Release 2021.02.15

Cookies for some new accounts doesn't work with age-gated videos without `has_verified=1`

.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 Issues with outdated version will be REJECTED.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 2021.02.09. 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 Issues with outdated version will be REJECTED.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 **2021.02.09**
 - [ ] 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 2021.02.09
  [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 2021.02.09. 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 **2021.02.09**
 - [ ] 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 2021.02.09. 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 **2021.02.09**
 - [ ] 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 2021.02.09. 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 **2021.02.09**
 - [ ] 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 2021.02.09
  [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 2021.02.09. 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 **2021.02.09**
 - [ ] 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
+      run: python devscripts/update-version.py
-    - name: Check the output from My action
+    - name: Print version
       run: echo "${{ steps.bump_version.outputs.ytdlc_version }}"
     - name: Run Make
       run: make
@@ -55,9 +55,7 @@ jobs:
         asset_content_type: application/octet-stream
     - name: Get SHA2-256SUMS for youtube-dlc
       id: sha2_file
-      env:
+      run: echo "::set-output name=sha2_unix::$(sha256sum youtube-dlc)"
-        SHA2: ${{ hashFiles('youtube-dlc') }}
-      run: echo "::set-output name=sha2_unix::$SHA2"
     - name: Install dependencies for pypi
       run: |
         python -m pip install --upgrade pip
@@ -75,6 +73,9 @@ jobs:
 
     runs-on: windows-latest
 
+    outputs:
+      sha2_windows: ${{ steps.sha2_file_win.outputs.sha2_windows }}
+
     needs: build_unix
 
     steps:
@@ -84,11 +85,14 @@ jobs:
       with:
           python-version: '3.8'
     - name: Install Requirements
-      run: pip install pyinstaller
+      run: pip install pyinstaller mutagen pycryptodome
     - name: Bump version
-      run: python scripts/update-version-workflow.py
+      id: bump_version
+      run: python devscripts/update-version.py
+    - name: Print version
+      run: echo "${{ steps.bump_version.outputs.ytdlc_version }}"
     - name: Run PyInstaller Script
-      run: python pyinst.py
+      run: python pyinst.py 64
     - name: Upload youtube-dlc.exe Windows binary
       id: upload-release-windows
       uses: actions/upload-release-asset@v1
@@ -101,14 +105,15 @@ jobs:
         asset_content_type: application/vnd.microsoft.portable-executable
     - name: Get SHA2-256SUMS for youtube-dlc.exe
       id: sha2_file_win
-      env:
+      run: echo "::set-output name=sha2_windows::$(certUtil -hashfile dist\youtube-dlc.exe SHA256 | findstr -v :)"
-        SHA2_win: ${{ hashFiles('dist/youtube-dlc.exe') }}
-      run: echo "::set-output name=sha2_windows::$SHA2_win"
 
   build_windows32:
 
     runs-on: windows-latest
 
+    outputs:
+      sha2_windows32: ${{ steps.sha2_file_win32.outputs.sha2_windows32 }}
+
     needs: [build_unix, build_windows]
 
     steps:
@@ -118,12 +123,17 @@ jobs:
       with:
           python-version: '3.4.4'
           architecture: 'x86'
+    - name: Install VS libs
+      run: choco install vcexpress2010
     - name: Install Requirements for 32 Bit
-      run: pip install pyinstaller==3.5
+      run: pip install pyinstaller==3.5 mutagen pycryptodome
     - name: Bump version
-      run: python scripts/update-version-workflow.py
+      id: bump_version
+      run: python devscripts/update-version.py
+    - name: Print version
+      run: echo "${{ steps.bump_version.outputs.ytdlc_version }}"
     - name: Run PyInstaller Script for 32 Bit
-      run: python pyinst32.py
+      run: python pyinst.py 32
     - name: Upload Executable youtube-dlc_x86.exe
       id: upload-release-windows32
       uses: actions/upload-release-asset@v1
@@ -136,9 +146,7 @@ jobs:
         asset_content_type: application/vnd.microsoft.portable-executable
     - name: Get SHA2-256SUMS for youtube-dlc_x86.exe
       id: sha2_file_win32
-      env:
+      run: echo "::set-output name=sha2_windows32::$(certUtil -hashfile dist\youtube-dlc_x86.exe SHA256 | findstr -v :)"
-        SHA2_win32: ${{ hashFiles('dist/youtube-dlc_x86.exe') }}
-      run: echo "::set-output name=sha2_windows32::$SHA2_win32"
     - name: Make SHA2-256SUMS file
       env:
         SHA2_WINDOWS: ${{ needs.build_windows.outputs.sha2_windows }}
@@ -162,18 +170,15 @@ jobs:
         asset_name: SHA2-256SUMS
         asset_content_type: text/plain
 
-  update_version_badge:
+#  update_version_badge:
-
+#    runs-on: ubuntu-latest
-    runs-on: ubuntu-latest
+#    needs: build_unix
-
+#    steps:
-    needs: build_unix
+#    - name: Create Version Badge
-
+#      uses: schneegans/dynamic-badges-action@v1.0.0
-    steps:
+#      with:
-    - name: Create Version Badge
+#        auth: ${{ secrets.GIST_TOKEN }}
-      uses: schneegans/dynamic-badges-action@v1.0.0
+#        gistID: c69cb23c3c5b3316248e52022790aa57
-      with:
+#        filename: version.json
-        auth: ${{ secrets.GIST_TOKEN }}
+#        label: Version
-        gistID: c69cb23c3c5b3316248e52022790aa57
+#        message: ${{ needs.build_unix.outputs.ytdlc_version }}
-        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
+    name: Core Tests
-    if: "!contains(github.event.head_commit.message, 'skip ci')"
+    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
+    name: Core Test
-    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
-    - 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 +1,44 @@
+# 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
+test/local_parameters.json
-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
 .coverage
 cover/
+secrets/
 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 +55,40 @@ updates_key.pem
 *.swf
 *.part
 *.ytdl
-*.conf
+*.frag
+*.frag.urls
+*.aria2
 *.swp
+*.ogg
+*.opus
+*.info.json
+*.live_chat.json
+*.jpg
+*.png
+*.webp
+*.annotations.xml
+*.description
+
+# Config
+*.conf
 *.spec
-*.exe
+cookies
-test/local_parameters.json
-.tox
-youtube-dl.zsh
-youtube-dlc.zsh
-
-# IntelliJ related files
-.idea
-*.iml
-
-tmp/
-venv/
-
-# VS Code related files
-.vscode
-
 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 +15,6 @@ ohnonot
 samiksome
 alxnull
 FelixFrog
-Zocker1999NET
+Zocker1999NET
+nao20010128nao
+shirt-dev

Changelog.md

@@ -4,25 +4,145 @@
 # 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`
+* Update version.py using devscripts\update-version.py (be wary of timezones)
-* Commit to master as `[version] update`
+* Run `make issuetemplates`
+* Commit to master as `[version] update :ci skip all`
 * Push to origin/master
 * Update changelog in /releases
 
 -->
 
 
+### 2021.02.15
+* **Merge youtube-dl:** Upto [2021.02.10](https://github.com/ytdl-org/youtube-dl/releases/tag/2021.02.10) (except archive.org)
+* [niconico] Improved extraction and support encrypted/SMILE movies
+* Fix HLS AES-128 with multiple keys in external downloaders
+* [youtube_live_chat] Fix by using POST API
+* [rumble] Add support for video page
+* Option to allow downloading unplayable video formats (`--allow-unplayable-formats`)
+* [ExtractAudio] Don't re-encode when file is already in a common audio format
+* Change optional dependency to `pycryptodome`
+* [youtube] Fix search continuations
+* [youtube] Fix for new accounts
+* Improve build/updater:
+    * Fix SHA256 calculation in build and implement hash checking for updater
+    * Exit immediately in windows once the update process starts
+    * Fix updater for `x86.exe`
+    * Updater looks for both `yt-dlp` and `youtube-dlc` in releases for future-proofing
+* Fix issue with unicode filenames in aria2c
+* Fix `allow_playlist_files` not being correctly passed through
+* Fix for empty HTTP head requests
+* Fix `get_executable_path` in UNIX
+* [sponskrub] Print ffmpeg output and errors to terminal
+* `__real_download` should be false when ffmpeg unavailable and no download
+* Show `exe`/`zip`/`source` and 32/64bit in verbose message
+
+
+### 2021.02.09
+* **aria2c support for DASH/HLS**: by [shirt](https://github.com/shirt-dev)
+* **Implement Updater** (`-U`) by [shirt](https://github.com/shirt-dev)
+* [youtube] Fix comment extraction
+* [youtube_live_chat] Improve extraction
+* [youtube] Fix for channel URLs sometimes not downloading all pages
+* [aria2c] Changed default arguments to `--console-log-level=warn --summary-interval=0 --file-allocation=none -x16 -j16 -s16`
+* Add fallback for thumbnails
+* [embedthumbnail] Keep original thumbnail after conversion if write_thumbnail given
+* [embedsubtitle] Keep original subtitle after conversion if write_subtitles given
+* [pyinst.py] Move back to root dir
+* [youtube] Simplified renderer parsing and bugfixes
+* [movefiles] Fix compatibility with python2
+* [remuxvideo] Fix validation of conditional remux
+* [sponskrub] Don't raise error when the video does not exist
+* [documentation] Crypto is an optional dependency
+
+
+### 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 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:**
+    * Separate output templates can be given for the different metadata files by using `-o TYPE:TEMPLATE`
+    * The allowed 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](https://github.com/animelover1984) and [bbepis](https://github.com/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](https://github.com/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:**
@@ -33,7 +153,7 @@
 
 ### 2021.01.14
 * Added option `--break-on-reject`
-* [roosterteeth.com] Fix for bonus episodes by @Zocker1999NET
+* [roosterteeth.com] Fix for bonus episodes by [Zocker1999NET](https://github.com/Zocker1999NET)
 * [tiktok] Fix for when share_info is empty
 * [EmbedThumbnail] Fix bug due to incorrect function name
 * [documentation] Changed sponskrub links to point to [pukkandan/sponskrub](https://github.com/pukkandan/SponSkrub) since I am now providing both linux and windows releases
@@ -42,18 +162,18 @@
 
 
 ### 2021.01.12
-* [roosterteeth.com] Add subtitle support by @samiksome
+* [roosterteeth.com] Add subtitle support by [samiksome](https://github.com/samiksome)
-* Added `--force-overwrites`, `--no-force-overwrites` by @alxnull
+* Added `--force-overwrites`, `--no-force-overwrites` by [alxnull](https://github.com/alxnull)
 * Changed fork name to `yt-dlp`
-* Fix typos by @FelixFrog
+* Fix typos by [FelixFrog](https://github.com/FelixFrog)
 * [ci] Option to skip
 * [changelog] Added unreleased changes in blackjack4494/yt-dlc
 
 
 ### 2021.01.10
-* [archive.org] Fix extractor and add support for audio and playlists by @wporr
+* [archive.org] Fix extractor and add support for audio and playlists by [wporr](https://github.com/wporr)
-* [Animelab] Added by @mariuszskon
+* [Animelab] Added by [mariuszskon](https://github.com/mariuszskon)
-* [youtube:search] Fix view_count by @ohnonot
+* [youtube:search] Fix view_count by [ohnonot](https://github.com/ohnonot)
 * [youtube] Show if video is embeddable in info
 * Update version badge automatically in README
 * Enable `test_youtube_search_matching`
@@ -62,11 +182,11 @@
 
 ### 2021.01.09
 * [youtube] Fix bug in automatic caption extraction
-* Add `post_hooks` to YoutubeDL by @alexmerkel
+* Add `post_hooks` to YoutubeDL by [alexmerkel](https://github.com/alexmerkel)
-* Batch file enumeration improvements by @glenn-slayden
+* Batch file enumeration improvements by [glenn-slayden](https://github.com/glenn-slayden)
-* Stop immediately when reaching `--max-downloads` by @glenn-slayden
+* Stop immediately when reaching `--max-downloads` by [glenn-slayden](https://github.com/glenn-slayden)
-* Fix incorrect ANSI sequence for restoring console-window title by @glenn-slayden
+* Fix incorrect ANSI sequence for restoring console-window title by [glenn-slayden](https://github.com/glenn-slayden)
-* Kill child processes when yt-dlc is killed by @Unrud
+* Kill child processes when yt-dlc is killed by [Unrud](https://github.com/Unrud)
 
 
 ### 2021.01.08
@@ -76,11 +196,11 @@
 
 
 ### 2021.01.07-1
-* [Akamai] fix by @nixxo
+* [Akamai] fix by [nixxo](https://github.com/nixxo)
-* [Tiktok] merge youtube-dl tiktok extractor by @GreyAlien502
+* [Tiktok] merge youtube-dl tiktok extractor by [GreyAlien502](https://github.com/GreyAlien502)
-* [vlive] add support for playlists by @kyuyeunk
+* [vlive] add support for playlists by [kyuyeunk](https://github.com/kyuyeunk)
-* [youtube_live_chat] make sure playerOffsetMs is positive by @siikamiika
+* [youtube_live_chat] make sure playerOffsetMs is positive by [siikamiika](https://github.com/siikamiika)
-* Ignore extra data streams in ffmpeg by @jbruchon
+* Ignore extra data streams in ffmpeg by [jbruchon](https://github.com/jbruchon)
 * Allow passing different arguments to different postprocessors using `--postprocessor-args`
 * Deprecated `--sponskrub-args`. The same can now be done using `--postprocessor-args "sponskrub:<args>"`
 * [CI] Split tests into core-test and full-test
@@ -110,15 +230,15 @@
     * Changed video format sorting to show video only files and video+audio files together.
     * Added `--video-multistreams`, `--no-video-multistreams`, `--audio-multistreams`, `--no-audio-multistreams`
     * Added `b`,`w`,`v`,`a` as alias for `best`, `worst`, `video` and `audio` respectively
-* **Shortcut Options:** Added `--write-link`, `--write-url-link`, `--write-webloc-link`, `--write-desktop-link` by @h-h-h-h - See [Internet Shortcut Options]README.md(#internet-shortcut-options) for details
+* **Shortcut Options:** Added `--write-link`, `--write-url-link`, `--write-webloc-link`, `--write-desktop-link` by [h-h-h-h](https://github.com/h-h-h-h) - See [Internet Shortcut Options](README.md#internet-shortcut-options) for details
 * **Sponskrub integration:** Added `--sponskrub`, `--sponskrub-cut`, `--sponskrub-force`, `--sponskrub-location`, `--sponskrub-args` - See [SponSkrub Options](README.md#sponskrub-options-sponsorblock) for details
-* Added `--force-download-archive` (`--force-write-archive`) by @h-h-h-h
+* Added `--force-download-archive` (`--force-write-archive`) by [h-h-h-h](https://github.com/h-h-h-h)
 * Added `--list-formats-as-table`,  `--list-formats-old`
 * **Negative Options:** Makes it possible to negate most boolean options by adding a `no-` to the switch. Usefull when you want to reverse an option that is defined in a config file
     * 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](https://github.com/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
@@ -135,7 +255,7 @@
     * Redirect channel home to /video
     * Print youtube's warning message
     * Multiple pages are handled better for feeds
-* Add --break-on-existing by @gergesh
+* Add --break-on-existing by [gergesh](https://github.com/gergesh)
 * Pre-check video IDs in the archive before downloading
 * [bitwave.tv] New extractor
 * [Gedi] Add extractor

Makefile

@@ -4,7 +4,7 @@ man: README.txt youtube-dlc.1 youtube-dlc.bash-completion youtube-dlc.zsh youtub
 
 
 clean:
-	rm -rf youtube-dlc.1.temp.md youtube-dlc.1 youtube-dlc.bash-completion README.txt MANIFEST build/ dist/ .coverage cover/ youtube-dlc.tar.gz youtube-dlc.zsh youtube-dlc.fish youtube_dlc/extractor/lazy_extractors.py *.dump *.part* *.ytdl *.info.json *.mp4 *.m4a *.flv *.mp3 *.avi *.mkv *.webm *.3gp *.wav *.ape *.swf *.jpg *.png *.spec CONTRIBUTING.md.tmp youtube-dlc youtube-dlc.exe
+	rm -rf youtube-dlc.1.temp.md youtube-dlc.1 youtube-dlc.bash-completion README.txt MANIFEST build/ dist/ .coverage cover/ youtube-dlc.tar.gz youtube-dlc.zsh youtube-dlc.fish youtube_dlc/extractor/lazy_extractors.py *.dump *.part* *.ytdl *.info.json *.mp4 *.m4a *.flv *.mp3 *.avi *.mkv *.webm *.3gp *.wav *.ape *.swf *.jpg *.png *.spec *.frag *.frag.urls *.frag.aria2 CONTRIBUTING.md.tmp youtube-dlc youtube-dlc.exe
 	find . -name "*.pyc" -delete
 	find . -name "*.class" -delete
 

README.md

@@ -1,10 +1,14 @@
 # YT-DLP
 
-<!-- See: https://github.com/marketplace/actions/dynamic-badges -->
+[![Release version](https://img.shields.io/github/v/release/pukkandan/yt-dlp?color=brightgreen&label=Release)](https://github.com/pukkandan/yt-dlp/releases/latest)
-[![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)](LICENSE)
-[![License: Unlicense](https://img.shields.io/badge/License-Unlicense-blue.svg)](https://github.com/pukkandan/yt-dlp/blob/master/LICENSE)
+[![CI Status](https://github.com/pukkandan/yt-dlp/workflows/Core%20Tests/badge.svg?branch=master)](https://github.com/pukkandan/yt-dlp/actions)
-[![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)
+[![Discord](https://img.shields.io/discord/807245652072857610?color=blue&label=discord&logo=discord)](https://discord.gg/S75JaBna)  
-[![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)
+
+[![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 +45,7 @@ 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 +56,35 @@ 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 v2021.02.10**: 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
+    * All Youtube Feeds (`:ytfav`, `:ytwatchlater`, `:ytsubs`, `:ythistory`, `:ytrec`) works correctly and supports downloading multiple pages of content
-    * Youtube search works correctly (`ytsearch:`, `ytsearchdate:`) along with Search URLs
+    * Youtube search (`ytsearch:`, `ytsearchdate:`) along with Search URLs works correctly
     * Redirect channel's home URL automatically to `/video` to preserve the old behaviour
 
-* **New extractors**: Trovo.live, AnimeLab, Philo MSO, Rcs, Gedi, bitwave.tv
+* **Aria2c with HLS/DASH**: You can use aria2c as the external downloader for DASH(mpd) and HLS(m3u8) formats. No more slow ffmpeg/native downloads
 
-* **Fixed extractors**: archive.org, roosterteeth.com, skyit, instagram, itv, SouthparkDe, spreaker, Vlive, tiktok, akamai, ina
+* **New extractors**: AnimeLab, Philo MSO, Rcs, Gedi, bitwave.tv, mildom, audius
 
-* **New options**: `--list-formats-as-table`, `--write-link`, `--force-download-archive`, `--force-overwrites`, `--break-on-reject` etc
+* **Fixed extractors**: archive.org, roosterteeth.com, skyit, instagram, itv, SouthparkDe, spreaker, Vlive, tiktok, akamai, ina, rumble
+
+* **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
+
+* **Self-updater**: The releases can be updated using `youtube-dlc -U`
 
-* **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
 
@@ -77,27 +97,27 @@ 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`
+* Download the binary from the [latest release](https://github.com/pukkandan/yt-dlp/releases/latest) (recommended method)
-* Download the binary from the [latest release](https://github.com/pukkandan/yt-dlp/releases/latest)
+* Use [PyPI package](https://pypi.org/project/yt-dlp): `python -m pip install --upgrade yt-dlp`
 * 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`
 
 ### UPDATE
-`-U` does not work. Simply repeat the install process to update.
+Starting from version `2021.02.09`, you can use `youtube-dlc -U` to update if you are using the provided release.
+If you are using `pip`, simply re-run the same command that was used to install the program.
 
