Compare commits

...

29 Commits

Author SHA1 Message Date
pukkandan 1bfd5ba95b Release 2021.01.24 2021-01-24 21:31:13 +05:30
Remita Amine a820dc722e Update to ytdl-2021.01.24.1 2021-01-24 20:28:44 +05:30
pukkandan f74980cbae Plugin support
Extractor plugins are loaded from <root-dir>/ytdlp_plugins/extractor/__init__.py

Inspired by https://github.com/un-def/dl-plus

:ci skip dl
2021-01-24 20:24:07 +05:30
pukkandan c571435f9c [MoveFiles] More robust way to get final filename
:ci skip dl
2021-01-24 20:24:06 +05:30
pukkandan 6b4b65c4f4 [test] fix typo 2021-01-24 14:05:54 +05:30
pukkandan 10e3742eb1 Fix overwrite in --write-link
:ci skip dl
2021-01-24 14:05:32 +05:30
pukkandan 0202b52a0c #29 New option -P/--paths to give different paths for different types of files
Syntax: `-P "type:path" -P "type:path"`
Types: home, temp, description, annotation, subtitle, infojson, thumbnail
2021-01-23 17:53:17 +05:30
pukkandan b8f6bbe68a Warn when using old style (downloader/postprocessor)_args 2021-01-23 17:41:21 +05:30
pukkandan 256ed01025 [sponskrub] Print "unrecognized args" message correctly 2021-01-23 17:17:47 +05:30
pukkandan eab9b2bcaf Modified function cli_configuration_args
to directly parse new format of `postprocessor_args` and `external_downloader_args`
2021-01-23 17:00:11 +05:30
pukkandan 3bcaa37b1b [tests] Split core and download tests 2021-01-23 17:00:11 +05:30
pukkandan 46ee996e39 Allow passing different arguments to different external downloaders
* Now similar to --post-processor-args
* Also added `--downloader-args` as alias to `--external-downloader-args`
2021-01-23 17:00:10 +05:30
pukkandan 45016689fa Standardized function for creating dict from repeated options 2021-01-23 17:00:10 +05:30
pukkandan 430c2757ea [cbs] Make failure to extract title non-fatal
:skip ci
2021-01-23 08:51:57 +05:30
The Hatsune Daishi ffcb819171 #30 [mildom] Add extractor
Authored by @nao20010128nao
2021-01-22 19:13:30 +05:30
pukkandan b46696bdc8 Revert d9eebbc747 2021-01-22 01:09:24 +05:30
pukkandan 63be1aab2f Deprecate unnecessary aliases in formatSort
(I should never have made so many aliases in the first-place)
The aliases remain functional for backward compatability, but will be left undocumented
2021-01-21 19:05:57 +05:30
pukkandan d0757229fa Fix typecasting when pre-checking archive (Closes #26) 2021-01-21 17:36:42 +05:30
pukkandan 610d8e7692 [tests] Fix test_post_hooks
:skip ci all
2021-01-21 03:38:57 +05:30
pukkandan e2f6586c16 [version] update
:skip ci all
2021-01-21 03:01:26 +05:30
pukkandan c69911e4c1 Release 2021.01.20 2021-01-21 02:51:45 +05:30
pukkandan e7ff505132 [pokemon] Add /#/player URLs (Closes #24) 2021-01-21 02:26:24 +05:30
pukkandan fbced7341d [sponskrub] Better debug output and error message 2021-01-21 01:41:05 +05:30
pukkandan 43820c0370 Improved passing of multiple postprocessor-args
* Added `PP+exe:args` syntax
    If `PP+exe:args` is specifically given, only it used.
    Otherwise, `PP:args` and `exe:args` are combined.
    If none of the `PP`, `exe` or `PP+exe` args are given, `default` is used
    `Default` is purposely left undocumented since it exists only for backward compatibility

* Also added proper handling of args in `EmbedThumbnail`

Related: https://github.com/ytdl-org/youtube-dl/pull/27723
2021-01-21 01:36:10 +05:30
pukkandan 5c610515c9 [TrovoLive] Add extractor (partially fix #20)
Only VOD extractor has been implemented

Related: https://github.com/ytdl-org/youtube-dl/issues/26125
Related: https://github.com/blackjack4494/yt-dlc/issues/220
2021-01-20 00:42:39 +05:30
pukkandan 8a51f56439 [readme] Cleanup options
(Closes #23) :skip ci
2021-01-19 00:56:07 +05:30
pukkandan 67002a5ad8 [EmbedThumbnail] Simplify embedding in mkv (Closes #22) 2021-01-18 19:36:50 +05:30
pukkandan 477cf32f37 [sponskrub] Encode filenames correctly 2021-01-18 19:23:08 +05:30
pukkandan f57adf0e59 [version] update
:skip ci all
2021-01-17 00:36:23 +05:30
57 changed files with 2318 additions and 1163 deletions
+3 -3
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: 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 2021.01.14. 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 2021.01.20. 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 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. - 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. - 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'm reporting a broken site support
- [ ] I've verified that I'm running yt-dlp version **2021.01.14** - [ ] I've verified that I'm running yt-dlp version **2021.01.20**
- [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] 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 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 - [ ] 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] User config: []
[debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [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] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
[debug] yt-dlp version 2021.01.14 [debug] yt-dlp version 2021.01.20
[debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [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] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
[debug] Proxy map: {} [debug] Proxy map: {}
@@ -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: 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 2021.01.14. 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 2021.01.20. 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 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. - 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. - 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'm reporting a new site support request
- [ ] I've verified that I'm running yt-dlp version **2021.01.14** - [ ] I've verified that I'm running yt-dlp version **2021.01.20**
- [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] 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 checked that none of provided URLs violate any copyrights
- [ ] I've searched the bugtracker for similar site support requests including closed ones - [ ] I've searched the bugtracker for similar site support requests including closed ones
@@ -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: 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 2021.01.14. 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 2021.01.20. 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. - 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) - 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'm reporting a site feature request
- [ ] I've verified that I'm running yt-dlp version **2021.01.14** - [ ] I've verified that I'm running yt-dlp version **2021.01.20**
- [ ] I've searched the bugtracker for similar site feature requests including closed ones - [ ] I've searched the bugtracker for similar site feature requests including closed ones
+3 -3
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: 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 2021.01.14. 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 2021.01.20. 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 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. - 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. - 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'm reporting a broken site support issue
- [ ] I've verified that I'm running yt-dlp version **2021.01.14** - [ ] I've verified that I'm running yt-dlp version **2021.01.20**
- [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] 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 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 - [ ] 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] User config: []
[debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [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] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
[debug] yt-dlp version 2021.01.14 [debug] yt-dlp version 2021.01.20
[debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [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] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
[debug] Proxy map: {} [debug] Proxy map: {}
+2 -2
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: 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 2021.01.14. 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 2021.01.20. 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. - 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) - Finally, put x into all relevant boxes like this [x] (Dont forget to delete the empty space)
--> -->
- [ ] I'm reporting a feature request - [ ] I'm reporting a feature request
- [ ] I've verified that I'm running yt-dlp version **2021.01.14** - [ ] I've verified that I'm running yt-dlp version **2021.01.20**
- [ ] I've searched the bugtracker for similar feature requests including closed ones - [ ] I've searched the bugtracker for similar feature requests including closed ones
@@ -1,9 +1,9 @@
name: Full Test name: Core Tests
on: [push, pull_request] on: [push, pull_request]
jobs: jobs:
tests: tests:
name: Tests name: Core Tests
if: "!contains(github.event.head_commit.message, 'skip ci')" if: "!contains(github.event.head_commit.message, 'ci skip all')"
runs-on: ${{ matrix.os }} runs-on: ${{ matrix.os }}
strategy: strategy:
fail-fast: true fail-fast: true
@@ -12,7 +12,7 @@ jobs:
# TODO: python 2.6 # TODO: python 2.6
python-version: [2.7, 3.3, 3.4, 3.5, 3.6, 3.7, 3.8, 3.9, pypy-2.7, pypy-3.6, pypy-3.7] python-version: [2.7, 3.3, 3.4, 3.5, 3.6, 3.7, 3.8, 3.9, pypy-2.7, pypy-3.6, pypy-3.7]
python-impl: [cpython] python-impl: [cpython]
ytdl-test-set: [core, download] ytdl-test-set: [core]
run-tests-ext: [sh] run-tests-ext: [sh]
include: include:
# python 3.2 is only available on windows via setup-python # python 3.2 is only available on windows via setup-python
@@ -21,20 +21,11 @@ jobs:
python-impl: cpython python-impl: cpython
ytdl-test-set: core ytdl-test-set: core
run-tests-ext: bat run-tests-ext: bat
- os: windows-latest
python-version: 3.2
python-impl: cpython
ytdl-test-set: download
run-tests-ext: bat
# jython # jython
- os: ubuntu-latest - os: ubuntu-latest
python-impl: jython python-impl: jython
ytdl-test-set: core ytdl-test-set: core
run-tests-ext: sh run-tests-ext: sh
- os: ubuntu-latest
python-impl: jython
ytdl-test-set: download
run-tests-ext: sh
steps: steps:
- uses: actions/checkout@v2 - uses: actions/checkout@v2
- name: Set up Python ${{ matrix.python-version }} - name: Set up Python ${{ matrix.python-version }}
@@ -60,4 +51,4 @@ jobs:
env: env:
YTDL_TEST_SET: ${{ matrix.ytdl-test-set }} YTDL_TEST_SET: ${{ matrix.ytdl-test-set }}
run: ./devscripts/run_tests.${{ matrix.run-tests-ext }} run: ./devscripts/run_tests.${{ matrix.run-tests-ext }}
# flake8 has been moved to quick-test # Linter is in quick-test
+53
View File
@@ -0,0 +1,53 @@
name: Download Tests
on: [push, pull_request]
jobs:
tests:
name: Download Tests
if: "!contains(github.event.head_commit.message, 'ci skip dl') && !contains(github.event.head_commit.message, 'ci skip all')"
runs-on: ${{ matrix.os }}
strategy:
fail-fast: true
matrix:
os: [ubuntu-18.04]
# TODO: python 2.6
python-version: [2.7, 3.3, 3.4, 3.5, 3.6, 3.7, 3.8, 3.9, pypy-2.7, pypy-3.6, pypy-3.7]
python-impl: [cpython]
ytdl-test-set: [download]
run-tests-ext: [sh]
include:
# python 3.2 is only available on windows via setup-python
- os: windows-latest
python-version: 3.2
python-impl: cpython
ytdl-test-set: download
run-tests-ext: bat
# jython - disable for now since it takes too long to complete
# - os: ubuntu-latest
# python-impl: jython
# ytdl-test-set: download
# run-tests-ext: sh
steps:
- uses: actions/checkout@v2
- name: Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@v2
if: ${{ matrix.python-impl == 'cpython' }}
with:
python-version: ${{ matrix.python-version }}
- name: Set up Java 8
if: ${{ matrix.python-impl == 'jython' }}
uses: actions/setup-java@v1
with:
java-version: 8
- name: Install Jython
if: ${{ matrix.python-impl == 'jython' }}
run: |
wget http://search.maven.org/remotecontent?filepath=org/python/jython-installer/2.7.1/jython-installer-2.7.1.jar -O jython-installer.jar
java -jar jython-installer.jar -s -d "$HOME/jython"
echo "$HOME/jython/bin" >> $GITHUB_PATH
- name: Install nose
run: pip install nose
- name: Run tests
continue-on-error: ${{ matrix.ytdl-test-set == 'download' || matrix.python-impl == 'jython' }}
env:
YTDL_TEST_SET: ${{ matrix.ytdl-test-set }}
run: ./devscripts/run_tests.${{ matrix.run-tests-ext }}
+4 -4
View File
@@ -1,13 +1,13 @@
name: Core Test name: Quick Test
on: [push, pull_request] on: [push, pull_request]
jobs: jobs:
tests: tests:
name: Core Tests name: Core Tests
if: "!contains(github.event.head_commit.message, 'skip ci all')" if: "!contains(github.event.head_commit.message, 'ci skip all')"
runs-on: ubuntu-latest runs-on: ubuntu-latest
steps: steps:
- uses: actions/checkout@v2 - uses: actions/checkout@v2
- name: Set up Python 3.9 - name: Set up Python
uses: actions/setup-python@v2 uses: actions/setup-python@v2
with: with:
python-version: 3.9 python-version: 3.9
@@ -19,7 +19,7 @@ jobs:
run: ./devscripts/run_tests.sh run: ./devscripts/run_tests.sh
flake8: flake8:
name: Linter name: Linter
if: "!contains(github.event.head_commit.message, 'skip ci all')" if: "!contains(github.event.head_commit.message, 'ci skip all')"
runs-on: ubuntu-latest runs-on: ubuntu-latest
steps: steps:
- uses: actions/checkout@v2 - uses: actions/checkout@v2
+10 -1
View File
@@ -49,6 +49,7 @@ updates_key.pem
*.conf *.conf
*.swp *.swp
*.spec *.spec
*.exe
test/local_parameters.json test/local_parameters.json
.tox .tox
youtube-dl.zsh youtube-dl.zsh
@@ -64,6 +65,14 @@ venv/
# VS Code related files # VS Code related files
.vscode .vscode
# SublimeText files
*.sublime-workspace
# Cookies
cookies
cookies.txt cookies.txt
*.sublime-workspace # Plugins
ytdlp_plugins/extractor/*
!ytdlp_plugins/extractor/__init__.py
!ytdlp_plugins/extractor/sample.py
-248
View File
@@ -1,248 +0,0 @@
Ricardo Garcia Gonzalez
Danny Colligan
Benjamin Johnson
Vasyl' Vavrychuk
Witold Baryluk
Paweł Paprota
Gergely Imreh
Rogério Brito
Philipp Hagemeister
Sören Schulze
Kevin Ngo
Ori Avtalion
shizeeg
Filippo Valsorda
Christian Albrecht
Dave Vasilevsky
Jaime Marquínez Ferrándiz
Jeff Crouse
Osama Khalid
Michael Walter
M. Yasoob Ullah Khalid
Julien Fraichard
Johny Mo Swag
Axel Noack
Albert Kim
Pierre Rudloff
Huarong Huo
Ismael Mejía
Steffan Donal
Andras Elso
Jelle van der Waa
Marcin Cieślak
Anton Larionov
Takuya Tsuchida
Sergey M.
Michael Orlitzky
Chris Gahan
Saimadhav Heblikar
Mike Col
Oleg Prutz
pulpe
Andreas Schmitz
Michael Kaiser
Niklas Laxström
David Triendl
Anthony Weems
David Wagner
Juan C. Olivares
Mattias Harrysson
phaer
Sainyam Kapoor
Nicolas Évrard
Jason Normore
Hoje Lee
Adam Thalhammer
Georg Jähnig
Ralf Haring
Koki Takahashi
Ariset Llerena
Adam Malcontenti-Wilson
Tobias Bell
Naglis Jonaitis
Charles Chen
Hassaan Ali
Dobrosław Żybort
David Fabijan
Sebastian Haas
Alexander Kirk
Erik Johnson
Keith Beckman
Ole Ernst
Aaron McDaniel (mcd1992)
Magnus Kolstad
Hari Padmanaban
Carlos Ramos
5moufl
lenaten
Dennis Scheiba
Damon Timm
winwon
Xavier Beynon
Gabriel Schubiner
xantares
Jan Matějka
Mauroy Sébastien
William Sewell
Dao Hoang Son
Oskar Jauch
Matthew Rayfield
t0mm0
Tithen-Firion
Zack Fernandes
cryptonaut
Adrian Kretz
Mathias Rav
Petr Kutalek
Will Glynn
Max Reimann
Cédric Luthi
Thijs Vermeir
Joel Leclerc
Christopher Krooss
Ondřej Caletka
Dinesh S
Johan K. Jensen
Yen Chi Hsuan
Enam Mijbah Noor
David Luhmer
Shaya Goldberg
Paul Hartmann
Frans de Jonge
Robin de Rooij
Ryan Schmidt
Leslie P. Polzer
Duncan Keall
Alexander Mamay
Devin J. Pohly
Eduardo Ferro Aldama
Jeff Buchbinder
Amish Bhadeshia
Joram Schrijver
Will W.
Mohammad Teimori Pabandi
Roman Le Négrate
Matthias Küch
Julian Richen
Ping O.
