1
0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2026-01-13 02:11:18 +00:00

Compare commits

..

26 Commits

Author SHA1 Message Date
pukkandan
29b6000e35 Release 2021.01.29 2021-01-29 23:25:18 +05:30
pukkandan
e38df8f9fa Refactor update-version, pyinst.py and related files
* Refactor update-version
* Moved pyinst, update-version and icon into devscripts
* pyinst doesn't bump version anymore
* Merge pyinst and pyinst32. Usage: `pyinst.py [32|64]`
* Add mutagen as requirement
* Remove make_win and related files
2021-01-29 23:16:00 +05:30
pukkandan
caa15a7b57 [Audius] Add extractor (Closes #40)
Related: https://github.com/ytdl-org/youtube-dl/pull/27360
Related: https://github.com/ytdl-org/youtube-dl/issues/24216

Direct API URLs are not currently supported. See https://github.com/ytdl-org/youtube-dl/pull/27360#issuecomment-757123708 for details

Co-authored by: qulas
2021-01-29 22:30:22 +05:30
pukkandan
105b0b700e Populate "playlist_*" fields for setting playlist metadata filename
Related: #36
2021-01-29 01:57:14 +05:30
pukkandan
66c935fb16 Linter and misc cleanup
:ci skip dl
2021-01-29 01:03:32 +05:30
pukkandan
64c0d954e5 [youtube] Extract playlist description 2021-01-29 00:31:50 +05:30
pukkandan
bf330f5f29 [anvato] Workaround for anvato_token_generator import failing (Closes #35)
:ci skip dl
2021-01-28 15:57:37 +05:30
pukkandan
f6d7624f57 Partial solution for detecting existing files correctly even when extracting audio
* Does not work when audio format is 'best'
2021-01-28 15:50:03 +05:30
pukkandan
ece8a2a1b6 [embedthumbnail] Fix for missing output filename for ffmpeg call (Closes #38) 2021-01-28 15:48:33 +05:30
Bepis
8d0ea5f955 [Youtube] Improve comment API requests
co-authored by bbepis
2021-01-28 11:49:31 +05:30
pukkandan
0748b3317b Seperate import of lazy_extractors from that of normal extractors
This prevents "ModuleNotFoundError: No module named 'youtube_dl.extractor.lazy_extractors'" from appearing in the traceback

Related: https://github.com/animelover1984/youtube-dl/issues/17#issuecomment-757945024
2021-01-28 11:25:42 +05:30
pukkandan
6b591b2925 Detect existing files correctly even when there is remux/recode
:ci skip dl
2021-01-28 10:49:37 +05:30
pukkandan
179122495b [ffmpeg] Document more formats that are supported for remux/recode 2021-01-28 10:36:34 +05:30
pukkandan
02fd60d305 Write playlist description to file (Closes #36)
:ci skip dl
2021-01-28 06:25:18 +05:30
pukkandan
06167fbbd3 #31 Features from animelover1984/youtube-dl
* 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 from mp4
* [ffmpeg] Print entire stderr in verbose when there is error
* [EmbedSubtitle] Warn when embedding ass in mp4
* [avanto] Use NFLTokenGenerator if possible
2021-01-27 20:32:51 +05:30
pukkandan
4ff5e98991 More badges
:ci skip all
2021-01-27 20:16:34 +05:30
pukkandan
e4172ac903 Deprecate avconv/avprobe
All current functionality is left untouched. But don't expect any new features to work with avconv

:ci skip all
2021-01-26 23:27:32 +05:30
pukkandan
5bfa486205 Add option --parse-metadata
* The fields extracted by this can be used in `--output`
* Deprecated `--metadata-from-title`

:ci skip dl
2021-01-26 16:14:31 +05:30
pukkandan
9882064024 [movefiles] Don't give "cant find" warning when move is unnecessary 2021-01-26 15:53:32 +05:30
pukkandan
2d6921210d [postprocessor] fix write_debug when no _downloader 2021-01-26 15:53:22 +05:30
pukkandan
f137c99e9f Fix some fields not sorting correctly
bug introduced by: 63be1aab2f
2021-01-25 19:28:39 +05:30
pukkandan
6b8eb0c024 Report error message from youtube as error (Closes #33)
:ci skip dl
2021-01-25 10:26:51 +05:30
pukkandan
5b328c97d7 Changed revision number to use '.' instead of '-'
and refactor it

:ci skip dl
2021-01-25 02:25:05 +05:30
pukkandan
b5d265633d Fix wrong user config (Closes #32)
:ci skip dl
2021-01-25 01:52:47 +05:30
pukkandan
a392adf56c [version] update
:ci skip dl
2021-01-24 21:51:50 +05:30
pukkandan
0bc0a32290 Release 2021.01.24 2021-01-24 21:39:55 +05:30
45 changed files with 1410 additions and 696 deletions

View File

@@ -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 2021.01.20. If it's not, see https://github.com/pukkandan/yt-dlp on how to update. Issues with outdated version will be REJECTED.
- First of, make sure you are using the latest version of yt-dlp. Run `youtube-dlc --version` and ensure your version is 2021.01.24. 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 **2021.01.20**
- [ ] I've verified that I'm running yt-dlp version **2021.01.24**
- [ ] 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 2021.01.20
[debug] yt-dlp version 2021.01.24
[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: {}

View File

@@ -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 2021.01.20. If it's not, see https://github.com/pukkandan/yt-dlp on how to update. Issues with outdated version will be REJECTED.
- First of, make sure you are using the latest version of yt-dlp. Run `youtube-dlc --version` and ensure your version is 2021.01.24. 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 **2021.01.20**
- [ ] I've verified that I'm running yt-dlp version **2021.01.24**
- [ ] 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

View File

@@ -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 2021.01.20. If it's not, see https://github.com/pukkandan/yt-dlp on how to update. Issues with outdated version will be REJECTED.
- First of, make sure you are using the latest version of yt-dlp. Run `youtube-dlc --version` and ensure your version is 2021.01.24. 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 **2021.01.20**
- [ ] I've verified that I'm running yt-dlp version **2021.01.24**
- [ ] I've searched the bugtracker for similar site feature requests including closed ones

View File

@@ -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 2021.01.20. If it's not, see https://github.com/pukkandan/yt-dlp on how to update. Issues with outdated version will be REJECTED.
- First of, make sure you are using the latest version of yt-dlp. Run `youtube-dlc --version` and ensure your version is 2021.01.24. 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 **2021.01.20**
- [ ] I've verified that I'm running yt-dlp version **2021.01.24**
- [ ] 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 2021.01.20
[debug] yt-dlp version 2021.01.24
[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: {}

View File

@@ -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 2021.01.20. If it's not, see https://github.com/pukkandan/yt-dlp on how to update. Issues with outdated version will be REJECTED.
- First of, make sure you are using the latest version of yt-dlp. Run `youtube-dlc --version` and ensure your version is 2021.01.24. 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 **2021.01.20**
- [ ] I've verified that I'm running yt-dlp version **2021.01.24**
- [ ] I've searched the bugtracker for similar feature requests including closed ones

View File

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

87
.gitignore vendored
View File

@@ -1,35 +1,43 @@
# Python
*.pyc
*.pyo
*.class
*~
*.DS_Store
wine-py2exe/
py2exe.log
*.kate-swp
build/
dist/
zip/
tmp/
venv/
# Misc
*~
*.DS_Store
*.kate-swp
MANIFEST
README.txt
youtube-dl.1
youtube-dlc.1
youtube-dl.bash-completion
youtube-dlc.bash-completion
youtube-dl.fish
youtube-dlc.fish
youtube_dl/extractor/lazy_extractors.py
youtube_dlc/extractor/lazy_extractors.py
youtube-dl
youtube-dlc
youtube-dl.exe
youtube-dlc.exe
youtube-dl.tar.gz
youtube-dlc.tar.gz
youtube-dlc.spec
test/local_parameters.json
.coverage
cover/
updates_key.pem
*.egg-info
.tox
*.class
# Generated
README.txt
*.1
*.bash-completion
*.fish
*.exe
*.tar.gz
*.zsh
*.spec
# Binary
youtube-dl
youtube-dlc
*.exe
# Downloaded
*.srt
*.ttml
*.sbv
@@ -46,32 +54,29 @@ updates_key.pem
*.swf
*.part
*.ytdl
*.conf
*.swp
*.ogg
*.opus
# Config
*.conf
*.spec
*.exe
test/local_parameters.json
.tox
youtube-dl.zsh
youtube-dlc.zsh
# IntelliJ related files
.idea
*.iml
tmp/
venv/
# VS Code related files
.vscode
# SublimeText files
*.sublime-workspace
# Cookies
cookies
cookies.txt
# 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

