?P<val>(?:(?!\1).)+)\1' % key,
+                        source, key, group='val')
+
+                if get_attr('integration') == 'verizon-media':
+                    m3u8_url = 'https://content.uplynk.com/%s.m3u8' % get_attr('id')
             formats = self._extract_m3u8_formats(
                 m3u8_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls')
             text_tracks = self._search_regex(

youtube_dlc/options.py

@@ -14,12 +14,18 @@ from .compat import (
     compat_shlex_split,
 )
 from .utils import (
+    expand_path,
+    get_executable_path,
+    OUTTMPL_TYPES,
     preferredencoding,
     write_string,
 )
 from .version import __version__
 
 
+_remux_formats = ('mp4', 'mkv', 'flv', 'webm', 'mov', 'avi', 'mp3', 'mka', 'm4a', 'ogg', 'opus')
+
+
 def _hide_login_info(opts):
     PRIVATE_OPTS = set(['-p', '--password', '-u', '--username', '--video-password', '--ap-password', '--ap-username'])
     eqre = re.compile('^(?P<key>' + ('|'.join(re.escape(po) for po in PRIVATE_OPTS)) + ')=.+$')
@@ -62,7 +68,7 @@ def parseOpts(overrideArguments=None):
             userConfFile = os.path.join(xdg_config_home, '%s.conf' % package_name)
         userConf = _readOptions(userConfFile, default=None)
         if userConf is not None:
-            return userConf
+            return userConf, userConfFile
 
         # appdata
         appdata_dir = compat_getenv('appdata')
@@ -70,19 +76,21 @@ def parseOpts(overrideArguments=None):
             userConfFile = os.path.join(appdata_dir, package_name, 'config')
             userConf = _readOptions(userConfFile, default=None)
             if userConf is None:
-                userConf = _readOptions('%s.txt' % userConfFile, default=None)
+                userConfFile += '.txt'
+                userConf = _readOptions(userConfFile, default=None)
         if userConf is not None:
-            return userConf
+            return userConf, userConfFile
 
         # home
         userConfFile = os.path.join(compat_expanduser('~'), '%s.conf' % package_name)
         userConf = _readOptions(userConfFile, default=None)
         if userConf is None:
-            userConf = _readOptions('%s.txt' % userConfFile, default=None)
+            userConfFile += '.txt'
+            userConf = _readOptions(userConfFile, default=None)
         if userConf is not None:
-            return userConf
+            return userConf, userConfFile
 
-        return default
+        return default, None
 
     def _format_option_string(option):
         ''' ('-o', '--option') -> -o, --format METAVAR'''
@@ -104,6 +112,20 @@ def parseOpts(overrideArguments=None):
     def _comma_separated_values_options_callback(option, opt_str, value, parser):
         setattr(parser.values, option.dest, value.split(','))
 
+    def _dict_from_multiple_values_options_callback(
+            option, opt_str, value, parser, allowed_keys=r'[\w-]+', delimiter=':', default_key=None, process=None):
+
+        out_dict = getattr(parser.values, option.dest)
+        mobj = re.match(r'(?i)(?P<key>%s)%s(?P<val>.*)$' % (allowed_keys, delimiter), value)
+        if mobj is not None:
+            key, val = mobj.group('key').lower(), mobj.group('val')
+        elif default_key is not None:
+            key, val = default_key, value
+        else:
+            raise optparse.OptionValueError(
+                'wrong %s formatting; it should be %s, not "%s"' % (opt_str, option.metavar, value))
+        out_dict[key] = process(val) if callable(process) else val
+
     # No need to wrap help messages if we're on a wide console
     columns = compat_get_terminal_size().columns
     max_width = columns if columns else 80
@@ -173,7 +195,7 @@ def parseOpts(overrideArguments=None):
     general.add_option(
         '--config-location',
         dest='config_location', metavar='PATH',
-        help='Location of the configuration file; either the path to the config or its containing directory')
+        help='Location of the main configuration file; either the path to the config or its containing directory')
     general.add_option(
         '--flat-playlist',
         action='store_const', dest='extract_flat', const='in_playlist', default=False,
@@ -618,14 +640,21 @@ def parseOpts(overrideArguments=None):
             'video while downloading (some players may not be able to play it)'))
     downloader.add_option(
         '--external-downloader',
-        dest='external_downloader', metavar='COMMAND',
+        dest='external_downloader', metavar='NAME',
         help=(
             'Use the specified external downloader. '
-            'Currently supports %s' % ','.join(list_external_downloaders())))
+            'Currently supports %s' % ', '.join(list_external_downloaders())))
     downloader.add_option(
-        '--external-downloader-args',
-        dest='external_downloader_args', metavar='ARGS',
-        help='Give these arguments to the external downloader')
+        '--downloader-args', '--external-downloader-args',
+        metavar='NAME:ARGS', dest='external_downloader_args', default={}, type='str',
+        action='callback', callback=_dict_from_multiple_values_options_callback,
+        callback_kwargs={
+            'allowed_keys': '|'.join(list_external_downloaders()),
+            'default_key': 'default', 'process': compat_shlex_split},
+        help=(
+            'Give these arguments to the external downloader. '
+            'Specify the downloader name and the arguments separated by a colon ":". '
+            'You can use this option multiple times (Alias: --external-downloader-args)'))
 