Mister Hat
Peter Ding
jackyzy823
George Brighton
Remita Amine
Aurélio A. Heckert
Bernhard Minks
sceext
Zach Bruggeman
Tjark Saul
slangangular
Behrouz Abbasi
ngld
nyuszika7h
Shaun Walbridge
Lee Jenkins
Anssi Hannula
Lukáš Lalinský
Qijiang Fan
Rémy Léone
Marco Ferragina
reiv
Muratcan Simsek
Evan Lu
flatgreen
Brian Foley
Vignesh Venkat
Tom Gijselinck
Founder Fang
Andrew Alexeyew
Saso Bezlaj
Erwin de Haan
Jens Wille
Robin Houtevelts
Patrick Griffis
Aidan Rowe
mutantmonkey
Ben Congdon
Kacper Michajłow
José Joaquín Atria
Viťas Strádal
Kagami Hiiragi
Philip Huppert
blahgeek
Kevin Deldycke
inondle
Tomáš Čech
Déstin Reed
Roman Tsiupa
Artur Krysiak
Jakub Adam Wieczorek
Aleksandar Topuzović
Nehal Patel
Rob van Bekkum
Petr Zvoníček
Pratyush Singh
Aleksander Nitecki
Sebastian Blunt
Matěj Cepl
Xie Yanbo
Philip Xu
John Hawkinson
Rich Leeper
Zhong Jianxin
Thor77
Mattias Wadman
Arjan Verwer
Costy Petrisor
Logan B
Alex Seiler
Vijay Singh
Paul Hartmann
Stephen Chen
Fabian Stahl
Bagira
Odd Stråbø
Philip Herzog
Thomas Christlieb
Marek Rusinowski
Tobias Gruetzmacher
Olivier Bilodeau
Lars Vierbergen
Juanjo Benages
Xiao Di Guan
Thomas Winant
Daniel Twardowski
Jeremie Jarosh
Gerard Rovira
Marvin Ewald
Frédéric Bournival
Timendum
gritstub
Adam Voss
Mike Fährmann
Jan Kundrát
Giuseppe Fabiano
Örn Guðjónsson
Parmjit Virk
Genki Sky
Ľuboš Katrinec
Corey Nicholson
Ashutosh Chaudhary
John Dong
Tatsuyuki Ishi
Daniel Weber
Kay Bouché
Yang Hongbo
Lei Wang
Petr Novák
Leonardo Taccari
Martin Weinelt
Surya Oktafendri
TingPing
Alexandre Macabies
Bastian de Groot
Niklas Haas
András Veres-Szentkirályi
Enes Solak
Nathan Rossi
Thomas van der Berg
Luca Cherubin
+1
View File
@@ -16,3 +16,4 @@ samiksome
alxnull alxnull
FelixFrog FelixFrog
Zocker1999NET Zocker1999NET
nao20010128nao
+38 -7
View File
@@ -4,21 +4,52 @@
# Instuctions for creating release # Instuctions for creating release
* Run `make doc` * Run `make doc`
* Update Changelog.md and Authors-Fork * Update Changelog.md and CONTRIBUTORS
* Change "Merged with youtube-dl" version in Readme.md if needed
* Commit to master as `Release <version>` * Commit to master as `Release <version>`
* Push to origin/release - build task will now run * Push to origin/release - build task will now run
* Update version.py and run `make issuetemplates` * Update version.py and run `make issuetemplates`
* Commit to master as `[version] update` * Commit to master as `[version] update :skip ci all`
* Push to origin/master * Push to origin/master
* Update changelog in /releases * Update changelog in /releases
--> -->
### 2021.01.24
* **Merge youtube-dl:** Upto [2021.01.24](https://github.com/ytdl-org/youtube-dl/releases/tag/2021.01.16)
* Plugin support ([documentation](https://github.com/pukkandan/yt-dlp#plugins))
* **Multiple paths**: New option `-P`/`--paths` to give different paths for different types of files
* The syntax is `-P "type:path" -P "type:path"` ([documentation](https://github.com/pukkandan/yt-dlp#:~:text=-P,%20--paths%20TYPE:PATH))
* Valid types are: home, temp, description, annotation, subtitle, infojson, thumbnail
* Additionally, configuration file is taken from home directory or current directory ([documentation](https://github.com/pukkandan/yt-dlp#:~:text=Home%20Configuration))
* Allow passing different arguments to different external downloaders ([documentation](https://github.com/pukkandan/yt-dlp#:~:text=--downloader-args%20NAME:ARGS))
* [mildom] Add extractor by @nao20010128nao
* Warn when using old style `--external-downloader-args` and `--post-processor-args`
* Fix `--no-overwrite` when using `--write-link`
* [sponskrub] Output `unrecognized argument` error message correctly
* [cbs] Make failure to extract title non-fatal
* Fix typecasting when pre-checking archive
* Fix issue with setting title on unix
* Deprecate redundant aliases in `formatSort`. The aliases remain functional for backward compatability, but will be left undocumented
* [tests] Fix test_post_hooks
* [tests] Split core and download tests
### 2021.01.20
* [TrovoLive] Add extractor (only VODs)
* [pokemon] Add `/#/player` URLs
* Improved parsing of multiple postprocessor-args, add `--ppa` as alias
* [EmbedThumbnail] Simplify embedding in mkv
* [sponskrub] Encode filenames correctly, better debug output and error message
* [readme] Cleanup options
### 2021.01.16 ### 2021.01.16
* Update to ytdl-2021.01.16 * **Merge youtube-dl:** Upto [2021.01.16](https://github.com/ytdl-org/youtube-dl/releases/tag/2021.01.16)
* Portable configuration file: `./yt-dlp.conf` * **Configuration files:**
* Changes to configuration file paths. See [this](https://github.com/pukkandan/yt-dlp#configuration) for details * Portable configuration file: `./yt-dlp.conf`
* Allow the configuration files to be named `yt-dlp` instead of `youtube-dlc`. See [this](https://github.com/pukkandan/yt-dlp#configuration) for details
* Add PyPI release * Add PyPI release
@@ -61,7 +92,7 @@
### 2021.01.08 ### 2021.01.08
* **Merge youtube-dl:** Upto [2021.01.08](https://github.com/ytdl-org/youtube-dl/commit/bf6a74c620bd4d5726503c5302906bb36b009026) * **Merge youtube-dl:** Upto [2021.01.08](https://github.com/ytdl-org/youtube-dl/releases/tag/2021.01.08)
* Extractor stitcher ([1](https://github.com/ytdl-org/youtube-dl/commit/bb38a1215718cdf36d73ff0a7830a64cd9fa37cc), [2](https://github.com/ytdl-org/youtube-dl/commit/a563c97c5cddf55f8989ed7ea8314ef78e30107f)) have not been merged * Extractor stitcher ([1](https://github.com/ytdl-org/youtube-dl/commit/bb38a1215718cdf36d73ff0a7830a64cd9fa37cc), [2](https://github.com/ytdl-org/youtube-dl/commit/a563c97c5cddf55f8989ed7ea8314ef78e30107f)) have not been merged
* Moved changelog to seperate file * Moved changelog to seperate file
@@ -103,7 +134,7 @@
* Added `b`,`w`,`v`,`a` as alias for `best`, `worst`, `video` and `audio` respectively * Added `b`,`w`,`v`,`a` as alias for `best`, `worst`, `video` and `audio` respectively
* **Shortcut Options:** Added `--write-link`, `--write-url-link`, `--write-webloc-link`, `--write-desktop-link` by @h-h-h-h - See [Internet Shortcut Options]README.md(#internet-shortcut-options) for details * **Shortcut Options:** Added `--write-link`, `--write-url-link`, `--write-webloc-link`, `--write-desktop-link` by @h-h-h-h - See [Internet Shortcut Options]README.md(#internet-shortcut-options) for details
* **Sponskrub integration:** Added `--sponskrub`, `--sponskrub-cut`, `--sponskrub-force`, `--sponskrub-location`, `--sponskrub-args` - See [SponSkrub Options](README.md#sponskrub-options-sponsorblock) for details * **Sponskrub integration:** Added `--sponskrub`, `--sponskrub-cut`, `--sponskrub-force`, `--sponskrub-location`, `--sponskrub-args` - See [SponSkrub Options](README.md#sponskrub-options-sponsorblock) for details
* Added `--force-download-archive` (`--force-write-archive`) by by h-h-h-h * Added `--force-download-archive` (`--force-write-archive`) by @h-h-h-h
* Added `--list-formats-as-table`, `--list-formats-old` * Added `--list-formats-as-table`, `--list-formats-old`
* **Negative Options:** Makes it possible to negate most boolean options by adding a `no-` to the switch. Usefull when you want to reverse an option that is defined in a config file * **Negative Options:** Makes it possible to negate most boolean options by adding a `no-` to the switch. Usefull when you want to reverse an option that is defined in a config file
* Added `--no-ignore-dynamic-mpd`, `--no-allow-dynamic-mpd`, `--allow-dynamic-mpd`, `--youtube-include-hls-manifest`, `--no-youtube-include-hls-manifest`, `--no-youtube-skip-hls-manifest`, `--no-download`, `--no-download-archive`, `--resize-buffer`, `--part`, `--mtime`, `--no-keep-fragments`, `--no-cookies`, `--no-write-annotations`, `--no-write-info-json`, `--no-write-description`, `--no-write-thumbnail`, `--youtube-include-dash-manifest`, `--post-overwrites`, `--no-keep-video`, `--no-embed-subs`, `--no-embed-thumbnail`, `--no-add-metadata`, `--no-include-ads`, `--no-write-sub`, `--no-write-auto-sub`, `--no-playlist-reverse`, `--no-restrict-filenames`, `--youtube-include-dash-manifest`, `--no-format-sort-force`, `--flat-videos`, `--no-list-formats-as-table`, `--no-sponskrub`, `--no-sponskrub-cut`, `--no-sponskrub-force` * Added `--no-ignore-dynamic-mpd`, `--no-allow-dynamic-mpd`, `--allow-dynamic-mpd`, `--youtube-include-hls-manifest`, `--no-youtube-include-hls-manifest`, `--no-youtube-skip-hls-manifest`, `--no-download`, `--no-download-archive`, `--resize-buffer`, `--part`, `--mtime`, `--no-keep-fragments`, `--no-cookies`, `--no-write-annotations`, `--no-write-info-json`, `--no-write-description`, `--no-write-thumbnail`, `--youtube-include-dash-manifest`, `--post-overwrites`, `--no-keep-video`, `--no-embed-subs`, `--no-embed-thumbnail`, `--no-add-metadata`, `--no-include-ads`, `--no-write-sub`, `--no-write-auto-sub`, `--no-playlist-reverse`, `--no-restrict-filenames`, `--youtube-include-dash-manifest`, `--no-format-sort-force`, `--flat-videos`, `--no-list-formats-as-table`, `--no-sponskrub`, `--no-sponskrub-cut`, `--no-sponskrub-force`
+170 -131
View File
@@ -2,9 +2,8 @@
<!-- See: https://github.com/marketplace/actions/dynamic-badges --> <!-- 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/endpoint?url=https://gist.githubusercontent.com/pukkandan/c69cb23c3c5b3316248e52022790aa57/raw/version.json&color=brightgreen)](https://github.com/pukkandan/yt-dlp/releases/latest)
[![License: Unlicense](https://img.shields.io/badge/License-Unlicense-blue.svg)](https://github.com/pukkandan/yt-dlp/blob/master/LICENSE) [![License: Unlicense](https://img.shields.io/badge/License-Unlicense-blue.svg)](LICENSE)
[![Core Status](https://github.com/pukkandan/yt-dlp/workflows/Core%20Test/badge.svg?branch=master)](https://github.com/pukkandan/yt-dlp/actions?query=workflow%3ACore) [![CI Status](https://github.com/pukkandan/yt-dlp/workflows/Core%20Tests/badge.svg?branch=master)](https://github.com/pukkandan/yt-dlp/actions)
[![CI Status](https://github.com/pukkandan/yt-dlp/workflows/Full%20Test/badge.svg?branch=master)](https://github.com/pukkandan/yt-dlp/actions?query=workflow%3AFull)
A command-line program to download videos from youtube.com and many other [video platforms](docs/supportedsites.md) A command-line program to download videos from youtube.com and many other [video platforms](docs/supportedsites.md)
@@ -30,7 +29,7 @@ This is a fork of [youtube-dlc](https://github.com/blackjack4494/yt-dlc) which i
* [Authentication Options](#authentication-options) * [Authentication Options](#authentication-options)
* [Adobe Pass Options](#adobe-pass-options) * [Adobe Pass Options](#adobe-pass-options)
* [Post-processing Options](#post-processing-options) * [Post-processing Options](#post-processing-options)
* [SponSkrub Options (SponsorBlock)](#sponskrub-options-sponsorblock) * [SponSkrub (SponsorBlock) Options](#sponskrub-sponsorblock-options)
* [Extractor Options](#extractor-options) * [Extractor Options](#extractor-options)
* [CONFIGURATION](#configuration) * [CONFIGURATION](#configuration)
* [Authentication with .netrc file](#authentication-with-netrc-file) * [Authentication with .netrc file](#authentication-with-netrc-file)
@@ -41,30 +40,39 @@ This is a fork of [youtube-dlc](https://github.com/blackjack4494/yt-dlc) which i
* [Filtering Formats](#filtering-formats) * [Filtering Formats](#filtering-formats)
* [Sorting Formats](#sorting-formats) * [Sorting Formats](#sorting-formats)
* [Format Selection examples](#format-selection-examples) * [Format Selection examples](#format-selection-examples)
* [PLUGINS](#plugins)
* [MORE](#more) * [MORE](#more)
# NEW FEATURES # NEW FEATURES
The major new features from the latest release of [blackjack4494/yt-dlc](https://github.com/blackjack4494/yt-dlc) are: The major new features from the latest release of [blackjack4494/yt-dlc](https://github.com/blackjack4494/yt-dlc) are:
* **[SponSkrub Integration](#sponSkrub-options-sponsorblock)**: You can use [SponSkrub](https://github.com/pukkandan/SponSkrub) to mark/remove sponsor sections in youtube videos by utilizing the [SponsorBlock](https://sponsor.ajay.app) API * **[SponSkrub Integration](#sponskrub-sponsorblock-options)**: You can use [SponSkrub](https://github.com/pukkandan/SponSkrub) to mark/remove sponsor sections in youtube videos by utilizing the [SponsorBlock](https://sponsor.ajay.app) API
* **[Format Sorting](#sorting-formats)**: The default format sorting options have been changed so that higher resolution and better codecs will be now preferred instead of simply using larger bitrate. Furthermore, you can now specify the sort order using `-S`. This allows for much easier format selection that what is possible by simply using `--format` ([examples](#format-selection-examples)) * **[Format Sorting](#sorting-formats)**: The default format sorting options have been changed so that higher resolution and better codecs will be now preferred instead of simply using larger bitrate. Furthermore, you can now specify the sort order using `-S`. This allows for much easier format selection that what is possible by simply using `--format` ([examples](#format-selection-examples))
* **Merged with youtube-dl v2021.01.08**: You get all the latest features and patches of [youtube-dl](https://github.com/ytdl-org/youtube-dl) in addition to all the features of [youtube-dlc](https://github.com/blackjack4494/yt-dlc) * **Merged with youtube-dl v2021.01.24.1**: 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)
* **Youtube improvements**: * **Youtube improvements**:
* All Youtube Feeds (`:ytfav`, `:ytwatchlater`, `:ytsubs`, `:ythistory`, `:ytrec`) works correctly and support downloading multiple pages of content * All Youtube Feeds (`:ytfav`, `:ytwatchlater`, `:ytsubs`, `:ythistory`, `:ytrec`) works correctly and support downloading multiple pages of content
* Youtube search works correctly (`ytsearch:`, `ytsearchdate:`) along with Search URLs * Youtube search works correctly (`ytsearch:`, `ytsearchdate:`) along with Search URLs
* Redirect channel's home URL automatically to `/video` to preserve the old behaviour * Redirect channel's home URL automatically to `/video` to preserve the old behaviour
* **New extractors**: AnimeLab, Philo MSO, Rcs, Gedi, bitwave.tv * **New extractors**: AnimeLab, Philo MSO, Rcs, Gedi, bitwave.tv, mildom
* **Fixed extractors**: archive.org, roosterteeth.com, skyit, instagram, itv, SouthparkDe, spreaker, Vlive, tiktok, akamai, ina * **Fixed extractors**: archive.org, roosterteeth.com, skyit, instagram, itv, SouthparkDe, spreaker, Vlive, tiktok, akamai, ina
* **New options**: `--list-formats-as-table`, `--write-link`, `--force-download-archive`, `--force-overwrites` etc * **Plugin support**: Extractors can be loaded from an external file. See [plugins](#plugins) for details
and many other features and patches. See [changelog](Changelog.md) or [commits](https://github.com/pukkandan/yt-dlp/commits) for the full list of changes * **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
* **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
* **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
**PS**: Some of these changes are already in youtube-dlc, but are still unreleased. See [this](Changelog.md#unreleased-changes-in-blackjack4494yt-dlc) for details **PS**: Some of these changes are already in youtube-dlc, but are still unreleased. See [this](Changelog.md#unreleased-changes-in-blackjack4494yt-dlc) for details
@@ -123,9 +131,9 @@ Then simply type this
permissions (run with sudo if needed) permissions (run with sudo if needed)
-i, --ignore-errors Continue on download errors, for example to -i, --ignore-errors Continue on download errors, for example to
skip unavailable videos in a playlist skip unavailable videos in a playlist
(default) (Same as --no-abort-on-error) (default) (Alias: --no-abort-on-error)
--abort-on-error Abort downloading of further videos if an --abort-on-error Abort downloading of further videos if an
error occurs (Same as --no-ignore-errors) error occurs (Alias: --no-ignore-errors)
--dump-user-agent Display the current browser identification --dump-user-agent Display the current browser identification
--list-extractors List all supported extractors --list-extractors List all supported extractors
--extractor-descriptions Output descriptions of all supported --extractor-descriptions Output descriptions of all supported
@@ -140,25 +148,25 @@ Then simply type this
warning when guessing). "error" just throws warning when guessing). "error" just throws
an error. The default value "fixup_error" an error. The default value "fixup_error"
repairs broken URLs, but emits an error if repairs broken URLs, but emits an error if
this is not possible instead of searching. this is not possible instead of searching
--ignore-config, --no-config Disable loading any configuration files --ignore-config, --no-config Disable loading any configuration files
except the one provided by --config- except the one provided by --config-location.