 ### COMPILE
 
 **For Windows**:
-To build the Windows executable yourself (without version info!)
+To build the Windows executable, you must have pyinstaller (and optionally mutagen and pycryptodome)
+
+    python -m pip install --upgrade pyinstaller mutagen pycryptodome
+
+Once you have all the necessary dependancies installed, just run `py 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 +126,7 @@ 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.
@@ -120,9 +141,9 @@ Then simply type this
 ## General Options:
     -h, --help                       Print this help text and exit
     --version                        Print program version and exit
-    -U, --update                     [BROKEN] Update this program to latest
+    -U, --update                     Update this program to latest version. Make
-                                     version. Make sure that you have sufficient
+                                     sure that you have sufficient permissions
-                                     permissions (run with sudo if needed)
+                                     (run with sudo if needed)
     -i, --ignore-errors              Continue on download errors, for example to
                                      skip unavailable videos in a playlist
                                      (default) (Alias: --no-abort-on-error)
@@ -151,9 +172,9 @@ 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
+    --config-location PATH           Location of the main configuration file;
-                                     the path to the config or its containing
+                                     either the path to the config or its
-                                     directory
+                                     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 +324,36 @@ 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.
+    --external-downloader NAME       Use the specified external downloader.
-                                     Currently supports
+                                     Currently supports aria2c, avconv, axel,
-                                     aria2c,avconv,axel,curl,ffmpeg,httpie,wget
+                                     curl, ffmpeg, httpie, wget
-    --external-downloader-args ARGS  Give these arguments to the external
+    --downloader-args NAME:ARGS      Give these arguments to the external
-                                     downloader
+                                     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 +366,11 @@ 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)
+    -c, --continue                   Resume partially downloaded files/fragments
-    --no-continue                    Restart download of partially downloaded
+                                     (default)
-                                     files from beginning
+    --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 +383,18 @@ 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)
@@ -420,10 +468,6 @@ Then simply type this
                                      files in the current directory to debug
                                      problems
     --print-traffic                  Display sent and read HTTP traffic
-    -C, --call-home                  [Broken] Contact the youtube-dlc server for
-                                     debugging
-    --no-call-home                   Do not contact the youtube-dlc server for
-                                     debugging (default)
 
 ## Workarounds:
     --encoding ENCODING              Force the specified encoding (experimental)
@@ -435,7 +479,7 @@ 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
@@ -481,21 +525,26 @@ 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:
+                                     data on YouTube videos (default)
-                                     --no-youtube-skip-dash-manifest)
+                                     (Alias: --no-youtube-skip-dash-manifest)
     --youtube-skip-dash-manifest     Do not download the DASH manifests and
-                                     related data on YouTube videos (Alias:
+                                     related data on YouTube videos
-                                     --no-youtube-include-dash-manifest)
+                                     (Alias: --no-youtube-include-dash-manifest)
     --youtube-include-hls-manifest   Download the HLS manifests and related data
-                                     on YouTube videos (default) (Alias:
+                                     on YouTube videos (default)
-                                    --no-youtube-skip-hls-manifest)
+                                     (Alias: --no-youtube-skip-hls-manifest)
     --youtube-skip-hls-manifest      Do not download the HLS manifests and
-                                     related data on YouTube videos (Alias:
+                                     related data on YouTube videos
-                                     --no-youtube-include-hls-manifest)
+                                     (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,
                                      webm, flv. Ignored if no merge is required
+    --allow-unplayable-formats       Allow unplayable formats to be listed and
+                                     downloaded. All video postprocessing will
+                                     also be turned off
+    --no-allow-unplayable-formats    Do not allow unplayable formats to be
+                                     listed or downloaded (default)
 
 ## Subtitle Options:
     --write-subs                     Write subtitle file
@@ -535,27 +584,30 @@ Then simply type this
 
 ## Post-Processing Options:
     -x, --extract-audio              Convert video files to audio-only files
-                                     (requires ffmpeg or avconv and ffprobe or
+                                     (requires ffmpeg and ffprobe)
-                                     avprobe)
     --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
+    --audio-quality QUALITY          Specify ffmpeg audio quality, insert a
-                                     a value between 0 (better) and 9 (worse)
+                                     value between 0 (better) and 9 (worse) for
-                                     for VBR or a specific bitrate like 128K
+                                     VBR or a specific bitrate like 128K
                                      (default 5)
     --remux-video FORMAT             Remux the video into another container if
-                                     necessary (currently supported: mp4|mkv).
+                                     necessary (currently supported: mp4|mkv|flv
-                                     If target container does not support the
+                                     |webm|mov|avi|mp3|mka|m4a|ogg|opus). If
-                                     video/audio codec, remuxing will fail
+                                     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
+                                     re-encoding is necessary. The supported
-                                     supported: mp4|flv|ogg|webm|mkv|avi)
+                                     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 ':'
+                                     and the arguments separated by a colon ":"
-                                     to give the argument to only the specified
+                                     to give the argument to the specified
                                      postprocessor/executable. Supported
                                      postprocessors are: SponSkrub,
                                      ExtractAudio, VideoRemuxer, VideoConvertor,
@@ -563,14 +615,14 @@ Then simply type this
                                      FixupStretched, FixupM4a, FixupM3u8,
                                      SubtitlesConvertor and EmbedThumbnail. The
                                      supported executables are: SponSkrub,
-                                     FFmpeg, FFprobe, avconf, avprobe and
+                                     FFmpeg, FFprobe, and AtomicParsley. You can
-                                     AtomicParsley. You can use this option
+                                     use this option multiple times to give
-                                     multiple times to give different arguments
+                                     different arguments to different
-                                     to different postprocessors. You can also
+                                     postprocessors. You can also specify
-                                     specify "PP+EXE:ARGS" to give the arguments
+                                     "PP+EXE:ARGS" to give the arguments to the
-                                     to the specified executable only when being
+                                     specified executable only when being used
-                                     used by the specified postprocessor (Alias:
+                                     by the specified postprocessor. You can use
-                                     --ppa)
+                                     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 +636,20 @@ 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 /
+    --parse-metadata FIELD:FORMAT    Parse additional metadata like title/artist
-                                     artist from the video title. The format
+                                     from other fields. Give field name to
-                                     syntax is the same as --output. Regular
+                                     extract data from, and format of the field
-                                     expression with named capture groups may
+                                     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-
+                                     any existing values and can be use in
-                                     title "%(artist)s - %(title)s" matches a
+                                     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
+                                     (regex): --parse-metadata
-                                     "(?P<artist>.+?) - (?P<title>.+)"
+                                     "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 +657,9 @@ 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
+    --ffmpeg-location PATH           Location of the ffmpeg binary; either the
-                                     postprocessors (Alias: --no-prefer-ffmpeg)
+                                     path to the binary or its containing
-    --prefer-ffmpeg                  Prefer ffmpeg over avconv for running the
+                                     directory
-                                     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)
     --exec CMD                       Execute a command on the file after
                                      downloading and post-processing, similar to
                                      find's -exec syntax. Example: --exec 'adb
@@ -648,8 +698,9 @@ 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 +758,15 @@ 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 +796,7 @@ 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 +853,7 @@ 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 +873,7 @@ 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 +885,17 @@ 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 +904,7 @@ $ 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 +935,7 @@ 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 +974,35 @@ 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
+ - `hasvid`: Gives priority to formats that has a video stream
- - `audio`, `has_audio`: Gives priority to formats that has a audio stream
+ - `hasaud`: Gives priority to formats that has a audio stream
- - `extractor`, `preference`, `extractor_preference`: The format preference as given by the extractor
+ - `ie_pref`: The format preference as given by the extractor
- - `lang`, `language_preference`: Language 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
+ - `source`: 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`)
+ - `proto`: 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)
+ - `vcodec`: Video Codec (`av01` > `vp9` > `h265` > `h264` > `vp8` > `h263` > `theora` > other > unknown)
- - `acodec`, `audio_codec`: Audio Codec (`opus` > `vorbis` > `aac` > `mp4a` > `mp3` > `ac3` > `dts` > 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.
+ - `vext`: 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`.
+ - `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`, `extension`: Equivalent to `vext,aext`
+ - `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
+ - `fs_approx`: Approximate filesize calculated from the manifests
- - `size`, `filesize_estimate`: Exact filesize if available, otherwise approximate filesize
+ - `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.
+ - `res`: Video resolution, calculated as the smallest dimension.
- - `fps`, `framerate`: Framerate of video
+ - `fps`: Framerate of video
- - `tbr`, `total_bitrate`: Total average bitrate in KBit/s
+ - `tbr`: Total average bitrate in KBit/s
- - `vbr`, `video_bitrate`: Average video bitrate in KBit/s
+ - `vbr`: Average video bitrate in KBit/s
- - `abr`, `audio_bitrate`: Average audio bitrate in KBit/s
+ - `abr`: Average audio bitrate in KBit/s
- - `br`, `bitrate`: Equivalent to using `tbr,vbr,abr`
+ - `br`: Equivalent to using `tbr,vbr,abr`
- - `samplerate`, `asr`: Audio sample rate in Hz
+ - `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 +1041,7 @@ $ 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 +1089,7 @@ $ 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 +1125,11 @@ $ 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/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.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

@@ -1,6 +1,5 @@
 # Supported sites
  - **1tv**: Первый канал
- - **1up.com**
  - **20min**
  - **220.ro**
  - **23video**
@@ -47,12 +46,13 @@
  - **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 +79,9 @@
  - **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 +114,9 @@
  - **BiliBili**
  - **BilibiliAudio**
  - **BilibiliAudioAlbum**
+ - **BilibiliChannel**
  - **BiliBiliPlayer**
+ - **BiliBiliSearch**: Bilibili video search, "bilisearch" keyword
  - **BioBioChileTV**
  - **Biography**
  - **BIQLE**
@@ -197,8 +202,6 @@
  - **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**
@@ -390,6 +393,8 @@
  - **HungamaSong**
  - **Hypem**
  - **ign.com**
+ - **IGNArticle**
+ - **IGNVideo**
  - **IHeartRadio**
  - **iheartradio:podcast**
  - **imdb**: Internet Movie Database trailers
@@ -520,6 +525,12 @@
  - **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 +560,7 @@
  - **mtv:video**
  - **mtvjapan**
  - **mtvservices:embedded**
+ - **MTVUutisetArticle**
  - **MuenchenTV**: münchen.tv
  - **mva**: Microsoft Virtual Academy videos
  - **mva:course**: Microsoft Virtual Academy courses
@@ -690,7 +702,6 @@
  - **parliamentlive.tv**: UK parliament videos
  - **Patreon**
  - **pbs**: Public Broadcasting Service (PBS) and member stations: PBS: Public Broadcasting Service, APT - Alabama Public Television (WBIQ), GPB/Georgia Public Broadcasting (WGTV), Mississippi Public Broadcasting (WMPN), Nashville Public Television (WNPT), WFSU-TV (WFSU), WSRE (WSRE), WTCI (WTCI), WPBA/Channel 30 (WPBA), Alaska Public Media (KAKM), Arizona PBS (KAET), KNME-TV/Channel 5 (KNME), Vegas PBS (KLVX), AETN/ARKANSAS ETV NETWORK (KETS), KET (WKLE), WKNO/Channel 10 (WKNO), LPB/LOUISIANA PUBLIC BROADCASTING (WLPB), OETA (KETA), Ozarks Public Television (KOZK), WSIU Public Broadcasting (WSIU), KEET TV (KEET), KIXE/Channel 9 (KIXE), KPBS San Diego (KPBS), KQED (KQED), KVIE Public Television (KVIE), PBS SoCal/KOCE (KOCE), ValleyPBS (KVPT), CONNECTICUT PUBLIC TELEVISION (WEDH), KNPB Channel 5 (KNPB), SOPTV (KSYS), Rocky Mountain PBS (KRMA), KENW-TV3 (KENW), KUED Channel 7 (KUED), Wyoming PBS (KCWC), Colorado Public Television / KBDI 12 (KBDI), KBYU-TV (KBYU), Thirteen/WNET New York (WNET), WGBH/Channel 2 (WGBH), WGBY (WGBY), NJTV Public Media NJ (WNJT), WLIW21 (WLIW), mpt/Maryland Public Television (WMPB), WETA Television and Radio (WETA), WHYY (WHYY), PBS 39 (WLVT), WVPT - Your Source for PBS and More! (WVPT), Howard University Television (WHUT), WEDU PBS (WEDU), WGCU Public Media (WGCU), WPBT2 (WPBT), WUCF TV (WUCF), WUFT/Channel 5 (WUFT), WXEL/Channel 42 (WXEL), WLRN/Channel 17 (WLRN), WUSF Public Broadcasting (WUSF), ETV (WRLK), UNC-TV (WUNC), PBS Hawaii - Oceanic Cable Channel 10 (KHET), Idaho Public Television (KAID), KSPS (KSPS), OPB (KOPB), KWSU/Channel 10 & KTNW/Channel 31 (KWSU), WILL-TV (WILL), Network Knowledge - WSEC/Springfield (WSEC), WTTW11 (WTTW), Iowa Public Television/IPTV (KDIN), Nine Network (KETC), PBS39 Fort Wayne (WFWA), WFYI Indianapolis (WFYI), Milwaukee Public Television (WMVS), WNIN (WNIN), WNIT Public Television (WNIT), WPT (WPNE), WVUT/Channel 22 (WVUT), WEIU/Channel 51 (WEIU), WQPT-TV (WQPT), WYCC PBS Chicago (WYCC), WIPB-TV (WIPB), WTIU (WTIU), CET  (WCET), ThinkTVNetwork (WPTD), WBGU-TV (WBGU), WGVU TV (WGVU), NET1 (KUON), Pioneer Public Television (KWCM), SDPB Television (KUSD), TPT (KTCA), KSMQ (KSMQ), KPTS/Channel 8 (KPTS), KTWU/Channel 11 (KTWU), East Tennessee PBS (WSJK), WCTE-TV (WCTE), WLJT, Channel 11 (WLJT), WOSU TV (WOSU), WOUB/WOUC (WOUB), WVPB (WVPB), WKYU-PBS (WKYU), KERA 13 (KERA), MPBN (WCBB), Mountain Lake PBS (WCFE), NHPTV (WENH), Vermont PBS (WETK), witf (WITF), WQED Multimedia (WQED), WMHT Educational Telecommunications (WMHT), Q-TV (WDCQ), WTVS Detroit Public TV (WTVS), CMU Public Television (WCMU), WKAR-TV (WKAR), WNMU-TV Public TV 13 (WNMU), WDSE - WRPT (WDSE), WGTE TV (WGTE), Lakeland Public Television (KAWE), KMOS-TV - Channels 6.1, 6.2 and 6.3 (KMOS), MontanaPBS (KUSM), KRWG/Channel 22 (KRWG), KACV (KACV), KCOS/Channel 13 (KCOS), WCNY/Channel 24 (WCNY), WNED (WNED), WPBS (WPBS), WSKG Public TV (WSKG), WXXI (WXXI), WPSU (WPSU), WVIA Public Media Studios (WVIA), WTVI (WTVI), Western Reserve PBS (WNEO), WVIZ/PBS ideastream (WVIZ), KCTS 9 (KCTS), Basin PBS (KPBT), KUHT / Channel 8 (KUHT), KLRN (KLRN), KLRU (KLRU), WTJX Channel 12 (WTJX), WCVE PBS (WCVE), KBTC Public Television (KBTC)
- - **pcmag**
  - **PearVideo**
  - **PeerTube**
  - **People**
@@ -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**
@@ -1205,9 +1218,9 @@
  - **youtube:history**: Youtube watch history, ":ythistory" for short (requires authentication)
  - **youtube:playlist**: YouTube.com playlists
  - **youtube:recommended**: YouTube.com recommended videos, ":ytrec" for short (requires authentication)
- - **youtube:search**: YouTube.com searches
+ - **youtube:search**: YouTube.com searches, "ytsearch" keyword
  - **youtube:search:date**: YouTube.com searches, newest videos first, "ytsearchdate" keyword
- - **youtube:search_url**: YouTube.com searches, "ytsearch" keyword
+ - **youtube:search_url**: YouTube.com search URLs
  - **youtube:subscriptions**: YouTube.com subscriptions feed, ":ytsubs" for short (requires authentication)
  - **youtube:tab**: YouTube.com tab
  - **youtube:watchlater**: Youtube watch later list, ":ytwatchlater" for short (requires authentication)

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

@@ -1,55 +1,41 @@
+#!/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__
 
-from datetime import datetime
+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'
+FILE_DESCRIPTION = 'Media Downloader%s' % (' (32 Bit)' if _x86 else '')
+
+# 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__']
 
-_LATEST_VERSION = locals()['__version__']
+VERSION_LIST = VERSION.split('.')
+VERSION_LIST = list(map(int, VERSION_LIST)) + [0] * (4 - len(VERSION_LIST))
 
-_OLD_VERSION = _LATEST_VERSION.rsplit("-", 1)
+print('Version: %s%s' % (VERSION, _x86))
+print('Remember to update the version using devscipts\\update-version.py')
 
-if len(_OLD_VERSION) > 0:
+VERSION_FILE = VSVersionInfo(
-    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,
+        filevers=VERSION_LIST,
-        prodvers=_ver_tuple,
+        prodvers=VERSION_LIST,
         mask=0x3F,
         flags=0x0,
         OS=0x4,
@@ -58,35 +44,35 @@ version_file = VSVersionInfo(
         date=(0, 0),
     ),
     kids=[
-        StringFileInfo(
+        StringFileInfo([
-            [
+            StringTable(
-                StringTable(
+                '040904B0', [
-                    "040904B0",
+                    StringStruct('Comments', 'Youtube-dlc%s Command Line Interface.' % _x86),
-                    [
+                    StringStruct('CompanyName', 'https://github.com/pukkandan/yt-dlp'),
-                        StringStruct("Comments", "Youtube-dlc Command Line Interface."),
+                    StringStruct('FileDescription', FILE_DESCRIPTION),
-                        StringStruct("CompanyName", "theidel@uni-bremen.de"),
+                    StringStruct('FileVersion', VERSION),
-                        StringStruct("FileDescription", FILE_DESCRIPTION),
+                    StringStruct('InternalName', 'youtube-dlc%s' % _x86),
-                        StringStruct("FileVersion", version),
+                    StringStruct(
-                        StringStruct("InternalName", "youtube-dlc"),
+                        'LegalCopyright',
-                        StringStruct(
+                        'pukkandan@gmail.com | UNLICENSE',
-                            "LegalCopyright",
+                    ),
-                            "theidel@uni-bremen.de | UNLICENSE",
+                    StringStruct('OriginalFilename', 'youtube-dlc%s.exe' % _x86),
-                        ),
+                    StringStruct('ProductName', 'Youtube-dlc%s' % _x86),
-                        StringStruct("OriginalFilename", "youtube-dlc.exe"),
+                    StringStruct('ProductVersion', '%s%s' % (VERSION, _x86)),
-                        StringStruct("ProductName", "Youtube-dlc"),
+                ])]),
-                        StringStruct("ProductVersion", version + " | git.io/JLh7K"),
+        VarFileInfo([VarStruct('Translation', [0, 1200])])
-                    ],
-                )
-            ]
-        ),
-        VarFileInfo([VarStruct("Translation", [0, 1200])])
     ]
 )
 
 PyInstaller.__main__.run([
-    '--name=youtube-dlc',
+    '--name=youtube-dlc%s' % _x86,
     '--onefile',
-    '--icon=win/icon/cloud.ico',
+    '--icon=devscripts/cloud.ico',
+    '--exclude-module=youtube_dl',
+    '--exclude-module=test',
+    '--exclude-module=ytdlp_plugins',
+    '--hidden-import=mutagen',
+    '--hidden-import=Crypto',
     'youtube_dlc/__main__.py',
 ])
-SetVersion('dist/youtube-dlc.exe', version_file)
+SetVersion('dist/youtube-dlc%s.exe' % _x86, 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 +1,2 @@
+mutagen
+pycryptodome

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', 'pycryptodome']
+
+
 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):
+        def fname(templ, na_placeholder='NA'):
-            ydl = YoutubeDL({'outtmpl': templ})
+            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'
+        NA_TEST_OUTTMPL = '%(uploader_date)s-%(width)d-%(id)s.%(ext)s'
-        self.assertEqual(fname('%(uploader_date)s-%(id)s.%(ext)s'), 'NA-1234.mp4')
+        # 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
+import youtube_dlc.YoutubeDL
-from youtube_dl.utils import DownloadError
+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