     workarounds = optparse.OptionGroup(parser, 'Workarounds')
     workarounds.add_option(
@@ -651,8 +680,9 @@ def parseOpts(overrideArguments=None):
     )
     workarounds.add_option(
         '--add-header',
-        metavar='FIELD:VALUE', dest='headers', action='append',
-        help='Specify a custom HTTP header and its value, separated by a colon \':\'. You can use this option multiple times',
+        metavar='FIELD:VALUE', dest='headers', default={}, type='str',
+        action='callback', callback=_dict_from_multiple_values_options_callback,
+        help='Specify a custom HTTP header and its value, separated by a colon ":". You can use this option multiple times',
     )
     workarounds.add_option(
         '--bidi-workaround',
@@ -797,10 +827,33 @@ def parseOpts(overrideArguments=None):
     filesystem.add_option(
         '--id', default=False,
         action='store_true', dest='useid', help=optparse.SUPPRESS_HELP)
+    filesystem.add_option(
+        '-P', '--paths',
+        metavar='TYPE:PATH', dest='paths', default={}, type='str',
+        action='callback', callback=_dict_from_multiple_values_options_callback,
+        callback_kwargs={
+            'allowed_keys': 'home|temp|%s' % '|'.join(OUTTMPL_TYPES.keys()),
+            'process': lambda x: x.strip()},
+        help=(
+            'The paths where the files should be downloaded. '
+            'Specify the type of file and the path separated by a colon ":". '
+            'All the same types as --output are supported. '
+            'Additionally, you can also provide "home" and "temp" paths. '
+            'All intermediary files are first downloaded to the temp path and '
+            'then the final files are moved over to the home path after download is finished. '
+            'This option is ignored if --output is an absolute path'))
     filesystem.add_option(
         '-o', '--output',
-        dest='outtmpl', metavar='TEMPLATE',
+        metavar='[TYPE:]TEMPLATE', dest='outtmpl', default={}, type='str',
+        action='callback', callback=_dict_from_multiple_values_options_callback,
+        callback_kwargs={
+            'allowed_keys': '|'.join(OUTTMPL_TYPES.keys()),
+            'default_key': 'default', 'process': lambda x: x.strip()},
         help='Output filename template, see "OUTPUT TEMPLATE" for details')
+    filesystem.add_option(
+        '--output-na-placeholder',
+        dest='outtmpl_na_placeholder', metavar='TEXT', default='NA',
+        help=('Placeholder value for unavailable meta fields in output filename template (default: "%default")'))
     filesystem.add_option(
         '--autonumber-size',
         dest='autonumber_size', metavar='NUMBER', type=int,
@@ -844,11 +897,13 @@ def parseOpts(overrideArguments=None):
     filesystem.add_option(
         '-c', '--continue',
         action='store_true', dest='continue_dl', default=True,
-        help='Resume partially downloaded files (default)')
+        help='Resume partially downloaded files/fragments (default)')
     filesystem.add_option(
         '--no-continue',
         action='store_false', dest='continue_dl',
-        help='Restart download of partially downloaded files from beginning')
+        help=(
+            'Do not resume partially downloaded fragments. '
+            'If the file is unfragmented, restart download of the entire file'))
     filesystem.add_option(
         '--part',
         action='store_false', dest='nopart', default=False,
@@ -876,7 +931,7 @@ def parseOpts(overrideArguments=None):
     filesystem.add_option(
         '--write-info-json',
         action='store_true', dest='writeinfojson', default=False,
-        help='Write video metadata to a .info.json file')
+        help='Write video metadata to a .info.json file (this may contain personal information)')
     filesystem.add_option(
         '--no-write-info-json',
         action='store_false', dest='writeinfojson',
@@ -889,6 +944,22 @@ def parseOpts(overrideArguments=None):
         '--no-write-annotations',
         action='store_false', dest='writeannotations',
         help='Do not write video annotations (default)')
+    filesystem.add_option(
+        '--write-playlist-metafiles',
+        action='store_true', dest='allow_playlist_files', default=True,
+        help=(
+            'Write playlist metadata in addition to the video metadata '
+            'when using --write-info-json, --write-description etc. (default)'))
+    filesystem.add_option(
+        '--no-write-playlist-metafiles',
+        action='store_false', dest='allow_playlist_files',
+        help=(
+            'Do not write playlist metadata when using '
+            '--write-info-json, --write-description etc.'))
+    filesystem.add_option(
+        '--get-comments',
+        action='store_true', dest='getcomments', default=False,
+        help='Retrieve video comments to be placed in the .info.json file')
     filesystem.add_option(
         '--load-info-json', '--load-info',
         dest='load_info_filename', metavar='FILE',
@@ -956,37 +1027,44 @@ def parseOpts(overrideArguments=None):
     postproc.add_option(
         '-x', '--extract-audio',
         action='store_true', dest='extractaudio', default=False,
-        help='Convert video files to audio-only files (requires ffmpeg or avconv and ffprobe or avprobe)')
+        help='Convert video files to audio-only files (requires ffmpeg and ffprobe)')
     postproc.add_option(
         '--audio-format', metavar='FORMAT', dest='audioformat', default='best',
         help='Specify audio format: "best", "aac", "flac", "mp3", "m4a", "opus", "vorbis", or "wav"; "%default" by default; No effect without -x')
     postproc.add_option(
         '--audio-quality', metavar='QUALITY',
         dest='audioquality', default='5',
-        help='Specify ffmpeg/avconv audio quality, insert a value between 0 (better) and 9 (worse) for VBR or a specific bitrate like 128K (default %default)')
+        help='Specify ffmpeg audio quality, insert a value between 0 (better) and 9 (worse) for VBR or a specific bitrate like 128K (default %default)')
     postproc.add_option(
         '--remux-video',
         metavar='FORMAT', dest='remuxvideo', default=None,
         help=(
-            'Remux the video into another container if necessary (currently supported: mp4|mkv). '
-            'If target container does not support the video/audio codec, remuxing will fail'))
+            'Remux the video into another container if necessary (currently supported: %s). '
+            'If target container does not support the video/audio codec, remuxing will fail. '
+            'You can specify multiple rules; eg. "aac>m4a/mov>mp4/mkv" will remux aac to m4a, mov to mp4 '
+            'and anything else to mkv.' % '|'.join(_remux_formats)))
     postproc.add_option(
         '--recode-video',
         metavar='FORMAT', dest='recodevideo', default=None,
-        help='Re-encode the video into another format if re-encoding is necessary (currently supported: mp4|flv|ogg|webm|mkv|avi)')
+        help=(
+            'Re-encode the video into another format if re-encoding is necessary. '
+            'The supported formats are the same as --remux-video'))
     postproc.add_option(
-        '--postprocessor-args', '--ppa', metavar='NAME:ARGS',
-        dest='postprocessor_args', action='append',
+        '--postprocessor-args', '--ppa',
+        metavar='NAME:ARGS', dest='postprocessor_args', default={}, type='str',
+        action='callback', callback=_dict_from_multiple_values_options_callback,
+        callback_kwargs={'default_key': 'default-compat', 'allowed_keys': r'\w+(?:\+\w+)?', 'process': compat_shlex_split},
         help=(
             'Give these arguments to the postprocessors. '
             'Specify the postprocessor/executable name and the arguments separated by a colon ":" '
-            'to give the argument to only the specified postprocessor/executable. Supported postprocessors are: '
+            'to give the argument to the specified postprocessor/executable. Supported postprocessors are: '
             'SponSkrub, ExtractAudio, VideoRemuxer, VideoConvertor, EmbedSubtitle, Metadata, Merger, '
             'FixupStretched, FixupM4a, FixupM3u8, SubtitlesConvertor and EmbedThumbnail. '
-            'The supported executables are: SponSkrub, FFmpeg, FFprobe, avconf, avprobe and AtomicParsley. '
+            'The supported executables are: SponSkrub, FFmpeg, FFprobe, and AtomicParsley. '
             'You can use this option multiple times to give different arguments to different postprocessors. '
             'You can also specify "PP+EXE:ARGS" to give the arguments to the specified executable '
-            'only when being used by the specified postprocessor (Alias: --ppa)'))
+            'only when being used by the specified postprocessor. '
+            'You can use this option multiple times (Alias: --ppa)'))
     postproc.add_option(
         '-k', '--keep-video',
         action='store_true', dest='keepvideo', default=False,
@@ -1030,14 +1108,20 @@ def parseOpts(overrideArguments=None):
     postproc.add_option(
         '--metadata-from-title',
         metavar='FORMAT', dest='metafromtitle',
+        help=optparse.SUPPRESS_HELP)
+    postproc.add_option(
+        '--parse-metadata',
+        metavar='FIELD:FORMAT', dest='metafromfield', action='append',
         help=(
-            'Parse additional metadata like song title / artist from the video title. '
-            'The format syntax is the same as --output. Regular expression with '
-            'named capture groups may also be used. '
-            'The parsed parameters replace existing values. '
-            'Example: --metadata-from-title "%(artist)s - %(title)s" matches a title like '
+            'Parse additional metadata like title/artist from other fields. '
+            'Give field name to extract data from, and format of the field seperated by a ":". '
+            'Either regular expression with named capture groups or a '
+            'similar syntax to the output template can also be used. '
+            'The parsed parameters replace any existing values and can be use in output template'
+            'This option can be used multiple times. '
+            'Example: --parse-metadata "title:%(artist)s - %(title)s" matches a title like '
             '"Coldplay - Paradise". '
-            'Example (regex): --metadata-from-title "(?P<artist>.+?) - (?P<title>.+)"'))
+            'Example (regex): --parse-metadata "description:Artist - (?P<artist>.+?)"'))
     postproc.add_option(
         '--xattrs',
         action='store_true', dest='xattrs', default=False,
@@ -1052,15 +1136,15 @@ def parseOpts(overrideArguments=None):
     postproc.add_option(
         '--prefer-avconv', '--no-prefer-ffmpeg',
         action='store_false', dest='prefer_ffmpeg',
-        help='Prefer avconv over ffmpeg for running the postprocessors (Alias: --no-prefer-ffmpeg)')
+        help=optparse.SUPPRESS_HELP)
     postproc.add_option(
         '--prefer-ffmpeg', '--no-prefer-avconv',
-        action='store_true', dest='prefer_ffmpeg',
-        help='Prefer ffmpeg over avconv for running the postprocessors (default) (Alias: --no-prefer-avconv)')
+        action='store_true', dest='prefer_ffmpeg', default=True,
+        help=optparse.SUPPRESS_HELP)
     postproc.add_option(
         '--ffmpeg-location', '--avconv-location', metavar='PATH',
         dest='ffmpeg_location',
-        help='Location of the ffmpeg/avconv binary; either the path to the binary or its containing directory (Alias: --avconv-location)')
+        help='Location of the ffmpeg binary; either the path to the binary or its containing directory')
     postproc.add_option(
         '--exec',
         metavar='CMD', dest='exec_cmd',
@@ -1146,59 +1230,69 @@ def parseOpts(overrideArguments=None):
             return conf
 