location. When given inside a configuration When given inside a configuration
file, no further configuration files are file, no further configuration files are
loaded. Additionally, (for backward loaded. Additionally, (for backward
compatibility) if this option is found compatibility) if this option is found
inside the system configuration file, the inside the system configuration file, the
user configuration is not loaded. user configuration is not loaded
--config-location PATH Location of the configuration file; either --config-location PATH Location of the main configuration file;
the path to the config or its containing either the path to the config or its
directory. containing directory
--flat-playlist Do not extract the videos of a playlist, --flat-playlist Do not extract the videos of a playlist,
only list them. only list them
--flat-videos Do not resolve the video urls --flat-videos Do not resolve the video urls
--no-flat-playlist Extract the videos of a playlist --no-flat-playlist Extract the videos of a playlist
--mark-watched Mark videos watched (YouTube only) --mark-watched Mark videos watched (YouTube only)
--no-mark-watched Do not mark videos watched --no-mark-watched Do not mark videos watched
--no-color Do not emit color codes in output --no-colors Do not emit color codes in output
## Network Options: ## Network Options:
--proxy URL Use the specified HTTP/HTTPS/SOCKS proxy. --proxy URL Use the specified HTTP/HTTPS/SOCKS proxy.
@@ -176,7 +184,7 @@ Then simply type this
some geo-restricted sites. The default some geo-restricted sites. The default
proxy specified by --proxy (or none, if the proxy specified by --proxy (or none, if the
option is not present) is used for the option is not present) is used for the
actual downloading. actual downloading
--geo-bypass Bypass geographic restriction via faking --geo-bypass Bypass geographic restriction via faking
X-Forwarded-For HTTP header X-Forwarded-For HTTP header
--no-geo-bypass Do not bypass geographic restriction via --no-geo-bypass Do not bypass geographic restriction via
@@ -198,7 +206,7 @@ Then simply type this
indexed 1, 2, 5, 8 in the playlist. You can indexed 1, 2, 5, 8 in the playlist. You can
specify range: "--playlist-items specify range: "--playlist-items
1-3,7,10-13", it will download the videos 1-3,7,10-13", it will download the videos
at index 1, 2, 3, 7, 10, 11, 12 and 13. at index 1, 2, 3, 7, 10, 11, 12 and 13
--match-title REGEX Download only matching titles (regex or --match-title REGEX Download only matching titles (regex or
caseless sub-string) caseless sub-string)
--reject-title REGEX Skip download for matching titles (regex or --reject-title REGEX Skip download for matching titles (regex or
@@ -222,38 +230,38 @@ Then simply type this
--max-views COUNT Do not download any videos with more than --max-views COUNT Do not download any videos with more than
COUNT views COUNT views
--match-filter FILTER Generic video filter. Specify any key (see --match-filter FILTER Generic video filter. Specify any key (see
the "OUTPUT TEMPLATE" for a list of "OUTPUT TEMPLATE" for a list of available
available keys) to match if the key is keys) to match if the key is present, !key
present, !key to check if the key is not to check if the key is not present,
present, key > NUMBER (like "comment_count key>NUMBER (like "comment_count > 12", also
> 12", also works with >=, <, <=, !=, =) to works with >=, <, <=, !=, =) to compare
compare against a number, key = 'LITERAL' against a number, key = 'LITERAL' (like
(like "uploader = 'Mike Smith'", also works "uploader = 'Mike Smith'", also works with
with !=) to match against a string literal !=) to match against a string literal and &
and & to require multiple matches. Values to require multiple matches. Values which
which are not known are excluded unless you are not known are excluded unless you put a
put a question mark (?) after the operator. question mark (?) after the operator. For
For example, to only match videos that have example, to only match videos that have
been liked more than 100 times and disliked been liked more than 100 times and disliked
less than 50 times (or the dislike less than 50 times (or the dislike
functionality is not available at the given functionality is not available at the given
service), but who also have a description, service), but who also have a description,
use --match-filter "like_count > 100 & use --match-filter "like_count > 100 &
dislike_count <? 50 & description" . dislike_count <? 50 & description"
--no-match-filter Do not use generic video filter (default) --no-match-filter Do not use generic video filter (default)
--no-playlist Download only the video, if the URL refers --no-playlist Download only the video, if the URL refers
to a video and a playlist. to a video and a playlist
--yes-playlist Download the playlist, if the URL refers to --yes-playlist Download the playlist, if the URL refers to
a video and a playlist. a video and a playlist
--age-limit YEARS Download only videos suitable for the given --age-limit YEARS Download only videos suitable for the given
age age
--download-archive FILE Download only videos not listed in the --download-archive FILE Download only videos not listed in the
archive file. Record the IDs of all archive file. Record the IDs of all
downloaded videos in it. downloaded videos in it
--break-on-existing Stop the download process when encountering --break-on-existing Stop the download process when encountering
a file that's in the archive. a file that is in the archive
--break-on-reject Stop the download process when encountering --break-on-reject Stop the download process when encountering
a file that has been filtered out. a file that has been filtered out
--no-download-archive Do not use archive file (default) --no-download-archive Do not use archive file (default)
--include-ads Download advertisements as well --include-ads Download advertisements as well
(experimental) (experimental)
@@ -263,15 +271,15 @@ Then simply type this
-r, --limit-rate RATE Maximum download rate in bytes per second -r, --limit-rate RATE Maximum download rate in bytes per second
(e.g. 50K or 4.2M) (e.g. 50K or 4.2M)
-R, --retries RETRIES Number of retries (default is 10), or -R, --retries RETRIES Number of retries (default is 10), or
"infinite". "infinite"
--fragment-retries RETRIES Number of retries for a fragment (default --fragment-retries RETRIES Number of retries for a fragment (default
is 10), or "infinite" (DASH, hlsnative and is 10), or "infinite" (DASH, hlsnative and
ISM) ISM)
--skip-unavailable-fragments Skip unavailable fragments for DASH, --skip-unavailable-fragments Skip unavailable fragments for DASH,
hlsnative and ISM (default) hlsnative and ISM (default)
(Same as --no-abort-on-unavailable-fragment) (Alias: --no-abort-on-unavailable-fragment)
--abort-on-unavailable-fragment Abort downloading if a fragment is unavailable --abort-on-unavailable-fragment Abort downloading if a fragment is unavailable
(Same as --no-skip-unavailable-fragments) (Alias: --no-skip-unavailable-fragments)
--keep-fragments Keep downloaded fragments on disk after --keep-fragments Keep downloaded fragments on disk after
downloading is finished downloading is finished
--no-keep-fragments Delete downloaded fragments after --no-keep-fragments Delete downloaded fragments after
@@ -301,19 +309,36 @@ Then simply type this
allowing to play the video while allowing to play the video while
downloading (some players may not be able downloading (some players may not be able
to play it) to play it)
--external-downloader COMMAND Use the specified external downloader. --external-downloader NAME Use the specified external downloader.
Currently supports Currently supports aria2c, avconv, axel,
aria2c,avconv,axel,curl,ffmpeg,httpie,wget curl, ffmpeg, httpie, wget
--external-downloader-args ARGS Give these arguments to the external --downloader-args NAME:ARGS Give these arguments to the external
downloader downloader. Specify the downloader name and
the arguments separated by a colon ":". You
can use this option multiple times (Alias:
--external-downloader-args)
## Filesystem Options: ## Filesystem Options:
-a, --batch-file FILE File containing URLs to download ('-' for -a, --batch-file FILE File containing URLs to download ('-' for
stdin), one URL per line. Lines starting stdin), one URL per line. Lines starting
with '#', ';' or ']' are considered as with '#', ';' or ']' are considered as
comments and ignored. comments and ignored
-o, --output TEMPLATE Output filename template, see the "OUTPUT -P, --paths TYPE:PATH The paths where the files should be
downloaded. Specify the type of file and
the path separated by a colon ":"
(supported: description|annotation|subtitle
|infojson|thumbnail). Additionally, you can
also provide "home" and "temp" paths. All
intermediary files are first downloaded to
the temp path and then the final files are
moved over to the home path after download
is finished. Note that this option is
ignored if --output is an absolute path
-o, --output TEMPLATE Output filename template, see "OUTPUT
TEMPLATE" for details TEMPLATE" for details
--output-na-placeholder TEXT Placeholder value for unavailable meta
fields in output filename template
(default: "NA")
--autonumber-start NUMBER Specify the start value for %(autonumber)s --autonumber-start NUMBER Specify the start value for %(autonumber)s
(default is 1) (default is 1)
--restrict-filenames Restrict filenames to only ASCII --restrict-filenames Restrict filenames to only ASCII
@@ -358,7 +383,7 @@ Then simply type this
~/.cache/youtube-dl . At the moment, only ~/.cache/youtube-dl . At the moment, only
YouTube player files (for videos with YouTube player files (for videos with
obfuscated signatures) are cached, but that obfuscated signatures) are cached, but that
may change. may change
--no-cache-dir Disable filesystem caching --no-cache-dir Disable filesystem caching
--rm-cache-dir Delete all filesystem cache files --rm-cache-dir Delete all filesystem cache files
--trim-file-name LENGTH Limit the filename length (extension --trim-file-name LENGTH Limit the filename length (extension
@@ -373,13 +398,13 @@ Then simply type this
formats formats
## Internet Shortcut Options: ## Internet Shortcut Options:
--write-link Write an internet shortcut file, depending on --write-link Write an internet shortcut file, depending
the current platform (.url/.webloc/.desktop). on the current platform (.url, .webloc or
The URL may be cached by the OS. .desktop). The URL may be cached by the OS
--write-url-link Write a Windows .url internet shortcut file. --write-url-link Write a .url Windows internet shortcut. The
(The OS caches the URL based on the file path) OS caches the URL based on the file path
--write-webloc-link Write a .webloc macOS internet shortcut file --write-webloc-link Write a .webloc macOS internet shortcut
--write-desktop-link Write a .desktop Linux internet shortcut file --write-desktop-link Write a .desktop Linux internet shortcut
## Verbosity / Simulation Options: ## Verbosity / Simulation Options:
-q, --quiet Activate quiet mode -q, --quiet Activate quiet mode
@@ -396,18 +421,18 @@ Then simply type this
--get-filename Simulate, quiet but print output filename --get-filename Simulate, quiet but print output filename
--get-format Simulate, quiet but print output format --get-format Simulate, quiet but print output format
-j, --dump-json Simulate, quiet but print JSON information. -j, --dump-json Simulate, quiet but print JSON information.
See the "OUTPUT TEMPLATE" for a description See "OUTPUT TEMPLATE" for a description of
of available keys. available keys
-J, --dump-single-json Simulate, quiet but print JSON information -J, --dump-single-json Simulate, quiet but print JSON information
for each command-line argument. If the URL for each command-line argument. If the URL
refers to a playlist, dump the whole refers to a playlist, dump the whole
playlist information in a single line. playlist information in a single line
--print-json Be quiet and print the video information as --print-json Be quiet and print the video information as
JSON (video is still being downloaded). JSON (video is still being downloaded)
--force-write-archive Force download archive entries to be written --force-write-archive Force download archive entries to be
as far as no errors occur, even if -s or written as far as no errors occur,even if
another simulation switch is used. -s or another simulation switch is used
(Same as --force-download-archive) (Alias: --force-download-archive)
--newline Output progress bar as new lines --newline Output progress bar as new lines
--no-progress Do not print progress bar --no-progress Do not print progress bar
--console-title Display progress in console titlebar --console-title Display progress in console titlebar
@@ -433,7 +458,7 @@ Then simply type this
--referer URL Specify a custom referer, use if the video --referer URL Specify a custom referer, use if the video
access is restricted to one domain access is restricted to one domain
--add-header FIELD:VALUE Specify a custom HTTP header and its value, --add-header FIELD:VALUE Specify a custom HTTP header and its value,
separated by a colon ':'. You can use this separated by a colon ":". You can use this
option multiple times option multiple times
--bidi-workaround Work around terminals that lack --bidi-workaround Work around terminals that lack
bidirectional text support. Requires bidiv bidirectional text support. Requires bidiv
@@ -443,11 +468,11 @@ Then simply type this
of a range for randomized sleep before each of a range for randomized sleep before each
download (minimum possible number of download (minimum possible number of
seconds to sleep) when used along with seconds to sleep) when used along with
--max-sleep-interval. --max-sleep-interval
--max-sleep-interval SECONDS Upper bound of a range for randomized sleep --max-sleep-interval SECONDS Upper bound of a range for randomized sleep
before each download (maximum possible before each download (maximum possible
number of seconds to sleep). Must only be number of seconds to sleep). Must only be
used along with --min-sleep-interval. used along with --min-sleep-interval
--sleep-subtitles SECONDS Enforce sleep interval on subtitles as well --sleep-subtitles SECONDS Enforce sleep interval on subtitles as well
## Video Format Options: ## Video Format Options:
@@ -474,22 +499,22 @@ Then simply type this
formats of same quality formats of same quality
-F, --list-formats List all available formats of requested -F, --list-formats List all available formats of requested
videos videos
--list-formats-as-table Present the output of -F in a more tabular --list-formats-as-table Present the output of -F in tabular form
form (default) (default)
(Same as --no-list-formats-as-table)
--list-formats-old Present the output of -F in the old form --list-formats-old Present the output of -F in the old form
--youtube-include-dash-manifest Download the DASH manifests and related data (Alias: --no-list-formats-as-table)
on YouTube videos (default) --youtube-include-dash-manifest Download the DASH manifests and related
(Same as --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 --youtube-skip-dash-manifest Do not download the DASH manifests and
related data on YouTube videos related data on YouTube videos (Alias:
(Same as --no-youtube-include-dash-manifest) --no-youtube-include-dash-manifest)
--youtube-include-hls-manifest Download the HLS manifests and related data --youtube-include-hls-manifest Download the HLS manifests and related data
on YouTube videos (default) on YouTube videos (default) (Alias:
(Same as --no-youtube-skip-hls-manifest) --no-youtube-skip-hls-manifest)
--youtube-skip-hls-manifest Do not download the HLS manifests and --youtube-skip-hls-manifest Do not download the HLS manifests and
related data on YouTube videos related data on YouTube videos (Alias:
(Same as --no-youtube-include-hls-manifest) --no-youtube-include-hls-manifest)
--merge-output-format FORMAT If a merge is required (e.g. --merge-output-format FORMAT If a merge is required (e.g.
bestvideo+bestaudio), output to given bestvideo+bestaudio), output to given
container format. One of mkv, mp4, ogg, container format. One of mkv, mp4, ogg,
@@ -515,7 +540,7 @@ Then simply type this
## Authentication Options: ## Authentication Options:
-u, --username USERNAME Login with this account ID -u, --username USERNAME Login with this account ID
-p, --password PASSWORD Account password. If this option is left -p, --password PASSWORD Account password. If this option is left
out, youtube-dlc will ask interactively. out, youtube-dlc will ask interactively
-2, --twofactor TWOFACTOR Two-factor authentication code -2, --twofactor TWOFACTOR Two-factor authentication code
-n, --netrc Use .netrc authentication data -n, --netrc Use .netrc authentication data
--video-password PASSWORD Video password (vimeo, youku) --video-password PASSWORD Video password (vimeo, youku)
@@ -527,7 +552,7 @@ Then simply type this
--ap-username USERNAME Multiple-system operator account login --ap-username USERNAME Multiple-system operator account login
--ap-password PASSWORD Multiple-system operator account password. --ap-password PASSWORD Multiple-system operator account password.