@@ -19,55 +19,46 @@ from youtube_dlc.compat import compat_str, compat_urlretrieve
 _TESTS = [
     (
         'https://s.ytimg.com/yts/jsbin/html5player-vflHOr_nV.js',
-        'js',
         86,
         '>=<;:/.-[+*)(\'&%$#"!ZYX0VUTSRQPONMLKJIHGFEDCBA\\yxwvutsrqponmlkjihgfedcba987654321',
     ),
     (
         'https://s.ytimg.com/yts/jsbin/html5player-vfldJ8xgI.js',
-        'js',
         85,
         '3456789a0cdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRS[UVWXYZ!"#$%&\'()*+,-./:;<=>?@',
     ),
     (
         'https://s.ytimg.com/yts/jsbin/html5player-vfle-mVwz.js',
-        'js',
         90,
         ']\\[@?>=<;:/.-,+*)(\'&%$#"hZYXWVUTSRQPONMLKJIHGFEDCBAzyxwvutsrqponmlkjiagfedcb39876',
     ),
     (
         'https://s.ytimg.com/yts/jsbin/html5player-en_US-vfl0Cbn9e.js',
-        'js',
         84,
         'O1I3456789abcde0ghijklmnopqrstuvwxyzABCDEFGHfJKLMN2PQRSTUVW@YZ!"#$%&\'()*+,-./:;<=',
     ),
     (
         'https://s.ytimg.com/yts/jsbin/html5player-en_US-vflXGBaUN.js',
-        'js',
         '2ACFC7A61CA478CD21425E5A57EBD73DDC78E22A.2094302436B2D377D14A3BBA23022D023B8BC25AA',
         'A52CB8B320D22032ABB3A41D773D2B6342034902.A22E87CDD37DBE75A5E52412DC874AC16A7CFCA2',
     ),
     (
         'https://s.ytimg.com/yts/jsbin/html5player-en_US-vflBb0OQx.js',
-        'js',
         84,
         '123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQ0STUVWXYZ!"#$%&\'()*+,@./:;<=>'
     ),
     (
         'https://s.ytimg.com/yts/jsbin/html5player-en_US-vfl9FYC6l.js',
-        'js',
         83,
         '123456789abcdefghijklmnopqr0tuvwxyzABCDETGHIJKLMNOPQRS>UVWXYZ!"#$%&\'()*+,-./:;<=F'
     ),
     (
         'https://s.ytimg.com/yts/jsbin/html5player-en_US-vflCGk6yw/html5player.js',
-        'js',
         '4646B5181C6C3020DF1D9C7FCFEA.AD80ABF70C39BD369CCCAE780AFBB98FA6B6CB42766249D9488C288',
         '82C8849D94266724DC6B6AF89BBFA087EACCD963.B93C07FBA084ACAEFCF7C9D1FD0203C6C1815B6B'
     ),
     (
         'https://s.ytimg.com/yts/jsbin/html5player-en_US-vflKjOTVq/html5player.js',
-        'js',
         '312AA52209E3623129A412D56A40F11CB0AF14AE.3EE09501CB14E3BCDC3B2AE808BF3F1D14E7FBF12',
         '112AA5220913623229A412D56A40F11CB0AF14AE.3EE0950FCB14EEBCDC3B2AE808BF331D14E7FBF3',
     )
@@ -78,6 +69,10 @@ class TestPlayerInfo(unittest.TestCase):
     def test_youtube_extract_player_info(self):
         PLAYER_URLS = (
             ('https://www.youtube.com/s/player/64dddad9/player_ias.vflset/en_US/base.js', '64dddad9'),
+            ('https://www.youtube.com/s/player/64dddad9/player_ias.vflset/fr_FR/base.js', '64dddad9'),
+            ('https://www.youtube.com/s/player/64dddad9/player-plasma-ias-phone-en_US.vflset/base.js', '64dddad9'),
+            ('https://www.youtube.com/s/player/64dddad9/player-plasma-ias-phone-de_DE.vflset/base.js', '64dddad9'),
+            ('https://www.youtube.com/s/player/64dddad9/player-plasma-ias-tablet-en_US.vflset/base.js', '64dddad9'),
             # obsolete
             ('https://www.youtube.com/yts/jsbin/player_ias-vfle4-e03/en_US/base.js', 'vfle4-e03'),
             ('https://www.youtube.com/yts/jsbin/player_ias-vfl49f_g4/en_US/base.js', 'vfl49f_g4'),
@@ -86,13 +81,9 @@ 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_id = YoutubeIE._extract_player_info(player_url)
-            player_type, player_id = YoutubeIE._extract_player_info(player_url)
-            self.assertEqual(player_type, expected_player_type)
             self.assertEqual(player_id, expected_player_id)
 
 
@@ -104,13 +95,13 @@ class TestSignature(unittest.TestCase):
             os.mkdir(self.TESTDATA_DIR)
 
 
-def make_tfunc(url, stype, sig_input, expected_sig):
+def make_tfunc(url, sig_input, expected_sig):
     m = re.match(r'.*-([a-zA-Z0-9_-]+)(?:/watch_as3|/html5player)?\.[a-z]+$', url)
     assert m, '%r should follow URL format' % url
     test_id = m.group(1)
 
     def test_func(self):
-        basename = 'player-%s.%s' % (test_id, stype)
+        basename = 'player-%s.js' % test_id
         fn = os.path.join(self.TESTDATA_DIR, basename)
 
         if not os.path.exists(fn):
@@ -118,22 +109,16 @@ def make_tfunc(url, stype, sig_input, expected_sig):
 
         ydl = FakeYDL()
         ie = YoutubeIE(ydl)
-        if stype == 'js':
+        with io.open(fn, encoding='utf-8') as testf:
-            with io.open(fn, encoding='utf-8') as testf:
+            jscode = testf.read()
-                jscode = testf.read()
+        func = ie._parse_sig_js(jscode)
-            func = ie._parse_sig_js(jscode)
-        else:
-            assert stype == 'swf'
-            with open(fn, 'rb') as testf:
-                swfcode = testf.read()
-            func = ie._parse_sig_swf(swfcode)
         src_sig = (
             compat_str(string.printable[:sig_input])
             if isinstance(sig_input, int) else sig_input)
         got_sig = func(src_sig)
         self.assertEqual(got_sig, expected_sig)
 
-    test_func.__name__ = str('test_signature_' + stype + '_' + test_id)
+    test_func.__name__ = str('test_signature_js_' + test_id)
     setattr(TestSignature, test_func.__name__, test_func)
 
 

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/__init__.py

@@ -18,13 +18,11 @@ from .options import (
 )
 from .compat import (
     compat_getpass,
-    compat_shlex_split,
     workaround_optparse_bug9161,
 )
 from .utils import (
     DateRange,
     decodeOption,
-    DEFAULT_OUTTMPL,
     DownloadError,
     ExistingVideoReached,
     expand_path,
@@ -33,11 +31,12 @@ from .utils import (
     preferredencoding,
     read_batch_urls,
     RejectedVideoReached,
+    REMUX_EXTENSIONS,
+    render_table,
     SameFileError,
     setproctitle,
     std_headers,
     write_string,
-    render_table,
 )
 from .update import update_self
 from .downloader import (
@@ -46,6 +45,7 @@ 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 +70,7 @@ def _real_main(argv=None):
         std_headers['Referer'] = opts.referer
 
     # Custom HTTP headers
-    if opts.headers is not None:
+    std_headers.update(opts.headers)
-        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
 
     # Dump user agent
     if opts.dump_user_agent:
@@ -216,12 +209,14 @@ 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_EXTENSIONS:
             parser.error('invalid video recode format specified')
+    if opts.remuxvideo is not None:
+        opts.remuxvideo = opts.remuxvideo.replace(' ', '')
+        remux_regex = r'{0}(?:/{0})*$'.format(r'(?:\w+>)?(?:%s)' % '|'.join(REMUX_EXTENSIONS))
+        if not re.match(remux_regex, opts.remuxvideo):
+            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')
@@ -235,37 +230,79 @@ def _real_main(argv=None):
     if opts.extractaudio and not opts.keepvideo and opts.format is None:
         opts.format = 'bestaudio/best'
 
-    # --all-sub automatically sets --write-sub if --write-auto-sub is not given
+    outtmpl = opts.outtmpl
-    # this was the old behaviour if only --all-sub was given.
+    if not outtmpl:
-    if opts.allsubtitles and not opts.writeautomaticsub:
+        outtmpl = {'default': (
-        opts.writesubtitles = True
+            '%(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'
-    outtmpl = ((opts.outtmpl is not None and opts.outtmpl)
+            else '%(autonumber)s-%(title)s-%(id)s.%(ext)s' if opts.usetitle and opts.autonumber
-               or (opts.format == '-1' and opts.usetitle and '%(title)s-%(id)s-%(format)s.%(ext)s')
+            else '%(title)s-%(id)s.%(ext)s' if opts.usetitle
-               or (opts.format == '-1' and '%(id)s-%(format)s.%(ext)s')
+            else '%(id)s.%(ext)s' if opts.useid
-               or (opts.usetitle and opts.autonumber and '%(autonumber)s-%(title)s-%(id)s.%(ext)s')
+            else '%(autonumber)s-%(id)s.%(ext)s' if opts.autonumber
-               or (opts.usetitle and '%(title)s-%(id)s.%(ext)s')
+            else None)}
-               or (opts.useid and '%(id)s.%(ext)s')
+    outtmpl_default = outtmpl.get('default')
-               or (opts.autonumber and '%(autonumber)s-%(id)s.%(ext)s')
+    if outtmpl_default is not None and not os.path.splitext(outtmpl_default)[1] and opts.extractaudio:
-               or DEFAULT_OUTTMPL)
-    if not os.path.splitext(outtmpl)[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
 
+    def report_conflict(arg1, arg2):
+        write_string('WARNING: %s is ignored since %s was given\n' % (arg2, arg1), out=sys.stderr)
+    if opts.remuxvideo and opts.recodevideo:
+        report_conflict('--recode-video', '--remux-video')
+        opts.remuxvideo = False
+    if opts.allow_unplayable_formats:
+        if opts.extractaudio:
+            report_conflict('--allow-unplayable-formats', '--extract-audio')
+            opts.extractaudio = False
+        if opts.remuxvideo:
+            report_conflict('--allow-unplayable-formats', '--remux-video')
+            opts.remuxvideo = False
+        if opts.recodevideo:
+            report_conflict('--allow-unplayable-formats', '--recode-video')
+            opts.recodevideo = False
+        if opts.addmetadata:
+            report_conflict('--allow-unplayable-formats', '--add-metadata')
+            opts.addmetadata = False
+        if opts.embedsubtitles:
+            report_conflict('--allow-unplayable-formats', '--embed-subs')
+            opts.embedsubtitles = False
+        if opts.embedthumbnail:
+            report_conflict('--allow-unplayable-formats', '--embed-thumbnail')
+            opts.embedthumbnail = False
+        if opts.xattrs:
+            report_conflict('--allow-unplayable-formats', '--xattrs')
+            opts.xattrs = False
+        if opts.fixup and opts.fixup.lower() not in ('never', 'ignore'):
+            report_conflict('--allow-unplayable-formats', '--fixup')
+        opts.fixup = 'never'
+        if opts.sponskrub:
+            report_conflict('--allow-unplayable-formats', '--sponskrub')
+        opts.sponskrub = False
+
     # PostProcessors
     postprocessors = []
-    if opts.metafromtitle:
+    if opts.metafromfield:
         postprocessors.append({
-            'key': 'MetadataFromTitle',
+            'key': 'MetadataFromField',
-            'titleformat': opts.metafromtitle
+            'formats': opts.metafromfield,
+            'when': 'beforedl'
         })
     if opts.extractaudio:
         postprocessors.append({
@@ -300,9 +337,17 @@ def _real_main(argv=None):
             'format': opts.convertsubtitles,
         })
     if opts.embedsubtitles:
+        already_have_subtitle = opts.writesubtitles
         postprocessors.append({
             'key': 'FFmpegEmbedSubtitle',
+            'already_have_subtitle': already_have_subtitle
         })
+        if not already_have_subtitle:
+            opts.writesubtitles = True
+    # --all-sub automatically sets --write-sub if --write-auto-sub is not given
+    # this was the old behaviour if only --all-sub was given.
+    if opts.allsubtitles and not opts.writeautomaticsub:
+        opts.writesubtitles = True
     if opts.embedthumbnail:
         already_have_thumbnail = opts.writethumbnail or opts.write_all_thumbnails
         postprocessors.append({
@@ -326,32 +371,31 @@ 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.
+    # ExecAfterDownload must be the last PP
-    # So if the user is able to remove the file before your postprocessor runs it might cause a few problems.
     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 = {}
+    def report_args_compat(arg, name):
-    if opts.postprocessor_args is not None:
+        write_string(
-        for string in opts.postprocessor_args:
+            'WARNING: %s given without specifying name. The arguments will be given to all %s\n' % (arg, name),
-            mobj = re.match(r'(?P<pp>\w+(?:\+\w+)?):(?P<args>.*)$', string)
+            out=sys.stderr)
-            if mobj is None:
+    if 'default' in opts.external_downloader_args:
-                if 'sponskrub' not in postprocessor_args:  # for backward compatibility
+        report_args_compat('--external-downloader-args', 'external downloaders')
-                    postprocessor_args['sponskrub'] = []
+
-                    if opts.verbose:
+    if 'default-compat' in opts.postprocessor_args and 'default' not in opts.postprocessor_args:
-                        write_string('[debug] Adding postprocessor args from command line option sponskrub: \n')
+        report_args_compat('--post-processor-args', 'post-processors')
-                pp_key, pp_args = 'default', string
+        opts.postprocessor_args.setdefault('sponskrub', [])
-            else:
+        opts.postprocessor_args['default'] = opts.postprocessor_args['default-compat']
-                pp_key, pp_args = mobj.group('pp').lower(), mobj.group('args')
+
-            if opts.verbose:
+    final_ext = (
-                write_string('[debug] Adding postprocessor args from command line option %s: %s\n' % (pp_key, pp_args))
+        opts.recodevideo
-            postprocessor_args[pp_key] = compat_shlex_split(pp_args)
+        or (opts.remuxvideo in REMUX_EXTENSIONS) and opts.remuxvideo
+        or (opts.extractaudio and opts.audioformat != 'best') and opts.audioformat
+        or None)
 
     match_filter = (
         None if opts.match_filter is None
@@ -383,6 +427,7 @@ def _real_main(argv=None):
         'simulate': opts.simulate or any_getting,
         'skip_download': opts.skip_download,
         'format': opts.format,
+        'allow_unplayable_formats': opts.allow_unplayable_formats,
         'format_sort': opts.format_sort,
         'format_sort_force': opts.format_sort_force,
         'allow_multiple_video_streams': opts.allow_multiple_video_streams,
@@ -390,6 +435,8 @@ 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 +459,15 @@ 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,
+        'allow_playlist_files': opts.allow_playlist_files,
+        'getcomments': opts.getcomments,
         'writethumbnail': opts.writethumbnail,
         'write_all_thumbnails': opts.write_all_thumbnails,
         'writelink': opts.writelink,
@@ -469,6 +518,7 @@ def _real_main(argv=None):
         'extract_flat': opts.extract_flat,
         'mark_watched': opts.mark_watched,
         'merge_output_format': opts.merge_output_format,
+        'final_ext': final_ext,
         'postprocessors': postprocessors,
         'fixup': opts.fixup,
         'source_address': opts.source_address,
@@ -485,8 +535,8 @@ 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,
+        'external_downloader_args': opts.external_downloader_args,
-        'postprocessor_args': postprocessor_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,
@@ -499,16 +549,22 @@ def _real_main(argv=None):
     }
 
     with YoutubeDL(ydl_opts) as ydl:
-        # Update version
+        actual_use = len(all_urls) or opts.load_info_filename
-        if opts.update_self:
-            update_self(ydl.to_screen, opts.verbose, ydl._opener)
 
         # Remove cache dir
         if opts.rm_cachedir:
             ydl.cache.remove()
 
+        # Update version
+        if opts.update_self:
+            # If updater returns True, exit. Required for windows
+            if update_self(ydl.to_screen, opts.verbose, ydl._opener):
+                if actual_use:
+                    parser.error('The program must exit for the update to complete')
+                sys.exit()
+
         # Maybe do nothing
-        if (len(all_urls) < 1) and (opts.load_info_filename is None):
+        if not actual_use:
             if opts.update_self or opts.rm_cachedir:
                 sys.exit()
 

youtube_dlc/downloader/__init__.py

@@ -1,23 +1,33 @@
 from __future__ import unicode_literals
 
+from ..utils import (
+    determine_protocol,
+)
+
+
+def _get_real_downloader(info_dict, protocol=None, *args, **kwargs):
+    info_copy = info_dict.copy()
+    if protocol:
+        info_copy['protocol'] = protocol
+    return get_suitable_downloader(info_copy, *args, **kwargs)
+
+
+# Some of these require _get_real_downloader
 from .common import FileDownloader
+from .dash import DashSegmentsFD
 from .f4m import F4mFD
 from .hls import HlsFD
 from .http import HttpFD
 from .rtmp import RtmpFD
-from .dash import DashSegmentsFD
 from .rtsp import RtspFD
 from .ism import IsmFD
+from .niconico import NiconicoDmcFD
 from .youtube_live_chat import YoutubeLiveChatReplayFD
 from .external import (
     get_external_downloader,
     FFmpegFD,
 )
 
-from ..utils import (
-    determine_protocol,
-)
-
 PROTOCOL_MAP = {
     'rtmp': RtmpFD,
     'm3u8_native': HlsFD,
@@ -27,11 +37,12 @@ PROTOCOL_MAP = {
     'f4m': F4mFD,
     'http_dash_segments': DashSegmentsFD,
     'ism': IsmFD,
+    'niconico_dmc': NiconicoDmcFD,
     'youtube_live_chat_replay': YoutubeLiveChatReplayFD,
 }
 
 
-def get_suitable_downloader(info_dict, params={}):
+def get_suitable_downloader(info_dict, params={}, default=HttpFD):
     """Get the downloader class that can handle the info dict."""
     protocol = determine_protocol(info_dict)
     info_dict['protocol'] = protocol
@@ -45,16 +56,17 @@ def get_suitable_downloader(info_dict, params={}):
         if ed.can_download(info_dict):
             return ed
 
-    if protocol.startswith('m3u8') and info_dict.get('is_live'):
+    if protocol.startswith('m3u8'):
-        return FFmpegFD
+        if info_dict.get('is_live'):
+            return FFmpegFD
+        elif _get_real_downloader(info_dict, 'frag_urls', params, None):
+            return HlsFD
+        elif params.get('hls_prefer_native') is True:
+            return HlsFD
+        elif params.get('hls_prefer_native') is False:
+            return FFmpegFD
 
-    if protocol == 'm3u8' and params.get('hls_prefer_native') is True:
+    return PROTOCOL_MAP.get(protocol, default)
-        return HlsFD
-
-    if protocol == 'm3u8_native' and params.get('hls_prefer_native') is False:
-        return FFmpegFD
-
-    return PROTOCOL_MAP.get(protocol, HttpFD)
 
 
 __all__ = [

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/dash.py

@@ -1,6 +1,8 @@
 from __future__ import unicode_literals
 
+from ..downloader import _get_real_downloader
 from .fragment import FragmentFD
+
 from ..compat import compat_urllib_error
 from ..utils import (
     DownloadError,
@@ -20,31 +22,42 @@ class DashSegmentsFD(FragmentFD):
         fragments = info_dict['fragments'][:1] if self.params.get(
             'test', False) else info_dict['fragments']
 
+        real_downloader = _get_real_downloader(info_dict, 'frag_urls', self.params, None)
+
         ctx = {
             'filename': filename,
             'total_frags': len(fragments),
         }
 
-        self._prepare_and_start_frag_download(ctx)
+        if real_downloader:
+            self._prepare_external_frag_download(ctx)
+        else:
+            self._prepare_and_start_frag_download(ctx)
 
         fragment_retries = self.params.get('fragment_retries', 0)
         skip_unavailable_fragments = self.params.get('skip_unavailable_fragments', True)
 