         configs = {
-            'command_line': compat_conf(sys.argv[1:]),
-            'custom': [], 'portable': [], 'user': [], 'system': []}
-        opts, args = parser.parse_args(configs['command_line'])
+            'command-line': compat_conf(sys.argv[1:]),
+            'custom': [], 'home': [], 'portable': [], 'user': [], 'system': []}
+        paths = {'command-line': False}
+        opts, args = parser.parse_args(configs['command-line'])
 
         def get_configs():
-            if '--config-location' in configs['command_line']:
+            if '--config-location' in configs['command-line']:
                 location = compat_expanduser(opts.config_location)
                 if os.path.isdir(location):
                     location = os.path.join(location, 'youtube-dlc.conf')
                 if not os.path.exists(location):
                     parser.error('config-location %s does not exist.' % location)
-                configs['custom'] = _readOptions(location)
-
-            if '--ignore-config' in configs['command_line']:
+                configs['custom'] = _readOptions(location, default=None)
+                if configs['custom'] is None:
+                    configs['custom'] = []
+                else:
+                    paths['custom'] = location
+            if '--ignore-config' in configs['command-line']:
                 return
             if '--ignore-config' in configs['custom']:
                 return
 
-            def get_portable_path():
-                path = os.path.dirname(sys.argv[0])
-                if os.path.abspath(sys.argv[0]) != os.path.abspath(sys.executable):  # Not packaged
-                    path = os.path.join(path, '..')
-                return os.path.abspath(path)
-
-            run_path = get_portable_path()
-            configs['portable'] = _readOptions(os.path.join(run_path, 'yt-dlp.conf'), default=None)
-            if configs['portable'] is None:
-                configs['portable'] = _readOptions(os.path.join(run_path, 'youtube-dlc.conf'))
+            def read_options(path, user=False):
+                for package in ('yt-dlp', 'youtube-dlc'):
+                    if user:
+                        config, current_path = _readUserConf(package, default=None)
+                    else:
+                        current_path = os.path.join(path, '%s.conf' % package)
+                        config = _readOptions(current_path, default=None)
+                    if config is not None:
+                        return config, current_path
+                return [], None
 
+            configs['portable'], paths['portable'] = read_options(get_executable_path())
             if '--ignore-config' in configs['portable']:
                 return
-            configs['system'] = _readOptions('/etc/yt-dlp.conf', default=None)
-            if configs['system'] is None:
-                configs['system'] = _readOptions('/etc/youtube-dlc.conf')
 
+            def get_home_path():
+                opts = parser.parse_args(configs['portable'] + configs['custom'] + configs['command-line'])[0]
+                return expand_path(opts.paths.get('home', '')).strip()
+
+            configs['home'], paths['home'] = read_options(get_home_path())
+            if '--ignore-config' in configs['home']:
+                return
+
+            configs['system'], paths['system'] = read_options('/etc')
             if '--ignore-config' in configs['system']:
                 return
-            configs['user'] = _readUserConf('yt-dlp', default=None)
-            if configs['user'] is None:
-                configs['user'] = _readUserConf('youtube-dlc')
+
+            configs['user'], paths['user'] = read_options('', True)
             if '--ignore-config' in configs['user']:
-                configs['system'] = []
+                configs['system'], paths['system'] = [], None
 
         get_configs()
-        argv = configs['system'] + configs['user'] + configs['portable'] + configs['custom'] + configs['command_line']
+        argv = configs['system'] + configs['user'] + configs['home'] + configs['portable'] + configs['custom'] + configs['command-line']
         opts, args = parser.parse_args(argv)
         if opts.verbose:
-            for conf_label, conf in (
-                    ('System config', configs['system']),
-                    ('User config', configs['user']),
-                    ('Portable config', configs['portable']),
-                    ('Custom config', configs['custom']),
-                    ('Command-line args', configs['command_line'])):
-                write_string('[debug] %s: %s\n' % (conf_label, repr(_hide_login_info(conf))))
+            for label in ('System', 'User', 'Portable', 'Home', 'Custom', 'Command-line'):
+                key = label.lower()
+                if paths.get(key) is None:
+                    continue
+                if paths[key]:
+                    write_string('[debug] %s config file: %s\n' % (label, paths[key]))
+                write_string('[debug] %s config: %s\n' % (label, repr(_hide_login_info(configs[key]))))
 
     return parser, opts, args

youtube_dlc/postprocessor/__init__.py

@@ -16,7 +16,9 @@ from .ffmpeg import (
 )
 from .xattrpp import XAttrMetadataPP
 from .execafterdownload import ExecAfterDownloadPP
-from .metadatafromtitle import MetadataFromTitlePP
+from .metadatafromfield import MetadataFromFieldPP
+from .metadatafromfield import MetadataFromTitlePP
+from .movefilesafterdownload import MoveFilesAfterDownloadPP
 from .sponskrub import SponSkrubPP
 