View File

@@ -8,14 +8,48 @@
* Change "Merged with youtube-dl" version in Readme.md if needed
* Commit to master as `Release <version>`
* Push to origin/release - build task will now run
* Update version.py and run `make issuetemplates`
* Commit to master as `[version] update :skip ci all`
* Update version.py using devscripts\update-version.py
* Run `make issuetemplates`
* Commit to master as `[version] update :ci skip all`
* Push to origin/master
* Update changelog in /releases
-->
### 2021.01.29
* **Features from [animelover1984/youtube-dl](https://github.com/animelover1984/youtube-dl)**: Co-authored by @animelover1984 and @bbepis
* Add `--get-comments`
* [youtube] Extract comments
* [billibilli] Added BiliBiliSearchIE, BilibiliChannelIE
* [billibilli] Extract comments
* [billibilli] Better video extraction
* Write playlist data to infojson
* [FFmpegMetadata] Embed infojson inside the video
* [EmbedThumbnail] Try embedding in mp4 using ffprobe and `-disposition`
* [EmbedThumbnail] Treat mka like mkv and mov like mp4
* [EmbedThumbnail] Embed in ogg/opus
* [VideoRemuxer] Conditionally remux video
* [VideoRemuxer] Add `-movflags +faststart` when remuxing to mp4
* [ffmpeg] Print entire stderr in verbose when there is error
* [EmbedSubtitle] Warn when embedding ass in mp4
* [anvato] Use NFLTokenGenerator if possible
* **Parse additional metadata**: New option `--parse-metadata` to extract additional metadata from existing fields
* The extracted fields can be used in `--output`
* Deprecated `--metadata-from-title`
* [Audius] Add extractor
* [youtube] Extract playlist description and write it to `.description` file
* Detect existing files even when using `recode`/`remux` (`extract-audio` is partially fixed)
* Fix wrong user config from v2021.01.24
* [youtube] Report error message from youtube as error instead of warning
* [FormatSort] Fix some fields not sorting from v2021.01.24
* [postprocessor] Deprecate `avconv`/`avprobe`. All current functionality is left untouched. But don't expect any new features to work with avconv
* [postprocessor] fix `write_debug` to not throw error when there is no `_downloader`
* [movefiles] Don't give "cant find" warning when move is unnecessary
* Refactor `update-version`, `pyinst.py` and related files
* [ffmpeg] Document more formats that are supported for remux/recode
### 2021.01.24
* **Merge youtube-dl:** Upto [2021.01.24](https://github.com/ytdl-org/youtube-dl/releases/tag/2021.01.16)
* Plugin support ([documentation](https://github.com/pukkandan/yt-dlp#plugins))
@@ -30,8 +64,8 @@
* [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 compatability, but will be left undocumented
* 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

142
README.md
View File

@@ -1,9 +1,12 @@
# YT-DLP
<!-- See: https://github.com/marketplace/actions/dynamic-badges -->
[![Release Version](https://img.shields.io/endpoint?url=https://gist.githubusercontent.com/pukkandan/c69cb23c3c5b3316248e52022790aa57/raw/version.json&color=brightgreen)](https://github.com/pukkandan/yt-dlp/releases/latest)
[![Release version](https://img.shields.io/github/v/release/pukkandan/yt-dlp?color=brightgreen&label=Release)](https://github.com/pukkandan/yt-dlp/releases/latest)
[![License: Unlicense](https://img.shields.io/badge/License-Unlicense-blue.svg)](LICENSE)
[![CI Status](https://github.com/pukkandan/yt-dlp/workflows/Core%20Tests/badge.svg?branch=master)](https://github.com/pukkandan/yt-dlp/actions)
[![CI Status](https://github.com/pukkandan/yt-dlp/workflows/Core%20Tests/badge.svg?branch=master)](https://github.com/pukkandan/yt-dlp/actions)
[![Commits](https://img.shields.io/github/commit-activity/m/pukkandan/yt-dlp?label=commits)](https://github.com/pukkandan/yt-dlp/commits)
[![Last Commit](https://img.shields.io/github/last-commit/pukkandan/yt-dlp/master)](https://github.com/pukkandan/yt-dlp/commits)
[![Downloads](https://img.shields.io/github/downloads/pukkandan/yt-dlp/total)](https://github.com/pukkandan/yt-dlp/releases/latest)
[![PyPi Downloads](https://img.shields.io/pypi/dm/yt-dlp?label=PyPi)](https://pypi.org/project/yt-dlp)
A command-line program to download videos from youtube.com and many other [video platforms](docs/supportedsites.md)
@@ -53,25 +56,30 @@ The major new features from the latest release of [blackjack4494/yt-dlc](https:/
* **Merged with youtube-dl v2021.01.24.1**: You get all the latest features and patches of [youtube-dl](https://github.com/ytdl-org/youtube-dl) in addition to all the features of [youtube-dlc](https://github.com/blackjack4494/yt-dlc)
* **Merged with animelover1984/youtube-dl**: You get most of the features and improvements from [animelover1984/youtube-dl](https://github.com/animelover1984/youtube-dl) including `--get-comments`, `BiliBiliSearch`, `BilibiliChannel`, Embedding thumbnail in mp4/ogg/opus, Playlist infojson etc. Note that the NicoNico improvements are not available. See [#31](https://github.com/pukkandan/yt-dlp/pull/31) for details.
* **Youtube improvements**:
* All Youtube Feeds (`:ytfav`, `:ytwatchlater`, `:ytsubs`, `:ythistory`, `:ytrec`) works correctly and support downloading multiple pages of content
* Youtube search works correctly (`ytsearch:`, `ytsearchdate:`) along with Search URLs
* Redirect channel's home URL automatically to `/video` to preserve the old behaviour
* **New extractors**: AnimeLab, Philo MSO, Rcs, Gedi, bitwave.tv, mildom
* **New extractors**: AnimeLab, Philo MSO, Rcs, Gedi, bitwave.tv, mildom, audius
* **Fixed extractors**: archive.org, roosterteeth.com, skyit, instagram, itv, SouthparkDe, spreaker, Vlive, tiktok, akamai, ina
* **Plugin support**: Extractors can be loaded from an external file. See [plugins](#plugins) for details
* **Multiple paths**: You can give different paths for different types of files. You can also set a temporary path where intermediary files are downloaded to. See [--paths](#:~:text=-P,%20--paths%20TYPE:PATH) for details
* **Multiple paths**: You can give different 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**: `--list-formats-as-table`, `--write-link`, `--force-download-archive`, `--force-overwrites`, `--break-on-reject` etc
* **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`, `%(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
@@ -83,7 +91,7 @@ If you are coming from [youtube-dl](https://github.com/ytdl-org/youtube-dl), the
# INSTALLATION
You can install yt-dlp using one of the following methods:
* Use [PyPI package](https://pypi.org/project/yt-dlp/): `python -m pip install --upgrade yt-dlp`
* Use [PyPI package](https://pypi.org/project/yt-dlp): `python -m pip install --upgrade yt-dlp`
* Download the binary from the [latest release](https://github.com/pukkandan/yt-dlp/releases/latest)
* Use pip+git: `python -m pip install --upgrade git+https://github.com/pukkandan/yt-dlp.git@release`
* Install master branch: `python -m pip install --upgrade git+https://github.com/pukkandan/yt-dlp`
@@ -94,16 +102,15 @@ You can install yt-dlp using one of the following methods:
### COMPILE
**For Windows**:
To build the Windows executable yourself (without version info!)
To build the Windows executable, you must have pyinstaller (and optionally mutagen for embedding thumbnail in opus/ogg files)
python -m pip install --upgrade pyinstaller mutagen
For the 64bit version, run `py devscripts\pyinst.py 64` using 64bit python3. Similarly, to install 32bit version, run `py devscripts\pyinst.py 32` using 32bit python (preferably 3)
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
@@ -112,6 +119,7 @@ Then simply type this
make
**Note**: In either platform, `devscripts\update-version.py` can be used to automatically update the version number
# DESCRIPTION
**youtube-dlc** is a command-line program to download videos from youtube.com many other [video platforms](docs/supportedsites.md). It requires the Python interpreter, version 2.6, 2.7, or 3.2+, and it is not platform specific. It should work on your Unix box, on Windows or on macOS. It is released to the public domain, which means you can modify it, redistribute it or use it however you like.
@@ -315,8 +323,8 @@ Then simply type this
--downloader-args NAME:ARGS Give these arguments to the external
downloader. Specify the downloader name and
the arguments separated by a colon ":". You
can use this option multiple times (Alias:
--external-downloader-args)
can use this option multiple times
(Alias: --external-downloader-args)
## Filesystem Options:
-a, --batch-file FILE File containing URLs to download ('-' for
@@ -370,6 +378,8 @@ Then simply type this
--write-annotations Write video annotations to a
.annotations.xml file
--no-write-annotations Do not write video annotations (default)
--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)
@@ -504,17 +514,17 @@ Then simply type this
--list-formats-old Present the output of -F in the old form
(Alias: --no-list-formats-as-table)
--youtube-include-dash-manifest Download the DASH manifests and related
data on YouTube videos (default) (Alias:
--no-youtube-skip-dash-manifest)
data on YouTube videos (default)
(Alias: --no-youtube-skip-dash-manifest)
--youtube-skip-dash-manifest Do not download the DASH manifests and
related data on YouTube videos (Alias:
--no-youtube-include-dash-manifest)
related data on YouTube videos
(Alias: --no-youtube-include-dash-manifest)
--youtube-include-hls-manifest Download the HLS manifests and related data
on YouTube videos (default) (Alias:
--no-youtube-skip-hls-manifest)
on YouTube videos (default)
(Alias: --no-youtube-skip-hls-manifest)
--youtube-skip-hls-manifest Do not download the HLS manifests and
related data on YouTube videos (Alias:
--no-youtube-include-hls-manifest)
related data on YouTube videos
(Alias: --no-youtube-include-hls-manifest)
--merge-output-format FORMAT If a merge is required (e.g.
bestvideo+bestaudio), output to given
container format. One of mkv, mp4, ogg,
@@ -558,23 +568,26 @@ Then simply type this
## Post-Processing Options:
-x, --extract-audio Convert video files to audio-only files
(requires ffmpeg or avconv and ffprobe or
avprobe)
(requires ffmpeg and ffprobe)
--audio-format FORMAT Specify audio format: "best", "aac",
"flac", "mp3", "m4a", "opus", "vorbis", or
"wav"; "best" by default; No effect without
-x
--audio-quality QUALITY Specify ffmpeg/avconv audio quality, insert
a value between 0 (better) and 9 (worse)
for VBR or a specific bitrate like 128K
--audio-quality QUALITY Specify ffmpeg audio quality, insert a
value between 0 (better) and 9 (worse) for
VBR or a specific bitrate like 128K
(default 5)
--remux-video FORMAT Remux the video into another container if
necessary (currently supported: mp4|mkv).
If target container does not support the
video/audio codec, remuxing will fail
necessary (currently supported: mp4|mkv|flv
|webm|mov|avi|mp3|mka|m4a|ogg|opus). If
target container does not support the
video/audio codec, remuxing will fail. You
can specify multiple rules; eg.
"aac>m4a/mov>mp4/mkv" will remux aac to
m4a, mov to mp4 and anything else to mkv.
--recode-video FORMAT Re-encode the video into another format if
re-encoding is necessary (currently
supported: mp4|flv|ogg|webm|mkv|avi)
re-encoding is necessary. The supported
formats are the same as --remux-video
--postprocessor-args NAME:ARGS Give these arguments to the postprocessors.
Specify the postprocessor/executable name
and the arguments separated by a colon ":"
@@ -586,15 +599,14 @@ Then simply type this
FixupStretched, FixupM4a, FixupM3u8,
SubtitlesConvertor and EmbedThumbnail. The
supported executables are: SponSkrub,
FFmpeg, FFprobe, avconf, avprobe and
AtomicParsley. You can use this option
multiple times to give different arguments
to different postprocessors. You can also
specify "PP+EXE:ARGS" to give the arguments
to the specified executable only when being
used by the specified postprocessor. You
can use this option multiple times (Alias:
--ppa)
FFmpeg, FFprobe, and AtomicParsley. You can
use this option multiple times to give
different arguments to different
postprocessors. You can also specify
"PP+EXE:ARGS" to give the arguments to the
specified executable only when being used
by the specified postprocessor. You can use
this option multiple times (Alias: --ppa)
-k, --keep-video Keep the intermediate video file on disk
after post-processing
--no-keep-video Delete the intermediate video file after
@@ -608,16 +620,20 @@ Then simply type this
--no-embed-thumbnail Do not embed thumbnail (default)
--add-metadata Write metadata to the video file
--no-add-metadata Do not write metadata (default)
--metadata-from-title FORMAT Parse additional metadata like song title /
artist from the video title. The format
syntax is the same as --output. Regular
expression with named capture groups may
--parse-metadata FIELD:FORMAT Parse additional metadata like title/artist
from other fields. Give field name to
extract data from, and format of the field
seperated by a ":". Either regular
expression with named capture groups or a
similar syntax to the output template can
also be used. The parsed parameters replace
existing values. Example: --metadata-from-
title "%(artist)s - %(title)s" matches a
any existing values and can be use in
output templateThis option can be used
multiple times. Example: --parse-metadata
"title:%(artist)s - %(title)s" matches a
title like "Coldplay - Paradise". Example
(regex): --metadata-from-title
"(?P<artist>.+?) - (?P<title>.+)"
(regex): --parse-metadata
"description:Artist - (?P<artist>.+?)"
--xattrs Write metadata to the video file's xattrs
(using dublin core and xdg standards)
--fixup POLICY Automatically correct known faults of the
@@ -625,15 +641,9 @@ Then simply type this
emit a warning), detect_or_warn (the
default; fix file if we can, warn
otherwise)
--prefer-avconv Prefer avconv over ffmpeg for running the
postprocessors (Alias: --no-prefer-ffmpeg)
--prefer-ffmpeg Prefer ffmpeg over avconv for running the
postprocessors (default)
(Alias: --no-prefer-avconv)
--ffmpeg-location PATH Location of the ffmpeg/avconv binary;
either the path to the binary or its
containing directory
(Alias: --avconv-location)
--ffmpeg-location PATH Location of the ffmpeg binary; either the
path to the binary or its containing
directory
--exec CMD Execute a command on the file after
downloading and post-processing, similar to
find's -exec syntax. Example: --exec 'adb
@@ -766,7 +776,7 @@ 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
@@ -871,7 +881,7 @@ $ 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.
@@ -902,7 +912,7 @@ 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
@@ -1096,7 +1106,7 @@ $ youtube-dlc -S '+res:480,codec,br'
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`)
**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)