+        fragment_urls = []
         frag_index = 0
         for i, fragment in enumerate(fragments):
             frag_index += 1
             if frag_index <= ctx['fragment_index']:
                 continue
+            fragment_url = fragment.get('url')
+            if not fragment_url:
+                assert fragment_base_url
+                fragment_url = urljoin(fragment_base_url, fragment['path'])
+
+            if real_downloader:
+                fragment_urls.append(fragment_url)
+                continue
+
             # In DASH, the first segment contains necessary headers to
             # generate a valid MP4 file, so always abort for the first segment
             fatal = i == 0 or not skip_unavailable_fragments
             count = 0
             while count <= fragment_retries:
                 try:
-                    fragment_url = fragment.get('url')
-                    if not fragment_url:
-                        assert fragment_base_url
-                        fragment_url = urljoin(fragment_base_url, fragment['path'])
                     success, frag_content = self._download_fragment(ctx, fragment_url, info_dict)
                     if not success:
                         return False
@@ -75,6 +88,16 @@ class DashSegmentsFD(FragmentFD):
                 self.report_error('giving up after %s fragment retries' % fragment_retries)
                 return False
 
-        self._finish_frag_download(ctx)
+        if real_downloader:
-
+            info_copy = info_dict.copy()
+            info_copy['url_list'] = fragment_urls
+            fd = real_downloader(self.ydl, self.params)
+            # TODO: Make progress updates work without hooking twice
+            # for ph in self._progress_hooks:
+            #     fd.add_progress_hook(ph)
+            success = fd.real_download(filename, info_copy)
+            if not success:
+                return False
+        else:
+            self._finish_frag_download(ctx)
         return True

youtube_dlc/downloader/external.py

@@ -6,6 +6,12 @@ import subprocess
 import sys
 import time
 
+try:
+    from Crypto.Cipher import AES
+    can_decrypt_frag = True
+except ImportError:
+    can_decrypt_frag = False
+
 from .common import FileDownloader
 from ..compat import (
     compat_setenv,
@@ -18,15 +24,20 @@ from ..utils import (
     cli_bool_option,
     cli_configuration_args,
     encodeFilename,
+    error_to_compat_str,
     encodeArgument,
     handle_youtubedl_headers,
     check_executable,
     is_outdated_version,
     process_communicate_or_kill,
+    sanitized_Request,
+    sanitize_open,
 )
 
 
 class ExternalFD(FileDownloader):
+    SUPPORTED_PROTOCOLS = ('http', 'https', 'ftp', 'ftps')
+
     def real_download(self, filename, info_dict):
         self.report_destination(filename)
         tmpfilename = self.temp_name(filename)
@@ -79,7 +90,7 @@ class ExternalFD(FileDownloader):
 
     @classmethod
     def supports(cls, info_dict):
-        return info_dict['protocol'] in ('http', 'https', 'ftp', 'ftps')
+        return info_dict['protocol'] in cls.SUPPORTED_PROTOCOLS
 
     @classmethod
     def can_download(cls, info_dict):
@@ -95,7 +106,8 @@ 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 """
@@ -108,8 +120,53 @@ class ExternalFD(FileDownloader):
         _, stderr = process_communicate_or_kill(p)
         if p.returncode != 0:
             self.to_stderr(stderr.decode('utf-8', 'replace'))
+
+        if 'url_list' in info_dict:
+            file_list = []
+            for [i, url] in enumerate(info_dict['url_list']):
+                tmpsegmentname = '%s_%s.frag' % (tmpfilename, i)
+                file_list.append(tmpsegmentname)
+            key_list = info_dict.get('key_list')
+            decrypt_info = None
+            dest, _ = sanitize_open(tmpfilename, 'wb')
+            for i, file in enumerate(file_list):
+                src, _ = sanitize_open(file, 'rb')
+                if key_list:
+                    decrypt_info = next((x for x in key_list if x['INDEX'] == i), decrypt_info)
+                    if decrypt_info['METHOD'] == 'AES-128':
+                        iv = decrypt_info.get('IV')
+                        decrypt_info['KEY'] = decrypt_info.get('KEY') or self.ydl.urlopen(
+                            self._prepare_url(info_dict, info_dict.get('_decryption_key_url') or decrypt_info['URI'])).read()
+                        encrypted_data = src.read()
+                        decrypted_data = AES.new(
+                            decrypt_info['KEY'], AES.MODE_CBC, iv).decrypt(encrypted_data)
+                        dest.write(decrypted_data)
+                    else:
+                        fragment_data = src.read()
+                        dest.write(fragment_data)
+                else:
+                    fragment_data = src.read()
+                    dest.write(fragment_data)
+                src.close()
+            dest.close()
+            if not self.params.get('keep_fragments', False):
+                for file_path in file_list:
+                    try:
+                        os.remove(file_path)
+                    except OSError as ose:
+                        self.report_error("Unable to delete file %s; %s" % (file_path, error_to_compat_str(ose)))
+                try:
+                    file_path = '%s.frag.urls' % tmpfilename
+                    os.remove(file_path)
+                except OSError as ose:
+                    self.report_error("Unable to delete file %s; %s" % (file_path, error_to_compat_str(ose)))
+
         return p.returncode
 
+    def _prepare_url(self, info_dict, url):
+        headers = info_dict.get('http_headers')
+        return sanitized_Request(url, None, headers) if headers else url
+
 
 class CurlFD(ExternalFD):
     AVAILABLE_OPT = '-V'
@@ -185,15 +242,17 @@ class WgetFD(ExternalFD):
 
 class Aria2cFD(ExternalFD):
     AVAILABLE_OPT = '-v'
+    SUPPORTED_PROTOCOLS = ('http', 'https', 'ftp', 'ftps', 'frag_urls')
 
     def _make_cmd(self, tmpfilename, info_dict):
         cmd = [self.exe, '-c']
-        cmd += self._configuration_args([
-            '--min-split-size', '1M', '--max-connection-per-server', '4'])
         dn = os.path.dirname(tmpfilename)
+        if 'url_list' not in info_dict:
+            cmd += ['--out', os.path.basename(tmpfilename)]
+        verbose_level_args = ['--console-log-level=warn', '--summary-interval=0']
+        cmd += self._configuration_args(['--file-allocation=none', '-x16', '-j16', '-s16'] + verbose_level_args)
         if dn:
             cmd += ['--dir', dn]
-        cmd += ['--out', os.path.basename(tmpfilename)]
         if info_dict.get('http_headers') is not None:
             for key, val in info_dict['http_headers'].items():
                 cmd += ['--header', '%s: %s' % (key, val)]
@@ -201,7 +260,22 @@ class Aria2cFD(ExternalFD):
         cmd += self._option('--all-proxy', 'proxy')
         cmd += self._bool_option('--check-certificate', 'nocheckcertificate', 'false', 'true', '=')
         cmd += self._bool_option('--remote-time', 'updatetime', 'true', 'false', '=')
-        cmd += ['--', info_dict['url']]
+        cmd += ['--auto-file-renaming=false']
+        if 'url_list' in info_dict:
+            cmd += verbose_level_args
+            cmd += ['--uri-selector', 'inorder', '--download-result=hide']
+            url_list_file = '%s.frag.urls' % tmpfilename
+            url_list = []
+            for [i, url] in enumerate(info_dict['url_list']):
+                tmpsegmentname = '%s_%s.frag' % (os.path.basename(tmpfilename), i)
+                url_list.append('%s\n\tout=%s' % (url, tmpsegmentname))
+            stream, _ = sanitize_open(url_list_file, 'wb')
+            stream.write('\n'.join(url_list).encode('utf-8'))
+            stream.close()
+
+            cmd += ['-i', url_list_file]
+        else:
+            cmd += ['--', info_dict['url']]
         return cmd
 
 
@@ -220,9 +294,7 @@ class HttpieFD(ExternalFD):
 
 
 class FFmpegFD(ExternalFD):
-    @classmethod
+    SUPPORTED_PROTOCOLS = ('http', 'https', 'ftp', 'ftps', 'm3u8', 'rtsp', 'rtmp', 'mms')
-    def supports(cls, info_dict):
-        return info_dict['protocol'] in ('http', 'https', 'ftp', 'ftps', 'm3u8', 'rtsp', 'rtmp', 'mms')
 
     @classmethod
     def available(cls):
@@ -232,7 +304,7 @@ 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/f4m.py

@@ -267,13 +267,14 @@ class F4mFD(FragmentFD):
         media = doc.findall(_add_ns('media'))
         if not media:
             self.report_error('No media found')
-        for e in (doc.findall(_add_ns('drmAdditionalHeader'))
+        if not self.params.get('allow_unplayable_formats'):
-                  + doc.findall(_add_ns('drmAdditionalHeaderSet'))):
+            for e in (doc.findall(_add_ns('drmAdditionalHeader'))
-            # If id attribute is missing it's valid for all media nodes
+                      + doc.findall(_add_ns('drmAdditionalHeaderSet'))):
-            # without drmAdditionalHeaderId or drmAdditionalHeaderSetId attribute
+                # If id attribute is missing it's valid for all media nodes
-            if 'id' not in e.attrib:
+                # without drmAdditionalHeaderId or drmAdditionalHeaderSetId attribute
-                self.report_error('Missing ID in f4m DRM')
+                if 'id' not in e.attrib:
-        media = remove_encrypted_media(media)
+                    self.report_error('Missing ID in f4m DRM')
+            media = remove_encrypted_media(media)
         if not media:
             self.report_error('Unsupported DRM')
         return media

youtube_dlc/downloader/fragment.py

@@ -95,11 +95,12 @@ class FragmentFD(FileDownloader):
         frag_index_stream.write(json.dumps({'downloader': downloader}))
         frag_index_stream.close()
 
-    def _download_fragment(self, ctx, frag_url, info_dict, headers=None):
+    def _download_fragment(self, ctx, frag_url, info_dict, headers=None, request_data=None):
         fragment_filename = '%s-Frag%d' % (ctx['tmpfilename'], ctx['fragment_index'])
         fragment_info_dict = {
             'url': frag_url,
             'http_headers': headers or info_dict.get('http_headers'),
+            'request_data': request_data,
         }
         success = ctx['dl'].download(fragment_filename, fragment_info_dict)
         if not success:
@@ -277,3 +278,24 @@ class FragmentFD(FileDownloader):
             'status': 'finished',
             'elapsed': elapsed,
         })
+
+    def _prepare_external_frag_download(self, ctx):
+        if 'live' not in ctx:
+            ctx['live'] = False
+        if not ctx['live']:
+            total_frags_str = '%d' % ctx['total_frags']
+            ad_frags = ctx.get('ad_frags', 0)
+            if ad_frags:
+                total_frags_str += ' (not including %d ad)' % ad_frags
+        else:
+            total_frags_str = 'unknown (live)'
+        self.to_screen(
+            '[%s] Total fragments: %s' % (self.FD_NAME, total_frags_str))
+
+        tmpfilename = self.temp_name(ctx['filename'])
+
+        # Should be initialized before ytdl file check
+        ctx.update({
+            'tmpfilename': tmpfilename,
+            'fragment_index': 0,
+        })

youtube_dlc/downloader/hls.py

@@ -8,6 +8,7 @@ try:
 except ImportError:
     can_decrypt_frag = False
 
+from ..downloader import _get_real_downloader
 from .fragment import FragmentFD
 from .external import FFmpegFD
 
@@ -28,9 +29,8 @@ class HlsFD(FragmentFD):
     FD_NAME = 'hlsnative'
 
     @staticmethod
-    def can_download(manifest, info_dict):
+    def can_download(manifest, info_dict, allow_unplayable_formats=False):
-        UNSUPPORTED_FEATURES = (
+        UNSUPPORTED_FEATURES = [
-            r'#EXT-X-KEY:METHOD=(?!NONE|AES-128)',  # encrypted streams [1]
             # r'#EXT-X-BYTERANGE',  # playlists composed of byte ranges of media files [2]
 
             # Live streams heuristic does not always work (e.g. geo restricted to Germany
@@ -49,7 +49,11 @@ class HlsFD(FragmentFD):
             # 3. https://tools.ietf.org/html/draft-pantos-http-live-streaming-17#section-4.3.3.2
             # 4. https://tools.ietf.org/html/draft-pantos-http-live-streaming-17#section-4.3.3.5
             # 5. https://tools.ietf.org/html/draft-pantos-http-live-streaming-17#section-4.3.2.5
-        )
+        ]
+        if not allow_unplayable_formats:
+            UNSUPPORTED_FEATURES += [
+                r'#EXT-X-KEY:METHOD=(?!NONE|AES-128)',  # encrypted streams [1]
+            ]
         check_results = [not re.search(feature, manifest) for feature in UNSUPPORTED_FEATURES]
         is_aes128_enc = '#EXT-X-KEY:METHOD=AES-128' in manifest
         check_results.append(can_decrypt_frag or not is_aes128_enc)
@@ -65,7 +69,7 @@ class HlsFD(FragmentFD):
         man_url = urlh.geturl()
         s = urlh.read().decode('utf-8', 'ignore')
 
-        if not self.can_download(s, info_dict):
+        if not self.can_download(s, info_dict, self.params.get('allow_unplayable_formats')):
             if info_dict.get('extra_param_to_segment_url') or info_dict.get('_decryption_key_url'):
                 self.report_error('pycrypto not found. Please install it.')
                 return False
@@ -73,10 +77,13 @@ class HlsFD(FragmentFD):
                 'hlsnative has detected features it does not support, '
                 'extraction will be delegated to ffmpeg')
             fd = FFmpegFD(self.ydl, self.params)
-            for ph in self._progress_hooks:
+            # TODO: Make progress updates work without hooking twice
-                fd.add_progress_hook(ph)
+            # for ph in self._progress_hooks:
+            #     fd.add_progress_hook(ph)
             return fd.real_download(filename, info_dict)
 
+        real_downloader = _get_real_downloader(info_dict, 'frag_urls', self.params, None)
+
         def is_ad_fragment_start(s):
             return (s.startswith('#ANVATO-SEGMENT-INFO') and 'type=ad' in s
                     or s.startswith('#UPLYNK-SEGMENT') and s.endswith(',ad'))
@@ -85,6 +92,8 @@ class HlsFD(FragmentFD):
             return (s.startswith('#ANVATO-SEGMENT-INFO') and 'type=master' in s
                     or s.startswith('#UPLYNK-SEGMENT') and s.endswith(',segment'))
 
+        fragment_urls = []
+
         media_frags = 0
         ad_frags = 0
         ad_frag_next = False
@@ -109,7 +118,10 @@ class HlsFD(FragmentFD):
             'ad_frags': ad_frags,
         }
 
-        self._prepare_and_start_frag_download(ctx)
+        if real_downloader:
+            self._prepare_external_frag_download(ctx)
+        else:
+            self._prepare_and_start_frag_download(ctx)
 
         fragment_retries = self.params.get('fragment_retries', 0)
         skip_unavailable_fragments = self.params.get('skip_unavailable_fragments', True)
@@ -122,6 +134,7 @@ class HlsFD(FragmentFD):
         i = 0
         media_sequence = 0
         decrypt_info = {'METHOD': 'NONE'}
+        key_list = []
         byte_range = {}
         frag_index = 0
         ad_frag_next = False
@@ -140,6 +153,11 @@ class HlsFD(FragmentFD):
                         else compat_urlparse.urljoin(man_url, line))
                     if extra_query:
                         frag_url = update_url_query(frag_url, extra_query)
+
+                    if real_downloader:
+                        fragment_urls.append(frag_url)
+                        continue
+
                     count = 0
                     headers = info_dict.get('http_headers', {})
                     if byte_range:
@@ -168,6 +186,7 @@ class HlsFD(FragmentFD):
                         self.report_error(
                             'giving up after %s fragment retries' % fragment_retries)
                         return False
+
                     if decrypt_info['METHOD'] == 'AES-128':
                         iv = decrypt_info.get('IV') or compat_struct_pack('>8xq', media_sequence)
                         decrypt_info['KEY'] = decrypt_info.get('KEY') or self.ydl.urlopen(
@@ -197,6 +216,10 @@ class HlsFD(FragmentFD):
                             decrypt_info['URI'] = update_url_query(decrypt_info['URI'], extra_query)
                         if decrypt_url != decrypt_info['URI']:
                             decrypt_info['KEY'] = None
+                    key_data = decrypt_info.copy()
+                    key_data['INDEX'] = frag_index
+                    key_list.append(key_data)
+
                 elif line.startswith('#EXT-X-MEDIA-SEQUENCE'):
                     media_sequence = int(line[22:])
                 elif line.startswith('#EXT-X-BYTERANGE'):
@@ -211,6 +234,17 @@ class HlsFD(FragmentFD):
                 elif is_ad_fragment_end(line):
                     ad_frag_next = False
 
-        self._finish_frag_download(ctx)
+        if real_downloader:
-
+            info_copy = info_dict.copy()
+            info_copy['url_list'] = fragment_urls
+            info_copy['key_list'] = key_list
+            fd = real_downloader(self.ydl, self.params)
+            # TODO: Make progress updates work without hooking twice
+            # for ph in self._progress_hooks:
+            #     fd.add_progress_hook(ph)
+            success = fd.real_download(filename, info_copy)
+            if not success:
+                return False
+        else:
+            self._finish_frag_download(ctx)
         return True

youtube_dlc/downloader/http.py

@@ -27,6 +27,7 @@ from ..utils import (
 class HttpFD(FileDownloader):
     def real_download(self, filename, info_dict):
         url = info_dict['url']
+        request_data = info_dict.get('request_data', None)
 
         class DownloadContext(dict):
             __getattr__ = dict.get
@@ -101,7 +102,7 @@ class HttpFD(FileDownloader):
                 range_end = ctx.data_len - 1
             has_range = range_start is not None
             ctx.has_range = has_range
-            request = sanitized_Request(url, None, headers)
+            request = sanitized_Request(url, request_data, headers)
             if has_range:
                 set_range(request, range_start, range_end)
             # Establish connection
@@ -152,7 +153,7 @@ class HttpFD(FileDownloader):
                     try:
                         # Open the connection again without the range header
                         ctx.data = self.ydl.urlopen(
-                            sanitized_Request(url, None, headers))
+                            sanitized_Request(url, request_data, headers))
                         content_length = ctx.data.info()['Content-Length']
                     except (compat_urllib_error.HTTPError, ) as err:
                         if err.code < 500 or err.code >= 600:

youtube_dlc/downloader/niconico.py

@@ -0,0 +1,54 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import threading
+
+from .common import FileDownloader
+from ..downloader import _get_real_downloader
+from ..extractor.niconico import NiconicoIE
+from ..compat import compat_urllib_request
+
+
+class NiconicoDmcFD(FileDownloader):
+    """ Downloading niconico douga from DMC with heartbeat """
+
+    FD_NAME = 'niconico_dmc'
+
+    def real_download(self, filename, info_dict):
+        self.to_screen('[%s] Downloading from DMC' % self.FD_NAME)
+
+        ie = NiconicoIE(self.ydl)
+        info_dict, heartbeat_info_dict = ie._get_heartbeat_info(info_dict)
+
+        fd = _get_real_downloader(info_dict, params=self.params)(self.ydl, self.params)
+
+        success = download_complete = False
+        timer = [None]
+
+        heartbeat_lock = threading.Lock()
+        heartbeat_url = heartbeat_info_dict['url']
+        heartbeat_data = heartbeat_info_dict['data']
+        heartbeat_interval = heartbeat_info_dict.get('interval', 30)
+        self.to_screen('[%s] Heartbeat with %s second interval...' % (self.FD_NAME, heartbeat_interval))
+
+        def heartbeat():
+            try:
+                compat_urllib_request.urlopen(url=heartbeat_url, data=heartbeat_data.encode())
+            except Exception:
+                self.to_screen('[%s] Heartbeat failed' % self.FD_NAME)
+
+            with heartbeat_lock:
+                if not download_complete:
+                    timer[0] = threading.Timer(heartbeat_interval, heartbeat)
+                    timer[0].start()
+
+        try:
+            heartbeat()
+            success = fd.real_download(filename, info_dict)
+        finally:
+            if heartbeat_lock:
+                with heartbeat_lock:
+                    timer[0].cancel()
+                    download_complete = True
+
+            return success

youtube_dlc/downloader/youtube_live_chat.py

@@ -1,9 +1,14 @@
 from __future__ import division, unicode_literals
 
-import re
 import json
 
 from .fragment import FragmentFD
+from ..compat import compat_urllib_error
+from ..utils import (
+    try_get,
+    RegexNotFoundError,
+)
+from ..extractor.youtube import YoutubeBaseInfoExtractor as YT_BaseIE
 
 
 class YoutubeLiveChatReplayFD(FragmentFD):
@@ -15,6 +20,7 @@ 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 = {
@@ -23,19 +29,53 @@ class YoutubeLiveChatReplayFD(FragmentFD):
             'total_frags': None,
         }
 