 
@@ -38,7 +40,9 @@ __all__ = [
     'FFmpegSubtitlesConvertorPP',
     'FFmpegVideoConvertorPP',
     'FFmpegVideoRemuxerPP',
+    'MetadataFromFieldPP',
     'MetadataFromTitlePP',
+    'MoveFilesAfterDownloadPP',
     'SponSkrubPP',
     'XAttrMetadataPP',
 ]

youtube_dlc/postprocessor/common.py

@@ -4,8 +4,9 @@ import os
 
 from ..compat import compat_str
 from ..utils import (
-    PostProcessingError,
+    cli_configuration_args,
     encodeFilename,
+    PostProcessingError,
 )
 
 
@@ -55,7 +56,7 @@ class PostProcessor(object):
 
     def write_debug(self, text, prefix=True, *args, **kwargs):
         tag = '[debug] ' if prefix else ''
-        if self.get_param('verbose', False):
+        if self.get_param('verbose', False) and self._downloader:
             return self._downloader.to_screen('%s%s' % (tag, text), *args, **kwargs)
 
     def get_param(self, name, default=None, *args, **kwargs):
@@ -91,39 +92,10 @@ class PostProcessor(object):
             self.report_warning(errnote)
 
     def _configuration_args(self, default=[], exe=None):
-        args = self.get_param('postprocessor_args', {})
-        pp_key = self.pp_key().lower()
-
-        if isinstance(args, (list, tuple)):  # for backward compatibility
-            return default if pp_key == 'sponskrub' else args
-        if args is None:
-            return default
-        assert isinstance(args, dict)
-
-        exe_args = None
-        if exe is not None:
-            assert isinstance(exe, compat_str)
-            exe = exe.lower()
-            specific_args = args.get('%s+%s' % (pp_key, exe))
-            if specific_args is not None:
-                assert isinstance(specific_args, (list, tuple))
-                return specific_args
-            exe_args = args.get(exe)
-
-        pp_args = args.get(pp_key) if pp_key != exe else None
-        if pp_args is None and exe_args is None:
-            default = args.get('default', default)
-            assert isinstance(default, (list, tuple))
-            return default
-
-        if pp_args is None:
-            pp_args = []
-        elif exe_args is None:
-            exe_args = []
-
-        assert isinstance(pp_args, (list, tuple))
-        assert isinstance(exe_args, (list, tuple))
-        return pp_args + exe_args
+        key = self.pp_key().lower()
+        args, is_compat = cli_configuration_args(
+            self._downloader.params, 'postprocessor_args', key, default, exe)
+        return args if not is_compat or key != 'sponskrub' else default
 
 
 class AudioConversionError(PostProcessingError):

youtube_dlc/postprocessor/embedthumbnail.py

@@ -4,6 +4,15 @@ from __future__ import unicode_literals
 
 import os
 import subprocess
+import struct
+import re
+import base64
+
+try:
+    import mutagen
+    _has_mutagen = True
+except ImportError:
+    _has_mutagen = False
 
 from .ffmpeg import FFmpegPostProcessor
 
@@ -11,11 +20,12 @@ from ..utils import (
     check_executable,
     encodeArgument,
     encodeFilename,
+    error_to_compat_str,
     PostProcessingError,
     prepend_extension,
+    process_communicate_or_kill,
     replace_extension,
     shell_quote,
-    process_communicate_or_kill,
 )
 
 
@@ -32,6 +42,7 @@ class EmbedThumbnailPP(FFmpegPostProcessor):
     def run(self, info):
         filename = info['filepath']
         temp_filename = prepend_extension(filename, 'temp')
+        files_to_delete = []
 
         if not info.get('thumbnails'):
             self.to_screen('There aren\'t any thumbnails to embed')
@@ -68,11 +79,12 @@ class EmbedThumbnailPP(FFmpegPostProcessor):
             escaped_thumbnail_jpg_filename = replace_extension(escaped_thumbnail_filename, 'jpg')
             self.to_screen('Converting thumbnail "%s" to JPEG' % escaped_thumbnail_filename)
             self.run_ffmpeg(escaped_thumbnail_filename, escaped_thumbnail_jpg_filename, ['-bsf:v', 'mjpeg2jpeg'])
-            os.remove(encodeFilename(escaped_thumbnail_filename))
+            files_to_delete.append(escaped_thumbnail_filename)
             thumbnail_jpg_filename = replace_extension(thumbnail_filename, 'jpg')
             # Rename back to unescaped for further processing
             os.rename(encodeFilename(escaped_thumbnail_jpg_filename), encodeFilename(thumbnail_jpg_filename))
             thumbnail_filename = thumbnail_jpg_filename
+            thumbnail_ext = 'jpg'
 
         success = True
         if info['ext'] == 'mp3':
@@ -83,47 +95,98 @@ class EmbedThumbnailPP(FFmpegPostProcessor):
             self.to_screen('Adding thumbnail to "%s"' % filename)
             self.run_ffmpeg_multiple_files([filename, thumbnail_filename], temp_filename, options)
 
-        elif info['ext'] == 'mkv':
-            options = [
-                '-c', 'copy', '-map', '0', '-dn', '-attach', thumbnail_filename,
-                '-metadata:s:t', 'mimetype=image/jpeg', '-metadata:s:t', 'filename=cover.jpg']
+        elif info['ext'] in ['mkv', 'mka']:
+            options = ['-c', 'copy', '-map', '0', '-dn']
+
+            mimetype = 'image/%s' % ('png' if thumbnail_ext == 'png' else 'jpeg')
+            old_stream, new_stream = self.get_stream_number(
+                filename, ('tags', 'mimetype'), mimetype)
+            if old_stream is not None:
+                options.extend(['-map', '-0:%d' % old_stream])
+                new_stream -= 1
+            options.extend([
+                '-attach', thumbnail_filename,
+                '-metadata:s:%d' % new_stream, 'mimetype=%s' % mimetype,
+                '-metadata:s:%d' % new_stream, 'filename=cover.%s' % thumbnail_ext])
 
             self.to_screen('Adding thumbnail to "%s"' % filename)
-            self.run_ffmpeg_multiple_files([filename], temp_filename, options)
+            self.run_ffmpeg(filename, temp_filename, options)
 
-        elif info['ext'] in ['m4a', 'mp4']:
-            if not check_executable('AtomicParsley', ['-v']):
-                raise EmbedThumbnailPPError('AtomicParsley was not found. Please install.')
+        elif info['ext'] in ['m4a', 'mp4', 'mov']:
+            try:
+                options = ['-c', 'copy', '-map', '0', '-dn', '-map', '1']
 