If this option is left out, youtube-dlc If this option is left out, youtube-dlc
will ask interactively. will ask interactively
--ap-list-mso List all supported multiple-system --ap-list-mso List all supported multiple-system
operators operators
@@ -551,18 +576,25 @@ Then simply type this
re-encoding is necessary (currently re-encoding is necessary (currently
supported: mp4|flv|ogg|webm|mkv|avi) supported: mp4|flv|ogg|webm|mkv|avi)
--postprocessor-args NAME:ARGS Give these arguments to the postprocessors. --postprocessor-args NAME:ARGS Give these arguments to the postprocessors.
Specify the postprocessor name and the Specify the postprocessor/executable name
arguments separated by a colon ':' to give and the arguments separated by a colon ":"
the argument to only the specified to give the argument to the specified
postprocessor. Supported names are postprocessor/executable. Supported
postprocessors are: SponSkrub,
ExtractAudio, VideoRemuxer, VideoConvertor, ExtractAudio, VideoRemuxer, VideoConvertor,
EmbedSubtitle, Metadata, Merger, EmbedSubtitle, Metadata, Merger,
FixupStretched, FixupM4a, FixupM3u8, FixupStretched, FixupM4a, FixupM3u8,
SubtitlesConvertor, EmbedThumbnail, SubtitlesConvertor and EmbedThumbnail. The
XAttrMetadata, SponSkrub and Default. You supported executables are: SponSkrub,
can use this option multiple times to give FFmpeg, FFprobe, avconf, avprobe and
different arguments to different AtomicParsley. You can use this option
postprocessors 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 -k, --keep-video Keep the intermediate video file on disk
after post-processing after post-processing
--no-keep-video Delete the intermediate video file after --no-keep-video Delete the intermediate video file after
@@ -594,13 +626,14 @@ Then simply type this
default; fix file if we can, warn default; fix file if we can, warn
otherwise) otherwise)
--prefer-avconv Prefer avconv over ffmpeg for running the --prefer-avconv Prefer avconv over ffmpeg for running the
postprocessors (Same as --no-prefer-ffmpeg) postprocessors (Alias: --no-prefer-ffmpeg)
--prefer-ffmpeg Prefer ffmpeg over avconv for running the --prefer-ffmpeg Prefer ffmpeg over avconv for running the
postprocessors (default) postprocessors (default)
(Same as --no-prefer-avconv) (Alias: --no-prefer-avconv)
--ffmpeg-location PATH Location of the ffmpeg/avconv binary; --ffmpeg-location PATH Location of the ffmpeg/avconv binary;
either the path to the binary or its either the path to the binary or its
containing directory. containing directory
(Alias: --avconv-location)
--exec CMD Execute a command on the file after --exec CMD Execute a command on the file after
downloading and post-processing, similar to downloading and post-processing, similar to
find's -exec syntax. Example: --exec 'adb find's -exec syntax. Example: --exec 'adb
@@ -608,11 +641,14 @@ Then simply type this
--convert-subs FORMAT Convert the subtitles to other format --convert-subs FORMAT Convert the subtitles to other format
(currently supported: srt|ass|vtt|lrc) (currently supported: srt|ass|vtt|lrc)
## [SponSkrub](https://github.com/pukkandan/SponSkrub) Options ([SponsorBlock](https://sponsor.ajay.app)): ## SponSkrub (SponsorBlock) Options:
--sponskrub Use sponskrub to mark sponsored sections [SponSkrub](https://github.com/pukkandan/SponSkrub) is a utility to
with the data available in SponsorBlock mark/remove sponsor segments from downloaded YouTube videos using
API. This is enabled by default if the [SponsorBlock API](https://sponsor.ajay.app)
sponskrub binary exists (Youtube only)
--sponskrub Use sponskrub to mark sponsored sections.
This is enabled by default if the sponskrub
binary exists (Youtube only)
--no-sponskrub Do not use sponskrub --no-sponskrub Do not use sponskrub
--sponskrub-cut Cut out the sponsor sections instead of --sponskrub-cut Cut out the sponsor sections instead of
simply marking them simply marking them
@@ -624,20 +660,21 @@ Then simply type this
video was already downloaded (default) video was already downloaded (default)
--sponskrub-location PATH Location of the sponskrub binary; either --sponskrub-location PATH Location of the sponskrub binary; either
the path to the binary or its containing the path to the binary or its containing
directory. directory
## Extractor Options: ## Extractor Options:
--ignore-dynamic-mpd Do not process dynamic DASH manifests
(Same as --no-allow-dynamic-mpd)
--allow-dynamic-mpd Process dynamic DASH manifests (default) --allow-dynamic-mpd Process dynamic DASH manifests (default)
(Same as --no-ignore-dynamic-mpd) (Alias: --no-ignore-dynamic-mpd)
--ignore-dynamic-mpd Do not process dynamic DASH manifests
(Alias: --no-allow-dynamic-mpd)
# CONFIGURATION # CONFIGURATION
You can configure youtube-dlc by placing any supported command line option to a configuration file. The configuration is loaded from the following locations: You can configure youtube-dlc by placing any supported command line option to a configuration file. The configuration is loaded from the following locations:
1. The file given by `--config-location` 1. **Main Configuration**: The file given by `--config-location`
1. **Portable Configuration**: `yt-dlp.conf` or `youtube-dlc.conf` in the same directory as the bundled binary. If you are running from source-code (`<root dir>/youtube_dlc/__main__.py`), the root directory is used instead. 1. **Portable Configuration**: `yt-dlp.conf` or `youtube-dlc.conf` in the same directory as the bundled binary. If you are running from source-code (`<root dir>/youtube_dlc/__main__.py`), the root directory is used instead.
1. **Home Configuration**: `yt-dlp.conf` or `youtube-dlc.conf` in the home path given by `-P "home:<path>"`, or in the current directory if no such path is given
1. **User Configuration**: 1. **User Configuration**:
* `%XDG_CONFIG_HOME%/yt-dlp/config` (recommended on Linux/macOS) * `%XDG_CONFIG_HOME%/yt-dlp/config` (recommended on Linux/macOS)
* `%XDG_CONFIG_HOME%/yt-dlp.conf` * `%XDG_CONFIG_HOME%/yt-dlp.conf`
@@ -695,7 +732,7 @@ set HOME=%USERPROFILE%
# OUTPUT TEMPLATE # OUTPUT TEMPLATE
The `-o` option allows users to indicate a template for the output file names. The `-o` option is used to indicate a template for the output file names while `-P` option is used to specify the path each type of file should be saved to.
**tl;dr:** [navigate me to examples](#output-template-examples). **tl;dr:** [navigate me to examples](#output-template-examples).
@@ -786,7 +823,7 @@ Available for the media that is a track or a part of a music album:
- `disc_number` (numeric): Number of the disc or other physical medium the track belongs to - `disc_number` (numeric): Number of the disc or other physical medium the track belongs to
- `release_year` (numeric): Year (YYYY) when the album was released - `release_year` (numeric): Year (YYYY) when the album was released
Each aforementioned sequence when referenced in an output template will be replaced by the actual value corresponding to the sequence name. Note that some of the sequences are not guaranteed to be present since they depend on the metadata obtained by a particular extractor. Such sequences will be replaced with `NA`. Each aforementioned sequence when referenced in an output template will be replaced by the actual value corresponding to the sequence name. Note that some of the sequences are not guaranteed to be present since they depend on the metadata obtained by a particular extractor. Such sequences will be replaced with placeholder value provided with `--output-na-placeholder` (`NA` by default).
For example for `-o %(title)s-%(id)s.%(ext)s` and an mp4 video with title `youtube-dlc test video` and id `BaW_jenozKcj`, this will result in a `youtube-dlc test video-BaW_jenozKcj.mp4` file created in the current directory. For example for `-o %(title)s-%(id)s.%(ext)s` and an mp4 video with title `youtube-dlc test video` and id `BaW_jenozKcj`, this will result in a `youtube-dlc test video-BaW_jenozKcj.mp4` file created in the current directory.
@@ -904,35 +941,35 @@ Format selectors can also be grouped using parentheses, for example if you want
You can change the criteria for being considered the `best` by using `-S` (`--format-sort`). The general format for this is `--format-sort field1,field2...`. The available fields are: You can change the criteria for being considered the `best` by using `-S` (`--format-sort`). The general format for this is `--format-sort field1,field2...`. The available fields are:
- `video`, `has_video`: Gives priority to formats that has a video stream - `hasvid`: Gives priority to formats that has a video stream
- `audio`, `has_audio`: Gives priority to formats that has a audio stream - `hasaud`: Gives priority to formats that has a audio stream
- `extractor`, `preference`, `extractor_preference`: The format preference as given by the extractor - `ie_pref`: The format preference as given by the extractor
- `lang`, `language_preference`: Language preference as given by the extractor - `lang`: Language preference as given by the extractor
- `quality`: The quality of the format. This is a metadata field available in some websites - `quality`: The quality of the format. This is a metadata field available in some websites
- `source`, `source_preference`: Preference of the source as given by the extractor - `source`: Preference of the source as given by the extractor
- `proto`, `protocol`: Protocol used for download (`https`/`ftps` > `http`/`ftp` > `m3u8-native` > `m3u8` > `http-dash-segments` > other > `mms`/`rtsp` > unknown > `f4f`/`f4m`) - `proto`: Protocol used for download (`https`/`ftps` > `http`/`ftp` > `m3u8-native` > `m3u8` > `http-dash-segments` > other > `mms`/`rtsp` > unknown > `f4f`/`f4m`)
- `vcodec`, `video_codec`: Video Codec (`vp9` > `h265` > `h264` > `vp8` > `h263` > `theora` > other > unknown) - `vcodec`: Video Codec (`vp9` > `h265` > `h264` > `vp8` > `h263` > `theora` > other > unknown)
- `acodec`, `audio_codec`: Audio Codec (`opus` > `vorbis` > `aac` > `mp4a` > `mp3` > `ac3` > `dts` > other > unknown) - `acodec`: Audio Codec (`opus` > `vorbis` > `aac` > `mp4a` > `mp3` > `ac3` > `dts` > other > unknown)
- `codec`: Equivalent to `vcodec,acodec` - `codec`: Equivalent to `vcodec,acodec`
- `vext`, `video_ext`: Video Extension (`mp4` > `webm` > `flv` > other > unknown). If `--prefer-free-formats` is used, `webm` is prefered. - `vext`: Video Extension (`mp4` > `webm` > `flv` > other > unknown). If `--prefer-free-formats` is used, `webm` is prefered.
- `aext`, `audio_ext`: Audio Extension (`m4a` > `aac` > `mp3` > `ogg` > `opus` > `webm` > other > unknown). If `--prefer-free-formats` is used, the order changes to `opus` > `ogg` > `webm` > `m4a` > `mp3` > `aac`. - `aext`: Audio Extension (`m4a` > `aac` > `mp3` > `ogg` > `opus` > `webm` > other > unknown). If `--prefer-free-formats` is used, the order changes to `opus` > `ogg` > `webm` > `m4a` > `mp3` > `aac`.
- `ext`, `extension`: Equivalent to `vext,aext` - `ext`: Equivalent to `vext,aext`
- `filesize`: Exact filesize, if know in advance. This will be unavailable for mu38 and DASH formats. - `filesize`: Exact filesize, if know in advance. This will be unavailable for mu38 and DASH formats.
- `filesize_approx`: Approximate filesize calculated from the manifests - `fs_approx`: Approximate filesize calculated from the manifests
- `size`, `filesize_estimate`: Exact filesize if available, otherwise approximate filesize - `size`: Exact filesize if available, otherwise approximate filesize
- `height`: Height of video - `height`: Height of video
- `width`: Width of video - `width`: Width of video
- `res`, `dimension`: Video resolution, calculated as the smallest dimension. - `res`: Video resolution, calculated as the smallest dimension.
- `fps`, `framerate`: Framerate of video - `fps`: Framerate of video
- `tbr`, `total_bitrate`: Total average bitrate in KBit/s - `tbr`: Total average bitrate in KBit/s
- `vbr`, `video_bitrate`: Average video bitrate in KBit/s - `vbr`: Average video bitrate in KBit/s
- `abr`, `audio_bitrate`: Average audio bitrate in KBit/s - `abr`: Average audio bitrate in KBit/s
- `br`, `bitrate`: Equivalent to using `tbr,vbr,abr` - `br`: Equivalent to using `tbr,vbr,abr`
- `samplerate`, `asr`: Audio sample rate in Hz - `asr`: Audio sample rate in Hz
Note that any other **numerical** field made available by the extractor can also be used. All fields, unless specified otherwise, are sorted in decending order. To reverse this, prefix the field with a `+`. Eg: `+res` prefers format with the smallest resolution. Additionally, you can suffix a prefered value for the fields, seperated by a `:`. Eg: `res:720` prefers larger videos, but no larger than 720p and the smallest video if there are no videos less than 720p. For `codec` and `ext`, you can provide two prefered values, the first for video and the second for audio. Eg: `+codec:avc:m4a` (equivalent to `+vcodec:avc,+acodec:m4a`) sets the video codec preference to `h264` > `h265` > `vp9` > `vp8` > `h263` > `theora` and audio codec preference to `mp4a` > `aac` > `vorbis` > `opus` > `mp3` > `ac3` > `dts`. You can also make the sorting prefer the nearest values to the provided by using `~` as the delimiter. Eg: `filesize~1G` prefers the format with filesize closest to 1 GiB. Note that any other **numerical** field made available by the extractor can also be used. All fields, unless specified otherwise, are sorted in decending order. To reverse this, prefix the field with a `+`. Eg: `+res` prefers format with the smallest resolution. Additionally, you can suffix a prefered value for the fields, seperated by a `:`. Eg: `res:720` prefers larger videos, but no larger than 720p and the smallest video if there are no videos less than 720p. For `codec` and `ext`, you can provide two prefered values, the first for video and the second for audio. Eg: `+codec:avc:m4a` (equivalent to `+vcodec:avc,+acodec:m4a`) sets the video codec preference to `h264` > `h265` > `vp9` > `vp8` > `h263` > `theora` and audio codec preference to `mp4a` > `aac` > `vorbis` > `opus` > `mp3` > `ac3` > `dts`. You can also make the sorting prefer the nearest values to the provided by using `~` as the delimiter. Eg: `filesize~1G` prefers the format with filesize closest to 1 GiB.
The fields `has_video`, `extractor`, `lang`, `quality` are always given highest priority in sorting, irrespective of the user-defined order. This behaviour can be changed by using `--force-format-sort`. Apart from these, the default order used is: `res,fps,codec,size,br,asr,proto,ext,has_audio,source,format_id`. Note that the extractors may override this default order, but they cannot override the user-provided order. The fields `hasvid`, `ie_pref`, `lang`, `quality` are always given highest priority in sorting, irrespective of the user-defined order. This behaviour can be changed by using `--force-format-sort`. Apart from these, the default order used is: `res,fps,codec,size,br,asr,proto,ext,hasaud,source,id`. Note that the extractors may override this default order, but they cannot override the user-provided order.
If your format selector is `worst`, the last item is selected after sorting. This means it will select the format that is worst in all repects. Most of the time, what you actually want is the video with the smallest filesize instead. So it is generally better to use `-f best -S +size,+br,+res,+fps`. If your format selector is `worst`, the last item is selected after sorting. This means it will select the format that is worst in all repects. Most of the time, what you actually want is the video with the smallest filesize instead. So it is generally better to use `-f best -S +size,+br,+res,+fps`.
@@ -971,7 +1008,7 @@ $ youtube-dlc -f 'wv*+wa/w'
$ youtube-dlc -S '+res' $ youtube-dlc -S '+res'
# Download the smallest video available # Download the smallest video available
$ youtube-dlc -S '+size,+bitrate' $ youtube-dlc -S '+size,+br'
@@ -1019,7 +1056,7 @@ $ youtube-dlc -f '(bv*+ba/b)[protocol^=http][protocol!*=dash] / (bv*+ba/b)'
# Download best video available via the best protocol # Download best video available via the best protocol
# (https/ftps > http/ftp > m3u8_native > m3u8 > http_dash_segments ...) # (https/ftps > http/ftp > m3u8_native > m3u8 > http_dash_segments ...)
$ youtube-dlc -S 'protocol' $ youtube-dlc -S 'proto'
@@ -1055,9 +1092,11 @@ $ youtube-dlc -S 'res:720,fps'
$ youtube-dlc -S '+res:480,codec,br' $ youtube-dlc -S '+res:480,codec,br'
``` ```
# PLUGINS
Plugins are loaded from `<root-dir>/ytdlp_plugins/<type>/__init__.py`. Currently only `extractor` plugins are supported. Support for `downloader` and `postprocessor` plugins may be added in the future. See [ytdlp_plugins](ytdlp_plugins) for example.