-        def dl_fragment(url):
+        ie = YT_BaseIE(self.ydl)
-            headers = info_dict.get('http_headers', {})
-            return self._download_fragment(ctx, url, info_dict, headers)
 
-        def parse_yt_initial_data(data):
+        def dl_fragment(url, data=None, headers=None):
-            window_patt = b'window\\["ytInitialData"\\]\\s*=\\s*(.*?)(?<=});'
+            http_headers = info_dict.get('http_headers', {})
-            var_patt = b'var\\s+ytInitialData\\s*=\\s*(.*?)(?<=});'
+            if headers:
-            for patt in window_patt, var_patt:
+                http_headers = http_headers.copy()
+                http_headers.update(headers)
+            return self._download_fragment(ctx, url, info_dict, http_headers, data)
+
+        def download_and_parse_fragment(url, frag_index, request_data):
+            count = 0
+            while count <= fragment_retries:
                 try:
-                    raw_json = re.search(patt, data).group(1)
+                    success, raw_fragment = dl_fragment(url, request_data, {'content-type': 'application/json'})
-                    return json.loads(raw_json)
+                    if not success:
-                except AttributeError:
+                        return False, None, None
-                    continue
+                    try:
+                        data = ie._extract_yt_initial_data(video_id, raw_fragment.decode('utf-8', 'replace'))
+                    except RegexNotFoundError:
+                        data = None
+                    if not data:
+                        data = json.loads(raw_fragment)
+                    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)
 
@@ -43,55 +83,41 @@ class YoutubeLiveChatReplayFD(FragmentFD):
             'https://www.youtube.com/watch?v={}'.format(video_id))
         if not success:
             return False
-        data = parse_yt_initial_data(raw_fragment)
+        try:
-        continuation_id = data['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation']
+            data = ie._extract_yt_initial_data(video_id, raw_fragment.decode('utf-8', 'replace'))
+        except RegexNotFoundError:
+            return False
+        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
+        ytcfg = ie._extract_ytcfg(video_id, raw_fragment.decode('utf-8', 'replace'))
-        offset = None
+
+        if not ytcfg:
+            return False
+        api_key = try_get(ytcfg, lambda x: x['INNERTUBE_API_KEY'])
+        innertube_context = try_get(ytcfg, lambda x: x['INNERTUBE_CONTEXT'])
+        if not api_key or not innertube_context:
+            return False
+        url = 'https://www.youtube.com/youtubei/v1/live_chat/get_live_chat_replay?key=' + api_key
+
+        frag_index = offset = 0
         while continuation_id is not None:
-            data = None
+            frag_index += 1
-            if first:
+            request_data = {
-                url = 'https://www.youtube.com/live_chat_replay?continuation={}'.format(continuation_id)
+                'context': innertube_context,
-                success, raw_fragment = dl_fragment(url)
+                'continuation': continuation_id,
-                if not success:
+            }
-                    return False
+            if frag_index > 1:
-                data = parse_yt_initial_data(raw_fragment)
+                request_data['currentPlayerState'] = {'playerOffsetMs': str(max(offset - 5000, 0))}
-            else:
+            success, continuation_id, offset = download_and_parse_fragment(
-                url = ('https://www.youtube.com/live_chat_replay/get_live_chat_replay'
+                url, frag_index, json.dumps(request_data, ensure_ascii=False).encode('utf-8') + b'\n')
-                       + '?continuation={}'.format(continuation_id)
+            if not success:
-                       + '&playerOffsetMs={}'.format(max(offset - 5000, 0))
+                return False
-                       + '&hidden=false'
+            if test:
-                       + '&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:
                 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 ..utils import (
-from ..compat import compat_urlparse
+    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/(?P<display_id>[0-9a-z-]+)-|
-                                video/embed\?.*?\bid=
+                                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',
+            'id': '51286501',
-            'ext': 'flv',
+            'title': "Peter Billingsley: From child actor in 'A Christmas Story' to Hollywood power player",
-            'display_id': 'dramatic-video-rare-death-job-america',
+            'description': 'Billingsley went from a child actor to Hollywood power player.',
-            'title': 'Occupational Hazards',
-            'description': 'Nightline investigates the dangers that lurk at various jobs.',
-            'thumbnail': r're:^https?://.*\.jpg$',
-            'upload_date': '20100428',
-            'timestamp': 1272412800,
         },
-        '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',
+            'upload_date': '20160505',
-            'timestamp': 1463329500,
+            '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)
+        story_id = self._match_id(url)
-        display_id = mobj.group('display_id')
+        webpage = self._download_webpage(url, story_id)
-        video_id = mobj.group('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)
+        def entries():
-        video_url = self._search_regex(
+            featured_video = story.get('featuredVideo') or {}
-            r'window\.abcnvideo\.url\s*=\s*"([^"]+)"', webpage, 'video URL')
+            feed = try_get(featured_video, lambda x: x['video']['feed'])
-        full_video_url = compat_urlparse.urljoin(url, video_url)
+            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
+        return self.playlist_result(
-        date_str = self._html_search_regex(
+            entries(), story_id, article_contents.get('headline'),
-            r'<span[^>]+class="timestamp">([^<]+)</span>',
+            article_contents.get('subHead'))
-            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

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(
+            self.raise_login_required()
-                'This video is only available for paying users', expected=True)
-            # self.raise_login_required() # FIXME: Login is not implemented
 
         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)
+        post_type, name = re.match(self._VALID_URL, url).groups()
-        webpage = self._download_webpage(url, program_name)
+        post_type = {
-        brightcove_id = self._search_regex(
+            'features': 'post',
-            r'RenderPagesVideo\(\'(.+?)\'', webpage, 'brightcove id')
+            'program': 'episode',
-        return self.url_result(self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id, 'BrightcoveNew', brightcove_id)
+            '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,
+            'timestamp': 1523318400,
-            'upload_date': '20180414',
+            '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' % (
+        if self._TOKEN_GENERATORS.get(access_key) is not None:
-            access_key, anvrid, server_time,
+            api['anvstk2'] = self._TOKEN_GENERATORS[access_key].generate(self, access_key, video_id)
-            self._ANVACK_TABLE.get(access_key, self._API_KEY)))
+        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
+        # available till 7.01.2022
-        'url': 'http://www.daserste.de/information/talk/maischberger/videos/das-groko-drama-zerlegen-sich-die-volksparteien-video-102.html',
+        'url': 'https://www.daserste.de/information/talk/maischberger/videos/maischberger-die-woche-video100.html',
-        'md5': '8e4ec85f31be7c7fc08a26cdbc5a1f49',
+        'md5': '867d8aa39eeaf6d76407c5ad1bb0d4c1',
         'info_dict': {
-            'display_id': 'das-groko-drama-zerlegen-sich-die-volksparteien-video',
+            'display_id': 'maischberger-die-woche',
-            'id': '102',
+            'id': '100',
             'ext': 'mp4',
-            'duration': 4435.0,
+            'duration': 3687.0,
-            'title': 'Das GroKo-Drama: Zerlegen sich die Volksparteien?',
+            'title': 'maischberger. die woche vom 7. Januar 2021',
-            'upload_date': '20180214',
+            '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',
+        'url': 'https://www.ardmediathek.de/mdr/video/die-robuste-roswita/Y3JpZDovL21kci5kZS9iZWl0cmFnL2Ntcy84MWMxN2MzZC0wMjkxLTRmMzUtODk4ZS0wYzhlOWQxODE2NGI/',
-        'md5': 'dfdc87d2e7e09d073d5a80770a9ce88f',
+        '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',
+            'thumbnail': 'https://img.ardmediathek.de/standard/00/78/56/67/84/575672121/16x9/960?mandant=ard',
-            'timestamp': 1577047500,
+            'timestamp': 1596658200,
-            'upload_date': '20191222',
+            '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+)|
+                            )(?P<id>\d+)|
-                            video/[bB][vV](?P<id>[^/?#&]+)
+                            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',
+            (r'<h1[^>]+\btitle=(["\'])(?P<title>(?:(?!\1).)+)\1',
-             '(?s)<h1[^>]*>(?P<title>.+?)</h1>'), webpage, 'title',
+             r'(?s)<h1[^>]*>(?P<title>.+?)</h1>'), webpage, 'title',
-            group='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/brightcove.py

@@ -478,11 +478,12 @@ class BrightcoveNewIE(AdobePassIE):
             container = source.get('container')
             ext = mimetype2ext(source.get('type'))
             src = source.get('src')
+            skip_unplayable = not self._downloader.params.get('allow_unplayable_formats')
             # https://support.brightcove.com/playback-api-video-fields-reference#key_systems_object
-            if container == 'WVM' or source.get('key_systems'):
+            if skip_unplayable and (container == 'WVM' or source.get('key_systems')):
                 num_drm_sources += 1
                 continue
-            elif ext == 'ism':
+            elif ext == 'ism' and skip_unplayable:
                 continue
             elif ext == 'm3u8' or container == 'M2TS':
                 if not src:
@@ -546,7 +547,8 @@ class BrightcoveNewIE(AdobePassIE):
                 error = errors[0]
                 raise ExtractorError(
                     error.get('message') or error.get('error_subcode') or error['error_code'], expected=True)
-            if sources and num_drm_sources == len(sources):
+            if (not self._downloader.params.get('allow_unplayable_formats')
+                    and sources and num_drm_sources == len(sources)):
                 raise ExtractorError('This video is DRM protected.', expected=True)
 
         self._sort_formats(formats)

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,
+            'timestamp': 1478608140,
-            'upload_date': '20160811',
+            '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',
+            'upload_date': '20170512',
-            'timestamp': 1512507300,
+            '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', {})
+        subtitols = media.get('subtitols') or []
-        if subtitols:
+        if isinstance(subtitols, dict):
-            sub_url = subtitols.get('url')
+            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

@@ -95,8 +95,11 @@ class CDAIE(InfoExtractor):
         if 'Ten film jest dostępny dla użytkowników premium' in webpage:
             raise ExtractorError('This video is only available for premium users.', expected=True)
 
+        if re.search(r'niedostępn[ey] w(?:&nbsp;|\s+)Twoim kraju\s*<', webpage):
+            self.raise_geo_restricted()
+
         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/ceskatelevize.py

@@ -147,7 +147,8 @@ class CeskaTelevizeIE(InfoExtractor):
                 is_live = item.get('type') == 'LIVE'
                 formats = []
                 for format_id, stream_url in item.get('streamUrls', {}).items():
-                    if 'drmOnly=true' in stream_url:
+                    if (not self._downloader.params.get('allow_unplayable_formats')
+                            and 'drmOnly=true' in stream_url):
                         continue
                     if 'playerType=flash' in stream_url:
                         stream_formats = self._extract_m3u8_formats(

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/
+    _VALID_URL = r'https?://(?:www\.)?cc\.com/(?:episodes|video(?:-clips)?)/(?P<id>[0-9a-z]{6})'
-        (video-clips|episodes|cc-studios|video-collections|shows(?=/[^/]+/(?!full-episodes)))
-        /(?P<title>.*)'''
     _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',
+        'url': 'http://www.cc.com/video-clips/5ke9v2/the-daily-show-with-trevor-noah-doc-rivers-and-steve-ballmer---the-nba-player-strike',
-        'md5': 'c4f48e9eda1b16dd10add0744344b6d8',
+        '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',
+            'title': 'The Daily Show with Trevor Noah|August 28, 2020|25|25149|Doc Rivers and Steve Ballmer - The NBA Player Strike',
-            'description': 'After a certain point, breastfeeding becomes c**kblocking.',
+            'description': 'md5:5334307c433892b85f4f5e5ac9ef7498',
-            'timestamp': 1376798400,
+            'timestamp': 1598670000,
-            'upload_date': '20130818',
+            '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',
+        'url': 'https://www.cc.com/video/k3sdvm/the-daily-show-with-jon-stewart-exclusive-the-fourth-estate',
-        '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',
         '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',
+            'id': '15907dc3-ec3c-11e8-a442-0e40cf2fc285',
-            'ext': 'flv',
+            'ext': 'mp4',
-            'title': 'Episode_the-mindy-project_shows_season-4_episode-3_full-episode_part1',
+            '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):
+    def _get_feed_query(self, uri):
-        video_id = self._match_id(url)
+        return {
-
+            'accountOverride': 'intl.mtvi.com',
-        webpage = self._download_webpage(url, video_id)
+            'arcEp': 'web.cc.tv',
-
+            'ep': 'b9032c3a',
-        mrss_url = self._search_regex(
+            'imageEp': 'web.cc.tv',
-            r'data-mrss=(["\'])(?P<url>(?:(?!\1).)+)\1',
+            'mgid': uri,
-            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',
         }
-        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",
+    Additionally, playlists can have "id", "title", and any other relevent
-    "uploader_id", "uploader_url", "duration" attributes with the same semantics
+    attributes with the same semantics as videos (see above).
-    as videos (see above).
 
 
     _type "multi_video" indicates that there are multiple videos that
@@ -967,15 +966,16 @@ 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:
             video_info['title'] = playlist_title
-        if playlist_description:
+        if playlist_description is not None:
             video_info['description'] = playlist_description
         return video_info
 
@@ -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',
+        default = ('hidden', 'hasvid', 'ie_pref', 'lang', 'quality',
-                   'res', 'fps', 'codec', 'size', 'br', 'asr',
+                   'res', 'fps', 'codec:vp9', 'size', 'br', 'asr',
-                   'proto', 'ext', 'has_audio', 'source', 'format_id')
+                   '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,
+            'proto': {'type': 'ordered', 'regex': True, 'field': 'protocol',
-                         'order': ['(ht|f)tps', '(ht|f)tp$', 'm3u8.+', 'm3u8', '.*dash', '', 'mms|rtsp', 'none', 'f4']},
+                      'order': ['(ht|f)tps', '(ht|f)tp$', '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'},
+            'ie_pref': {'priority': True, 'type': 'extractor', 'field': 'extractor_preference'},
-            'has_video': {'priority': True, 'field': 'vcodec', 'type': 'boolean', 'not_in_list': ('none',)},
+            'hasvid': {'priority': True, 'field': 'vcodec', 'type': 'boolean', 'not_in_list': ('none',)},
-            'has_audio': {'field': 'acodec', 'type': 'boolean', 'not_in_list': ('none',)},
+            'hasaud': {'field': 'acodec', 'type': 'boolean', 'not_in_list': ('none',)},
-            'language_preference': {'priority': True, 'convert': 'ignore'},
+            'lang': {'priority': True, 'convert': 'ignore', 'field': 'language_preference'},
             'quality': {'priority': True, 'convert': 'float_none'},
             'filesize': {'convert': 'bytes'},
-            'filesize_approx': {'convert': 'bytes'},
+            'fs_approx': {'convert': 'bytes', 'field': 'filesize_approx'},
-            'format_id': {'convert': 'string'},
+            '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},
+            'br': {'type': 'combined', 'field': ('tbr', 'vbr', 'abr'), 'same_limit': True},
-            'filesize_estimate': {'type': 'combined', 'same_limit': True, 'field': ('filesize', 'filesize_approx')},
+            'size': {'type': 'combined', 'same_limit': True, 'field': ('filesize', 'fs_approx')},
-            'extension': {'type': 'combined', 'field': ('vext', 'aext')},
+            'ext': {'type': 'combined', 'field': ('vext', 'aext')},
-            'dimension': {'type': 'multiple', 'field': ('height', 'width'), 'function': min},  # not named as 'resolution' because such a field exists
+            'res': {'type': 'multiple', 'field': ('height', 'width'), 'function': min},
-            'res': {'type': 'alias', 'field': 'dimension'},
+
-            'ext': {'type': 'alias', 'field': 'extension'},
+            # Most of these exist only for compatibility reasons
-            'br': {'type': 'alias', 'field': 'bitrate'},
+            '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
+            'language_preference': {'type': 'alias', 'field': 'lang'},  # not named as 'language' because such a field exists
-            'proto': {'type': 'alias', 'field': 'protocol'},
+            'protocol': {'type': 'alias', 'field': 'proto'},
-            'source': {'type': 'alias', 'field': 'source_preference'},
+            'source_preference': {'type': 'alias', 'field': 'source'},
-            'size': {'type': 'alias', 'field': 'filesize_estimate'},
+            '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'},
+            'video': {'type': 'alias', 'field': 'hasvid'},
-            'audio': {'type': 'alias', 'field': 'has_audio'},
+            'has_video': {'type': 'alias', 'field': 'hasvid'},
-            'extractor': {'type': 'alias', 'field': 'extractor_preference'},
+            'audio': {'type': 'alias', 'field': 'hasaud'},
-            'preference': {'type': 'alias', 'field': 'extractor_preference'}}
+            '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,
+            mpd_doc, mpd_id, mpd_base_url, mpd_url)
-            formats_dict=formats_dict, mpd_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:
@@ -2349,6 +2358,8 @@ class InfoExtractor(object):
                         extract_Initialization(segment_template)
             return ms_info
 
+        skip_unplayable = not self._downloader.params.get('allow_unplayable_formats')
+
         mpd_duration = parse_duration(mpd_doc.get('mediaPresentationDuration'))
         formats = []
         for period in mpd_doc.findall(_add_ns('Period')):
@@ -2358,11 +2369,11 @@ class InfoExtractor(object):
                 'timescale': 1,
             })
             for adaptation_set in period.findall(_add_ns('AdaptationSet')):
-                if is_drm_protected(adaptation_set):
+                if skip_unplayable and is_drm_protected(adaptation_set):
                     continue
                 adaption_set_ms_info = extract_multisegment_info(adaptation_set, period_ms_info)
                 for representation in adaptation_set.findall(_add_ns('Representation')):
-                    if is_drm_protected(representation):
+                    if skip_unplayable and is_drm_protected(representation):
                         continue
                     representation_attrib = adaptation_set.attrib.copy()
                     representation_attrib.update(representation.attrib)
@@ -2550,15 +2561,7 @@ class InfoExtractor(object):
                         else:
                             # Assuming direct URL to unfragmented media.
                             f['url'] = base_url
-
+                        formats.append(f)
-                        # 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)
                     else:
                         self.report_warning('Unknown MIME type %s in DASH manifest' % mime_type)
         return formats
@@ -2584,7 +2587,10 @@ class InfoExtractor(object):
          1. [MS-SSTR]: Smooth Streaming Protocol,
             https://msdn.microsoft.com/en-us/library/ff469518.aspx
         """
-        if ism_doc.get('IsLive') == 'TRUE' or ism_doc.find('Protection') is not None:
+        if ism_doc.get('IsLive') == 'TRUE':
+            return []
+        if (not self._downloader.params.get('allow_unplayable_formats')
+                and ism_doc.find('Protection') is not None):
             return []
 
         duration = int(ism_doc.attrib['Duration'])

youtube_dlc/extractor/crackle.py

@@ -103,7 +103,7 @@ class CrackleIE(InfoExtractor):
 
             formats = []
             for e in media['MediaURLs']:
-                if e.get('UseDRM') is True:
+                if not self._downloader.params.get('allow_unplayable_formats') and e.get('UseDRM') is True:
                     continue
                 format_url = url_or_none(e.get('Path'))
                 if not format_url:

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)
-
+        series_path = 'series/' + playlist_id
-        lessons = self._download_json(
+        lessons = self._call_api(
-            'https://egghead.io/api/v1/series/%s/lessons' % playlist_id,
+            series_path + '/lessons', playlist_id, 'course lessons')
-            playlist_id, 'Downloading course lessons JSON')
 
         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(
+        course = self._call_api(
-            'https://egghead.io/api/v1/series/%s' % playlist_id,
+            series_path, playlist_id, 'course', False) or {}
-            playlist_id, 'Downloading course JSON', fatal=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(
+        lesson = self._call_api(
-            'https://egghead.io/api/v1/lessons/%s' % display_id, display_id)
+            '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 (
@@ -495,8 +502,8 @@ from .hungama import (
 from .hypem import HypemIE
 from .ign import (
     IGNIE,
-    OneUPIE,
+    IGNVideoIE,
-    PCMagIE,
+    IGNArticleIE,
 )
 from .iheart import (
     IHeartRadioIE,
@@ -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']
+        video_url = video_data.get('data-url') or video_data['data-asset-source']
-        title = video_data.get('data-asset-title') or self._og_search_title(webpage)
+        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