-            cmd = [encodeFilename('AtomicParsley', True),
-                   encodeFilename(filename, True),
-                   encodeArgument('--artwork'),
-                   encodeFilename(thumbnail_filename, True),
-                   encodeArgument('-o'),
-                   encodeFilename(temp_filename, True)]
-            cmd += [encodeArgument(o) for o in self._configuration_args(exe='AtomicParsley')]
+                old_stream, new_stream = self.get_stream_number(
+                    filename, ('disposition', 'attached_pic'), 1)
+                if old_stream is not None:
+                    options.extend(['-map', '-0:%d' % old_stream])
+                    new_stream -= 1
+                options.extend(['-disposition:%s' % new_stream, 'attached_pic'])
 
+                self.to_screen('Adding thumbnail to "%s"' % filename)
+                self.run_ffmpeg_multiple_files([filename, thumbnail_filename], temp_filename, options)
+
+            except PostProcessingError as err:
+                self.report_warning('unable to embed using ffprobe & ffmpeg; %s' % error_to_compat_str(err))
+                if not check_executable('AtomicParsley', ['-v']):
+                    raise EmbedThumbnailPPError('AtomicParsley was not found. Please install.')
+
+                cmd = [encodeFilename('AtomicParsley', True),
+                       encodeFilename(filename, True),
+                       encodeArgument('--artwork'),
+                       encodeFilename(thumbnail_filename, True),
+                       encodeArgument('-o'),
+                       encodeFilename(temp_filename, True)]
+                cmd += [encodeArgument(o) for o in self._configuration_args(exe='AtomicParsley')]
+
+                self.to_screen('Adding thumbnail to "%s"' % filename)
+                self.write_debug('AtomicParsley command line: %s' % shell_quote(cmd))
+                p = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+                stdout, stderr = process_communicate_or_kill(p)
+                if p.returncode != 0:
+                    msg = stderr.decode('utf-8', 'replace').strip()
+                    raise EmbedThumbnailPPError(msg)
+                # for formats that don't support thumbnails (like 3gp) AtomicParsley
+                # won't create to the temporary file
+                if b'No changes' in stdout:
+                    self.report_warning('The file format doesn\'t support embedding a thumbnail')
+                    success = False
+
+        elif info['ext'] in ['ogg', 'opus']:
+            if not _has_mutagen:
+                raise EmbedThumbnailPPError('module mutagen was not found. Please install using `python -m pip install mutagen`')
             self.to_screen('Adding thumbnail to "%s"' % filename)
-            self.write_debug('AtomicParsley command line: %s' % shell_quote(cmd))
 
-            p = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
-            stdout, stderr = process_communicate_or_kill(p)
+            size_regex = r',\s*(?P<w>\d+)x(?P<h>\d+)\s*[,\[]'
+            size_result = self.run_ffmpeg(thumbnail_filename, thumbnail_filename, ['-hide_banner'])
+            mobj = re.search(size_regex, size_result)
+            width, height = int(mobj.group('w')), int(mobj.group('h'))
+            mimetype = ('image/%s' % ('png' if thumbnail_ext == 'png' else 'jpeg')).encode('ascii')
 
-            if p.returncode != 0:
-                msg = stderr.decode('utf-8', 'replace').strip()
-                raise EmbedThumbnailPPError(msg)
-            # for formats that don't support thumbnails (like 3gp) AtomicParsley
-            # won't create to the temporary file
-            if b'No changes' in stdout:
-                self.report_warning('The file format doesn\'t support embedding a thumbnail')
-                success = False
+            # https://xiph.org/flac/format.html#metadata_block_picture
+            data = bytearray()
+            data += struct.pack('>II', 3, len(mimetype))
+            data += mimetype
+            data += struct.pack('>IIIIII', 0, width, height, 8, 0, os.stat(thumbnail_filename).st_size)  # 32 if png else 24
+
+            fin = open(thumbnail_filename, "rb")
+            data += fin.read()
+            fin.close()
+
+            temp_filename = filename
+            f = mutagen.File(temp_filename)
+            f.tags['METADATA_BLOCK_PICTURE'] = base64.b64encode(data).decode('ascii')
+            f.save()
 
         else:
-            raise EmbedThumbnailPPError('Only mp3, mkv, m4a and mp4 are supported for thumbnail embedding for now.')
+            raise EmbedThumbnailPPError('Supported filetypes for thumbnail embedding are: mp3, mkv/mka, ogg/opus, m4a/mp4/mov')
 
-        if success:
+        if success and temp_filename != filename:
             os.remove(encodeFilename(filename))
             os.rename(encodeFilename(temp_filename), encodeFilename(filename))
-
-        files_to_delete = [] if self._already_have_thumbnail else [thumbnail_filename]
+        if self._already_have_thumbnail:
+            info['__files_to_move'][thumbnail_filename] = replace_extension(
+                info['__thumbnail_filename'], os.path.splitext(thumbnail_filename)[1][1:])
+        else:
+            files_to_delete.append(thumbnail_filename)
         return files_to_delete, info

youtube_dlc/postprocessor/ffmpeg.py

@@ -5,6 +5,7 @@ import os
 import subprocess
 import time
 import re
+import json
 
 
 from .common import AudioConversionError, PostProcessor
@@ -20,8 +21,9 @@ from ..utils import (
     subtitles_filename,
     dfxp2srt,
     ISO639Utils,
-    replace_extension,
     process_communicate_or_kill,
+    replace_extension,
+    traverse_dict,
 )
 
 
@@ -59,7 +61,7 @@ class FFmpegPostProcessor(PostProcessor):
 
     def check_version(self):
         if not self.available:
-            raise FFmpegPostProcessorError('ffmpeg or avconv not found. Please install one.')
+            raise FFmpegPostProcessorError('ffmpeg not found. Please install')
 
         required_version = '10-0' if self.basename == 'avconv' else '1.0'
         if is_outdated_version(
@@ -102,7 +104,7 @@ class FFmpegPostProcessor(PostProcessor):
                 if not os.path.exists(location):
                     self.report_warning(
                         'ffmpeg-location %s does not exist! '
-                        'Continuing without avconv/ffmpeg.' % (location))
+                        'Continuing without ffmpeg.' % (location))
                     self._versions = {}
                     return
                 elif not os.path.isdir(location):
@@ -110,7 +112,7 @@ class FFmpegPostProcessor(PostProcessor):
                     if basename not in programs:
                         self.report_warning(
                             'Cannot identify executable %s, its basename should be one of %s. '
-                            'Continuing without avconv/ffmpeg.' %
+                            'Continuing without ffmpeg.' %
                             (location, ', '.join(programs)))
                         self._versions = {}
                         return None
@@ -163,7 +165,7 @@ class FFmpegPostProcessor(PostProcessor):
 
     def get_audio_codec(self, path):
         if not self.probe_available and not self.available:
-            raise PostProcessingError('ffprobe/avprobe and ffmpeg/avconv not found. Please install one.')
+            raise PostProcessingError('ffprobe and ffmpeg not found. Please install')
         try:
             if self.probe_available:
                 cmd = [
@@ -201,6 +203,37 @@ class FFmpegPostProcessor(PostProcessor):
                 return mobj.group(1)
         return None
 