View File

Before

Width:  |  Height:  |  Size: 4.2 KiB

After

Width:  |  Height:  |  Size: 4.2 KiB

69
devscripts/pyinst.py Normal file
View File

@@ -0,0 +1,69 @@
from __future__ import unicode_literals
import sys
from PyInstaller.utils.win32.versioninfo import (
VarStruct, VarFileInfo, StringStruct, StringTable,
StringFileInfo, FixedFileInfo, VSVersionInfo, SetVersion,
)
import PyInstaller.__main__
assert len(sys.argv) > 1 and sys.argv[1] in ("32", "64")
_x86 = "_x86" if sys.argv[1] == "32" else ""
FILE_DESCRIPTION = 'Media Downloader%s' % (" (32 Bit)" if _x86 else '')
SHORT_URLS = {"32": "git.io/JUGsM", "64": "git.io/JLh7K"}
exec(compile(open('youtube_dlc/version.py').read(), 'youtube_dlc/version.py', 'exec'))
VERSION = locals()['__version__']
VERSION_LIST = VERSION.replace('-', '.').split('.')
VERSION_LIST = list(map(int, VERSION_LIST)) + [0] * (4 - len(VERSION_LIST))
print('Version: %s%s' % (VERSION, _x86))
print('Remember to update the version using devscipts\\update-version.py')
VERSION_FILE = VSVersionInfo(
ffi=FixedFileInfo(
filevers=VERSION_LIST,
prodvers=VERSION_LIST,
mask=0x3F,
flags=0x0,
OS=0x4,
fileType=0x1,
subtype=0x0,
date=(0, 0),
),
kids=[
StringFileInfo([
StringTable(
"040904B0", [
StringStruct("Comments", "Youtube-dlc%s Command Line Interface." % _x86),
StringStruct("CompanyName", "pukkandan@gmail.com"),
StringStruct("FileDescription", FILE_DESCRIPTION),
StringStruct("FileVersion", VERSION),
StringStruct("InternalName", "youtube-dlc%s" % _x86),
StringStruct(
"LegalCopyright",
"pukkandan@gmail.com | UNLICENSE",
),
StringStruct("OriginalFilename", "youtube-dlc%s.exe" % _x86),
StringStruct("ProductName", "Youtube-dlc%s" % _x86),
StringStruct("ProductVersion", "%s%s | %s" % (VERSION, _x86, SHORT_URLS[sys.argv[1]])),
])]),
VarFileInfo([VarStruct("Translation", [0, 1200])])
]
)
PyInstaller.__main__.run([
'--name=youtube-dlc%s' % _x86,
'--onefile',
'--icon=devscripts/cloud.ico',
'--exclude-module=youtube_dl',
'--exclude-module=test',
'--exclude-module=ytdlp_plugins',
'--hidden-import=mutagen',
'youtube_dlc/__main__.py',
])
SetVersion('dist/youtube-dlc%s.exe' % _x86, VERSION_FILE)

View File

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

View File

@@ -80,6 +80,8 @@
- **AudioBoom**
- **audiomack**
- **audiomack:album**
- **Audius**
- **audius:playlist**
- **AWAAN**
- **awaan:live**
- **awaan:season**
@@ -112,7 +114,9 @@
- **BiliBili**
- **BilibiliAudio**
- **BilibiliAudioAlbum**
- **BilibiliChannel**
- **BiliBiliPlayer**
- **BiliBiliSearch**: Bilibili video search, "bilisearch" keyword
- **BioBioChileTV**
- **Biography**
- **BIQLE**

View File

@@ -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 --exclude-module ytdlp_plugins

View File

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

View File

@@ -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)

1
requirements.txt Normal file
View File

@@ -0,0 +1 @@
mutagen

View File

@@ -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()

View File

@@ -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)]))

View File

@@ -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

View File

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

View File

@@ -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]+)')

View File

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

View File

@@ -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])])
]
)