@@ -130,7 +130,9 @@ from .kinja import KinjaEmbedIE
 from .gedi import GediEmbedsIE
 from .rcs import RCSEmbedsIE
 from .bitchute import BitChuteIE
+from .rumble import RumbleEmbedIE
 from .arcpublishing import ArcPublishingIE
+from .medialaan import MedialaanIE
 
 
 class GenericIE(InfoExtractor):
@@ -2224,6 +2226,20 @@ 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 +2479,9 @@ 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 +2613,11 @@ 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[^"]+)"',
@@ -3315,6 +3339,13 @@ class GenericIE(InfoExtractor):
             return self.playlist_from_matches(
                 bitchute_urls, video_id, video_title, ie=BitChuteIE.ie_key())
 
+        rumble_urls = RumbleEmbedIE._extract_urls(webpage)
+        if len(rumble_urls) == 1:
+            return self.url_result(rumble_urls[0], RumbleEmbedIE.ie_key())
+        if rumble_urls:
+            return self.playlist_from_matches(
+                rumble_urls, video_id, video_title, ie=RumbleEmbedIE.ie_key())
+
         # Look for HTML5 media
         entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
         if entries:

youtube_dlc/extractor/globo.py

@@ -96,7 +96,7 @@ class GloboIE(InfoExtractor):
         video = self._download_json(
             'http://api.globovideos.com/videos/%s/playlist' % video_id,
             video_id)['videos'][0]
-        if video.get('encrypted') is True:
+        if not self._downloader.params.get('allow_unplayable_formats') and video.get('encrypted') is True:
             raise ExtractorError('This video is DRM protected.', expected=True)
 
         title = video['title']

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/hotstar.py

@@ -141,7 +141,7 @@ class HotStarIE(HotStarBaseIE):
 
         title = video_data['title']
 
-        if video_data.get('drmProtected'):
+        if not self._downloader.params.get('allow_unplayable_formats') and video_data.get('drmProtected'):
             raise ExtractorError('This video is DRM protected.', expected=True)
 
         headers = {'Referer': url}

youtube_dlc/extractor/ign.py

@@ -3,230 +3,255 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..compat import (
+    compat_parse_qs,
+    compat_urllib_parse_urlparse,
+)
 from ..utils import (
+    HEADRequest,
+    determine_ext,
     int_or_none,
     parse_iso8601,
+    strip_or_none,
+    try_get,
 )
 
 
-class IGNIE(InfoExtractor):
+class IGNBaseIE(InfoExtractor):
+    def _call_api(self, slug):
+        return self._download_json(
+            'http://apis.ign.com/{0}/v3/{0}s/slug/{1}'.format(self._PAGE_TYPE, slug), slug)
+
+
+class IGNIE(IGNBaseIE):
     """
     Extractor for some of the IGN sites, like www.ign.com, es.ign.com de.ign.com.
     Some videos of it.ign.com are also supported
     """
 
-    _VALID_URL = r'https?://.+?\.ign\.com/(?:[^/]+/)?(?P<type>videos|show_videos|articles|feature|(?:[^/]+/\d+/video))(/.+)?/(?P<name_or_id>.+)'
+    _VALID_URL = r'https?://(?:.+?\.ign|www\.pcmag)\.com/videos/(?:\d{4}/\d{2}/\d{2}/)?(?P<id>[^/?&#]+)'
     IE_NAME = 'ign.com'
+    _PAGE_TYPE = 'video'
 
-    _API_URL_TEMPLATE = 'http://apis.ign.com/video/v3/videos/%s'
+    _TESTS = [{
-    _EMBED_RE = r'<iframe[^>]+?["\']((?:https?:)?//.+?\.ign\.com.+?/embed.+?)["\']'
+        'url': 'http://www.ign.com/videos/2013/06/05/the-last-of-us-review',
-
+        'md5': 'd2e1586d9987d40fad7867bf96a018ea',
-    _TESTS = [
+        'info_dict': {
-        {
+            'id': '8f862beef863986b2785559b9e1aa599',
-            'url': 'http://www.ign.com/videos/2013/06/05/the-last-of-us-review',
+            'ext': 'mp4',
-            'md5': 'febda82c4bafecd2d44b6e1a18a595f8',
+            'title': 'The Last of Us Review',
-            'info_dict': {
+            'description': 'md5:c8946d4260a4d43a00d5ae8ed998870c',
-                'id': '8f862beef863986b2785559b9e1aa599',
+            'timestamp': 1370440800,
-                'ext': 'mp4',
+            'upload_date': '20130605',
-                'title': 'The Last of Us Review',
+            'tags': 'count:9',
-                'description': 'md5:c8946d4260a4d43a00d5ae8ed998870c',
+        }
-                'timestamp': 1370440800,
+    }, {
-                'upload_date': '20130605',
+        'url': 'http://www.pcmag.com/videos/2015/01/06/010615-whats-new-now-is-gogo-snooping-on-your-data',
-                'uploader_id': 'cberidon@ign.com',
+        'md5': 'f1581a6fe8c5121be5b807684aeac3f6',
-            }
+        'info_dict': {
-        },
+            'id': 'ee10d774b508c9b8ec07e763b9125b91',
-        {
+            'ext': 'mp4',
-            'url': 'http://me.ign.com/en/feature/15775/100-little-things-in-gta-5-that-will-blow-your-mind',
+            'title': 'What\'s New Now: Is GoGo Snooping on Your Data?',
-            'info_dict': {
+            'description': 'md5:817a20299de610bd56f13175386da6fa',
-                'id': '100-little-things-in-gta-5-that-will-blow-your-mind',
+            'timestamp': 1420571160,
-            },
+            'upload_date': '20150106',
-            'playlist': [
+            'tags': 'count:4',
-                {
+        }
-                    'info_dict': {
+    }, {
-                        'id': '5ebbd138523268b93c9141af17bec937',
+        'url': 'https://www.ign.com/videos/is-a-resident-evil-4-remake-on-the-way-ign-daily-fix',
-                        'ext': 'mp4',
+        'only_matching': True,
-                        'title': 'GTA 5 Video Review',
+    }]
-                        'description': 'Rockstar drops the mic on this generation of games. Watch our review of the masterly Grand Theft Auto V.',
-                        'timestamp': 1379339880,
-                        'upload_date': '20130916',
-                        'uploader_id': 'danieljkrupa@gmail.com',
-                    },
-                },
-                {
-                    'info_dict': {
-                        'id': '638672ee848ae4ff108df2a296418ee2',
-                        'ext': 'mp4',
-                        'title': '26 Twisted Moments from GTA 5 in Slow Motion',
-                        'description': 'The twisted beauty of GTA 5 in stunning slow motion.',
-                        'timestamp': 1386878820,
-                        'upload_date': '20131212',
-                        'uploader_id': 'togilvie@ign.com',
-                    },
-                },
-            ],
-            'params': {
-                'skip_download': True,
-            },
-        },
-        {
-            'url': 'http://www.ign.com/articles/2014/08/15/rewind-theater-wild-trailer-gamescom-2014?watch',
-            'md5': '618fedb9c901fd086f6f093564ef8558',
-            'info_dict': {
-                'id': '078fdd005f6d3c02f63d795faa1b984f',
-                'ext': 'mp4',
-                'title': 'Rewind Theater - Wild Trailer Gamescom 2014',
-                'description': 'Brian and Jared explore Michel Ancel\'s captivating new preview.',
-                'timestamp': 1408047180,
-                'upload_date': '20140814',
-                'uploader_id': 'jamesduggan1990@gmail.com',
-            },
-        },
-        {
-            'url': 'http://me.ign.com/en/videos/112203/video/how-hitman-aims-to-be-different-than-every-other-s',
-            'only_matching': True,
-        },
-        {
-            'url': 'http://me.ign.com/ar/angry-birds-2/106533/video/lrd-ldyy-lwl-lfylm-angry-birds',
-            'only_matching': True,
-        },
-        {
-            # videoId pattern
-            'url': 'http://www.ign.com/articles/2017/06/08/new-ducktales-short-donalds-birthday-doesnt-go-as-planned',
-            'only_matching': True,
-        },
-    ]
-
-    def _find_video_id(self, webpage):
-        res_id = [
-            r'"video_id"\s*:\s*"(.*?)"',
-            r'class="hero-poster[^"]*?"[^>]*id="(.+?)"',
-            r'data-video-id="(.+?)"',
-            r'<object id="vid_(.+?)"',
-            r'<meta name="og:image" content=".*/(.+?)-(.+?)/.+.jpg"',
-            r'videoId&quot;\s*:\s*&quot;(.+?)&quot;',
-            r'videoId["\']\s*:\s*["\']([^"\']+?)["\']',
-        ]
-        return self._search_regex(res_id, webpage, 'video id', default=None)
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
+        display_id = self._match_id(url)
-        name_or_id = mobj.group('name_or_id')
+        video = self._call_api(display_id)
-        page_type = mobj.group('type')
+        video_id = video['videoId']
-        webpage = self._download_webpage(url, name_or_id)
+        metadata = video['metadata']
-        if page_type != 'video':
+        title = metadata.get('longTitle') or metadata.get('title') or metadata['name']
-            multiple_urls = re.findall(
-                r'<param name="flashvars"[^>]*value="[^"]*?url=(https?://www\.ign\.com/videos/.*?)["&]',
-                webpage)
-            if multiple_urls:
-                entries = [self.url_result(u, ie='IGN') for u in multiple_urls]
-                return {
-                    '_type': 'playlist',
-                    'id': name_or_id,
-                    'entries': entries,
-                }
-
-        video_id = self._find_video_id(webpage)
-        if not video_id:
-            return self.url_result(self._search_regex(
-                self._EMBED_RE, webpage, 'embed url'))
-        return self._get_video_info(video_id)
-
-    def _get_video_info(self, video_id):
-        api_data = self._download_json(
-            self._API_URL_TEMPLATE % video_id, video_id)
 
         formats = []
-        m3u8_url = api_data['refs'].get('m3uUrl')
+        refs = video.get('refs') or {}
+
+        m3u8_url = refs.get('m3uUrl')
         if m3u8_url:
             formats.extend(self._extract_m3u8_formats(
                 m3u8_url, video_id, 'mp4', 'm3u8_native',
                 m3u8_id='hls', fatal=False))
-        f4m_url = api_data['refs'].get('f4mUrl')
+
+        f4m_url = refs.get('f4mUrl')
         if f4m_url:
             formats.extend(self._extract_f4m_formats(
                 f4m_url, video_id, f4m_id='hds', fatal=False))
-        for asset in api_data['assets']:
+
+        for asset in (video.get('assets') or []):
+            asset_url = asset.get('url')
+            if not asset_url:
+                continue
             formats.append({
-                'url': asset['url'],
+                'url': asset_url,
-                'tbr': asset.get('actual_bitrate_kbps'),
+                'tbr': int_or_none(asset.get('bitrate'), 1000),
-                'fps': asset.get('frame_rate'),
+                'fps': int_or_none(asset.get('frame_rate')),
                 'height': int_or_none(asset.get('height')),
                 'width': int_or_none(asset.get('width')),
             })
+
+        mezzanine_url = try_get(video, lambda x: x['system']['mezzanineUrl'])
+        if mezzanine_url:
+            formats.append({
+                'ext': determine_ext(mezzanine_url, 'mp4'),
+                'format_id': 'mezzanine',
+                'preference': 1,
+                'url': mezzanine_url,
+            })
+
         self._sort_formats(formats)
 
-        thumbnails = [{
+        thumbnails = []
-            'url': thumbnail['url']
+        for thumbnail in (video.get('thumbnails') or []):
-        } for thumbnail in api_data.get('thumbnails', [])]
+            thumbnail_url = thumbnail.get('url')
+            if not thumbnail_url:
+                continue
+            thumbnails.append({
+                'url': thumbnail_url,
+            })
 
-        metadata = api_data['metadata']
+        tags = []
+        for tag in (video.get('tags') or []):
+            display_name = tag.get('displayName')
+            if not display_name:
+                continue
+            tags.append(display_name)
 
         return {
-            'id': api_data.get('videoId') or video_id,
+            'id': video_id,
-            'title': metadata.get('longTitle') or metadata.get('name') or metadata.get['title'],
+            'title': title,
-            'description': metadata.get('description'),
+            'description': strip_or_none(metadata.get('description')),
             'timestamp': parse_iso8601(metadata.get('publishDate')),
             'duration': int_or_none(metadata.get('duration')),
-            'display_id': metadata.get('slug') or video_id,
+            'display_id': display_id,
-            'uploader_id': metadata.get('creator'),
             'thumbnails': thumbnails,
             'formats': formats,
+            'tags': tags,
         }
 
 
-class OneUPIE(IGNIE):
+class IGNVideoIE(InfoExtractor):
-    _VALID_URL = r'https?://gamevideos\.1up\.com/(?P<type>video)/id/(?P<name_or_id>.+)\.html'
+    _VALID_URL = r'https?://.+?\.ign\.com/(?:[a-z]{2}/)?[^/]+/(?P<id>\d+)/(?:video|trailer)/'
-    IE_NAME = '1up.com'
-
     _TESTS = [{
-        'url': 'http://gamevideos.1up.com/video/id/34976.html',
+        'url': 'http://me.ign.com/en/videos/112203/video/how-hitman-aims-to-be-different-than-every-other-s',
-        'md5': 'c9cc69e07acb675c31a16719f909e347',
+        'md5': 'dd9aca7ed2657c4e118d8b261e5e9de1',
         'info_dict': {
-            'id': '34976',
+            'id': 'e9be7ea899a9bbfc0674accc22a36cc8',
             'ext': 'mp4',
-            'title': 'Sniper Elite V2 - Trailer',
+            'title': 'How Hitman Aims to Be Different Than Every Other Stealth Game - NYCC 2015',
-            'description': 'md5:bf0516c5ee32a3217aa703e9b1bc7826',
+            'description': 'Taking out assassination targets in Hitman has never been more stylish.',
-            'timestamp': 1313099220,
+            'timestamp': 1444665600,
-            'upload_date': '20110811',
+            'upload_date': '20151012',
-            'uploader_id': 'IGN',
         }
+    }, {
+        'url': 'http://me.ign.com/ar/angry-birds-2/106533/video/lrd-ldyy-lwl-lfylm-angry-birds',
+        'only_matching': True,
+    }, {
+        # Youtube embed
+        'url': 'https://me.ign.com/ar/ratchet-clank-rift-apart/144327/trailer/embed',
+        'only_matching': True,
+    }, {
+        # Twitter embed
+        'url': 'http://adria.ign.com/sherlock-season-4/9687/trailer/embed',
+        'only_matching': True,
+    }, {
+        # Vimeo embed
+        'url': 'https://kr.ign.com/bic-2018/3307/trailer/embed',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
+        video_id = self._match_id(url)
-        result = super(OneUPIE, self)._real_extract(url)
+        req = HEADRequest(url.rsplit('/', 1)[0] + '/embed')
-        result['id'] = mobj.group('name_or_id')
+        url = self._request_webpage(req, video_id).geturl()
-        return result
+        ign_url = compat_parse_qs(
+            compat_urllib_parse_urlparse(url).query).get('url', [None])[0]
+        if ign_url:
+            return self.url_result(ign_url, IGNIE.ie_key())
+        return self.url_result(url)
 
 
-class PCMagIE(IGNIE):
+class IGNArticleIE(IGNBaseIE):
-    _VALID_URL = r'https?://(?:www\.)?pcmag\.com/(?P<type>videos|article2)(/.+)?/(?P<name_or_id>.+)'
+    _VALID_URL = r'https?://.+?\.ign\.com/(?:articles(?:/\d{4}/\d{2}/\d{2})?|(?:[a-z]{2}/)?feature/\d+)/(?P<id>[^/?&#]+)'
-    IE_NAME = 'pcmag'
+    _PAGE_TYPE = 'article'
-
-    _EMBED_RE = r'iframe\.setAttribute\("src",\s*__util.objToUrlString\("http://widgets\.ign\.com/video/embed/content\.html?[^"]*url=([^"]+)["&]'
-
     _TESTS = [{
-        'url': 'http://www.pcmag.com/videos/2015/01/06/010615-whats-new-now-is-gogo-snooping-on-your-data',
+        'url': 'http://me.ign.com/en/feature/15775/100-little-things-in-gta-5-that-will-blow-your-mind',
-        'md5': '212d6154fd0361a2781075f1febbe9ad',
         'info_dict': {
-            'id': 'ee10d774b508c9b8ec07e763b9125b91',
+            'id': '524497489e4e8ff5848ece34',
-            'ext': 'mp4',
+            'title': '100 Little Things in GTA 5 That Will Blow Your Mind',
-            'title': '010615_What\'s New Now: Is GoGo Snooping on Your Data?',
+        },
-            'description': 'md5:a7071ae64d2f68cc821c729d4ded6bb3',
+        'playlist': [
-            'timestamp': 1420571160,
+            {
-            'upload_date': '20150106',
+                'info_dict': {
-            'uploader_id': 'cozzipix@gmail.com',
+                    'id': '5ebbd138523268b93c9141af17bec937',
-        }
+                    'ext': 'mp4',
+                    'title': 'GTA 5 Video Review',
+                    'description': 'Rockstar drops the mic on this generation of games. Watch our review of the masterly Grand Theft Auto V.',
+                    'timestamp': 1379339880,
+                    'upload_date': '20130916',
+                },
+            },
+            {
+                'info_dict': {
+                    'id': '638672ee848ae4ff108df2a296418ee2',
+                    'ext': 'mp4',
+                    'title': '26 Twisted Moments from GTA 5 in Slow Motion',
+                    'description': 'The twisted beauty of GTA 5 in stunning slow motion.',
+                    'timestamp': 1386878820,
+                    'upload_date': '20131212',
+                },
+            },
+        ],
+        'params': {
+            'playlist_items': '2-3',
+            'skip_download': True,
+        },
     }, {
-        'url': 'http://www.pcmag.com/article2/0,2817,2470156,00.asp',
+        'url': 'http://www.ign.com/articles/2014/08/15/rewind-theater-wild-trailer-gamescom-2014?watch',
-        'md5': '94130c1ca07ba0adb6088350681f16c1',
         'info_dict': {
-            'id': '042e560ba94823d43afcb12ddf7142ca',
+            'id': '53ee806780a81ec46e0790f8',
-            'ext': 'mp4',
+            'title': 'Rewind Theater - Wild Trailer Gamescom 2014',
-            'title': 'HTC\'s Weird New Re Camera - What\'s New Now',
+        },
-            'description': 'md5:53433c45df96d2ea5d0fda18be2ca908',
+        'playlist_count': 2,
-            'timestamp': 1412953920,
+    }, {
-            'upload_date': '20141010',
+        # videoId pattern
-            'uploader_id': 'chris_snyder@pcmag.com',
+        'url': 'http://www.ign.com/articles/2017/06/08/new-ducktales-short-donalds-birthday-doesnt-go-as-planned',
-        }
+        'only_matching': True,
+    }, {
+        # Youtube embed
+        'url': 'https://www.ign.com/articles/2021-mvp-named-in-puppy-bowl-xvii',
+        'only_matching': True,
+    }, {
+        # IMDB embed
+        'url': 'https://www.ign.com/articles/2014/08/07/sons-of-anarchy-final-season-trailer',
+        'only_matching': True,
+    }, {
+        # Facebook embed
+        'url': 'https://www.ign.com/articles/2017/09/20/marvels-the-punisher-watch-the-new-trailer-for-the-netflix-series',
+        'only_matching': True,
+    }, {
+        # Brightcove embed
+        'url': 'https://www.ign.com/articles/2016/01/16/supergirl-goes-flying-with-martian-manhunter-in-new-clip',
+        'only_matching': True,
     }]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        article = self._call_api(display_id)
+
+        def entries():
+            media_url = try_get(article, lambda x: x['mediaRelations'][0]['media']['metadata']['url'])
+            if media_url:
+                yield self.url_result(media_url, IGNIE.ie_key())
+            for content in (article.get('content') or []):
+                for video_url in re.findall(r'(?:\[(?:ignvideo\s+url|youtube\s+clip_id)|<iframe[^>]+src)="([^"]+)"', content):
+                    yield self.url_result(video_url)
+
+        return self.playlist_result(
+            entries(), article.get('articleId'),
+            strip_or_none(try_get(article, lambda x: x['metadata']['headline'])))

youtube_dlc/extractor/ivi.py

@@ -163,7 +163,10 @@ class IviIE(InfoExtractor):
         for f in result.get('files', []):
             f_url = f.get('url')
             content_format = f.get('content_format')
-            if not f_url or '-MDRM-' in content_format or '-FPS-' in content_format:
+            if not f_url:
+                continue
+            if (not self._downloader.params.get('allow_unplayable_formats')
+                    and ('-MDRM-' in content_format or '-FPS-' in content_format)):
                 continue
             formats.append({
                 'url': f_url,

youtube_dlc/extractor/kaltura.py

@@ -309,7 +309,7 @@ class KalturaIE(InfoExtractor):
             if f.get('fileExt') == 'chun':
                 continue
             # DRM-protected video, cannot be decrypted
-            if f.get('fileExt') == 'wvm':
+            if not self._downloader.params.get('allow_unplayable_formats') and f.get('fileExt') == 'wvm':
                 continue
             if not f.get('fileExt'):
                 # QT indicates QuickTime; some videos have broken fileExt