+    def get_metadata_object(self, path, opts=[]):
+        if self.probe_basename != 'ffprobe':
+            if self.probe_available:
+                self.report_warning('Only ffprobe is supported for metadata extraction')
+            raise PostProcessingError('ffprobe not found. Please install.')
+        self.check_version()
+
+        cmd = [
+            encodeFilename(self.probe_executable, True),
+            encodeArgument('-hide_banner'),
+            encodeArgument('-show_format'),
+            encodeArgument('-show_streams'),
+            encodeArgument('-print_format'),
+            encodeArgument('json'),
+        ]
+
+        cmd += opts
+        cmd.append(encodeFilename(self._ffmpeg_filename_argument(path), True))
+        if self._downloader.params.get('verbose', False):
+            self._downloader.to_screen('[debug] ffprobe command line: %s' % shell_quote(cmd))
+        p = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE, stdin=subprocess.PIPE)
+        stdout, stderr = p.communicate()
+        return json.loads(stdout.decode('utf-8', 'replace'))
+
+    def get_stream_number(self, path, keys, value):
+        streams = self.get_metadata_object(path)['streams']
+        num = next(
+            (i for i, stream in enumerate(streams) if traverse_dict(stream, keys, casesense=False) == value),
+            None)
+        return num, len(streams)
+
     def run_ffmpeg_multiple_files(self, input_paths, out_path, opts):
         self.check_version()
 
@@ -227,19 +260,23 @@ class FFmpegPostProcessor(PostProcessor):
         p = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE, stdin=subprocess.PIPE)
         stdout, stderr = process_communicate_or_kill(p)
         if p.returncode != 0:
-            stderr = stderr.decode('utf-8', 'replace')
-            msg = stderr.strip().split('\n')[-1]
-            raise FFmpegPostProcessorError(msg)
+            stderr = stderr.decode('utf-8', 'replace').strip()
+            if self._downloader.params.get('verbose', False):
+                self.report_error(stderr)
+            raise FFmpegPostProcessorError(stderr.split('\n')[-1])
         self.try_utime(out_path, oldest_mtime, oldest_mtime)
+        return stderr.decode('utf-8', 'replace')
 
     def run_ffmpeg(self, path, out_path, opts):
-        self.run_ffmpeg_multiple_files([path], out_path, opts)
+        return self.run_ffmpeg_multiple_files([path], out_path, opts)
 
     def _ffmpeg_filename_argument(self, fn):
         # Always use 'file:' because the filename may contain ':' (ffmpeg
         # interprets that as a protocol) or can start with '-' (-- is broken in
         # ffmpeg, see https://ffmpeg.org/trac/ffmpeg/ticket/2127 for details)
         # Also leave '-' intact in order not to break streaming to stdout.
+        if fn.startswith(('http://', 'https://')):
+            return fn
         return 'file:' + fn if fn != '-' else fn
 
 
@@ -349,21 +386,35 @@ class FFmpegExtractAudioPP(FFmpegPostProcessor):
 class FFmpegVideoRemuxerPP(FFmpegPostProcessor):
     def __init__(self, downloader=None, preferedformat=None):
         super(FFmpegVideoRemuxerPP, self).__init__(downloader)
-        self._preferedformat = preferedformat
+        self._preferedformats = preferedformat.lower().split('/')
 
     def run(self, information):
         path = information['filepath']
-        if information['ext'] == self._preferedformat:
-            self.to_screen('Not remuxing video file %s - already is in target format %s' % (path, self._preferedformat))
+        sourceext, targetext = information['ext'].lower(), None
+        for pair in self._preferedformats:
+            kv = pair.split('>')
+            if len(kv) == 1 or kv[0].strip() == sourceext:
+                targetext = kv[-1].strip()
+                break
+
+        _skip_msg = (
+            'could not find a mapping for %s' if not targetext
+            else 'already is in target format %s' if sourceext == targetext
+            else None)
+        if _skip_msg:
+            self.to_screen('Not remuxing media file %s; %s' % (path, _skip_msg % sourceext))
             return [], information
+
         options = ['-c', 'copy', '-map', '0', '-dn']
-        prefix, sep, ext = path.rpartition('.')
-        outpath = prefix + sep + self._preferedformat
-        self.to_screen('Remuxing video from %s to %s, Destination: ' % (information['ext'], self._preferedformat) + outpath)
+        if targetext in ['mp4', 'm4a', 'mov']:
+            options.extend(['-movflags', '+faststart'])
+        prefix, sep, oldext = path.rpartition('.')
+        outpath = prefix + sep + targetext
+        self.to_screen('Remuxing video from %s to %s; Destination: %s' % (sourceext, targetext, outpath))
         self.run_ffmpeg(path, outpath, options)
         information['filepath'] = outpath
-        information['format'] = self._preferedformat
-        information['ext'] = self._preferedformat
+        information['format'] = targetext
+        information['ext'] = targetext
         return [path], information
 
 
@@ -406,18 +457,22 @@ class FFmpegEmbedSubtitlePP(FFmpegPostProcessor):
         sub_langs = []
         sub_filenames = []
         webm_vtt_warn = False
+        mp4_ass_warn = False
 
         for lang, sub_info in subtitles.items():
             sub_ext = sub_info['ext']
             if sub_ext == 'json':
-                self.to_screen('JSON subtitles cannot be embedded')
+                self.report_warning('JSON subtitles cannot be embedded')
             elif ext != 'webm' or ext == 'webm' and sub_ext == 'vtt':
                 sub_langs.append(lang)
                 sub_filenames.append(subtitles_filename(filename, lang, sub_ext, ext))
             else:
                 if not webm_vtt_warn and ext == 'webm' and sub_ext != 'vtt':
                     webm_vtt_warn = True
-                    self.to_screen('Only WebVTT subtitles can be embedded in webm files')
+                    self.report_warning('Only WebVTT subtitles can be embedded in webm files')
+            if not mp4_ass_warn and ext == 'mp4' and sub_ext == 'ass':
+                mp4_ass_warn = True
+                self.report_warning('ASS subtitles cannot be properly embedded in mp4 files; expect issues')
 
         if not sub_langs:
             return [], information
@@ -441,7 +496,7 @@ class FFmpegEmbedSubtitlePP(FFmpegPostProcessor):
             opts.extend(['-metadata:s:s:%d' % i, 'language=%s' % lang_code])
 
         temp_filename = prepend_extension(filename, 'temp')
-        self.to_screen('Embedding subtitles in \'%s\'' % filename)
+        self.to_screen('Embedding subtitles in "%s"' % filename)
         self.run_ffmpeg_multiple_files(input_files, temp_filename, opts)
         os.remove(encodeFilename(filename))
         os.rename(encodeFilename(temp_filename), encodeFilename(filename))
@@ -471,7 +526,6 @@ class FFmpegMetadataPP(FFmpegPostProcessor):
         # 1. https://kdenlive.org/en/project/adding-meta-data-to-mp4-video/
         # 2. https://wiki.multimedia.cx/index.php/FFmpeg_Metadata
         # 3. https://kodi.wiki/view/Video_file_tagging
-        # 4. http://atomicparsley.sourceforge.net/mpeg-4files.html
 
         add('title', ('track', 'title'))
         add('date', 'upload_date')
@@ -524,6 +578,18 @@ class FFmpegMetadataPP(FFmpegPostProcessor):
                 in_filenames.append(metadata_filename)
                 options.extend(['-map_metadata', '1'])
 