View File

@@ -202,6 +202,8 @@ class YoutubeDL(object):
logtostderr: Log messages to stderr instead of stdout.
writedescription: Write the video description to a .description file
writeinfojson: Write the video description to a .info.json file
writecomments: Extract video comments. This will not be written to disk
unless writeinfojson is also given
writeannotations: Write the video annotations to a .annotations.xml file
writethumbnail: Write the thumbnail image to a file
write_all_thumbnails: Write all thumbnail formats to files
@@ -294,6 +296,9 @@ class YoutubeDL(object):
Progress hooks are guaranteed to be called at least once
(with status "finished") if the download is successful.
merge_output_format: Extension to use when merging formats.
final_ext: Expected final extension; used to detect when the file was
already downloaded and converted. "merge_output_format" is
replaced by this extension when given
fixup: Automatically correct known faults of the file.
One of:
- "never": do nothing
@@ -347,7 +352,7 @@ class YoutubeDL(object):
The following options are used by the post processors:
prefer_ffmpeg: If False, use avconv instead of ffmpeg if both are available,
otherwise prefer ffmpeg.
otherwise prefer ffmpeg. (avconv support is deprecated)
ffmpeg_location: Location of the ffmpeg/avconv binary; either the path
to the binary or its containing directory.
postprocessor_args: A dictionary of postprocessor/executable keys (in lower case)
@@ -375,8 +380,7 @@ class YoutubeDL(object):
params = None
_ies = []
_pps = []
_pps_end = []
_pps = {'beforedl': [], 'aftermove': [], 'normal': []}
__prepare_filename_warned = False
_download_retcode = None
_num_downloads = None
@@ -390,8 +394,7 @@ class YoutubeDL(object):
params = {}
self._ies = []
self._ies_instances = {}
self._pps = []
self._pps_end = []
self._pps = {'beforedl': [], 'aftermove': [], 'normal': []}
self.__prepare_filename_warned = False
self._post_hooks = []
self._progress_hooks = []
@@ -438,6 +441,11 @@ class YoutubeDL(object):
if self.params.get('geo_verification_proxy') is None:
self.params['geo_verification_proxy'] = self.params['cn_verification_proxy']
if self.params.get('final_ext'):
if self.params.get('merge_output_format'):
self.report_warning('--merge-output-format will be ignored since --remux-video or --recode-video is given')
self.params['merge_output_format'] = self.params['final_ext']
check_deprecated('autonumber_size', '--autonumber-size', 'output template with %(autonumber)0Nd, where N in the number of digits')
check_deprecated('autonumber', '--auto-number', '-o "%(autonumber)s-%(title)s.%(ext)s"')
check_deprecated('usetitle', '--title', '-o "%(title)s-%(id)s.%(ext)s"')
@@ -494,11 +502,13 @@ class YoutubeDL(object):
pp_class = get_postprocessor(pp_def_raw['key'])
pp_def = dict(pp_def_raw)
del pp_def['key']
after_move = pp_def.get('_after_move', False)
if '_after_move' in pp_def:
del pp_def['_after_move']
if 'when' in pp_def:
when = pp_def['when']
del pp_def['when']
else:
when = 'normal'
pp = pp_class(self, **compat_kwargs(pp_def))
self.add_post_processor(pp, after_move=after_move)
self.add_post_processor(pp, when=when)
for ph in self.params.get('post_hooks', []):
self.add_post_hook(ph)
@@ -550,12 +560,9 @@ class YoutubeDL(object):
for ie in gen_extractor_classes():
self.add_info_extractor(ie)
def add_post_processor(self, pp, after_move=False):
def add_post_processor(self, pp, when='normal'):
"""Add a PostProcessor object to the end of the chain."""
if after_move:
self._pps_end.append(pp)
else:
self._pps.append(pp)
self._pps[when].append(pp)
pp.set_downloader(self)
def add_post_hook(self, ph):
@@ -933,9 +940,7 @@ class YoutubeDL(object):
self.to_screen("[%s] %s: has already been recorded in archive" % (
ie_key, temp_id))
break
return self.__extract_info(url, ie, download, extra_info, process, info_dict)
else:
self.report_error('no suitable InfoExtractor for URL %s' % url)
@@ -1103,6 +1108,54 @@ class YoutubeDL(object):
# We process each entry in the playlist
playlist = ie_result.get('title') or ie_result.get('id')
self.to_screen('[download] Downloading playlist: %s' % playlist)
ie_copy = {
'playlist': playlist,
'playlist_id': ie_result.get('id'),
'playlist_title': ie_result.get('title'),
'playlist_uploader': ie_result.get('uploader'),
'playlist_uploader_id': ie_result.get('uploader_id'),
'playlist_index': 0
}
ie_copy.update(dict(ie_result))
def ensure_dir_exists(path):
return make_dir(path, self.report_error)
if self.params.get('writeinfojson', False):
infofn = replace_extension(
self.prepare_filepath(self.prepare_filename(ie_copy), 'infojson'),
'info.json', ie_result.get('ext'))
if not ensure_dir_exists(encodeFilename(infofn)):
return
if self.params.get('overwrites', True) and os.path.exists(encodeFilename(infofn)):
self.to_screen('[info] Playlist metadata is already present')
else:
self.to_screen('[info] Writing playlist metadata as JSON to: ' + infofn)
playlist_info = dict(ie_result)
playlist_info.pop('entries')
try:
write_json_file(self.filter_requested_info(playlist_info), infofn)
except (OSError, IOError):
self.report_error('Cannot write playlist metadata to JSON file ' + infofn)
if self.params.get('writedescription', False):
descfn = replace_extension(
self.prepare_filepath(self.prepare_filename(ie_copy), 'description'),
'description', ie_result.get('ext'))
if not ensure_dir_exists(encodeFilename(descfn)):
return
if not self.params.get('overwrites', True) and os.path.exists(encodeFilename(descfn)):
self.to_screen('[info] Playlist description is already present')
elif ie_result.get('description') is None:
self.report_warning('There\'s no playlist description to write.')
else:
try:
self.to_screen('[info] Writing playlist description to: ' + descfn)
with io.open(encodeFilename(descfn), 'w', encoding='utf-8') as descfile:
descfile.write(ie_result['description'])
except (OSError, IOError):
self.report_error('Cannot write playlist description file ' + descfn)
return
playlist_results = []
@@ -1948,6 +2001,8 @@ class YoutubeDL(object):
self._num_downloads += 1
info_dict = self.pre_process(info_dict)
filename = self.prepare_filename(info_dict, warn=True)
info_dict['_filename'] = full_filename = self.prepare_filepath(filename)
temp_filename = self.prepare_filepath(filename, 'temp')
@@ -2098,14 +2153,15 @@ class YoutubeDL(object):
if not ensure_dir_exists(encodeFilename(infofn)):
return
if not self.params.get('overwrites', True) and os.path.exists(encodeFilename(infofn)):
self.to_screen('[info] Video description metadata is already present')
self.to_screen('[info] Video metadata is already present')
else:
self.to_screen('[info] Writing video description metadata as JSON to: ' + infofn)
self.to_screen('[info] Writing video metadata as JSON to: ' + infofn)
try:
write_json_file(self.filter_requested_info(info_dict), infofn)
except (OSError, IOError):
self.report_error('Cannot write metadata to JSON file ' + infofn)
self.report_error('Cannot write video metadata to JSON file ' + infofn)
return
info_dict['__infojson_filepath'] = infofn
thumbdir = os.path.dirname(self.prepare_filepath(filename, 'thumbnail'))
for thumbfn in self._write_thumbnails(info_dict, temp_filename):
@@ -2165,22 +2221,27 @@ class YoutubeDL(object):
if not self.params.get('skip_download', False):
try:
def existing_file(filename, temp_filename):
file_exists = os.path.exists(encodeFilename(filename))
tempfile_exists = (
False if temp_filename == filename
else os.path.exists(encodeFilename(temp_filename)))
if not self.params.get('overwrites', False) and (file_exists or tempfile_exists):
existing_filename = temp_filename if tempfile_exists else filename
self.to_screen('[download] %s has already been downloaded and merged' % existing_filename)
return existing_filename
if tempfile_exists:
self.report_file_delete(temp_filename)
os.remove(encodeFilename(temp_filename))
if file_exists:
self.report_file_delete(filename)
os.remove(encodeFilename(filename))
return None
def existing_file(*filepaths):
ext = info_dict.get('ext')
final_ext = self.params.get('final_ext', ext)
existing_files = []
for file in orderedSet(filepaths):
if final_ext != ext:
converted = replace_extension(file, final_ext, ext)
if os.path.exists(encodeFilename(converted)):
existing_files.append(converted)
if os.path.exists(encodeFilename(file)):
existing_files.append(file)
if not existing_files or self.params.get('overwrites', False):
for file in orderedSet(existing_files):
self.report_file_delete(file)
os.remove(encodeFilename(file))
return None
self.report_file_already_downloaded(existing_files[0])
info_dict['ext'] = os.path.splitext(existing_files[0])[1][1:]
return existing_files[0]
success = True
if info_dict.get('requested_formats') is not None:
@@ -2189,7 +2250,7 @@ class YoutubeDL(object):
if not merger.available:
postprocessors = []
self.report_warning('You have requested multiple '
'formats but ffmpeg or avconv are not installed.'
'formats but ffmpeg is not installed.'
' The formats won\'t be merged.')
else:
postprocessors = [merger]
@@ -2273,7 +2334,7 @@ class YoutubeDL(object):
if fixup_policy is None:
fixup_policy = 'detect_or_warn'
INSTALL_FFMPEG_MESSAGE = 'Install ffmpeg or avconv to fix this automatically.'
INSTALL_FFMPEG_MESSAGE = 'Install ffmpeg to fix this automatically.'
stretched_ratio = info_dict.get('stretched_ratio')
if stretched_ratio is not None and stretched_ratio != 1:
@@ -2292,7 +2353,8 @@ class YoutubeDL(object):
assert fixup_policy in ('ignore', 'never')
if (info_dict.get('requested_formats') is None
and info_dict.get('container') == 'm4a_dash'):
and info_dict.get('container') == 'm4a_dash'
and info_dict.get('ext') == 'm4a'):
if fixup_policy == 'warn':
self.report_warning(
'%s: writing DASH m4a. '
@@ -2400,41 +2462,45 @@ class YoutubeDL(object):
(k, v) for k, v in info_dict.items()
if k not in ['requested_formats', 'requested_subtitles'])
def run_pp(self, pp, infodict, files_to_move={}):
files_to_delete = []
try:
files_to_delete, infodict = pp.run(infodict)
except PostProcessingError as e:
self.report_error(e.msg)
if not files_to_delete:
return files_to_move, infodict
if self.params.get('keepvideo', False):
for f in files_to_delete:
files_to_move.setdefault(f, '')
else:
for old_filename in set(files_to_delete):
self.to_screen('Deleting original file %s (pass -k to keep)' % old_filename)
try:
os.remove(encodeFilename(old_filename))
except (IOError, OSError):
self.report_warning('Unable to remove downloaded original file')
if old_filename in files_to_move:
del files_to_move[old_filename]
return files_to_move, infodict
def pre_process(self, ie_info):
info = dict(ie_info)
for pp in self._pps['beforedl']:
info = self.run_pp(pp, info)[1]
return info
def post_process(self, filename, ie_info, files_to_move={}):
"""Run all the postprocessors on the given file."""
info = dict(ie_info)
info['filepath'] = filename
def run_pp(pp):
files_to_delete = []
infodict = info
try:
files_to_delete, infodict = pp.run(infodict)
except PostProcessingError as e:
self.report_error(e.msg)
if not files_to_delete:
return infodict
if self.params.get('keepvideo', False):
for f in files_to_delete:
files_to_move.setdefault(f, '')
else:
for old_filename in set(files_to_delete):
self.to_screen('Deleting original file %s (pass -k to keep)' % old_filename)
try:
os.remove(encodeFilename(old_filename))
except (IOError, OSError):
self.report_warning('Unable to remove downloaded original file')
if old_filename in files_to_move:
del files_to_move[old_filename]
return infodict
for pp in ie_info.get('__postprocessors', []) + self._pps:
info = run_pp(pp)
info = run_pp(MoveFilesAfterDownloadPP(self, files_to_move))
files_to_move = {}
for pp in self._pps_end:
info = run_pp(pp)
for pp in ie_info.get('__postprocessors', []) + self._pps['normal']:
files_to_move, info = self.run_pp(pp, info, files_to_move)
info = self.run_pp(MoveFilesAfterDownloadPP(self, files_to_move), info, files_to_move)[1]
for pp in self._pps['aftermove']:
files_to_move, info = self.run_pp(pp, info, {})
def _make_archive_id(self, info_dict):
video_id = info_dict.get('id')