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/limelight.py

@@ -96,7 +96,9 @@ class LimelightBaseIE(InfoExtractor):
         urls = []
         for stream in pc_item.get('streams', []):
             stream_url = stream.get('url')
-            if not stream_url or stream.get('drmProtected') or stream_url in urls:
+            if not stream_url or stream_url in urls:
+                continue
+            if not self._downloader.params.get('allow_unplayable_formats') and stream.get('drmProtected'):
                 continue
             urls.append(stream_url)
             ext = determine_ext(stream_url)

youtube_dlc/extractor/medialaan.py

@@ -2,268 +2,113 @@ from __future__ import unicode_literals
 
 import re
 
-from .gigya import GigyaBaseIE
+from .common import InfoExtractor
-
-from ..compat import compat_str
 from ..utils import (
+    extract_attributes,
     int_or_none,
-    parse_duration,
+    mimetype2ext,
-    try_get,
+    parse_iso8601,
-    unified_timestamp,
 )
 
 
-class MedialaanIE(GigyaBaseIE):
+class MedialaanIE(InfoExtractor):
     _VALID_URL = r'''(?x)
                     https?://
-                        (?:www\.|nieuws\.)?
                         (?:
-                            (?P<site_id>vtm|q2|vtmkzoom)\.be/
+                            (?:embed\.)?mychannels.video/embed/|
-                            (?:
+                            embed\.mychannels\.video/(?:s(?:dk|cript)/)?production/|
-                                video(?:/[^/]+/id/|/?\?.*?\baid=)|
+                            (?: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': 'https://www.bndestem.nl/video/de-terugkeer-van-ally-de-aap-en-wie-vertrekt-er-nog-bij-nac~p193993',
-        'url': 'http://vtm.be/video/volledige-afleveringen/id/vtm_20170219_VM0678361_vtmwatch',
         'info_dict': {
-            'id': 'vtm_20170219_VM0678361_vtmwatch',
+            'id': '193993',
             'ext': 'mp4',
-            'title': 'Allemaal Chris afl. 6',
+            'title': 'De terugkeer van Ally de Aap en wie vertrekt er nog bij NAC?',
-            'description': 'md5:4be86427521e7b07e0adb0c9c554ddb2',
+            'timestamp': 1611663540,
-            'timestamp': 1487533280,
+            'upload_date': '20210126',
-            'upload_date': '20170219',
+            'duration': 238,
-            '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',
         },
         'params': {
             'skip_download': True,
         },
-        'skip': 'Requires account credentials',
     }, {
-        # clip
+        'url': 'https://www.gelderlander.nl/video/kanalen/degelderlander~c320/series/snel-nieuws~s984/noodbevel-in-doetinchem-politie-stuurt-mensen-centrum-uit~p194093',
-        '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',
         'only_matching': True,
     }, {
-        # vod
+        'url': 'https://embed.mychannels.video/sdk/production/193993?options=TFTFF_default',
-        'url': 'http://vtm.be/video?aid=163157',
         'only_matching': True,
     }, {
-        # vod
+        'url': 'https://embed.mychannels.video/script/production/193993',
-        'url': 'http://www.q2.be/video/volledige-afleveringen/id/2be_20170301_VM0684442_q2',
         'only_matching': True,
     }, {
-        # clip
+        'url': 'https://embed.mychannels.video/production/193993',
-        'url': 'http://vtmkzoom.be/k3-dansstudio/een-nieuw-seizoen-van-k3-dansstudio',
         'only_matching': True,
     }, {
-        # http/s redirect
+        'url': 'https://mychannels.video/embed/193993',
-        'url': 'https://vtmkzoom.be/video?aid=45724',
+        'only_matching': True,
-        'info_dict': {
-            'id': '257136373657000',
-            'ext': 'mp4',
-            'title': 'K3 Dansstudio Ushuaia afl.6',
-        },
-        'params': {
-            'skip_download': True,
-        },
-        'skip': 'Requires account credentials',
     }, {
-        # nieuws.vtm.be
+        'url': 'https://embed.mychannels.video/embed/193993',
-        'url': 'https://nieuws.vtm.be/stadion/stadion/genk-nog-moeilijk-programma',
         'only_matching': True,
     }]
 
-    def _real_initialize(self):
+    @staticmethod
-        self._logged_in = False
+    def _extract_urls(webpage):
-
+        entries = []
-    def _login(self):
+        for element in re.findall(r'(<div[^>]+data-mychannels-type="video"[^>]*>)', webpage):
-        username, password = self._get_login_info()
+            mychannels_id = extract_attributes(element).get('data-mychannels-id')
-        if username is None:
+            if mychannels_id:
-            self.raise_login_required()
+                entries.append('https://mychannels.video/embed/' + mychannels_id)
-
+        return entries
-        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
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
+        production_id = self._match_id(url)
-        video_id, site_id = mobj.group('id', 'site_id')
+        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)
+        formats = []
-
+        for source in (production.get('sources') or []):
-        config = self._parse_json(
+            src = source.get('src')
-            self._search_regex(
+            if not src:
-                r'videoJSConfig\s*=\s*JSON\.parse\(\'({.+?})\'\);',
+                continue
-                webpage, 'config', default='{}'), video_id,
+            ext = mimetype2ext(source.get('type'))
-            transform_source=lambda s: s.replace(
+            if ext == 'm3u8':
-                '\\\\', '\\').replace(r'\"', '"').replace(r"\'", "'"))
+                formats.extend(self._extract_m3u8_formats(
-
+                    src, production_id, 'mp4', 'm3u8_native',
-        vod_id = config.get('vodId') or self._search_regex(
+                    m3u8_id='hls', fatal=False))
-            (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')),
-                }
             else:
-                info = self._parse_html5_media_entries(
+                formats.append({
-                    url, webpage, video_id, m3u8_id='hls')[0]
+                    'ext': ext,
-                info.update({
+                    'url': src,
-                    'id': video_id,
-                    'title': self._html_search_meta('description', webpage),
-                    'duration': parse_duration(self._html_search_meta('duration', webpage)),
                 })
-        # vod, authentication required
+        self._sort_formats(formats)
-        else:
-            if not self._logged_in:
-                self._login()
 
-            settings = self._parse_json(
+        return {
-                self._search_regex(
+            'id': production_id,
-                    r'jQuery\.extend\(Drupal\.settings\s*,\s*({.+?})\);',
+            'title': title,
-                    webpage, 'drupal settings', default='{}'),
+            'formats': formats,
-                video_id)
+            'thumbnail': production.get('posterUrl'),
-
+            'timestamp': parse_iso8601(production.get('publicationDate'), ' '),
-            def get(container, item):
+            'duration': int_or_none(production.get('duration')) or None,
-                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

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/niconico.py

@@ -1,25 +1,25 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import datetime
+import re
-import functools
 import json
-import math
+import datetime
 
 from .common import InfoExtractor
+from ..postprocessor.ffmpeg import FFmpegPostProcessor
 from ..compat import (
     compat_parse_qs,
     compat_urllib_parse_urlparse,
 )
 from ..utils import (
-    determine_ext,
     dict_get,
     ExtractorError,
-    float_or_none,
-    InAdvancePagedList,
     int_or_none,
+    float_or_none,
+    OnDemandPagedList,
     parse_duration,
     parse_iso8601,
+    PostProcessingError,
     remove_start,
     try_get,
     unified_timestamp,
@@ -191,37 +191,87 @@ class NiconicoIE(InfoExtractor):
             self._downloader.report_warning('unable to log in: bad username or password')
         return login_ok
 
-    def _extract_format_for_quality(self, api_data, video_id, audio_quality, video_quality):
+    def _get_heartbeat_info(self, info_dict):
-        def yesno(boolean):
-            return 'yes' if boolean else 'no'
 
-        session_api_data = api_data['video']['dmcInfo']['session_api']
+        video_id, video_src_id, audio_src_id = info_dict['url'].split(':')[1].split('/')
-        session_api_endpoint = session_api_data['urls'][0]
 
-        format_id = '-'.join(map(lambda s: remove_start(s['id'], 'archive_'), [video_quality, audio_quality]))
+        # Get video webpage for API data.
+        webpage, handle = self._download_webpage_handle(
+            'http://www.nicovideo.jp/watch/' + video_id, video_id)
+
+        api_data = self._parse_json(self._html_search_regex(
+            'data-api-data="([^"]+)"', webpage,
+            'API data', default='{}'), video_id)
+
+        session_api_data = try_get(api_data, lambda x: x['video']['dmcInfo']['session_api'])
+        session_api_endpoint = try_get(session_api_data, lambda x: x['urls'][0])
+
+        # ping
+        self._download_json(
+            'https://nvapi.nicovideo.jp/v1/2ab0cbaa/watch', video_id,
+            query={'t': try_get(api_data, lambda x: x['video']['dmcInfo']['tracking_id'])},
+            headers={
+                'Origin': 'https://www.nicovideo.jp',
+                'Referer': 'https://www.nicovideo.jp/watch/' + video_id,
+                'X-Frontend-Id': '6',
+                'X-Frontend-Version': '0'
+            })
+
+        yesno = lambda x: 'yes' if x else 'no'
+
+        # m3u8 (encryption)
+        if 'encryption' in try_get(api_data, lambda x: x['video']['dmcInfo']) or {}:
+            protocol = 'm3u8'
+            session_api_http_parameters = {
+                'parameters': {
+                    'hls_parameters': {
+                        'encryption': {
+                            'hls_encryption_v1': {
+                                'encrypted_key': try_get(api_data, lambda x: x['video']['dmcInfo']['encryption']['hls_encryption_v1']['encrypted_key']),
+                                'key_uri': try_get(api_data, lambda x: x['video']['dmcInfo']['encryption']['hls_encryption_v1']['key_uri'])
+                            }
+                        },
+                        'transfer_preset': '',
+                        'use_ssl': yesno(session_api_endpoint['is_ssl']),
+                        'use_well_known_port': yesno(session_api_endpoint['is_well_known_port']),
+                        'segment_duration': 6000
+                    }
+                }
+            }
+        # http
+        else:
+            protocol = 'http'
+            session_api_http_parameters = {
+                'parameters': {
+                    'http_output_download_parameters': {
+                        'use_ssl': yesno(session_api_endpoint['is_ssl']),
+                        'use_well_known_port': yesno(session_api_endpoint['is_well_known_port']),
+                    }
+                }
+            }
 
         session_response = self._download_json(
             session_api_endpoint['url'], video_id,
             query={'_format': 'json'},
             headers={'Content-Type': 'application/json'},
-            note='Downloading JSON metadata for %s' % format_id,
+            note='Downloading JSON metadata for %s' % info_dict['format_id'],
             data=json.dumps({
                 'session': {
                     'client_info': {
-                        'player_id': session_api_data['player_id'],
+                        'player_id': session_api_data.get('player_id'),
                     },
                     'content_auth': {
-                        'auth_type': session_api_data['auth_types'][session_api_data['protocols'][0]],
+                        'auth_type': try_get(session_api_data, lambda x: x['auth_types'][session_api_data['protocols'][0]]),
-                        'content_key_timeout': session_api_data['content_key_timeout'],
+                        'content_key_timeout': session_api_data.get('content_key_timeout'),
                         'service_id': 'nicovideo',
-                        'service_user_id': session_api_data['service_user_id']
+                        'service_user_id': session_api_data.get('service_user_id')
                     },
-                    'content_id': session_api_data['content_id'],
+                    'content_id': session_api_data.get('content_id'),
                     'content_src_id_sets': [{
                         'content_src_ids': [{
                             'src_id_to_mux': {
-                                'audio_src_ids': [audio_quality['id']],
+                                'audio_src_ids': [audio_src_id],
-                                'video_src_ids': [video_quality['id']],
+                                'video_src_ids': [video_src_id],
                             }
                         }]
                     }],
@@ -229,52 +279,78 @@ class NiconicoIE(InfoExtractor):
                     'content_uri': '',
                     'keep_method': {
                         'heartbeat': {
-                            'lifetime': session_api_data['heartbeat_lifetime']
+                            'lifetime': session_api_data.get('heartbeat_lifetime')
                         }
                     },
-                    'priority': session_api_data['priority'],
+                    'priority': session_api_data.get('priority'),
                     'protocol': {
                         'name': 'http',
                         'parameters': {
-                            'http_parameters': {
+                            'http_parameters': session_api_http_parameters
-                                'parameters': {
-                                    'http_output_download_parameters': {
-                                        'use_ssl': yesno(session_api_endpoint['is_ssl']),
-                                        'use_well_known_port': yesno(session_api_endpoint['is_well_known_port']),
-                                    }
-                                }
-                            }
                         }
                     },
-                    'recipe_id': session_api_data['recipe_id'],
+                    'recipe_id': session_api_data.get('recipe_id'),
                     'session_operation_auth': {
                         'session_operation_auth_by_signature': {
-                            'signature': session_api_data['signature'],
+                            'signature': session_api_data.get('signature'),
-                            'token': session_api_data['token'],
+                            'token': session_api_data.get('token'),
                         }
                     },
                     'timing_constraint': 'unlimited'
                 }
             }).encode())
 
-        resolution = video_quality.get('resolution', {})
+        info_dict['url'] = session_response['data']['session']['content_uri']
+        info_dict['protocol'] = protocol
+
+        # get heartbeat info
+        heartbeat_info_dict = {
+            'url': session_api_endpoint['url'] + '/' + session_response['data']['session']['id'] + '?_format=json&_method=PUT',
+            'data': json.dumps(session_response['data']),
+            # interval, convert milliseconds to seconds, then halve to make a buffer.
+            'interval': float_or_none(session_api_data.get('heartbeat_lifetime'), scale=2000),
+        }
+
+        return info_dict, heartbeat_info_dict
+
+    def _extract_format_for_quality(self, api_data, video_id, audio_quality, video_quality):
+        def parse_format_id(id_code):
+            mobj = re.match(r'''(?x)
+                    (?:archive_)?
+                    (?:(?P<codec>[^_]+)_)?
+                    (?:(?P<br>[\d]+)kbps_)?
+                    (?:(?P<res>[\d+]+)p_)?
+                ''', '%s_' % id_code)
+            return mobj.groupdict() if mobj else {}
+
+        protocol = 'niconico_dmc'
+        format_id = '-'.join(map(lambda s: remove_start(s['id'], 'archive_'), [video_quality, audio_quality]))
+        vdict = parse_format_id(video_quality['id'])
+        adict = parse_format_id(audio_quality['id'])
+        resolution = video_quality.get('resolution', {'height': vdict.get('res')})
 
         return {
-            'url': session_response['data']['session']['content_uri'],
+            'url': '%s:%s/%s/%s' % (protocol, video_id, video_quality['id'], audio_quality['id']),
             'format_id': format_id,
             'ext': 'mp4',  # Session API are used in HTML5, which always serves mp4
-            'abr': float_or_none(audio_quality.get('bitrate'), 1000),
+            'vcodec': vdict.get('codec'),
-            'vbr': float_or_none(video_quality.get('bitrate'), 1000),
+            'acodec': adict.get('codec'),
-            'height': resolution.get('height'),
+            'vbr': float_or_none(video_quality.get('bitrate'), 1000) or float_or_none(vdict.get('br')),
-            'width': resolution.get('width'),
+            'abr': float_or_none(audio_quality.get('bitrate'), 1000) or float_or_none(adict.get('br')),
+            'height': int_or_none(resolution.get('height', vdict.get('res'))),
+            'width': int_or_none(resolution.get('width')),
+            'quality': -2 if 'low' in format_id else -1,  # Default quality value is -1
+            'protocol': protocol,
+            'http_headers': {
+                'Origin': 'https://www.nicovideo.jp',
+                'Referer': 'https://www.nicovideo.jp/watch/' + video_id,
+            }
         }
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
-        # Get video webpage. We are not actually interested in it for normal
+        # Get video webpage for API data.
-        # cases, but need the cookies in order to be able to download the
-        # info webpage
         webpage, handle = self._download_webpage_handle(
             'http://www.nicovideo.jp/watch/' + video_id, video_id)
         if video_id.startswith('so'):
@@ -284,80 +360,134 @@ class NiconicoIE(InfoExtractor):
             'data-api-data="([^"]+)"', webpage,
             'API data', default='{}'), video_id)
 
-        def _format_id_from_url(video_url):
+        def get_video_info_web(items):
-            return 'economy' if video_real_url.endswith('low') else 'normal'
+            return dict_get(api_data['video'], items)
+
+        # Get video info
+        video_info_xml = self._download_xml(
+            'http://ext.nicovideo.jp/api/getthumbinfo/' + video_id,
+            video_id, note='Downloading video info page')
+
+        def get_video_info_xml(items):
+            if not isinstance(items, list):
+                items = [items]
+            for item in items:
+                ret = xpath_text(video_info_xml, './/' + item)
+                if ret:
+                    return ret
+
+        if get_video_info_xml('error'):
+            error_code = get_video_info_xml('code')
+
+            if error_code == 'DELETED':
+                raise ExtractorError('The video has been deleted.',
+                                     expected=True)
+            elif error_code == 'NOT_FOUND':
+                raise ExtractorError('The video is not found.',
+                                     expected=True)
+            elif error_code == 'COMMUNITY':
+                self.to_screen('%s: The video is community members only.' % video_id)
+            else:
+                raise ExtractorError('%s reports error: %s' % (self.IE_NAME, error_code))
+
+        # Start extracting video formats
+        formats = []
+
+        # Get HTML5 videos info
+        try:
+            dmc_info = api_data['video']['dmcInfo']
+        except KeyError:
+            raise ExtractorError('The video can\'t downloaded.',
+                                 expected=True)
+
+        quality_info = dmc_info.get('quality')
+        for audio_quality in quality_info.get('audios') or {}:
+            for video_quality in quality_info.get('videos') or {}:
+                if not audio_quality.get('available') or not video_quality.get('available'):
+                    continue
+                formats.append(self._extract_format_for_quality(
+                    api_data, video_id, audio_quality, video_quality))
+
+        # Get flv/swf info
+        video_real_url = try_get(api_data, lambda x: x['video']['smileInfo']['url'])
+        is_economy = video_real_url.endswith('low')
+
+        if is_economy:
+            self.report_warning('Site is currently in economy mode! You will only have access to lower quality streams')
+
+        # Invoking ffprobe to determine resolution
+        pp = FFmpegPostProcessor(self._downloader)
+        cookies = self._get_cookies('https://nicovideo.jp').output(header='', sep='; path=/; domain=nicovideo.jp;\n')
+
+        self.to_screen('%s: %s' % (video_id, 'Checking smile format with ffprobe'))
 
         try:
-            video_real_url = api_data['video']['smileInfo']['url']
+            metadata = pp.get_metadata_object(video_real_url, ['-cookies', cookies])
-        except KeyError:  # Flash videos
+        except PostProcessingError as err:
-            # Get flv info
+            raise ExtractorError(err.msg, expected=True)
-            flv_info_webpage = self._download_webpage(
-                'http://flapi.nicovideo.jp/api/getflv/' + video_id + '?as3=1',
-                video_id, 'Downloading flv info')
 