**Note**: `<root-dir>` is the directory of the binary (`<root-dir>/youtube-dlc`), or the root directory of the module if you are running directly from source-code ((`<root dir>/youtube_dlc/__main__.py`)
# MORE # 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)
+12 -4
View File
@@ -47,12 +47,13 @@
- **Amara** - **Amara**
- **AMCNetworks** - **AMCNetworks**
- **AmericasTestKitchen** - **AmericasTestKitchen**
- **AmericasTestKitchenSeason**
- **anderetijden**: npo.nl, ntr.nl, omroepwnl.nl, zapp.nl and npo3.nl - **anderetijden**: npo.nl, ntr.nl, omroepwnl.nl, zapp.nl and npo3.nl
- **AnimeLab** - **AnimeLab**
- **AnimeLabShows** - **AnimeLabShows**
- **AnimeOnDemand** - **AnimeOnDemand**
- **Anvato** - **Anvato**
- **aol.com** - **aol.com**: Yahoo screen and movies
- **APA** - **APA**
- **Aparat** - **Aparat**
- **AppleConnect** - **AppleConnect**
@@ -197,8 +198,6 @@
- **CNNArticle** - **CNNArticle**
- **CNNBlogs** - **CNNBlogs**
- **ComedyCentral** - **ComedyCentral**
- **ComedyCentralFullEpisodes**
- **ComedyCentralShortname**
- **ComedyCentralTV** - **ComedyCentralTV**
- **CondeNast**: Condé Nast media group: Allure, Architectural Digest, Ars Technica, Bon Appétit, Brides, Condé Nast, Condé Nast Traveler, Details, Epicurious, GQ, Glamour, Golf Digest, SELF, Teen Vogue, The New Yorker, Vanity Fair, Vogue, W Magazine, WIRED - **CondeNast**: Condé Nast media group: Allure, Architectural Digest, Ars Technica, Bon Appétit, Brides, Condé Nast, Condé Nast Traveler, Details, Epicurious, GQ, Glamour, Golf Digest, SELF, Teen Vogue, The New Yorker, Vanity Fair, Vogue, W Magazine, WIRED
- **CONtv** - **CONtv**
@@ -520,6 +519,12 @@
- **Mgoon** - **Mgoon**
- **MGTV**: 芒果TV - **MGTV**: 芒果TV
- **MiaoPai** - **MiaoPai**
- **mildom**: Record ongoing live by specific user in Mildom
- **mildom:user:vod**: Download all VODs from specific user in Mildom
- **mildom:vod**: Download a VOD in Mildom
- **minds**
- **minds:channel**
- **minds:group**
- **MinistryGrid** - **MinistryGrid**
- **Minoto** - **Minoto**
- **miomio.tv** - **miomio.tv**
@@ -880,6 +885,8 @@
- **Sport5** - **Sport5**
- **SportBox** - **SportBox**
- **SportDeutschland** - **SportDeutschland**
- **spotify**
- **spotify:show**
- **Spreaker** - **Spreaker**
- **SpreakerPage** - **SpreakerPage**
- **SpreakerShow** - **SpreakerShow**
@@ -962,12 +969,13 @@
- **TNAFlixNetworkEmbed** - **TNAFlixNetworkEmbed**
- **toggle** - **toggle**
- **ToonGoggles** - **ToonGoggles**
- **Tosh**: Tosh.0
- **tou.tv** - **tou.tv**
- **Toypics**: Toypics video - **Toypics**: Toypics video
- **ToypicsUser**: Toypics user profile - **ToypicsUser**: Toypics user profile
- **TrailerAddict** (Currently broken) - **TrailerAddict** (Currently broken)
- **Trilulilu** - **Trilulilu**
- **Trovo**
- **TrovoVod**
- **TruNews** - **TruNews**
- **TruTV** - **TruTV**
- **Tube8** - **Tube8**
+1 -1
View File
@@ -1 +1 @@
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 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
+11 -4
View File
@@ -637,13 +637,20 @@ class TestYoutubeDL(unittest.TestCase):
'title2': '%PATH%', 'title2': '%PATH%',
} }
def fname(templ): def fname(templ, na_placeholder='NA'):
ydl = YoutubeDL({'outtmpl': templ}) params = {'outtmpl': templ}
if na_placeholder != 'NA':
params['outtmpl_na_placeholder'] = na_placeholder
ydl = YoutubeDL(params)
return ydl.prepare_filename(info) return ydl.prepare_filename(info)
self.assertEqual(fname('%(id)s.%(ext)s'), '1234.mp4') self.assertEqual(fname('%(id)s.%(ext)s'), '1234.mp4')
self.assertEqual(fname('%(id)s-%(width)s.%(ext)s'), '1234-NA.mp4') self.assertEqual(fname('%(id)s-%(width)s.%(ext)s'), '1234-NA.mp4')
# Replace missing fields with 'NA' NA_TEST_OUTTMPL = '%(uploader_date)s-%(width)d-%(id)s.%(ext)s'
self.assertEqual(fname('%(uploader_date)s-%(id)s.%(ext)s'), 'NA-1234.mp4') # Replace missing fields with 'NA' by default
self.assertEqual(fname(NA_TEST_OUTTMPL), 'NA-NA-1234.mp4')
# Or by provided placeholder
self.assertEqual(fname(NA_TEST_OUTTMPL, na_placeholder='none'), 'none-none-1234.mp4')
self.assertEqual(fname(NA_TEST_OUTTMPL, na_placeholder=''), '--1234.mp4')
self.assertEqual(fname('%(height)d.%(ext)s'), '1080.mp4') self.assertEqual(fname('%(height)d.%(ext)s'), '1080.mp4')
self.assertEqual(fname('%(height)6d.%(ext)s'), ' 1080.mp4') self.assertEqual(fname('%(height)6d.%(ext)s'), ' 1080.mp4')
self.assertEqual(fname('%(height)-6d.%(ext)s'), '1080 .mp4') self.assertEqual(fname('%(height)-6d.%(ext)s'), '1080 .mp4')
+3 -3
View File
@@ -8,11 +8,11 @@ import unittest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from test.helper import get_params, try_rm from test.helper import get_params, try_rm
import youtube_dl.YoutubeDL import youtube_dlc.YoutubeDL
from youtube_dl.utils import DownloadError from youtube_dlc.utils import DownloadError
class YoutubeDL(youtube_dl.YoutubeDL): class YoutubeDL(youtube_dlc.YoutubeDL):
def __init__(self, *args, **kwargs): def __init__(self, *args, **kwargs):
super(YoutubeDL, self).__init__(*args, **kwargs) super(YoutubeDL, self).__init__(*args, **kwargs)
self.to_stderr = self.to_screen self.to_stderr = self.to_screen
+1 -1
View File
@@ -1 +1 @@
py "%~dp0youtube_dlc\__main__.py" %* @py "%~dp0youtube_dlc\__main__.py" %*
+191 -96
View File
@@ -69,6 +69,7 @@ from .utils import (
iri_to_uri, iri_to_uri,
ISO3166Utils, ISO3166Utils,
locked_file, locked_file,
make_dir,
make_HTTPS_handler, make_HTTPS_handler,
MaxDownloadsReached, MaxDownloadsReached,
orderedSet, orderedSet,
@@ -104,7 +105,7 @@ from .utils import (
process_communicate_or_kill, process_communicate_or_kill,
) )
from .cache import Cache from .cache import Cache
from .extractor import get_info_extractor, gen_extractor_classes, _LAZY_LOADER from .extractor import get_info_extractor, gen_extractor_classes, _LAZY_LOADER, _PLUGIN_CLASSES
from .extractor.openload import PhantomJSwrapper from .extractor.openload import PhantomJSwrapper
from .downloader import get_suitable_downloader from .downloader import get_suitable_downloader
from .downloader.rtmp import rtmpdump_version from .downloader.rtmp import rtmpdump_version
@@ -114,8 +115,9 @@ from .postprocessor import (
FFmpegFixupStretchedPP, FFmpegFixupStretchedPP,
FFmpegMergerPP, FFmpegMergerPP,
FFmpegPostProcessor, FFmpegPostProcessor,
FFmpegSubtitlesConvertorPP, # FFmpegSubtitlesConvertorPP,
get_postprocessor, get_postprocessor,
MoveFilesAfterDownloadPP,
) )
from .version import __version__ from .version import __version__
@@ -179,9 +181,12 @@ class YoutubeDL(object):
allow_multiple_video_streams: Allow multiple video streams to be merged into a single file allow_multiple_video_streams: Allow multiple video streams to be merged into a single file
allow_multiple_audio_streams: Allow multiple audio streams to be merged into a single file allow_multiple_audio_streams: Allow multiple audio streams to be merged into a single file
outtmpl: Template for output names. outtmpl: Template for output names.
restrictfilenames: Do not allow "&" and spaces in file names. outtmpl_na_placeholder: Placeholder for unavailable meta fields.
trim_file_name: Limit length of filename (extension excluded). restrictfilenames: Do not allow "&" and spaces in file names
ignoreerrors: Do not stop on download errors. (Default True when running youtube-dlc, but False when directly accessing YoutubeDL class) trim_file_name: Limit length of filename (extension excluded)
ignoreerrors: Do not stop on download errors
(Default True when running youtube-dlc,
but False when directly accessing YoutubeDL class)
force_generic_extractor: Force downloader to use the generic extractor force_generic_extractor: Force downloader to use the generic extractor
overwrites: Overwrite all video and metadata files if True, overwrites: Overwrite all video and metadata files if True,
overwrite only non-video files if None overwrite only non-video files if None
@@ -232,10 +237,11 @@ class YoutubeDL(object):
download_archive: File name of a file where all downloads are recorded. download_archive: File name of a file where all downloads are recorded.
Videos already present in the file are not downloaded Videos already present in the file are not downloaded
again. again.
break_on_existing: Stop the download process after attempting to download a file that's break_on_existing: Stop the download process after attempting to download a
in the archive. file that is in the archive.
break_on_reject: Stop the download process when encountering a video that has been filtered out. break_on_reject: Stop the download process when encountering a video that
cookiefile: File name where cookies should be read from and dumped to. has been filtered out.
cookiefile: File name where cookies should be read from and dumped to
nocheckcertificate:Do not verify SSL certificates nocheckcertificate:Do not verify SSL certificates
prefer_insecure: Use HTTP instead of HTTPS to retrieve information. prefer_insecure: Use HTTP instead of HTTPS to retrieve information.
At the moment, this is only supported by YouTube. At the moment, this is only supported by YouTube.
@@ -256,6 +262,8 @@ class YoutubeDL(object):
postprocessors: A list of dictionaries, each with an entry postprocessors: A list of dictionaries, each with an entry
* key: The name of the postprocessor. See * key: The name of the postprocessor. See
youtube_dlc/postprocessor/__init__.py for a list. youtube_dlc/postprocessor/__init__.py for a list.
* _after_move: Optional. If True, run this post_processor
after 'MoveFilesAfterDownload'
as well as any further keyword arguments for the as well as any further keyword arguments for the
postprocessor. postprocessor.
post_hooks: A list of functions that get called as the final step post_hooks: A list of functions that get called as the final step
@@ -342,10 +350,11 @@ class YoutubeDL(object):
otherwise prefer ffmpeg. otherwise prefer ffmpeg.
ffmpeg_location: Location of the ffmpeg/avconv binary; either the path ffmpeg_location: Location of the ffmpeg/avconv binary; either the path
to the binary or its containing directory. to the binary or its containing directory.
postprocessor_args: A dictionary of postprocessor names (in lower case) and a list postprocessor_args: A dictionary of postprocessor/executable keys (in lower case)
of additional command-line arguments for the postprocessor. and a list of additional command-line arguments for the
Use 'default' as the name for arguments to passed to all PP. postprocessor/executable. The dict can also have "PP+EXE" keys
which are used when the given exe is used by the given PP.
Use 'default' as the name for arguments to passed to all PP
The following options are used by the Youtube extractor: The following options are used by the Youtube extractor:
youtube_include_dash_manifest: If True (default), DASH manifests and related youtube_include_dash_manifest: If True (default), DASH manifests and related
data will be downloaded and processed by extractor. data will be downloaded and processed by extractor.
@@ -367,6 +376,8 @@ class YoutubeDL(object):
params = None params = None
_ies = [] _ies = []
_pps = [] _pps = []
_pps_end = []
__prepare_filename_warned = False
_download_retcode = None _download_retcode = None
_num_downloads = None _num_downloads = None
_playlist_level = 0 _playlist_level = 0
@@ -380,6 +391,8 @@ class YoutubeDL(object):
self._ies = [] self._ies = []
self._ies_instances = {} self._ies_instances = {}
self._pps = [] self._pps = []
self._pps_end = []
self.__prepare_filename_warned = False
self._post_hooks = [] self._post_hooks = []
self._progress_hooks = [] self._progress_hooks = []
self._download_retcode = 0 self._download_retcode = 0
@@ -481,8 +494,11 @@ class YoutubeDL(object):
pp_class = get_postprocessor(pp_def_raw['key']) pp_class = get_postprocessor(pp_def_raw['key'])
pp_def = dict(pp_def_raw) pp_def = dict(pp_def_raw)
del pp_def['key'] del pp_def['key']
after_move = pp_def.get('_after_move', False)
if '_after_move' in pp_def:
del pp_def['_after_move']
pp = pp_class(self, **compat_kwargs(pp_def)) pp = pp_class(self, **compat_kwargs(pp_def))
self.add_post_processor(pp) self.add_post_processor(pp, after_move=after_move)
for ph in self.params.get('post_hooks', []): for ph in self.params.get('post_hooks', []):
self.add_post_hook(ph) self.add_post_hook(ph)
@@ -534,9 +550,12 @@ class YoutubeDL(object):
for ie in gen_extractor_classes(): for ie in gen_extractor_classes():
self.add_info_extractor(ie) self.add_info_extractor(ie)
def add_post_processor(self, pp): def add_post_processor(self, pp, after_move=False):
"""Add a PostProcessor object to the end of the chain.""" """Add a PostProcessor object to the end of the chain."""
self._pps.append(pp) if after_move:
self._pps_end.append(pp)
else:
self._pps.append(pp)
pp.set_downloader(self) pp.set_downloader(self)
def add_post_hook(self, ph): def add_post_hook(self, ph):
@@ -597,7 +616,7 @@ class YoutubeDL(object):
# already of type unicode() # already of type unicode()
ctypes.windll.kernel32.SetConsoleTitleW(ctypes.c_wchar_p(message)) ctypes.windll.kernel32.SetConsoleTitleW(ctypes.c_wchar_p(message))
elif 'TERM' in os.environ: elif 'TERM' in os.environ:
self._write_string('\033[0;%s\007' % message, self._screen_file) self._write_string('\033]0;%s\007' % message, self._screen_file)
def save_console_title(self): def save_console_title(self):
if not self.params.get('consoletitle', False): if not self.params.get('consoletitle', False):
@@ -700,7 +719,7 @@ class YoutubeDL(object):
except UnicodeEncodeError: except UnicodeEncodeError:
self.to_screen('Deleting already existent file') self.to_screen('Deleting already existent file')
def prepare_filename(self, info_dict): def prepare_filename(self, info_dict, warn=False):
"""Generate the output filename.""" """Generate the output filename."""
try: try:
template_dict = dict(info_dict) template_dict = dict(info_dict)
@@ -725,7 +744,7 @@ class YoutubeDL(object):
template_dict = dict((k, v if isinstance(v, compat_numeric_types) else sanitize(k, v)) template_dict = dict((k, v if isinstance(v, compat_numeric_types) else sanitize(k, v))
for k, v in template_dict.items() for k, v in template_dict.items()
if v is not None and not isinstance(v, (list, tuple, dict))) if v is not None and not isinstance(v, (list, tuple, dict)))
template_dict = collections.defaultdict(lambda: 'NA', template_dict) template_dict = collections.defaultdict(lambda: self.params.get('outtmpl_na_placeholder', 'NA'), template_dict)
outtmpl = self.params.get('outtmpl', DEFAULT_OUTTMPL) outtmpl = self.params.get('outtmpl', DEFAULT_OUTTMPL)
@@ -745,8 +764,8 @@ class YoutubeDL(object):
# Missing numeric fields used together with integer presentation types # Missing numeric fields used together with integer presentation types
# in format specification will break the argument substitution since # in format specification will break the argument substitution since
# string 'NA' is returned for missing fields. We will patch output # string NA placeholder is returned for missing fields. We will patch
# template for missing fields to meet string presentation type. # output template for missing fields to meet string presentation type.