+        if '__infojson_filename' in info and info['ext'] in ('mkv', 'mka'):
+            old_stream, new_stream = self.get_stream_number(
+                filename, ('tags', 'mimetype'), 'application/json')
+            if old_stream is not None:
+                options.extend(['-map', '-0:%d' % old_stream])
+                new_stream -= 1
+
+            options.extend([
+                '-attach', info['__infojson_filename'],
+                '-metadata:s:%d' % new_stream, 'mimetype=application/json'
+            ])
+
         self.to_screen('Adding metadata to \'%s\'' % filename)
         self.run_ffmpeg_multiple_files(in_filenames, temp_filename, options)
         if chapters:

youtube_dlc/postprocessor/metadatafromfield.py

@@ -0,0 +1,71 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import PostProcessor
+from ..compat import compat_str
+from ..utils import str_or_none
+
+
+class MetadataFromFieldPP(PostProcessor):
+    regex = r'(?P<field>\w+):(?P<format>.+)$'
+
+    def __init__(self, downloader, formats):
+        PostProcessor.__init__(self, downloader)
+        assert isinstance(formats, (list, tuple))
+        self._data = []
+        for f in formats:
+            assert isinstance(f, compat_str)
+            match = re.match(self.regex, f)
+            assert match is not None
+            self._data.append({
+                'field': match.group('field'),
+                'format': match.group('format'),
+                'regex': self.format_to_regex(match.group('format'))})
+
+    def format_to_regex(self, fmt):
+        r"""
+        Converts a string like
+           '%(title)s - %(artist)s'
+        to a regex like
+           '(?P<title>.+)\ \-\ (?P<artist>.+)'
+        """
+        if not re.search(r'%\(\w+\)s', fmt):
+            return fmt
+        lastpos = 0
+        regex = ''
+        # replace %(..)s with regex group and escape other string parts
+        for match in re.finditer(r'%\((\w+)\)s', fmt):
+            regex += re.escape(fmt[lastpos:match.start()])
+            regex += r'(?P<' + match.group(1) + r'>[^\r\n]+)'
+            lastpos = match.end()
+        if lastpos < len(fmt):
+            regex += re.escape(fmt[lastpos:])
+        return regex
+
+    def run(self, info):
+        for dictn in self._data:
+            field, regex = dictn['field'], dictn['regex']
+            if field not in info:
+                self.report_warning('Video doesnot have a %s' % field)
+                continue
+            data_to_parse = str_or_none(info[field])
+            if data_to_parse is None:
+                self.report_warning('Field %s cannot be parsed' % field)
+                continue
+            self.write_debug('Searching for r"%s" in %s' % (regex, field))
+            match = re.search(regex, data_to_parse)
+            if match is None:
+                self.report_warning('Could not interpret video %s as "%s"' % (field, dictn['format']))
+                continue
+            for attribute, value in match.groupdict().items():
+                info[attribute] = value
+                self.to_screen('parsed %s from %s: %s' % (attribute, field, value if value is not None else 'NA'))
+        return [], info
+
+
+class MetadataFromTitlePP(MetadataFromFieldPP):  # for backward compatibility
+    def __init__(self, downloader, titleformat):
+        super(MetadataFromTitlePP, self).__init__(downloader, ['title:%s' % titleformat])
+        self._titleformat = titleformat
+        self._titleregex = self._data[0]['regex']

youtube_dlc/postprocessor/metadatafromtitle.py

@@ -1,44 +0,0 @@
-from __future__ import unicode_literals
-
-import re
-
-from .common import PostProcessor
-
-
-class MetadataFromTitlePP(PostProcessor):
-    def __init__(self, downloader, titleformat):
-        super(MetadataFromTitlePP, self).__init__(downloader)
-        self._titleformat = titleformat
-        self._titleregex = (self.format_to_regex(titleformat)
-                            if re.search(r'%\(\w+\)s', titleformat)
-                            else titleformat)
-
-    def format_to_regex(self, fmt):
-        r"""
-        Converts a string like
-           '%(title)s - %(artist)s'
-        to a regex like
-           '(?P<title>.+)\ \-\ (?P<artist>.+)'
-        """
-        lastpos = 0
-        regex = ''
-        # replace %(..)s with regex group and escape other string parts
-        for match in re.finditer(r'%\((\w+)\)s', fmt):
-            regex += re.escape(fmt[lastpos:match.start()])
-            regex += r'(?P<' + match.group(1) + '>.+)'
-            lastpos = match.end()
-        if lastpos < len(fmt):
-            regex += re.escape(fmt[lastpos:])
-        return regex
-
-    def run(self, info):
-        title = info['title']
-        match = re.match(self._titleregex, title)
-        if match is None:
-            self.to_screen('Could not interpret title of video as "%s"' % self._titleformat)
-            return [], info
-        for attribute, value in match.groupdict().items():
-            info[attribute] = value
-            self.to_screen('parsed %s: %s' % (attribute, value if value is not None else 'NA'))
-
-        return [], info

youtube_dlc/postprocessor/movefilesafterdownload.py

@@ -0,0 +1,54 @@
+from __future__ import unicode_literals
+import os
+import shutil
+
+from .common import PostProcessor
+from ..utils import (
+    encodeFilename,
+    make_dir,
+    PostProcessingError,
+)
+from ..compat import compat_str
+
+
+class MoveFilesAfterDownloadPP(PostProcessor):
+
+    def __init__(self, downloader, files_to_move):
+        PostProcessor.__init__(self, downloader)
+        self.files_to_move = files_to_move
+
+    @classmethod
+    def pp_key(cls):
+        return 'MoveFiles'
+
+    def run(self, info):
+        dl_path, dl_name = os.path.split(encodeFilename(info['filepath']))
+        finaldir = info.get('__finaldir', dl_path)
+        finalpath = os.path.join(finaldir, dl_name)
+        self.files_to_move.update(info['__files_to_move'])
+        self.files_to_move[info['filepath']] = finalpath
+
+        for oldfile, newfile in self.files_to_move.items():
+            if not newfile:
+                newfile = os.path.join(finaldir, os.path.basename(encodeFilename(oldfile)))
+            oldfile, newfile = compat_str(oldfile), compat_str(newfile)
+            if os.path.abspath(encodeFilename(oldfile)) == os.path.abspath(encodeFilename(newfile)):
+                continue
+            if not os.path.exists(encodeFilename(oldfile)):
+                self.report_warning('File "%s" cannot be found' % oldfile)
+                continue
+            if os.path.exists(encodeFilename(newfile)):
+                if self.get_param('overwrites', True):
+                    self.report_warning('Replacing existing file "%s"' % newfile)
+                    os.remove(encodeFilename(newfile))
+                else:
+                    self.report_warning(
+                        'Cannot move file "%s" out of temporary directory since "%s" already exists. '
+                        % (oldfile, newfile))
+                    continue
+            make_dir(newfile, PostProcessingError)
+            self.to_screen('Moving file "%s" to "%s"' % (oldfile, newfile))
+            shutil.move(oldfile, newfile)  # os.rename cannot move between volumes
+
+        info['filepath'] = compat_str(finalpath)
+        return [], info