-            flv_info = compat_parse_qs(flv_info_webpage)
+        v_stream = a_stream = {}
-            if 'url' not in flv_info:
-                if 'deleted' in flv_info:
-                    raise ExtractorError('The video has been deleted.',
-                                         expected=True)
-                elif 'closed' in flv_info:
-                    raise ExtractorError('Niconico videos now require logging in',
-                                         expected=True)
-                elif 'error' in flv_info:
-                    raise ExtractorError('%s reports error: %s' % (
-                        self.IE_NAME, flv_info['error'][0]), expected=True)
-                else:
-                    raise ExtractorError('Unable to find video URL')
 
-            video_info_xml = self._download_xml(
+        # Some complex swf files doesn't have video stream (e.g. nm4809023)
-                'http://ext.nicovideo.jp/api/getthumbinfo/' + video_id,
+        for stream in metadata['streams']:
-                video_id, note='Downloading video info page')
+            if stream['codec_type'] == 'video':
+                v_stream = stream
+            elif stream['codec_type'] == 'audio':
+                a_stream = stream
 
-            def get_video_info(items):
+        # Community restricted videos seem to have issues with the thumb API not returning anything at all
-                if not isinstance(items, list):
+        filesize = int(
-                    items = [items]
+            (get_video_info_xml('size_high') if not is_economy else get_video_info_xml('size_low'))
-                for item in items:
+            or metadata['format']['size']
-                    ret = xpath_text(video_info_xml, './/' + item)
+        )
-                    if ret:
+        extension = (
-                        return ret
+            get_video_info_xml('movie_type')
+            or 'mp4' if 'mp4' in metadata['format']['format_name'] else metadata['format']['format_name']
+        )
 
-            video_real_url = flv_info['url'][0]
+        # 'creation_time' tag on video stream of re-encoded SMILEVIDEO mp4 files are '1970-01-01T00:00:00.000000Z'.
+        timestamp = (
+            parse_iso8601(get_video_info_web('first_retrieve'))
+            or unified_timestamp(get_video_info_web('postedDateTime'))
+        )
+        metadata_timestamp = (
+            parse_iso8601(try_get(v_stream, lambda x: x['tags']['creation_time']))
+            or timestamp if extension != 'mp4' else 0
+        )
 
-            extension = get_video_info('movie_type')
+        # According to compconf, smile videos from pre-2017 are always better quality than their DMC counterparts
-            if not extension:
+        smile_threshold_timestamp = parse_iso8601('2016-12-08T00:00:00+09:00')
-                extension = determine_ext(video_real_url)
 
-            formats = [{
+        is_source = timestamp < smile_threshold_timestamp or metadata_timestamp > 0
+
+        # If movie file size is unstable, old server movie is not source movie.
+        if filesize > 1:
+            formats.append({
                 'url': video_real_url,
+                'format_id': 'smile' if not is_economy else 'smile_low',
+                'format_note': 'SMILEVIDEO source' if not is_economy else 'SMILEVIDEO low quality',
                 'ext': extension,
-                'format_id': _format_id_from_url(video_real_url),
+                'container': extension,
-            }]
+                'vcodec': v_stream.get('codec_name'),
-        else:
+                'acodec': a_stream.get('codec_name'),
-            formats = []
+                # Some complex swf files doesn't have total bit rate metadata (e.g. nm6049209)
+                'tbr': int_or_none(metadata['format'].get('bit_rate'), scale=1000),
+                'vbr': int_or_none(v_stream.get('bit_rate'), scale=1000),
+                'abr': int_or_none(a_stream.get('bit_rate'), scale=1000),
+                'height': int_or_none(v_stream.get('height')),
+                'width': int_or_none(v_stream.get('width')),
+                'source_preference': 5 if not is_economy else -2,
+                'quality': 5 if is_source and not is_economy else None,
+                'filesize': filesize
+            })
 
-            dmc_info = api_data['video'].get('dmcInfo')
+        if len(formats) == 0:
-            if dmc_info:  # "New" HTML5 videos
+            raise ExtractorError('Unable to find video info.')
-                quality_info = dmc_info['quality']
-                for audio_quality in quality_info['audios']:
-                    for video_quality in quality_info['videos']:
-                        if not audio_quality['available'] or not video_quality['available']:
-                            continue
-                        formats.append(self._extract_format_for_quality(
-                            api_data, video_id, audio_quality, video_quality))
 
-                self._sort_formats(formats)
+        self._sort_formats(formats)
-            else:  # "Old" HTML5 videos
-                formats = [{
-                    'url': video_real_url,
-                    'ext': 'mp4',
-                    'format_id': _format_id_from_url(video_real_url),
-                }]
-
-            def get_video_info(items):
-                return dict_get(api_data['video'], items)
 
         # Start extracting information
-        title = get_video_info('title')
+        title = get_video_info_web('originalTitle')
         if not title:
             title = self._og_search_title(webpage, default=None)
         if not title:
@@ -372,14 +502,13 @@ class NiconicoIE(InfoExtractor):
         video_detail = watch_api_data.get('videoDetail', {})
 
         thumbnail = (
-            get_video_info(['thumbnail_url', 'thumbnailURL'])
+            self._html_search_regex(r'<meta property="og:image" content="([^"]+)">', webpage, 'thumbnail data', default=None)
+            or get_video_info_web(['thumbnail_url', 'largeThumbnailURL', 'thumbnailURL'])
             or self._html_search_meta('image', webpage, 'thumbnail', default=None)
             or video_detail.get('thumbnail'))
 
-        description = get_video_info('description')
+        description = get_video_info_web('description')
 
-        timestamp = (parse_iso8601(get_video_info('first_retrieve'))
-                     or unified_timestamp(get_video_info('postedDateTime')))
         if not timestamp:
             match = self._html_search_meta('datePublished', webpage, 'date published', default=None)
             if match:
@@ -389,7 +518,7 @@ class NiconicoIE(InfoExtractor):
                 video_detail['postedAt'].replace('/', '-'),
                 delimiter=' ', timezone=datetime.timedelta(hours=9))
 
-        view_count = int_or_none(get_video_info(['view_counter', 'viewCount']))
+        view_count = int_or_none(get_video_info_web(['view_counter', 'viewCount']))
         if not view_count:
             match = self._html_search_regex(
                 r'>Views: <strong[^>]*>([^<]+)</strong>',
@@ -398,7 +527,7 @@ class NiconicoIE(InfoExtractor):
                 view_count = int_or_none(match.replace(',', ''))
         view_count = view_count or video_detail.get('viewCount')
 
-        comment_count = (int_or_none(get_video_info('comment_num'))
+        comment_count = (int_or_none(get_video_info_web('comment_num'))
                          or video_detail.get('commentCount')
                          or try_get(api_data, lambda x: x['thread']['commentCount']))
         if not comment_count:
@@ -409,19 +538,19 @@ class NiconicoIE(InfoExtractor):
                 comment_count = int_or_none(match.replace(',', ''))
 
         duration = (parse_duration(
-            get_video_info('length')
+            get_video_info_web('length')
             or self._html_search_meta(
                 'video:duration', webpage, 'video duration', default=None))
             or video_detail.get('length')
-            or get_video_info('duration'))
+            or get_video_info_web('duration'))
 
-        webpage_url = get_video_info('watch_url') or url
+        webpage_url = get_video_info_web('watch_url') or url
 
         # Note: cannot use api_data.get('owner', {}) because owner may be set to "null"
         # in the JSON, which will cause None to be returned instead of {}.
         owner = try_get(api_data, lambda x: x.get('owner'), dict) or {}
-        uploader_id = get_video_info(['ch_id', 'user_id']) or owner.get('id')
+        uploader_id = get_video_info_web(['ch_id', 'user_id']) or owner.get('id')
-        uploader = get_video_info(['ch_name', 'user_nickname']) or owner.get('nickname')
+        uploader = get_video_info_web(['ch_name', 'user_nickname']) or owner.get('nickname')
 
         return {
             'id': video_id,
@@ -456,60 +585,45 @@ class NiconicoPlaylistIE(InfoExtractor):
         'url': 'https://www.nicovideo.jp/user/805442/mylist/27411728',
         'only_matching': True,
     }]
-    _PAGE_SIZE = 100
-
-    def _call_api(self, list_id, resource, query):
-        return self._download_json(
-            'https://nvapi.nicovideo.jp/v2/mylists/' + list_id, list_id,
-            'Downloading %s JSON metatdata' % resource, query=query,
-            headers={'X-Frontend-Id': 6})['data']['mylist']
-
-    def _parse_owner(self, item):
-        owner = item.get('owner') or {}
-        if owner:
-            return {
-                'uploader': owner.get('name'),
-                'uploader_id': owner.get('id'),
-            }
-        return {}
-
-    def _fetch_page(self, list_id, page):
-        page += 1
-        items = self._call_api(list_id, 'page %d' % page, {
-            'page': page,
-            'pageSize': self._PAGE_SIZE,
-        })['items']
-        for item in items:
-            video = item.get('video') or {}
-            video_id = video.get('id')
-            if not video_id:
-                continue
-            count = video.get('count') or {}
-            get_count = lambda x: int_or_none(count.get(x))
-            info = {
-                '_type': 'url',
-                'id': video_id,
-                'title': video.get('title'),
-                'url': 'https://www.nicovideo.jp/watch/' + video_id,
-                'description': video.get('shortDescription'),
-                'duration': int_or_none(video.get('duration')),
-                'view_count': get_count('view'),
-                'comment_count': get_count('comment'),
-                'ie_key': NiconicoIE.ie_key(),
-            }
-            info.update(self._parse_owner(video))
-            yield info
 
     def _real_extract(self, url):
         list_id = self._match_id(url)
-        mylist = self._call_api(list_id, 'list', {
+        webpage = self._download_webpage(url, list_id)
-            'pageSize': 1,
+
-        })
+        header = self._parse_json(self._html_search_regex(
-        entries = InAdvancePagedList(
+            r'data-common-header="([^"]+)"', webpage,
-            functools.partial(self._fetch_page, list_id),
+            'webpage header'), list_id)
-            math.ceil(mylist['totalItemCount'] / self._PAGE_SIZE),
+        frontendId = header.get('initConfig').get('frontendId')
-            self._PAGE_SIZE)
+        frontendVersion = header.get('initConfig').get('frontendVersion')
-        result = self.playlist_result(
+
-            entries, list_id, mylist.get('name'), mylist.get('description'))
+        def get_page_data(pagenum, pagesize):
-        result.update(self._parse_owner(mylist))
+            return self._download_json(
-        return result
+                'http://nvapi.nicovideo.jp/v2/mylists/' + list_id, list_id,
+                query={'page': 1 + pagenum, 'pageSize': pagesize},
+                headers={
+                    'X-Frontend-Id': frontendId,
+                    'X-Frontend-Version': frontendVersion,
+                }).get('data').get('mylist')
+
+        data = get_page_data(0, 1)
+        title = data.get('name')
+        description = data.get('description')
+        uploader = data.get('owner').get('name')
+        uploader_id = data.get('owner').get('id')
+
+        def pagefunc(pagenum):
+            data = get_page_data(pagenum, 25)
+            return ({
+                '_type': 'url',
+                'url': 'http://www.nicovideo.jp/watch/' + item.get('watchId'),
+            } for item in data.get('items'))
+
+        return {
+            '_type': 'playlist',
+            'id': list_id,
+            'title': title,
+            'description': description,
+            'uploader': uploader,
+            'uploader_id': uploader_id,
+            'entries': OnDemandPagedList(pagefunc, 25),
+        }

youtube_dlc/extractor/ninecninemedia.py

@@ -36,7 +36,8 @@ class NineCNineMediaIE(InfoExtractor):
                 '$include': '[HasClosedCaptions]',
             })
 
-        if try_get(content_package, lambda x: x['Constraints']['Security']['Type']):
+        if (not self._downloader.params.get('allow_unplayable_formats')
+                and try_get(content_package, lambda x: x['Constraints']['Security']['Type'])):
             raise ExtractorError('This video is DRM protected.', expected=True)
 
         manifest_base_url = content_package_url + 'manifest.'

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 = [{
+    _TEST = {
-        'url': 'http://9gag.com/tv/p/Kk2X5/people-are-awesome-2013-is-absolutely-awesome',
+        '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': 'Capybara Agility Training',
-            'title': '\"People Are Awesome 2013\" Is Absolutely Awesome',
+            'upload_date': '20191108',
-            'uploader_id': 'UCdEH6EjDKwtTe-sO2f0_1XA',
+            'timestamp': 1573237208,
-            'uploader': 'CompilationChannel',
+            'categories': ['Awesome'],
-            'upload_date': '20131110',
+            'tags': ['Weimaraner', 'American Pit Bull Terrier'],
-            'view_count': int,
+            'duration': 44,
-        },
+            'like_count': int,
-        'add_ie': ['Youtube'],
+            'dislike_count': int,
-    }, {
+            'comment_count': int,
-        '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',
-        },
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
+        post_id = self._match_id(url)
-        video_id = mobj.group('id')
+        post = self._download_json(
-        display_id = mobj.group('display_id') or video_id
+            '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(
+        title = post['title']
-            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)
 
-        ie_key = None
+        duration = None
-        source_url = post_view.get('sourceUrl')
+        formats = []
-        if not source_url:
+        thumbnails = []
-            external_video_id = post_view['videoExternalId']
+        for key, image in (post.get('images') or {}).items():
-            external_video_provider = post_view['videoExternalProvider']
+            image_url = url_or_none(image.get('url'))
-            source_url = self._EXTERNAL_VIDEO_PROVIDER[external_video_provider]['url'] % external_video_id
+            if not image_url:
-            ie_key = self._EXTERNAL_VIDEO_PROVIDER[external_video_provider]['ie_key']
+                continue
-        title = post_view['title']
+            ext = determine_ext(image_url)
-        description = post_view.get('description')
+            image_id = key.strip('image')
-        view_count = str_to_int(post_view.get('externalView'))
+            common = {
-        thumbnail = post_view.get('thumbnail_700w') or post_view.get('ogImageUrl') or post_view.get('thumbnail_300w')
+                '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',
+            'id': post_id,
-            'url': source_url,
-            'ie_key': ie_key,
-            'id': video_id,
-            'display_id': display_id,
             'title': title,
-            'description': description,
+            'timestamp': int_or_none(post.get('creationTs')),
-            'view_count': view_count,
+            'duration': duration,
-            'thumbnail': thumbnail,
+            '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/ninenow.py

@@ -66,7 +66,7 @@ class NineNowIE(InfoExtractor):
 
         video_data = common_data['video']
 
-        if video_data.get('drm'):
+        if not self._downloader.params.get('allow_unplayable_formats') and video_data.get('drm'):
             raise ExtractorError('This video is DRM protected.', expected=True)
 
         brightcove_id = video_data.get('brightcoveId') or 'ref:' + video_data['referenceId']

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):
+        for kind, vid in re.findall(r'if\s+\(\s*imageQualityType\s*==\s*\'([^\']+)\'\s*\)\s*{\s*video_id\s*=\s*"(\d+)"', webpage):
-            player = extract_attributes(mobj.group(0))
+            player_path = '/intent?id=%s&type=url' % vid
-            player_path = player.get('href')
-            if not player_path:
-                continue
-            kind = self._search_regex(
-                r'(low|high)$', player.get('class') or '', 'kind',
-                default='low')
             player_url = compat_urlparse.urljoin(url, player_path)
-            player_page = self._download_webpage(
+            formats.append({
-                player_url, video_id, note='Downloading player page')
+                'url': player_url,
-            entries = self._parse_html5_media_entries(
+                'format_id': kind,
-                player_url, player_page, video_id, m3u8_id='hls-%s' % kind,
+                'ext': 'mp4',
-                m3u8_entry_protocol='m3u8_native')
+                'protocol': 'm3u8',
-            kind_formats = entries[0]['formats']
+                'quality': 2 if kind == 'high' else 1,
-            for f in kind_formats:
+            })
-                f['quality'] = 2 if kind == 'high' else 1
-            formats.extend(kind_formats)
 
         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
+            r'<a[^>]+class="tag-[^"]+"[^>]*>([^<]+)</a>', tag_block
-        ) if post_content else None
+        ) 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/npo.py

@@ -246,7 +246,7 @@ class NPOIE(NPOBaseIE):
                 })
 
         if not formats:
-            if drm:
+            if not self._downloader.params.get('allow_unplayable_formats') and drm:
                 raise ExtractorError('This video is DRM protected.', expected=True)
             return
 

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:
+        self._login(host)
-            if not self._downloader.params.get('cookiefile'):
-                raise ExtractorError(
-                    'PornHub Premium requires authentication.'
-                    ' You may want to use --cookies.',
-                    expected=True)
 
         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(),
+            videos_url, ie=PornHubPagedVideoListIE.ie_key(), video_id=user_id)
-            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):
+    def _entries(self, url, host, item_id):
-        mobj = re.match(self._VALID_URL, url)
+        page = self._extract_page(url)
-        host = mobj.group('host')
-        item_id = mobj.group('id')
 
-        page = int_or_none(self._search_regex(
+        VIDEOS = '/videos'
-            r'\bpage=(\d+)', url, 'page', default=None))
 
-        entries = []
+        def download_page(base_url, num, fallback=False):
-        for page_num in (page, ) if page is not None else itertools.count(1):
+            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(
+                try:
-                    url, item_id, 'Downloading page %d' % page_num,
+                    webpage = download_page(base_url, page_num)
-                    query={'page': 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/prosiebensat1.py

@@ -34,7 +34,7 @@ class ProSiebenSat1BaseIE(InfoExtractor):
                 'ids': clip_id,
             })[0]
 
-        if video.get('is_protected') is True:
+        if not self._downloader.params.get('allow_unplayable_formats') and video.get('is_protected') is True:
             raise ExtractorError('This video is DRM protected.', expected=True)
 
         formats = []

youtube_dlc/extractor/rtbf.py

@@ -125,7 +125,7 @@ class RTBFIE(InfoExtractor):
                 })
 
         mpd_url = data.get('urlDash')
-        if not data.get('drm') and mpd_url:
+        if mpd_url and (self._downloader.params.get('allow_unplayable_formats') or not data.get('drm')):
             formats.extend(self._extract_mpd_formats(
                 mpd_url, media_id, mpd_id='dash', fatal=False))
 

youtube_dlc/extractor/rumble.py

@@ -1,6 +1,8 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
 from ..compat import compat_str
 from ..utils import (
@@ -28,6 +30,14 @@ class RumbleEmbedIE(InfoExtractor):
         'only_matching': True,
     }]
 
+    @staticmethod
+    def _extract_urls(webpage):
+        return [
+            mobj.group('url')
+            for mobj in re.finditer(
+                r'(?:<(?:script|iframe)[^>]+\bsrc=|["\']embedUrl["\']\s*:\s*)["\'](?P<url>%s)' % RumbleEmbedIE._VALID_URL,
+                webpage)]
+
     def _real_extract(self, url):
         video_id = self._match_id(url)
         video = self._download_json(

youtube_dlc/extractor/ruutu.py

@@ -200,8 +200,8 @@ class RuutuIE(InfoExtractor):
                 return node.get('value')
 
         if not formats:
-            drm = xpath_text(video_xml, './Clip/DRM', default=None)
+            if (not self._downloader.params.get('allow_unplayable_formats')
-            if drm:
+                    and xpath_text(video_xml, './Clip/DRM', default=None)):
                 raise ExtractorError('This video is DRM protected.', expected=True)
             ns_st_cds = pv('ns_st_cds')
             if ns_st_cds != 'free':

youtube_dlc/extractor/shahid.py

@@ -111,7 +111,7 @@ class ShahidIE(ShahidBaseIE):
         playout = self._call_api(
             'playout/url/' + video_id, video_id)['playout']
 
-        if playout.get('drm'):
+        if not self._downloader.params.get('allow_unplayable_formats') and playout.get('drm'):
             raise ExtractorError('This video is DRM protected.', expected=True)
 
         formats = self._extract_m3u8_formats(playout['url'], video_id, 'mp4')

youtube_dlc/extractor/sonyliv.py

@@ -75,7 +75,7 @@ class SonyLIVIE(InfoExtractor):
         video_id = self._match_id(url)
         content = self._call_api(
             '1.5', 'IN/CONTENT/VIDEOURL/VOD/' + video_id, video_id)
-        if content.get('isEncrypted'):
+        if not self._downloader.params.get('allow_unplayable_formats') and content.get('isEncrypted'):
             raise ExtractorError('This video is DRM protected.', expected=True)
         dash_url = content['videoURL']
         headers = {

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']