for numeric_field in self._NUMERIC_FIELDS: for numeric_field in self._NUMERIC_FIELDS:
if numeric_field not in template_dict: if numeric_field not in template_dict:
# As of [1] format syntax is: # As of [1] format syntax is:
@@ -794,11 +813,33 @@ class YoutubeDL(object):
# to workaround encoding issues with subprocess on python2 @ Windows # to workaround encoding issues with subprocess on python2 @ Windows
if sys.version_info < (3, 0) and sys.platform == 'win32': if sys.version_info < (3, 0) and sys.platform == 'win32':
filename = encodeFilename(filename, True).decode(preferredencoding()) filename = encodeFilename(filename, True).decode(preferredencoding())
return sanitize_path(filename) filename = sanitize_path(filename)
if warn and not self.__prepare_filename_warned:
if not self.params.get('paths'):
pass
elif filename == '-':
self.report_warning('--paths is ignored when an outputting to stdout')
elif os.path.isabs(filename):
self.report_warning('--paths is ignored since an absolute path is given in output template')
self.__prepare_filename_warned = True
return filename
except ValueError as err: except ValueError as err:
self.report_error('Error in output template: ' + str(err) + ' (encoding: ' + repr(preferredencoding()) + ')') self.report_error('Error in output template: ' + str(err) + ' (encoding: ' + repr(preferredencoding()) + ')')
return None return None
def prepare_filepath(self, filename, dir_type=''):
if filename == '-':
return filename
paths = self.params.get('paths', {})
assert isinstance(paths, dict)
homepath = expand_path(paths.get('home', '').strip())
assert isinstance(homepath, compat_str)
subdir = expand_path(paths.get(dir_type, '').strip()) if dir_type else ''
assert isinstance(subdir, compat_str)
return sanitize_path(os.path.join(homepath, subdir, filename))
def _match_entry(self, info_dict, incomplete): def _match_entry(self, info_dict, incomplete):
""" Returns None if the file should be downloaded """ """ Returns None if the file should be downloaded """
@@ -883,7 +924,9 @@ class YoutubeDL(object):
'and will probably not work.') 'and will probably not work.')
try: try:
temp_id = ie.extract_id(url) if callable(getattr(ie, 'extract_id', None)) else ie._match_id(url) temp_id = str_or_none(
ie.extract_id(url) if callable(getattr(ie, 'extract_id', None))
else ie._match_id(url))
except (AssertionError, IndexError, AttributeError): except (AssertionError, IndexError, AttributeError):
temp_id = None temp_id = None
if temp_id is not None and self.in_download_archive({'id': temp_id, 'ie_key': ie_key}): if temp_id is not None and self.in_download_archive({'id': temp_id, 'ie_key': ie_key}):
@@ -968,7 +1011,8 @@ class YoutubeDL(object):
if ((extract_flat == 'in_playlist' and 'playlist' in extra_info) if ((extract_flat == 'in_playlist' and 'playlist' in extra_info)
or extract_flat is True): or extract_flat is True):
self.__forced_printings( self.__forced_printings(
ie_result, self.prepare_filename(ie_result), ie_result,
self.prepare_filepath(self.prepare_filename(ie_result)),
incomplete=True) incomplete=True)
return ie_result return ie_result
@@ -1886,6 +1930,8 @@ class YoutubeDL(object):
assert info_dict.get('_type', 'video') == 'video' assert info_dict.get('_type', 'video') == 'video'
info_dict.setdefault('__postprocessors', [])
max_downloads = self.params.get('max_downloads') max_downloads = self.params.get('max_downloads')
if max_downloads is not None: if max_downloads is not None:
if self._num_downloads >= int(max_downloads): if self._num_downloads >= int(max_downloads):
@@ -1902,10 +1948,13 @@ class YoutubeDL(object):
self._num_downloads += 1 self._num_downloads += 1
info_dict['_filename'] = filename = self.prepare_filename(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')
files_to_move = {}
# Forced printings # Forced printings
self.__forced_printings(info_dict, filename, incomplete=False) self.__forced_printings(info_dict, full_filename, incomplete=False)
if self.params.get('simulate', False): if self.params.get('simulate', False):
if self.params.get('force_write_download_archive', False): if self.params.get('force_write_download_archive', False):
@@ -1918,20 +1967,19 @@ class YoutubeDL(object):
return return
def ensure_dir_exists(path): def ensure_dir_exists(path):
try: return make_dir(path, self.report_error)
dn = os.path.dirname(path)
if dn and not os.path.exists(dn):
os.makedirs(dn)
return True
except (OSError, IOError) as err:
self.report_error('unable to create directory ' + error_to_compat_str(err))
return False
if not ensure_dir_exists(sanitize_path(encodeFilename(filename))): if not ensure_dir_exists(encodeFilename(full_filename)):
return
if not ensure_dir_exists(encodeFilename(temp_filename)):
return return
if self.params.get('writedescription', False): if self.params.get('writedescription', False):
descfn = replace_extension(filename, 'description', info_dict.get('ext')) descfn = replace_extension(
self.prepare_filepath(filename, 'description'),
'description', info_dict.get('ext'))
if not ensure_dir_exists(encodeFilename(descfn)):
return
if not self.params.get('overwrites', True) and os.path.exists(encodeFilename(descfn)): if not self.params.get('overwrites', True) and os.path.exists(encodeFilename(descfn)):
self.to_screen('[info] Video description is already present') self.to_screen('[info] Video description is already present')
elif info_dict.get('description') is None: elif info_dict.get('description') is None:
@@ -1946,7 +1994,11 @@ class YoutubeDL(object):
return return
if self.params.get('writeannotations', False): if self.params.get('writeannotations', False):
annofn = replace_extension(filename, 'annotations.xml', info_dict.get('ext')) annofn = replace_extension(
self.prepare_filepath(filename, 'annotation'),
'annotations.xml', info_dict.get('ext'))
if not ensure_dir_exists(encodeFilename(annofn)):
return
if not self.params.get('overwrites', True) and os.path.exists(encodeFilename(annofn)): if not self.params.get('overwrites', True) and os.path.exists(encodeFilename(annofn)):
self.to_screen('[info] Video annotations are already present') self.to_screen('[info] Video annotations are already present')
elif not info_dict.get('annotations'): elif not info_dict.get('annotations'):
@@ -1980,9 +2032,13 @@ class YoutubeDL(object):
# ie = self.get_info_extractor(info_dict['extractor_key']) # ie = self.get_info_extractor(info_dict['extractor_key'])
for sub_lang, sub_info in subtitles.items(): for sub_lang, sub_info in subtitles.items():
sub_format = sub_info['ext'] sub_format = sub_info['ext']
sub_filename = subtitles_filename(filename, sub_lang, sub_format, info_dict.get('ext')) sub_filename = subtitles_filename(temp_filename, sub_lang, sub_format, info_dict.get('ext'))
sub_filename_final = subtitles_filename(
self.prepare_filepath(filename, 'subtitle'),
sub_lang, sub_format, info_dict.get('ext'))
if not self.params.get('overwrites', True) and os.path.exists(encodeFilename(sub_filename)): if not self.params.get('overwrites', True) and os.path.exists(encodeFilename(sub_filename)):
self.to_screen('[info] Video subtitle %s.%s is already present' % (sub_lang, sub_format)) self.to_screen('[info] Video subtitle %s.%s is already present' % (sub_lang, sub_format))
files_to_move[sub_filename] = sub_filename_final
else: else:
self.to_screen('[info] Writing video subtitles to: ' + sub_filename) self.to_screen('[info] Writing video subtitles to: ' + sub_filename)
if sub_info.get('data') is not None: if sub_info.get('data') is not None:
@@ -1991,6 +2047,7 @@ class YoutubeDL(object):
# See https://github.com/ytdl-org/youtube-dl/issues/10268 # See https://github.com/ytdl-org/youtube-dl/issues/10268
with io.open(encodeFilename(sub_filename), 'w', encoding='utf-8', newline='') as subfile: with io.open(encodeFilename(sub_filename), 'w', encoding='utf-8', newline='') as subfile:
subfile.write(sub_info['data']) subfile.write(sub_info['data'])
files_to_move[sub_filename] = sub_filename_final
except (OSError, IOError): except (OSError, IOError):
self.report_error('Cannot write subtitles file ' + sub_filename) self.report_error('Cannot write subtitles file ' + sub_filename)
return return
@@ -2006,6 +2063,7 @@ class YoutubeDL(object):
with io.open(encodeFilename(sub_filename), 'wb') as subfile: with io.open(encodeFilename(sub_filename), 'wb') as subfile:
subfile.write(sub_data) subfile.write(sub_data)
''' '''
files_to_move[sub_filename] = sub_filename_final
except (ExtractorError, IOError, OSError, ValueError, compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: except (ExtractorError, IOError, OSError, ValueError, compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
self.report_warning('Unable to download subtitle for "%s": %s' % self.report_warning('Unable to download subtitle for "%s": %s' %
(sub_lang, error_to_compat_str(err))) (sub_lang, error_to_compat_str(err)))
@@ -2013,29 +2071,32 @@ class YoutubeDL(object):
if self.params.get('skip_download', False): if self.params.get('skip_download', False):
if self.params.get('convertsubtitles', False): if self.params.get('convertsubtitles', False):
subconv = FFmpegSubtitlesConvertorPP(self, format=self.params.get('convertsubtitles')) # subconv = FFmpegSubtitlesConvertorPP(self, format=self.params.get('convertsubtitles'))
filename_real_ext = os.path.splitext(filename)[1][1:] filename_real_ext = os.path.splitext(filename)[1][1:]
filename_wo_ext = ( filename_wo_ext = (
os.path.splitext(filename)[0] os.path.splitext(full_filename)[0]
if filename_real_ext == info_dict['ext'] if filename_real_ext == info_dict['ext']
else filename) else full_filename)
afilename = '%s.%s' % (filename_wo_ext, self.params.get('convertsubtitles')) afilename = '%s.%s' % (filename_wo_ext, self.params.get('convertsubtitles'))
if subconv.available: # if subconv.available:
info_dict.setdefault('__postprocessors', []) # info_dict['__postprocessors'].append(subconv)
# info_dict['__postprocessors'].append(subconv)
if os.path.exists(encodeFilename(afilename)): if os.path.exists(encodeFilename(afilename)):
self.to_screen( self.to_screen(
'[download] %s has already been downloaded and ' '[download] %s has already been downloaded and '
'converted' % afilename) 'converted' % afilename)
else: else:
try: try:
self.post_process(filename, info_dict) self.post_process(full_filename, info_dict, files_to_move)
except (PostProcessingError) as err: except (PostProcessingError) as err:
self.report_error('postprocessing: %s' % str(err)) self.report_error('postprocessing: %s' % str(err))
return return
if self.params.get('writeinfojson', False): if self.params.get('writeinfojson', False):
infofn = replace_extension(filename, 'info.json', info_dict.get('ext')) infofn = replace_extension(
self.prepare_filepath(filename, 'infojson'),
'info.json', info_dict.get('ext'))
if not ensure_dir_exists(encodeFilename(infofn)):
return
if not self.params.get('overwrites', True) and os.path.exists(encodeFilename(infofn)): 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 description metadata is already present')
else: else:
@@ -2046,7 +2107,9 @@ class YoutubeDL(object):
self.report_error('Cannot write metadata to JSON file ' + infofn) self.report_error('Cannot write metadata to JSON file ' + infofn)
return return
self._write_thumbnails(info_dict, filename) thumbdir = os.path.dirname(self.prepare_filepath(filename, 'thumbnail'))
for thumbfn in self._write_thumbnails(info_dict, temp_filename):
files_to_move[thumbfn] = os.path.join(thumbdir, os.path.basename(thumbfn))
# Write internet shortcut files # Write internet shortcut files
url_link = webloc_link = desktop_link = False url_link = webloc_link = desktop_link = False
@@ -2071,8 +2134,8 @@ class YoutubeDL(object):
ascii_url = iri_to_uri(info_dict['webpage_url']) ascii_url = iri_to_uri(info_dict['webpage_url'])
def _write_link_file(extension, template, newline, embed_filename): def _write_link_file(extension, template, newline, embed_filename):
linkfn = replace_extension(filename, extension, info_dict.get('ext')) linkfn = replace_extension(full_filename, extension, info_dict.get('ext'))
if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(linkfn)): if self.params.get('overwrites', True) and os.path.exists(encodeFilename(linkfn)):
self.to_screen('[info] Internet shortcut is already present') self.to_screen('[info] Internet shortcut is already present')
else: else:
try: try:
@@ -2101,9 +2164,27 @@ class YoutubeDL(object):
must_record_download_archive = False must_record_download_archive = False
if not self.params.get('skip_download', False): if not self.params.get('skip_download', False):
try: 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
success = True
if info_dict.get('requested_formats') is not None: if info_dict.get('requested_formats') is not None:
downloaded = [] downloaded = []
success = True
merger = FFmpegMergerPP(self) merger = FFmpegMergerPP(self)
if not merger.available: if not merger.available:
postprocessors = [] postprocessors = []
@@ -2132,32 +2213,31 @@ class YoutubeDL(object):
# TODO: Check acodec/vcodec # TODO: Check acodec/vcodec
return False return False
filename_real_ext = os.path.splitext(filename)[1][1:]
filename_wo_ext = (
os.path.splitext(filename)[0]
if filename_real_ext == info_dict['ext']
else filename)
requested_formats = info_dict['requested_formats'] requested_formats = info_dict['requested_formats']
old_ext = info_dict['ext']
if self.params.get('merge_output_format') is None and not compatible_formats(requested_formats): if self.params.get('merge_output_format') is None and not compatible_formats(requested_formats):
info_dict['ext'] = 'mkv' info_dict['ext'] = 'mkv'
self.report_warning( self.report_warning(
'Requested formats are incompatible for merge and will be merged into mkv.') 'Requested formats are incompatible for merge and will be merged into mkv.')
def correct_ext(filename):
filename_real_ext = os.path.splitext(filename)[1][1:]
filename_wo_ext = (
os.path.splitext(filename)[0]
if filename_real_ext == old_ext
else filename)
return '%s.%s' % (filename_wo_ext, info_dict['ext'])
# Ensure filename always has a correct extension for successful merge # Ensure filename always has a correct extension for successful merge
filename = '%s.%s' % (filename_wo_ext, info_dict['ext']) full_filename = correct_ext(full_filename)
file_exists = os.path.exists(encodeFilename(filename)) temp_filename = correct_ext(temp_filename)
if not self.params.get('overwrites', False) and file_exists: dl_filename = existing_file(full_filename, temp_filename)
self.to_screen( if dl_filename is None:
'[download] %s has already been downloaded and '
'merged' % filename)
else:
if file_exists:
self.report_file_delete(filename)
os.remove(encodeFilename(filename))
for f in requested_formats: for f in requested_formats:
new_info = dict(info_dict) new_info = dict(info_dict)
new_info.update(f) new_info.update(f)
fname = prepend_extension( fname = prepend_extension(
self.prepare_filename(new_info), self.prepare_filepath(self.prepare_filename(new_info), 'temp'),
'f%s' % f['format_id'], new_info['ext']) 'f%s' % f['format_id'], new_info['ext'])
if not ensure_dir_exists(fname): if not ensure_dir_exists(fname):
return return
@@ -2169,14 +2249,15 @@ class YoutubeDL(object):
# Even if there were no downloads, it is being merged only now # Even if there were no downloads, it is being merged only now
info_dict['__real_download'] = True info_dict['__real_download'] = True
else: else:
# Delete existing file with --yes-overwrites
if self.params.get('overwrites', False):
if os.path.exists(encodeFilename(filename)):
self.report_file_delete(filename)
os.remove(encodeFilename(filename))
# Just a single file # Just a single file
success, real_download = dl(filename, info_dict) dl_filename = existing_file(full_filename, temp_filename)
info_dict['__real_download'] = real_download if dl_filename is None:
success, real_download = dl(temp_filename, info_dict)
info_dict['__real_download'] = real_download
dl_filename = dl_filename or temp_filename
info_dict['__finaldir'] = os.path.dirname(os.path.abspath(encodeFilename(full_filename)))
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
self.report_error('unable to download video data: %s' % error_to_compat_str(err)) self.report_error('unable to download video data: %s' % error_to_compat_str(err))
return return
@@ -2202,7 +2283,6 @@ class YoutubeDL(object):
elif fixup_policy == 'detect_or_warn': elif fixup_policy == 'detect_or_warn':
stretched_pp = FFmpegFixupStretchedPP(self) stretched_pp = FFmpegFixupStretchedPP(self)
if stretched_pp.available: if stretched_pp.available:
info_dict.setdefault('__postprocessors', [])
info_dict['__postprocessors'].append(stretched_pp) info_dict['__postprocessors'].append(stretched_pp)
else: else:
self.report_warning( self.report_warning(
@@ -2221,7 +2301,6 @@ class YoutubeDL(object):
elif fixup_policy == 'detect_or_warn': elif fixup_policy == 'detect_or_warn':
fixup_pp = FFmpegFixupM4aPP(self) fixup_pp = FFmpegFixupM4aPP(self)
if fixup_pp.available: if fixup_pp.available:
info_dict.setdefault('__postprocessors', [])
info_dict['__postprocessors'].append(fixup_pp) info_dict['__postprocessors'].append(fixup_pp)
else: else:
self.report_warning( self.report_warning(
@@ -2240,7 +2319,6 @@ class YoutubeDL(object):
elif fixup_policy == 'detect_or_warn': elif fixup_policy == 'detect_or_warn':
fixup_pp = FFmpegFixupM3u8PP(self) fixup_pp = FFmpegFixupM3u8PP(self)
if fixup_pp.available: if fixup_pp.available:
info_dict.setdefault('__postprocessors', [])
info_dict['__postprocessors'].append(fixup_pp) info_dict['__postprocessors'].append(fixup_pp)
else: else:
self.report_warning( self.report_warning(
@@ -2250,13 +2328,13 @@ class YoutubeDL(object):
assert fixup_policy in ('ignore', 'never') assert fixup_policy in ('ignore', 'never')
try: try:
self.post_process(filename, info_dict) self.post_process(dl_filename, info_dict, files_to_move)
except (PostProcessingError) as err: except (PostProcessingError) as err:
self.report_error('postprocessing: %s' % str(err)) self.report_error('postprocessing: %s' % str(err))
return return
try: try:
for ph in self._post_hooks: for ph in self._post_hooks:
ph(filename) ph(full_filename)
except Exception as err: except Exception as err:
self.report_error('post hooks: %s' % str(err)) self.report_error('post hooks: %s' % str(err))
return return
@@ -2322,27 +2400,41 @@ class YoutubeDL(object):
(k, v) for k, v in info_dict.items() (k, v) for k, v in info_dict.items()
if k not in ['requested_formats', 'requested_subtitles']) if k not in ['requested_formats', 'requested_subtitles'])
def post_process(self, filename, ie_info): def post_process(self, filename, ie_info, files_to_move={}):
"""Run all the postprocessors on the given file.""" """Run all the postprocessors on the given file."""