View File

@@ -15,6 +15,7 @@ import sys
from .options import (
parseOpts,
_remux_formats,
)
from .compat import (
compat_getpass,
@@ -45,6 +46,7 @@ from .downloader import (
from .extractor import gen_extractors, list_extractors
from .extractor.common import InfoExtractor
from .extractor.adobepass import MSO_INFO
from .postprocessor.metadatafromfield import MetadataFromFieldPP
from .YoutubeDL import YoutubeDL
@@ -208,12 +210,15 @@ def _real_main(argv=None):
opts.audioquality = opts.audioquality.strip('k').strip('K')
if not opts.audioquality.isdigit():
parser.error('invalid audio quality specified')
if opts.remuxvideo is not None:
if opts.remuxvideo not in ['mp4', 'mkv']:
parser.error('invalid video container format specified')
if opts.recodevideo is not None:
if opts.recodevideo not in ['mp4', 'flv', 'webm', 'ogg', 'mkv', 'avi']:
if opts.recodevideo not in _remux_formats:
parser.error('invalid video recode format specified')
if opts.remuxvideo and opts.recodevideo:
opts.remuxvideo = None
write_string('WARNING: --remux-video is ignored since --recode-video was given\n', out=sys.stderr)
if opts.remuxvideo is not None:
if opts.remuxvideo not in _remux_formats:
parser.error('invalid video remux format specified')
if opts.convertsubtitles is not None:
if opts.convertsubtitles not in ['srt', 'vtt', 'ass', 'lrc']:
parser.error('invalid subtitle format specified')
@@ -249,16 +254,25 @@ def _real_main(argv=None):
if re.match(InfoExtractor.FormatSort.regex, f) is None:
parser.error('invalid format sort string "%s" specified' % f)
if opts.metafromfield is None:
opts.metafromfield = []
if opts.metafromtitle is not None:
opts.metafromfield.append('title:%s' % opts.metafromtitle)
for f in opts.metafromfield:
if re.match(MetadataFromFieldPP.regex, f) is None:
parser.error('invalid format string "%s" specified for --parse-metadata' % f)
any_getting = opts.geturl or opts.gettitle or opts.getid or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat or opts.getduration or opts.dumpjson or opts.dump_single_json
any_printing = opts.print_json
download_archive_fn = expand_path(opts.download_archive) if opts.download_archive is not None else opts.download_archive
# PostProcessors
postprocessors = []
if opts.metafromtitle:
if opts.metafromfield:
postprocessors.append({
'key': 'MetadataFromTitle',
'titleformat': opts.metafromtitle
'key': 'MetadataFromField',
'formats': opts.metafromfield,
'when': 'beforedl'
})
if opts.extractaudio:
postprocessors.append({
@@ -324,7 +338,7 @@ def _real_main(argv=None):
postprocessors.append({
'key': 'ExecAfterDownload',
'exec_cmd': opts.exec_cmd,
'_after_move': True
'when': 'aftermove'
})
_args_compat_warning = 'WARNING: %s given without specifying name. The arguments will be given to all %s\n'
@@ -336,6 +350,8 @@ def _real_main(argv=None):
opts.postprocessor_args.setdefault('sponskrub', [])
opts.postprocessor_args['default'] = opts.postprocessor_args['default-compat']
audio_ext = opts.audioformat if (opts.extractaudio and opts.audioformat != 'best') else None
match_filter = (
None if opts.match_filter is None
else match_filter_func(opts.match_filter))
@@ -403,7 +419,8 @@ def _real_main(argv=None):
'updatetime': opts.updatetime,
'writedescription': opts.writedescription,
'writeannotations': opts.writeannotations,
'writeinfojson': opts.writeinfojson,
'writeinfojson': opts.writeinfojson or opts.getcomments,
'getcomments': opts.getcomments,
'writethumbnail': opts.writethumbnail,
'write_all_thumbnails': opts.write_all_thumbnails,
'writelink': opts.writelink,
@@ -454,6 +471,7 @@ def _real_main(argv=None):
'extract_flat': opts.extract_flat,
'mark_watched': opts.mark_watched,
'merge_output_format': opts.merge_output_format,
'final_ext': opts.recodevideo or opts.remuxvideo or audio_ext,
'postprocessors': postprocessors,
'fixup': opts.fixup,
'source_address': opts.source_address,

View File

@@ -233,7 +233,7 @@ class FFmpegFD(ExternalFD):
url = info_dict['url']
ffpp = FFmpegPostProcessor(downloader=self)
if not ffpp.available:
self.report_error('m3u8 download detected but ffmpeg or avconv could not be found. Please install one.')
self.report_error('m3u8 download detected but ffmpeg could not be found. Please install one.')
return False
ffpp.check_version()

View File

@@ -7,9 +7,10 @@ try:
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())

View File

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

View File

@@ -0,0 +1,224 @@
# 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+))'''
_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)
uploader, title, track_id = mobj.groups()
if track_id is None:
url = self._prepare_url(url, title)
track_data = self._resolve_url(url, title)
else: # API link
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 AudiusPlaylistIE(AudiusBaseIE):
_VALID_URL = r'https?://(?:www\.)?audius\.co/(?P<uploader>[\w\d-]+)/(?:album|playlist)/(?P<title>\S+)'
IE_NAME = 'audius:playlist'
_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(
'%s%s/tracks/%s' % (self._API_BASE, self._API_V, track_id),
ie=AudiusIE.ie_key(), video_id=track_id))
return entries
def _real_extract(self, url):
self._select_api_base()
mobj = re.match(self._VALID_URL, url)
uploader, title = mobj.groups()
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'))

View File

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

View File

@@ -1375,7 +1375,7 @@ class InfoExtractor(object):
'order': ['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']},
'proto': {'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']},
'vext': {'type': 'ordered', 'field': 'video_ext',
'order': ('mp4', 'webm', '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},
'ie_pref': {'priority': True, 'type': 'extractor'},
'ie_pref': {'priority': True, 'type': 'extractor', 'field': 'extractor_preference'},
'hasvid': {'priority': True, 'field': 'vcodec', 'type': 'boolean', 'not_in_list': ('none',)},
'hasaud': {'field': 'acodec', 'type': 'boolean', 'not_in_list': ('none',)},
'lang': {'priority': True, 'convert': 'ignore'},
'lang': {'priority': True, 'convert': 'ignore', 'field': 'language_preference'},
'quality': {'priority': True, 'convert': 'float_none'},
'filesize': {'convert': 'bytes'},
'fs_approx': {'convert': 'bytes'},
'id': {'convert': 'string'},
'fs_approx': {'convert': 'bytes', 'field': 'filesize_approx'},
'id': {'convert': 'string', 'field': 'format_id'},
'height': {'convert': 'float_none'},
'width': {'convert': 'float_none'},
'fps': {'convert': 'float_none'},
@@ -1399,7 +1399,7 @@ class InfoExtractor(object):
'vbr': {'convert': 'float_none'},
'abr': {'convert': 'float_none'},
'asr': {'convert': 'float_none'},
'source': {'convert': 'ignore'},
'source': {'convert': 'ignore', 'field': 'source_preference'},
'codec': {'type': 'combined', 'field': ('vcodec', 'acodec')},
'br': {'type': 'combined', 'field': ('tbr', 'vbr', 'abr'), 'same_limit': True},