youtube_dlc/postprocessor/sponskrub.py

@@ -84,6 +84,7 @@ class SponSkrubPP(PostProcessor):
         else:
             msg = stderr.decode('utf-8', 'replace').strip() or stdout.decode('utf-8', 'replace').strip()
             self.write_debug(msg, prefix=False)
-            msg = msg.split('\n')[-1]
+            line = 0 if msg[:12].lower() == 'unrecognised' else -1
+            msg = msg.split('\n')[line]
             raise PostProcessingError(msg if msg else 'sponskrub failed with error code %s' % p.returncode)
         return [], information

youtube_dlc/utils.py

@@ -16,6 +16,7 @@ import email.header
 import errno
 import functools
 import gzip
+import imp
 import io
 import itertools
 import json
@@ -49,6 +50,7 @@ from .compat import (
     compat_html_entities_html5,
     compat_http_client,
     compat_integer_types,
+    compat_numeric_types,
     compat_kwargs,
     compat_os_name,
     compat_parse_qs,
@@ -3672,6 +3674,18 @@ def url_or_none(url):
     return url if re.match(r'^(?:(?:https?|rt(?:m(?:pt?[es]?|fp)|sp[su]?)|mms|ftps?):)?//', url) else None
 
 
+def strftime_or_none(timestamp, date_format, default=None):
+    datetime_object = None
+    try:
+        if isinstance(timestamp, compat_numeric_types):  # unix timestamp
+            datetime_object = datetime.datetime.utcfromtimestamp(timestamp)
+        elif isinstance(timestamp, compat_str):  # assume YYYYMMDD
+            datetime_object = datetime.datetime.strptime(timestamp, '%Y%m%d')
+        return datetime_object.strftime(date_format)
+    except (ValueError, TypeError, AttributeError):
+        return default
+
+
 def parse_duration(s):
     if not isinstance(s, compat_basestring):
         return None
@@ -4155,7 +4169,18 @@ def qualities(quality_ids):
     return q
 
 
-DEFAULT_OUTTMPL = '%(title)s [%(id)s].%(ext)s'
+DEFAULT_OUTTMPL = {
+    'default': '%(title)s [%(id)s].%(ext)s',
+}
+OUTTMPL_TYPES = {
+    'subtitle': None,
+    'thumbnail': None,
+    'description': 'description',
+    'annotation': 'annotations.xml',
+    'infojson': 'info.json',
+    'pl_description': 'description',
+    'pl_infojson': 'info.json',
+}
 
 
 def limit_length(s, length):
@@ -4656,12 +4681,35 @@ def cli_valueless_option(params, command_option, param, expected_value=True):
     return [command_option] if param == expected_value else []
 
 
-def cli_configuration_args(params, param, default=[]):
-    ex_args = params.get(param)
-    if ex_args is None:
-        return default
-    assert isinstance(ex_args, list)
-    return ex_args
+def cli_configuration_args(params, arg_name, key, default=[], exe=None):  # returns arg, for_compat
+    argdict = params.get(arg_name, {})
+    if isinstance(argdict, (list, tuple)):  # for backward compatibility
+        return argdict, True
+
+    if argdict is None:
+        return default, False
+    assert isinstance(argdict, dict)
+
+    assert isinstance(key, compat_str)
+    key = key.lower()
+
+    args = exe_args = None
+    if exe is not None:
+        assert isinstance(exe, compat_str)
+        exe = exe.lower()
+        args = argdict.get('%s+%s' % (key, exe))
+        if args is None:
+            exe_args = argdict.get(exe)
+
+    if args is None:
+        args = argdict.get(key) if key != exe else None
+    if args is None and exe_args is None:
+        args = argdict.get('default', default)
+
+    args, exe_args = args or [], exe_args or []
+    assert isinstance(args, (list, tuple))
+    assert isinstance(exe_args, (list, tuple))
+    return args + exe_args, False
 
 
 class ISO639Utils(object):
@@ -5863,3 +5911,61 @@ def clean_podcast_url(url):
                 st\.fm # https://podsights.com/docs/
             )/e
         )/''', '', url)
+
+
+_HEX_TABLE = '0123456789abcdef'
+
+
+def random_uuidv4():
+    return re.sub(r'[xy]', lambda x: _HEX_TABLE[random.randint(0, 15)], 'xxxxxxxx-xxxx-4xxx-yxxx-xxxxxxxxxxxx')
+
+
+def make_dir(path, to_screen=None):
+    try:
+        dn = os.path.dirname(path)
+        if dn and not os.path.exists(dn):
+            os.makedirs(dn)
+        return True
+    except (OSError, IOError) as err:
+        if callable(to_screen) is not None:
+            to_screen('unable to create directory ' + error_to_compat_str(err))
+        return False
+
+
+def get_executable_path():
+    path = os.path.dirname(sys.argv[0])
+    if os.path.abspath(sys.argv[0]) != os.path.abspath(sys.executable):  # Not packaged
+        path = os.path.join(path, '..')
+    return os.path.abspath(path)
+
+
+def load_plugins(name, type, namespace):
+    plugin_info = [None]
+    classes = []
+    try:
+        plugin_info = imp.find_module(
+            name, [os.path.join(get_executable_path(), 'ytdlp_plugins')])
+        plugins = imp.load_module(name, *plugin_info)
+        for name in dir(plugins):
+            if not name.endswith(type):
+                continue
+            klass = getattr(plugins, name)
+            classes.append(klass)
+            namespace[name] = klass
+    except ImportError:
+        pass
+    finally:
+        if plugin_info[0] is not None:
+            plugin_info[0].close()
+    return classes
+
+
+def traverse_dict(dictn, keys, casesense=True):
+    if not isinstance(dictn, dict):
+        return None
+    first_key = keys[0]
+    if not casesense:
+        dictn = {key.lower(): val for key, val in dictn.items()}
+        first_key = first_key.lower()
+    value = dictn.get(first_key, None)
+    return value if len(keys) < 2 else traverse_dict(value, keys[1:], casesense)

youtube_dlc/version.py

@@ -1,3 +1,3 @@
 from __future__ import unicode_literals
 
-__version__ = '2021.01.16'
+__version__ = '2021.01.29'

ytdlp_plugins/extractor/__init__.py

@@ -0,0 +1,2 @@
+# flake8: noqa
+from .sample import SamplePluginIE

ytdlp_plugins/extractor/sample.py

@@ -0,0 +1,12 @@
+from __future__ import unicode_literals
+
+from youtube_dlc.extractor.common import InfoExtractor
+
+
+class SamplePluginIE(InfoExtractor):
+    _WORKING = False
+    IE_DESC = False
+    _VALID_URL = r'^sampleplugin:'
+
+    def _real_extract(self, url):
+        self.to_screen('URL "%s" sucessfully captured' % url)