View File

@@ -90,6 +90,7 @@ from .atvat import ATVAtIE
from .audimedia import AudiMediaIE
from .audioboom import AudioBoomIE
from .audiomack import AudiomackIE, AudiomackAlbumIE
from .audius import AudiusIE, AudiusPlaylistIE
from .awaan import (
AWAANIE,
AWAANVideoIE,
@@ -122,10 +123,12 @@ 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 (

View File

@@ -2424,9 +2424,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
default=None
))
# annotations
video_annotations = None
if self._downloader.params.get('writeannotations', False):
# get xsrf for annotations or comments
get_annotations = self._downloader.params.get('writeannotations', False)
get_comments = self._downloader.params.get('getcomments', False)
if get_annotations or get_comments:
xsrf_token = None
ytcfg = self._extract_ytcfg(video_id, video_webpage)
if ytcfg:
@@ -2435,6 +2436,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
xsrf_token = self._search_regex(
r'([\'"])XSRF_TOKEN\1\s*:\s*([\'"])(?P<xsrf_token>(?:(?!\2).)+)\2',
video_webpage, 'xsrf token', group='xsrf_token', fatal=False)
# annotations
video_annotations = None
if get_annotations:
invideo_url = try_get(
player_response, lambda x: x['annotations'][0]['playerAnnotationsUrlsRenderer']['invideoUrl'], compat_str)
if xsrf_token and invideo_url:
@@ -2454,6 +2459,149 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
chapters = self._extract_chapters(video_webpage, description_original, video_id, video_duration)
# Get comments
# TODO: Refactor and move to seperate function
if get_comments:
expected_video_comment_count = 0
video_comments = []
def find_value(html, key, num_chars=2, separator='"'):
pos_begin = html.find(key) + len(key) + num_chars
pos_end = html.find(separator, pos_begin)
return html[pos_begin: pos_end]
def search_dict(partial, key):
if isinstance(partial, dict):
for k, v in partial.items():
if k == key:
yield v
else:
for o in search_dict(v, key):
yield o
elif isinstance(partial, list):
for i in partial:
for o in search_dict(i, key):
yield o
try:
ncd = next(search_dict(yt_initial_data, 'nextContinuationData'))
continuations = [ncd['continuation']]
# Handle videos where comments have been disabled entirely
except StopIteration:
continuations = []
def get_continuation(continuation, session_token, replies=False):
query = {
'pbj': 1,
'ctoken': continuation,
}
if replies:
query['action_get_comment_replies'] = 1
else:
query['action_get_comments'] = 1
while True:
content, handle = self._download_webpage_handle(
'https://www.youtube.com/comment_service_ajax',
video_id,
note=False,
expected_status=[413],
data=urlencode_postdata({
'session_token': session_token
}),
query=query,
headers={
'Accept': '*/*',
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:76.0) Gecko/20100101 Firefox/76.0',
'X-YouTube-Client-Name': '1',
'X-YouTube-Client-Version': '2.20201202.06.01'
}
)
response_code = handle.getcode()
if (response_code == 200):
return self._parse_json(content, video_id)
if (response_code == 413):
return None
raise ExtractorError('Unexpected HTTP error code: %s' % response_code)
first_continuation = True
while continuations:
continuation, itct = continuations.pop()
comment_response = get_continuation(continuation, xsrf_token)
if not comment_response:
continue
if list(search_dict(comment_response, 'externalErrorMessage')):
raise ExtractorError('Error returned from server: ' + next(search_dict(comment_response, 'externalErrorMessage')))
if 'continuationContents' not in comment_response['response']:
# Something is wrong here. Youtube won't accept this continuation token for some reason and responds with a user satisfaction dialog (error?)
continue
# not sure if this actually helps
if 'xsrf_token' in comment_response:
xsrf_token = comment_response['xsrf_token']
item_section = comment_response['response']['continuationContents']['itemSectionContinuation']
if first_continuation:
expected_video_comment_count = int(item_section['header']['commentsHeaderRenderer']['countText']['runs'][0]['text'].replace(' Comments', '').replace('1 Comment', '1').replace(',', ''))
first_continuation = False
if 'contents' not in item_section:
# continuation returned no comments?
# set an empty array as to not break the for loop
item_section['contents'] = []
for meta_comment in item_section['contents']:
comment = meta_comment['commentThreadRenderer']['comment']['commentRenderer']
video_comments.append({
'id': comment['commentId'],
'text': ''.join([c['text'] for c in comment['contentText']['runs']]),
'time_text': ''.join([c['text'] for c in comment['publishedTimeText']['runs']]),
'author': comment.get('authorText', {}).get('simpleText', ''),
'votes': comment.get('voteCount', {}).get('simpleText', '0'),
'author_thumbnail': comment['authorThumbnail']['thumbnails'][-1]['url'],
'parent': 'root'
})
if 'replies' not in meta_comment['commentThreadRenderer']:
continue
reply_continuations = [rcn['nextContinuationData']['continuation'] for rcn in meta_comment['commentThreadRenderer']['replies']['commentRepliesRenderer']['continuations']]
while reply_continuations:
time.sleep(1)
continuation = reply_continuations.pop()
replies_data = get_continuation(continuation, xsrf_token, True)
if not replies_data or 'continuationContents' not in replies_data[1]['response']:
continue
if self._downloader.params.get('verbose', False):
self.to_screen('[debug] Comments downloaded (chain %s) %s of ~%s' % (comment['commentId'], len(video_comments), expected_video_comment_count))
reply_comment_meta = replies_data[1]['response']['continuationContents']['commentRepliesContinuation']
for reply_meta in replies_data[1]['response']['continuationContents']['commentRepliesContinuation']['contents']:
reply_comment = reply_meta['commentRenderer']
video_comments.append({
'id': reply_comment['commentId'],
'text': ''.join([c['text'] for c in reply_comment['contentText']['runs']]),
'time_text': ''.join([c['text'] for c in reply_comment['publishedTimeText']['runs']]),
'author': reply_comment.get('authorText', {}).get('simpleText', ''),
'votes': reply_comment.get('voteCount', {}).get('simpleText', '0'),
'author_thumbnail': reply_comment['authorThumbnail']['thumbnails'][-1]['url'],
'parent': comment['commentId']
})
if 'continuations' not in reply_comment_meta or len(reply_comment_meta['continuations']) == 0:
continue
reply_continuations += [rcn['nextContinuationData']['continuation'] for rcn in reply_comment_meta['continuations']]
self.to_screen('Comments downloaded %s of ~%s' % (len(video_comments), expected_video_comment_count))
if 'continuations' in item_section:
continuations += [ncd['nextContinuationData']['continuation'] for ncd in item_section['continuations']]
time.sleep(1)
self.to_screen('Total comments downloaded %s of ~%s' % (len(video_comments), expected_video_comment_count))
else:
expected_video_comment_count = None
video_comments = None
# Look for the DASH manifest
if self._downloader.params.get('youtube_include_dash_manifest', True):
dash_mpd_fatal = True
@@ -2572,6 +2720,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
'release_year': release_year,
'subscriber_count': subscriber_count,
'playable_in_embed': playable_in_embed,
'comments': video_comments,
'comment_count': expected_video_comment_count,
}
@@ -3276,12 +3426,19 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
title += ' - %s' % tab_title
description = renderer.get('description')
playlist_id = renderer.get('externalId')
# this has thumbnails, but there is currently no thumbnail field for playlists
# sidebar.playlistSidebarRenderer has even more data, but its stucture is more complec
renderer = try_get(
data, lambda x: x['metadata']['playlistMetadataRenderer'], dict)
data, lambda x: x['microformat']['microformatDataRenderer'], dict)
if not renderer:
renderer = try_get(
data, lambda x: x['metadata']['playlistMetadataRenderer'], dict)
if renderer:
title = renderer.get('title')
description = None
description = renderer.get('description')
playlist_id = item_id
if playlist_id is None:
playlist_id = item_id
if title is None:
@@ -3371,8 +3528,16 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
webpage = self._download_webpage(url, item_id)
identity_token = self._extract_identity_token(webpage, item_id)
data = self._extract_yt_initial_data(item_id, webpage)
err_msg = None
for alert_type, alert_message in self._extract_alerts(data):
self._downloader.report_warning('YouTube said: %s - %s' % (alert_type, alert_message))
if alert_type.lower() == 'error':
if err_msg:
self._downloader.report_warning('YouTube said: %s - %s' % ('ERROR', err_msg))
err_msg = alert_message
else:
self._downloader.report_warning('YouTube said: %s - %s' % (alert_type, alert_message))
if err_msg:
raise ExtractorError('YouTube said: %s' % err_msg, expected=True)
tabs = try_get(
data, lambda x: x['contents']['twoColumnBrowseResultsRenderer']['tabs'], list)
if tabs:

View File

@@ -22,6 +22,9 @@ from .utils import (
from .version import __version__
_remux_formats = ('mp4', 'mkv', 'flv', 'webm', 'mov', 'avi', 'mp3', 'mka', 'm4a', 'ogg', 'opus')
def _hide_login_info(opts):
PRIVATE_OPTS = set(['-p', '--password', '-u', '--username', '--video-password', '--ap-password', '--ap-username'])
eqre = re.compile('^(?P<key>' + ('|'.join(re.escape(po) for po in PRIVATE_OPTS)) + ')=.+$')
@@ -934,6 +937,10 @@ def parseOpts(overrideArguments=None):
'--no-write-annotations',
action='store_false', dest='writeannotations',
help='Do not write video annotations (default)')
filesystem.add_option(
'--get-comments',
action='store_true', dest='getcomments', default=False,
help='Retrieve video comments to be placed in the .info.json file')
filesystem.add_option(
'--load-info-json', '--load-info',
dest='load_info_filename', metavar='FILE',
@@ -1001,24 +1008,28 @@ def parseOpts(overrideArguments=None):
postproc.add_option(
'-x', '--extract-audio',
action='store_true', dest='extractaudio', default=False,
help='Convert video files to audio-only files (requires ffmpeg/avconv and ffprobe/avprobe)')
help='Convert video files to audio-only files (requires ffmpeg and ffprobe)')
postproc.add_option(
'--audio-format', metavar='FORMAT', dest='audioformat', default='best',
help='Specify audio format: "best", "aac", "flac", "mp3", "m4a", "opus", "vorbis", or "wav"; "%default" by default; No effect without -x')
postproc.add_option(
'--audio-quality', metavar='QUALITY',
dest='audioquality', default='5',
help='Specify ffmpeg/avconv audio quality, insert a value between 0 (better) and 9 (worse) for VBR or a specific bitrate like 128K (default %default)')
help='Specify ffmpeg audio quality, insert a value between 0 (better) and 9 (worse) for VBR or a specific bitrate like 128K (default %default)')
postproc.add_option(
'--remux-video',
metavar='FORMAT', dest='remuxvideo', default=None,
help=(
'Remux the video into another container if necessary (currently supported: mp4|mkv). '
'If target container does not support the video/audio codec, remuxing will fail'))
'Remux the video into another container if necessary (currently supported: %s). '
'If target container does not support the video/audio codec, remuxing will fail. '
'You can specify multiple rules; eg. "aac>m4a/mov>mp4/mkv" will remux aac to m4a, mov to mp4 '
'and anything else to mkv.' % '|'.join(_remux_formats)))
postproc.add_option(
'--recode-video',
metavar='FORMAT', dest='recodevideo', default=None,
help='Re-encode the video into another format if re-encoding is necessary (currently supported: mp4|flv|ogg|webm|mkv|avi)')
help=(
'Re-encode the video into another format if re-encoding is necessary. '
'The supported formats are the same as --remux-video'))
postproc.add_option(
'--postprocessor-args', '--ppa',
metavar='NAME:ARGS', dest='postprocessor_args', default={}, type='str',
@@ -1030,7 +1041,7 @@ def parseOpts(overrideArguments=None):
'to give the argument to the specified postprocessor/executable. Supported postprocessors are: '
'SponSkrub, ExtractAudio, VideoRemuxer, VideoConvertor, EmbedSubtitle, Metadata, Merger, '
'FixupStretched, FixupM4a, FixupM3u8, SubtitlesConvertor and EmbedThumbnail. '
'The supported executables are: SponSkrub, FFmpeg, FFprobe, avconf, avprobe and AtomicParsley. '
'The supported executables are: SponSkrub, FFmpeg, FFprobe, and AtomicParsley. '
'You can use this option multiple times to give different arguments to different postprocessors. '
'You can also specify "PP+EXE:ARGS" to give the arguments to the specified executable '
'only when being used by the specified postprocessor. '
@@ -1078,14 +1089,20 @@ def parseOpts(overrideArguments=None):
postproc.add_option(
'--metadata-from-title',
metavar='FORMAT', dest='metafromtitle',
help=optparse.SUPPRESS_HELP)
postproc.add_option(
'--parse-metadata',
metavar='FIELD:FORMAT', dest='metafromfield', action='append',
help=(
'Parse additional metadata like song title / artist from the video title. '
'The format syntax is the same as --output. Regular expression with '
'named capture groups may also be used. '
'The parsed parameters replace existing values. '
'Example: --metadata-from-title "%(artist)s - %(title)s" matches a title like '
'Parse additional metadata like title/artist from other fields. '
'Give field name to extract data from, and format of the field seperated by a ":". '
'Either regular expression with named capture groups or a '
'similar syntax to the output template can also be used. '
'The parsed parameters replace any existing values and can be use in output template'
'This option can be used multiple times. '
'Example: --parse-metadata "title:%(artist)s - %(title)s" matches a title like '
'"Coldplay - Paradise". '
'Example (regex): --metadata-from-title "(?P<artist>.+?) - (?P<title>.+)"'))
'Example (regex): --parse-metadata "description:Artist - (?P<artist>.+?)"'))
postproc.add_option(
'--xattrs',
action='store_true', dest='xattrs', default=False,
@@ -1100,15 +1117,15 @@ def parseOpts(overrideArguments=None):
postproc.add_option(
'--prefer-avconv', '--no-prefer-ffmpeg',
action='store_false', dest='prefer_ffmpeg',
help='Prefer avconv over ffmpeg for running the postprocessors (Alias: --no-prefer-ffmpeg)')
help=optparse.SUPPRESS_HELP)
postproc.add_option(
'--prefer-ffmpeg', '--no-prefer-avconv',
action='store_true', dest='prefer_ffmpeg',
help='Prefer ffmpeg over avconv for running the postprocessors (default) (Alias: --no-prefer-avconv)')
action='store_true', dest='prefer_ffmpeg', default=True,
help=optparse.SUPPRESS_HELP)
postproc.add_option(
'--ffmpeg-location', '--avconv-location', metavar='PATH',
dest='ffmpeg_location',
help='Location of the ffmpeg/avconv binary; either the path to the binary or its containing directory (Alias: --avconv-location)')
help='Location of the ffmpeg binary; either the path to the binary or its containing directory')
postproc.add_option(
'--exec',
metavar='CMD', dest='exec_cmd',
@@ -1217,19 +1234,15 @@ def parseOpts(overrideArguments=None):
return
def read_options(path, user=False):
func = _readUserConf if user else _readOptions
current_path = os.path.join(path, 'yt-dlp.conf')
config = func(current_path, default=None)
if user:
config, current_path = config
if config is None:
current_path = os.path.join(path, 'youtube-dlc.conf')
config = func(current_path, default=None)
for package in ('yt-dlp', 'youtube-dlc'):
if user:
config, current_path = config
if config is None:
return [], None
return config, current_path
config, current_path = _readUserConf(package, default=None)
else:
current_path = os.path.join(path, '%s.conf' % package)
config = _readOptions(current_path, default=None)
if config is not None:
return config, current_path
return [], None
configs['portable'], paths['portable'] = read_options(get_executable_path())
if '--ignore-config' in configs['portable']:

View File

@@ -16,7 +16,8 @@ from .ffmpeg import (
)
from .xattrpp import XAttrMetadataPP
from .execafterdownload import ExecAfterDownloadPP
from .metadatafromtitle import MetadataFromTitlePP
from .metadatafromfield import MetadataFromFieldPP
from .metadatafromfield import MetadataFromTitlePP
from .movefilesafterdownload import MoveFilesAfterDownloadPP
from .sponskrub import SponSkrubPP
@@ -39,6 +40,7 @@ __all__ = [
'FFmpegSubtitlesConvertorPP',
'FFmpegVideoConvertorPP',
'FFmpegVideoRemuxerPP',
'MetadataFromFieldPP',
'MetadataFromTitlePP',
'MoveFilesAfterDownloadPP',
'SponSkrubPP',

View File

@@ -56,7 +56,7 @@ class PostProcessor(object):
def write_debug(self, text, prefix=True, *args, **kwargs):
tag = '[debug] ' if prefix else ''
if self.get_param('verbose', False):
if self.get_param('verbose', False) and self._downloader:
return self._downloader.to_screen('%s%s' % (tag, text), *args, **kwargs)
def get_param(self, name, default=None, *args, **kwargs):

View File

@@ -4,6 +4,15 @@ from __future__ import unicode_literals
import os
import subprocess
import struct
import re
import base64
try:
import mutagen
_has_mutagen = True
except ImportError:
_has_mutagen = False
from .ffmpeg import FFmpegPostProcessor
@@ -11,11 +20,12 @@ from ..utils import (
check_executable,
encodeArgument,
encodeFilename,
error_to_compat_str,
PostProcessingError,
prepend_extension,
process_communicate_or_kill,
replace_extension,
shell_quote,
process_communicate_or_kill,
)
@@ -73,6 +83,7 @@ class EmbedThumbnailPP(FFmpegPostProcessor):
# Rename back to unescaped for further processing
os.rename(encodeFilename(escaped_thumbnail_jpg_filename), encodeFilename(thumbnail_jpg_filename))
thumbnail_filename = thumbnail_jpg_filename
thumbnail_ext = 'jpg'
success = True
if info['ext'] == 'mp3':
@@ -83,47 +94,92 @@ class EmbedThumbnailPP(FFmpegPostProcessor):
self.to_screen('Adding thumbnail to "%s"' % filename)
self.run_ffmpeg_multiple_files([filename, thumbnail_filename], temp_filename, options)
elif info['ext'] == 'mkv':
options = [
'-c', 'copy', '-map', '0', '-dn', '-attach', thumbnail_filename,
'-metadata:s:t', 'mimetype=image/jpeg', '-metadata:s:t', 'filename=cover.jpg']
elif info['ext'] in ['mkv', 'mka']:
options = ['-c', 'copy', '-map', '0', '-dn']
mimetype = 'image/%s' % ('png' if thumbnail_ext == 'png' else 'jpeg')
old_stream, new_stream = self.get_stream_number(
filename, ('tags', 'mimetype'), mimetype)
if old_stream is not None:
options.extend(['-map', '-0:%d' % old_stream])
new_stream -= 1
options.extend([
'-attach', thumbnail_filename,
'-metadata:s:%d' % new_stream, 'mimetype=%s' % mimetype,
'-metadata:s:%d' % new_stream, 'filename=cover.%s' % thumbnail_ext])
self.to_screen('Adding thumbnail to "%s"' % filename)
self.run_ffmpeg_multiple_files([filename], temp_filename, options)
self.run_ffmpeg(filename, temp_filename, options)
elif info['ext'] in ['m4a', 'mp4']:
if not check_executable('AtomicParsley', ['-v']):
raise EmbedThumbnailPPError('AtomicParsley was not found. Please install.')
elif info['ext'] in ['m4a', 'mp4', 'mov']:
try:
options = ['-c', 'copy', '-map', '0', '-dn', '-map', '1']
cmd = [encodeFilename('AtomicParsley', True),
encodeFilename(filename, True),
encodeArgument('--artwork'),
encodeFilename(thumbnail_filename, True),
encodeArgument('-o'),
encodeFilename(temp_filename, True)]
cmd += [encodeArgument(o) for o in self._configuration_args(exe='AtomicParsley')]
old_stream, new_stream = self.get_stream_number(
filename, ('disposition', 'attached_pic'), 1)
if old_stream is not None:
options.extend(['-map', '-0:%d' % old_stream])
new_stream -= 1
options.extend(['-disposition:%s' % new_stream, 'attached_pic'])
self.to_screen('Adding thumbnail to "%s"' % filename)
self.write_debug('AtomicParsley command line: %s' % shell_quote(cmd))
self.to_screen('Adding thumbnail to "%s"' % filename)
self.run_ffmpeg_multiple_files([filename, thumbnail_filename], temp_filename, options)
p = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
stdout, stderr = process_communicate_or_kill(p)
except PostProcessingError as err:
self.report_warning('unable to embed using ffprobe & ffmpeg; %s' % error_to_compat_str(err))
if not check_executable('AtomicParsley', ['-v']):
raise EmbedThumbnailPPError('AtomicParsley was not found. Please install.')
if p.returncode != 0:
msg = stderr.decode('utf-8', 'replace').strip()
raise EmbedThumbnailPPError(msg)
# for formats that don't support thumbnails (like 3gp) AtomicParsley
# won't create to the temporary file
if b'No changes' in stdout:
self.report_warning('The file format doesn\'t support embedding a thumbnail')
success = False
cmd = [encodeFilename('AtomicParsley', True),
encodeFilename(filename, True),
encodeArgument('--artwork'),
encodeFilename(thumbnail_filename, True),
encodeArgument('-o'),
encodeFilename(temp_filename, True)]
cmd += [encodeArgument(o) for o in self._configuration_args(exe='AtomicParsley')]
self.to_screen('Adding thumbnail to "%s"' % filename)
self.write_debug('AtomicParsley command line: %s' % shell_quote(cmd))
p = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
stdout, stderr = process_communicate_or_kill(p)
if p.returncode != 0:
msg = stderr.decode('utf-8', 'replace').strip()
raise EmbedThumbnailPPError(msg)
# for formats that don't support thumbnails (like 3gp) AtomicParsley
# won't create to the temporary file
if b'No changes' in stdout:
self.report_warning('The file format doesn\'t support embedding a thumbnail')
success = False
elif info['ext'] in ['ogg', 'opus']:
if not _has_mutagen:
raise EmbedThumbnailPPError('module mutagen was not found. Please install using `python -m pip install mutagen`')
size_regex = r',\s*(?P<w>\d+)x(?P<h>\d+)\s*[,\[]'
size_result = self.run_ffmpeg(thumbnail_filename, thumbnail_filename, ['-hide_banner'])
mobj = re.search(size_regex, size_result)
width, height = int(mobj.group('w')), int(mobj.group('h'))
mimetype = ('image/%s' % ('png' if thumbnail_ext == 'png' else 'jpeg')).encode('ascii')
# https://xiph.org/flac/format.html#metadata_block_picture
data = bytearray()
data += struct.pack('>II', 3, len(mimetype))
data += mimetype
data += struct.pack('>IIIIII', 0, width, height, 8, 0, os.stat(thumbnail_filename).st_size) # 32 if png else 24
fin = open(thumbnail_filename, "rb")
data += fin.read()
fin.close()
temp_filename = filename
f = mutagen.File(temp_filename)
f.tags['METADATA_BLOCK_PICTURE'] = base64.b64encode(data).decode('ascii')
f.save()
else:
raise EmbedThumbnailPPError('Only mp3, mkv, m4a and mp4 are supported for thumbnail embedding for now.')
raise EmbedThumbnailPPError('Supported filetypes for thumbnail embedding are: mp3, mkv/mka, ogg/opus, m4a/mp4/mov')
if success:
if success and temp_filename != filename:
os.remove(encodeFilename(filename))
os.rename(encodeFilename(temp_filename), encodeFilename(filename))
files_to_delete = [] if self._already_have_thumbnail else [thumbnail_filename]
return files_to_delete, info

View File

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

View File

@@ -0,0 +1,66 @@
from __future__ import unicode_literals
import re
from .common import PostProcessor
from ..compat import compat_str
class MetadataFromFieldPP(PostProcessor):
regex = r'(?P<field>\w+):(?P<format>.+)$'
def __init__(self, downloader, formats):
PostProcessor.__init__(self, downloader)
assert isinstance(formats, (list, tuple))
self._data = []
for f in formats:
assert isinstance(f, compat_str)
match = re.match(self.regex, f)
assert match is not None
self._data.append({
'field': match.group('field'),
'format': match.group('format'),
'regex': self.format_to_regex(match.group('format'))})
def format_to_regex(self, fmt):
r"""
Converts a string like
'%(title)s - %(artist)s'
to a regex like
'(?P<title>.+)\ \-\ (?P<artist>.+)'
"""
if not re.search(r'%\(\w+\)s', fmt):
return fmt
lastpos = 0
regex = ''
# replace %(..)s with regex group and escape other string parts
for match in re.finditer(r'%\((\w+)\)s', fmt):
regex += re.escape(fmt[lastpos:match.start()])
regex += r'(?P<' + match.group(1) + r'>[^\r\n]+)'
lastpos = match.end()
if lastpos < len(fmt):
regex += re.escape(fmt[lastpos:])
return regex
def run(self, info):
for dictn in self._data:
field, regex = dictn['field'], dictn['regex']
if field not in info:
self.report_warning('Video doesnot have a %s' % field)
continue
self.write_debug('Searching for r"%s" in %s' % (regex, field))
match = re.search(regex, info[field])
if match is None:
self.report_warning('Could not interpret video %s as "%s"' % (field, dictn['format']))
continue
for attribute, value in match.groupdict().items():
info[attribute] = value
self.to_screen('parsed %s from %s: %s' % (attribute, field, value if value is not None else 'NA'))
return [], info
class MetadataFromTitlePP(MetadataFromFieldPP): # for backward compatibility
def __init__(self, downloader, titleformat):
super(MetadataFromTitlePP, self).__init__(downloader, ['title:%s' % titleformat])
self._titleformat = titleformat
self._titleregex = self._data[0]['regex']

View File

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

View File

@@ -28,14 +28,14 @@ class MoveFilesAfterDownloadPP(PostProcessor):
self.files_to_move[info['filepath']] = finalpath
for oldfile, newfile in self.files_to_move.items():
if not os.path.exists(encodeFilename(oldfile)):
self.report_warning('File "%s" cannot be found' % oldfile)
continue
if not newfile:
newfile = os.path.join(finaldir, os.path.basename(encodeFilename(oldfile)))
oldfile, newfile = compat_str(oldfile), compat_str(newfile)
if os.path.abspath(encodeFilename(oldfile)) == os.path.abspath(encodeFilename(newfile)):
continue
if not os.path.exists(encodeFilename(oldfile)):
self.report_warning('File "%s" cannot be found' % oldfile)
continue
if os.path.exists(encodeFilename(newfile)):
if self.get_param('overwrites', True):
self.report_warning('Replacing existing file "%s"' % newfile)

View File

@@ -5934,3 +5934,14 @@ def load_plugins(name, type, namespace):
if plugin_info[0] is not None:
plugin_info[0].close()
return classes
def traverse_dict(dictn, keys, casesense=True):
if not isinstance(dictn, dict):
return None
first_key = keys[0]
if not casesense:
dictn = {key.lower(): val for key, val in dictn.items()}
first_key = first_key.lower()
value = dictn.get(first_key, None)
return value if len(keys) < 2 else traverse_dict(value, keys[1:], casesense)

View File

@@ -1,3 +1,3 @@
from __future__ import unicode_literals
__version__ = '2021.01.20'
__version__ = '2021.01.24'