info = dict(ie_info) info = dict(ie_info)
info['filepath'] = filename info['filepath'] = filename
pps_chain = []
if ie_info.get('__postprocessors') is not None: def run_pp(pp):
pps_chain.extend(ie_info['__postprocessors'])
pps_chain.extend(self._pps)
for pp in pps_chain:
files_to_delete = [] files_to_delete = []
infodict = info
try: try:
files_to_delete, info = pp.run(info) files_to_delete, infodict = pp.run(infodict)
except PostProcessingError as e: except PostProcessingError as e:
self.report_error(e.msg) self.report_error(e.msg)
if files_to_delete and not self.params.get('keepvideo', False): 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): for old_filename in set(files_to_delete):
self.to_screen('Deleting original file %s (pass -k to keep)' % old_filename) self.to_screen('Deleting original file %s (pass -k to keep)' % old_filename)
try: try:
os.remove(encodeFilename(old_filename)) os.remove(encodeFilename(old_filename))
except (IOError, OSError): except (IOError, OSError):
self.report_warning('Unable to remove downloaded original file') 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)
def _make_archive_id(self, info_dict): def _make_archive_id(self, info_dict):
video_id = info_dict.get('id') video_id = info_dict.get('id')
@@ -2362,7 +2454,7 @@ class YoutubeDL(object):
break break
else: else:
return return
return extractor.lower() + ' ' + video_id return '%s %s' % (extractor.lower(), video_id)
def in_download_archive(self, info_dict): def in_download_archive(self, info_dict):
fn = self.params.get('download_archive') fn = self.params.get('download_archive')
@@ -2563,9 +2655,12 @@ class YoutubeDL(object):
self.get_encoding())) self.get_encoding()))
write_string(encoding_str, encoding=None) write_string(encoding_str, encoding=None)
self._write_string('[debug] yt-dlp version ' + __version__ + '\n') self._write_string('[debug] yt-dlp version %s\n' % __version__)
if _LAZY_LOADER: if _LAZY_LOADER:
self._write_string('[debug] Lazy loading extractors enabled' + '\n') self._write_string('[debug] Lazy loading extractors enabled\n')
if _PLUGIN_CLASSES:
self._write_string(
'[debug] Plugin Extractors: %s\n' % [ie.ie_key() for ie in _PLUGIN_CLASSES])
try: try:
sp = subprocess.Popen( sp = subprocess.Popen(
['git', 'rev-parse', '--short', 'HEAD'], ['git', 'rev-parse', '--short', 'HEAD'],
@@ -2574,7 +2669,7 @@ class YoutubeDL(object):
out, err = process_communicate_or_kill(sp) out, err = process_communicate_or_kill(sp)
out = out.decode().strip() out = out.decode().strip()
if re.match('[0-9a-f]+', out): if re.match('[0-9a-f]+', out):
self._write_string('[debug] Git HEAD: ' + out + '\n') self._write_string('[debug] Git HEAD: %s\n' % out)
except Exception: except Exception:
try: try:
sys.exc_clear() sys.exc_clear()
@@ -2696,14 +2791,11 @@ class YoutubeDL(object):
if thumbnails: if thumbnails:
thumbnails = [thumbnails[-1]] thumbnails = [thumbnails[-1]]
elif self.params.get('write_all_thumbnails', False): elif self.params.get('write_all_thumbnails', False):
thumbnails = info_dict.get('thumbnails') thumbnails = info_dict.get('thumbnails') or []
else: else:
return thumbnails = []
if not thumbnails:
# No thumbnails present, so return immediately
return
ret = []
for t in thumbnails: for t in thumbnails:
thumb_ext = determine_ext(t['url'], 'jpg') thumb_ext = determine_ext(t['url'], 'jpg')
suffix = '_%s' % t['id'] if len(thumbnails) > 1 else '' suffix = '_%s' % t['id'] if len(thumbnails) > 1 else ''
@@ -2711,6 +2803,7 @@ class YoutubeDL(object):
t['filename'] = thumb_filename = replace_extension(filename + suffix, thumb_ext, info_dict.get('ext')) t['filename'] = thumb_filename = replace_extension(filename + suffix, thumb_ext, info_dict.get('ext'))
if not self.params.get('overwrites', True) and os.path.exists(encodeFilename(thumb_filename)): if not self.params.get('overwrites', True) and os.path.exists(encodeFilename(thumb_filename)):
ret.append(thumb_filename)
self.to_screen('[%s] %s: Thumbnail %sis already present' % self.to_screen('[%s] %s: Thumbnail %sis already present' %
(info_dict['extractor'], info_dict['id'], thumb_display_id)) (info_dict['extractor'], info_dict['id'], thumb_display_id))
else: else:
@@ -2720,8 +2813,10 @@ class YoutubeDL(object):
uf = self.urlopen(t['url']) uf = self.urlopen(t['url'])
with open(encodeFilename(thumb_filename), 'wb') as thumbf: with open(encodeFilename(thumb_filename), 'wb') as thumbf:
shutil.copyfileobj(uf, thumbf) shutil.copyfileobj(uf, thumbf)
ret.append(thumb_filename)
self.to_screen('[%s] %s: Writing thumbnail %sto: %s' % self.to_screen('[%s] %s: Writing thumbnail %sto: %s' %
(info_dict['extractor'], info_dict['id'], thumb_display_id, thumb_filename)) (info_dict['extractor'], info_dict['id'], thumb_display_id, thumb_filename))
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
self.report_warning('Unable to download thumbnail "%s": %s' % self.report_warning('Unable to download thumbnail "%s": %s' %
(t['url'], error_to_compat_str(err))) (t['url'], error_to_compat_str(err)))
return ret
+17 -32
View File
@@ -8,8 +8,8 @@ __license__ = 'Public Domain'
import codecs import codecs
import io import io
import os import os
import re
import random import random
import re
import sys import sys
@@ -18,7 +18,6 @@ from .options import (
) )
from .compat import ( from .compat import (
compat_getpass, compat_getpass,
compat_shlex_split,
workaround_optparse_bug9161, workaround_optparse_bug9161,
) )
from .utils import ( from .utils import (
@@ -70,14 +69,7 @@ def _real_main(argv=None):
std_headers['Referer'] = opts.referer std_headers['Referer'] = opts.referer
# Custom HTTP headers # Custom HTTP headers
if opts.headers is not None: std_headers.update(opts.headers)
for h in opts.headers:
if ':' not in h:
parser.error('wrong header formatting, it should be key:value, not "%s"' % h)
key, value = h.split(':', 1)
if opts.verbose:
write_string('[debug] Adding header from command line option %s:%s\n' % (key, value))
std_headers[key] = value
# Dump user agent # Dump user agent
if opts.dump_user_agent: if opts.dump_user_agent:
@@ -252,6 +244,7 @@ def _real_main(argv=None):
parser.error('Cannot download a video and extract audio into the same' parser.error('Cannot download a video and extract audio into the same'
' file! Use "{0}.%(ext)s" instead of "{0}" as the output' ' file! Use "{0}.%(ext)s" instead of "{0}" as the output'
' template'.format(outtmpl)) ' template'.format(outtmpl))
for f in opts.format_sort: for f in opts.format_sort:
if re.match(InfoExtractor.FormatSort.regex, f) is None: if re.match(InfoExtractor.FormatSort.regex, f) is None:
parser.error('invalid format sort string "%s" specified' % f) parser.error('invalid format sort string "%s" specified' % f)
@@ -326,32 +319,22 @@ def _real_main(argv=None):
'force': opts.sponskrub_force, 'force': opts.sponskrub_force,
'ignoreerror': opts.sponskrub is None, 'ignoreerror': opts.sponskrub is None,
}) })
# Please keep ExecAfterDownload towards the bottom as it allows the user to modify the final file in any way. # ExecAfterDownload must be the last PP
# So if the user is able to remove the file before your postprocessor runs it might cause a few problems.
if opts.exec_cmd: if opts.exec_cmd:
postprocessors.append({ postprocessors.append({
'key': 'ExecAfterDownload', 'key': 'ExecAfterDownload',
'exec_cmd': opts.exec_cmd, 'exec_cmd': opts.exec_cmd,
'_after_move': True
}) })
external_downloader_args = None
if opts.external_downloader_args:
external_downloader_args = compat_shlex_split(opts.external_downloader_args)
postprocessor_args = {} _args_compat_warning = 'WARNING: %s given without specifying name. The arguments will be given to all %s\n'
if opts.postprocessor_args is not None: if 'default' in opts.external_downloader_args:
for string in opts.postprocessor_args: write_string(_args_compat_warning % ('--external-downloader-args', 'external downloaders'), out=sys.stderr),
mobj = re.match(r'(?P<pp>\w+):(?P<args>.*)$', string)
if mobj is None: if 'default-compat' in opts.postprocessor_args and 'default' not in opts.postprocessor_args:
if 'sponskrub' not in postprocessor_args: # for backward compatibility write_string(_args_compat_warning % ('--post-processor-args', 'post-processors'), out=sys.stderr),
postprocessor_args['sponskrub'] = [] opts.postprocessor_args.setdefault('sponskrub', [])
if opts.verbose: opts.postprocessor_args['default'] = opts.postprocessor_args['default-compat']
write_string('[debug] Adding postprocessor args from command line option sponskrub:\n')
pp_name, pp_args = 'default', string
else:
pp_name, pp_args = mobj.group('pp').lower(), mobj.group('args')
if opts.verbose:
write_string('[debug] Adding postprocessor args from command line option %s:%s\n' % (pp_name, pp_args))
postprocessor_args[pp_name] = compat_shlex_split(pp_args)
match_filter = ( match_filter = (
None if opts.match_filter is None None if opts.match_filter is None
@@ -390,6 +373,8 @@ def _real_main(argv=None):
'listformats': opts.listformats, 'listformats': opts.listformats,
'listformats_table': opts.listformats_table, 'listformats_table': opts.listformats_table,
'outtmpl': outtmpl, 'outtmpl': outtmpl,
'outtmpl_na_placeholder': opts.outtmpl_na_placeholder,
'paths': opts.paths,
'autonumber_size': opts.autonumber_size, 'autonumber_size': opts.autonumber_size,
'autonumber_start': opts.autonumber_start, 'autonumber_start': opts.autonumber_start,
'restrictfilenames': opts.restrictfilenames, 'restrictfilenames': opts.restrictfilenames,
@@ -485,8 +470,8 @@ def _real_main(argv=None):
'ffmpeg_location': opts.ffmpeg_location, 'ffmpeg_location': opts.ffmpeg_location,
'hls_prefer_native': opts.hls_prefer_native, 'hls_prefer_native': opts.hls_prefer_native,
'hls_use_mpegts': opts.hls_use_mpegts, 'hls_use_mpegts': opts.hls_use_mpegts,
'external_downloader_args': external_downloader_args, 'external_downloader_args': opts.external_downloader_args,
'postprocessor_args': postprocessor_args, 'postprocessor_args': opts.postprocessor_args,
'cn_verification_proxy': opts.cn_verification_proxy, 'cn_verification_proxy': opts.cn_verification_proxy,
'geo_verification_proxy': opts.geo_verification_proxy, 'geo_verification_proxy': opts.geo_verification_proxy,
'config_location': opts.config_location, 'config_location': opts.config_location,
+2 -1
View File
@@ -95,7 +95,8 @@ class ExternalFD(FileDownloader):
return cli_valueless_option(self.params, command_option, param, expected_value) return cli_valueless_option(self.params, command_option, param, expected_value)
def _configuration_args(self, default=[]): def _configuration_args(self, default=[]):
return cli_configuration_args(self.params, 'external_downloader_args', default) return cli_configuration_args(
self.params, 'external_downloader_args', self.get_basename(), default)[0]
def _call_downloader(self, tmpfilename, info_dict): def _call_downloader(self, tmpfilename, info_dict):
""" Either overwrite this or implement _make_cmd """ """ Either overwrite this or implement _make_cmd """
+6
View File
@@ -1,13 +1,19 @@
from __future__ import unicode_literals from __future__ import unicode_literals
from ..utils import load_plugins
try: try:
from .lazy_extractors import * from .lazy_extractors import *
from .lazy_extractors import _ALL_CLASSES from .lazy_extractors import _ALL_CLASSES
_LAZY_LOADER = True _LAZY_LOADER = True
_PLUGIN_CLASSES = []
except ImportError: except ImportError:
_LAZY_LOADER = False _LAZY_LOADER = False
from .extractors import * from .extractors import *
_PLUGIN_CLASSES = load_plugins('extractor', 'IE', globals())
_ALL_CLASSES = [ _ALL_CLASSES = [
klass klass
for name, klass in globals().items() for name, klass in globals().items()
+1 -1
View File
@@ -256,7 +256,7 @@ class AENetworksShowIE(AENetworksListBaseIE):
'title': 'Ancient Aliens', 'title': 'Ancient Aliens',
'description': 'md5:3f6d74daf2672ff3ae29ed732e37ea7f', 'description': 'md5:3f6d74daf2672ff3ae29ed732e37ea7f',
}, },
'playlist_mincount': 168, 'playlist_mincount': 150,
}] }]
_RESOURCE = 'series' _RESOURCE = 'series'
_ITEMS_KEY = 'episodes' _ITEMS_KEY = 'episodes'
+32 -9
View File
@@ -1,13 +1,16 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import json
import re
from .common import InfoExtractor from .common import InfoExtractor
class AlJazeeraIE(InfoExtractor): class AlJazeeraIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?aljazeera\.com/(?:programmes|video)/.*?/(?P<id>[^/]+)\.html' _VALID_URL = r'https?://(?:www\.)?aljazeera\.com/(?P<type>program/[^/]+|(?:feature|video)s)/\d{4}/\d{1,2}/\d{1,2}/(?P<id>[^/?&#]+)'
_TESTS = [{ _TESTS = [{
'url': 'http://www.aljazeera.com/programmes/the-slum/2014/08/deliverance-201482883754237240.html', 'url': 'https://www.aljazeera.com/program/episode/2014/9/19/deliverance',
'info_dict': { 'info_dict': {
'id': '3792260579001', 'id': '3792260579001',
'ext': 'mp4', 'ext': 'mp4',
@@ -20,14 +23,34 @@ class AlJazeeraIE(InfoExtractor):
'add_ie': ['BrightcoveNew'], 'add_ie': ['BrightcoveNew'],
'skip': 'Not accessible from Travis CI server', 'skip': 'Not accessible from Travis CI server',
}, { }, {
'url': 'http://www.aljazeera.com/video/news/2017/05/sierra-leone-709-carat-diamond-auctioned-170511100111930.html', 'url': 'https://www.aljazeera.com/videos/2017/5/11/sierra-leone-709-carat-diamond-to-be-auctioned-off',
'only_matching': True,
}, {
'url': 'https://www.aljazeera.com/features/2017/8/21/transforming-pakistans-buses-into-art',
'only_matching': True, 'only_matching': True,
}] }]
BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/665003303001/default_default/index.html?videoId=%s' BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/%s/%s_default/index.html?videoId=%s'
def _real_extract(self, url): def _real_extract(self, url):
program_name = self._match_id(url) post_type, name = re.match(self._VALID_URL, url).groups()
webpage = self._download_webpage(url, program_name) post_type = {
brightcove_id = self._search_regex( 'features': 'post',
r'RenderPagesVideo\(\'(.+?)\'', webpage, 'brightcove id') 'program': 'episode',
return self.url_result(self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id, 'BrightcoveNew', brightcove_id) 'videos': 'video',
}[post_type.split('/')[0]]
video = self._download_json(
'https://www.aljazeera.com/graphql', name, query={
'operationName': 'SingleArticleQuery',
'variables': json.dumps({
'name': name,
'postType': post_type,
}),
}, headers={
'wp-site': 'aje',
})['data']['article']['video']
video_id = video['id']
account_id = video.get('accountId') or '665003303001'
player_id = video.get('playerId') or 'BkeSH5BDb'
return self.url_result(
self.BRIGHTCOVE_URL_TEMPLATE % (account_id, player_id, video_id),
'BrightcoveNew', video_id)
+95 -2
View File
@@ -1,13 +1,16 @@
# coding: utf-8 # coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
import json
import re import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
clean_html, clean_html,
int_or_none,
try_get, try_get,
unified_strdate, unified_strdate,
unified_timestamp,
) )
@@ -22,8 +25,8 @@ class AmericasTestKitchenIE(InfoExtractor):
'ext': 'mp4', 'ext': 'mp4',
'description': 'md5:64e606bfee910627efc4b5f050de92b3', 'description': 'md5:64e606bfee910627efc4b5f050de92b3',
'thumbnail': r're:^https?://', 'thumbnail': r're:^https?://',
'timestamp': 1523664000, 'timestamp': 1523318400,
'upload_date': '20180414', 'upload_date': '20180410',
'release_date': '20180410', 'release_date': '20180410',
'series': "America's Test Kitchen", 'series': "America's Test Kitchen",
'season_number': 18, 'season_number': 18,
@@ -33,6 +36,27 @@ class AmericasTestKitchenIE(InfoExtractor):
'params': { 'params': {
'skip_download': True, 'skip_download': True,
}, },
}, {
# Metadata parsing behaves differently for newer episodes (705) as opposed to older episodes (582 above)
'url': 'https://www.americastestkitchen.com/episode/705-simple-chicken-dinner',
'md5': '06451608c57651e985a498e69cec17e5',
'info_dict': {
'id': '5fbe8c61bda2010001c6763b',
'title': 'Simple Chicken Dinner',
'ext': 'mp4',
'description': 'md5:eb68737cc2fd4c26ca7db30139d109e7',
'thumbnail': r're:^https?://',
'timestamp': 1610755200,
'upload_date': '20210116',
'release_date': '20210116',
'series': "America's Test Kitchen",
'season_number': 21,
'episode': 'Simple Chicken Dinner',
'episode_number': 3,
},
'params': {
'skip_download': True,
},
}, { }, {
'url': 'https://www.americastestkitchen.com/videos/3420-pan-seared-salmon', 'url': 'https://www.americastestkitchen.com/videos/3420-pan-seared-salmon',
'only_matching': True, 'only_matching': True,
@@ -60,7 +84,76 @@ class AmericasTestKitchenIE(InfoExtractor):
'url': 'https://player.zype.com/embed/%s.js?api_key=jZ9GUhRmxcPvX7M3SlfejB6Hle9jyHTdk2jVxG7wOHPLODgncEKVdPYBhuz9iWXQ' % video['zypeId'], 'url': 'https://player.zype.com/embed/%s.js?api_key=jZ9GUhRmxcPvX7M3SlfejB6Hle9jyHTdk2jVxG7wOHPLODgncEKVdPYBhuz9iWXQ' % video['zypeId'],
'ie_key': 'Zype', 'ie_key': 'Zype',
'description': clean_html(video.get('description')), 'description': clean_html(video.get('description')),
'timestamp': unified_timestamp(video.get('publishDate')),
'release_date': unified_strdate(video.get('publishDate')), 'release_date': unified_strdate(video.get('publishDate')),
'episode_number': int_or_none(episode.get('number')),
'season_number': int_or_none(episode.get('season')),
'series': try_get(episode, lambda x: x['show']['title']), 'series': try_get(episode, lambda x: x['show']['title']),
'episode': episode.get('title'), 'episode': episode.get('title'),
} }
class AmericasTestKitchenSeasonIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?(?P<show>americastestkitchen|cookscountry)\.com/episodes/browse/season_(?P<id>\d+)'
_TESTS = [{
# ATK Season
'url': 'https://www.americastestkitchen.com/episodes/browse/season_1',
'info_dict': {
'id': 'season_1',
'title': 'Season 1',
},
'playlist_count': 13,
}, {
# Cooks Country Season
'url': 'https://www.cookscountry.com/episodes/browse/season_12',
'info_dict': {
'id': 'season_12',
'title': 'Season 12',
},
'playlist_count': 13,
}]
def _real_extract(self, url):
show_name, season_number = re.match(self._VALID_URL, url).groups()
season_number = int(season_number)
slug = 'atk' if show_name == 'americastestkitchen' else 'cco'
season = 'Season %d' % season_number
season_search = self._download_json(
'https://y1fnzxui30-dsn.algolia.net/1/indexes/everest_search_%s_season_desc_production' % slug,
season, headers={
'Origin': 'https://www.%s.com' % show_name,
'X-Algolia-API-Key': '8d504d0099ed27c1b73708d22871d805',
'X-Algolia-Application-Id': 'Y1FNZXUI30',
}, query={
'facetFilters': json.dumps([
'search_season_list:' + season,
'search_document_klass:episode',
'search_show_slug:' + slug,
]),
'attributesToRetrieve': 'description,search_%s_episode_number,search_document_date,search_url,title' % slug,
'attributesToHighlight': '',
'hitsPerPage': 1000,
})
def entries():
for episode in (season_search.get('hits') or []):
search_url = episode.get('search_url')
if not search_url:
continue
yield {
'_type': 'url',
'url': 'https://www.%s.com%s' % (show_name, search_url),
'id': try_get(episode, lambda e: e['objectID'].split('_')[-1]),
'title': episode.get('title'),
'description': episode.get('description'),
'timestamp': unified_timestamp(episode.get('search_document_date')),
'season_number': season_number,
'episode_number': int_or_none(episode.get('search_%s_episode_number' % slug)),
'ie_key': AmericasTestKitchenIE.ie_key(),
}
return self.playlist_result(
entries(), 'season_%d' % season_number, season)
+9 -3
View File
@@ -3,7 +3,7 @@ from __future__ import unicode_literals
import re import re
from .common import InfoExtractor from .yahoo import YahooIE
from ..compat import ( from ..compat import (
compat_parse_qs, compat_parse_qs,
compat_urllib_parse_urlparse, compat_urllib_parse_urlparse,
@@ -15,9 +15,9 @@ from ..utils import (
) )
class AolIE(InfoExtractor): class AolIE(YahooIE):
IE_NAME = 'aol.com' IE_NAME = 'aol.com'
_VALID_URL = r'(?:aol-video:|https?://(?:www\.)?aol\.(?:com|ca|co\.uk|de|jp)/video/(?:[^/]+/)*)(?P<id>[0-9a-f]+)' _VALID_URL = r'(?:aol-video:|https?://(?:www\.)?aol\.(?:com|ca|co\.uk|de|jp)/video/(?:[^/]+/)*)(?P<id>\d{9}|[0-9a-f]{24}|[0-9a-f]{8}-(?:[0-9a-f]{4}-){3}[0-9a-f]{12})'
_TESTS = [{ _TESTS = [{
# video with 5min ID # video with 5min ID
@@ -76,10 +76,16 @@ class AolIE(InfoExtractor):
}, { }, {
'url': 'https://www.aol.jp/video/playlist/5a28e936a1334d000137da0c/5a28f3151e642219fde19831/', 'url': 'https://www.aol.jp/video/playlist/5a28e936a1334d000137da0c/5a28f3151e642219fde19831/',
'only_matching': True, 'only_matching': True,
}, {
# Yahoo video
'url': 'https://www.aol.com/video/play/991e6700-ac02-11ea-99ff-357400036f61/24bbc846-3e30-3c46-915e-fe8ccd7fcc46/',
'only_matching': True,
}] }]
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
if '-' in video_id:
return self._extract_yahoo_video(video_id, 'us')
response = self._download_json( response = self._download_json(
'https://feedapi.b2c.on.aol.com/v1.0/app/videos/aolon/%s/details' % video_id, 'https://feedapi.b2c.on.aol.com/v1.0/app/videos/aolon/%s/details' % video_id,
+18 -18
View File
@@ -226,13 +226,13 @@ class ARDMediathekIE(ARDMediathekBaseIE):
if doc.tag == 'rss': if doc.tag == 'rss':
return GenericIE()._extract_rss(url, video_id, doc) return GenericIE()._extract_rss(url, video_id, doc)
title = self._html_search_regex( title = self._og_search_title(webpage, default=None) or self._html_search_regex(
[r'<h1(?:\s+class="boxTopHeadline")?>(.*?)</h1>', [r'<h1(?:\s+class="boxTopHeadline")?>(.*?)</h1>',
r'<meta name="dcterms\.title" content="(.*?)"/>', r'<meta name="dcterms\.title" content="(.*?)"/>',
r'<h4 class="headline">(.*?)</h4>', r'<h4 class="headline">(.*?)</h4>',
r'<title[^>]*>(.*?)</title>'], r'<title[^>]*>(.*?)</title>'],
webpage, 'title') webpage, 'title')
description = self._html_search_meta( description = self._og_search_description(webpage, default=None) or self._html_search_meta(
'dcterms.abstract', webpage, 'description', default=None) 'dcterms.abstract', webpage, 'description', default=None)
if description is None: if description is None:
description = self._html_search_meta( description = self._html_search_meta(
@@ -289,18 +289,18 @@ class ARDMediathekIE(ARDMediathekBaseIE):
class ARDIE(InfoExtractor): class ARDIE(InfoExtractor):
_VALID_URL = r'(?P<mainurl>https?://(www\.)?daserste\.de/[^?#]+/videos(?:extern)?/(?P<display_id>[^/?#]+)-(?P<id>[0-9]+))\.html' _VALID_URL = r'(?P<mainurl>https?://(?:www\.)?daserste\.de/[^?#]+/videos(?:extern)?/(?P<display_id>[^/?#]+)-(?:video-?)?(?P<id>[0-9]+))\.html'
_TESTS = [{ _TESTS = [{
# available till 14.02.2019 # available till 7.01.2022
'url': 'http://www.daserste.de/information/talk/maischberger/videos/das-groko-drama-zerlegen-sich-die-volksparteien-video-102.html', 'url': 'https://www.daserste.de/information/talk/maischberger/videos/maischberger-die-woche-video100.html',
'md5': '8e4ec85f31be7c7fc08a26cdbc5a1f49', 'md5': '867d8aa39eeaf6d76407c5ad1bb0d4c1',
'info_dict': { 'info_dict': {
'display_id': 'das-groko-drama-zerlegen-sich-die-volksparteien-video', 'display_id': 'maischberger-die-woche',
'id': '102', 'id': '100',
'ext': 'mp4', 'ext': 'mp4',
'duration': 4435.0, 'duration': 3687.0,
'title': 'Das GroKo-Drama: Zerlegen sich die Volksparteien?', 'title': 'maischberger. die woche vom 7. Januar 2021',
'upload_date': '20180214', 'upload_date': '20210107',
'thumbnail': r're:^https?://.*\.jpg$', 'thumbnail': r're:^https?://.*\.jpg$',
}, },
}, { }, {
@@ -355,17 +355,17 @@ class ARDIE(InfoExtractor):
class ARDBetaMediathekIE(ARDMediathekBaseIE): class ARDBetaMediathekIE(ARDMediathekBaseIE):
_VALID_URL = r'https://(?:(?:beta|www)\.)?ardmediathek\.de/(?P<client>[^/]+)/(?P<mode>player|live|video|sendung|sammlung)/(?P<display_id>(?:[^/]+/)*)(?P<video_id>[a-zA-Z0-9]+)' _VALID_URL = r'https://(?:(?:beta|www)\.)?ardmediathek\.de/(?P<client>[^/]+)/(?P<mode>player|live|video|sendung|sammlung)/(?P<display_id>(?:[^/]+/)*)(?P<video_id>[a-zA-Z0-9]+)'
_TESTS = [{ _TESTS = [{
'url': 'https://ardmediathek.de/ard/video/die-robuste-roswita/Y3JpZDovL2Rhc2Vyc3RlLmRlL3RhdG9ydC9mYmM4NGM1NC0xNzU4LTRmZGYtYWFhZS0wYzcyZTIxNGEyMDE', 'url': 'https://www.ardmediathek.de/mdr/video/die-robuste-roswita/Y3JpZDovL21kci5kZS9iZWl0cmFnL2Ntcy84MWMxN2MzZC0wMjkxLTRmMzUtODk4ZS0wYzhlOWQxODE2NGI/',
'md5': 'dfdc87d2e7e09d073d5a80770a9ce88f', 'md5': 'a1dc75a39c61601b980648f7c9f9f71d',
'info_dict': { 'info_dict': {
'display_id': 'die-robuste-roswita', 'display_id': 'die-robuste-roswita',
'id': '70153354', 'id': '78566716',
'title': 'Die robuste Roswita', 'title': 'Die robuste Roswita',
'description': r're:^Der Mord.*trüber ist als die Ilm.', 'description': r're:^Der Mord.*totgeglaubte Ehefrau Roswita',
'duration': 5316, 'duration': 5316,
'thumbnail': 'https://img.ardmediathek.de/standard/00/70/15/33/90/-1852531467/16x9/960?mandant=ard', 'thumbnail': 'https://img.ardmediathek.de/standard/00/78/56/67/84/575672121/16x9/960?mandant=ard',
'timestamp': 1577047500, 'timestamp': 1596658200,
'upload_date': '20191222', 'upload_date': '20200805',
'ext': 'mp4', 'ext': 'mp4',
}, },
}, { }, {
+1 -1
View File
@@ -59,7 +59,7 @@ class CBSIE(CBSBaseIE):
'http://can.cbs.com/thunder/player/videoPlayerService.php', 'http://can.cbs.com/thunder/player/videoPlayerService.php',
content_id, query={'partner': site, 'contentId': content_id}) content_id, query={'partner': site, 'contentId': content_id})
video_data = xpath_element(items_data, './/item') video_data = xpath_element(items_data, './/item')
title = xpath_text(video_data, 'videoTitle', 'title', True) title = xpath_text(video_data, 'videoTitle', 'title') or xpath_text(video_data, 'videotitle', 'title')
tp_path = 'dJ5BDC/media/guid/%d/%s' % (mpx_acc, content_id) tp_path = 'dJ5BDC/media/guid/%d/%s' % (mpx_acc, content_id)
tp_release_url = 'http://link.theplatform.com/s/' + tp_path tp_release_url = 'http://link.theplatform.com/s/' + tp_path
+25 -116
View File
@@ -1,142 +1,51 @@
from __future__ import unicode_literals from __future__ import unicode_literals
from .mtv import MTVServicesInfoExtractor from .mtv import MTVServicesInfoExtractor
from .common import InfoExtractor
class ComedyCentralIE(MTVServicesInfoExtractor): class ComedyCentralIE(MTVServicesInfoExtractor):
_VALID_URL = r'''(?x)https?://(?:www\.)?cc\.com/ _VALID_URL = r'https?://(?:www\.)?cc\.com/(?:episodes|video(?:-clips)?)/(?P<id>[0-9a-z]{6})'
(video-clips|episodes|cc-studios|video-collections|shows(?=/[^/]+/(?!full-episodes)))
/(?P<title>.*)'''
_FEED_URL = 'http://comedycentral.com/feeds/mrss/' _FEED_URL = 'http://comedycentral.com/feeds/mrss/'
_TESTS = [{ _TESTS = [{
'url': 'http://www.cc.com/video-clips/kllhuv/stand-up-greg-fitzsimmons--uncensored---too-good-of-a-mother', 'url': 'http://www.cc.com/video-clips/5ke9v2/the-daily-show-with-trevor-noah-doc-rivers-and-steve-ballmer---the-nba-player-strike',
'md5': 'c4f48e9eda1b16dd10add0744344b6d8', 'md5': 'b8acb347177c680ff18a292aa2166f80',
'info_dict': { 'info_dict': {
'id': 'cef0cbb3-e776-4bc9-b62e-8016deccb354', 'id': '89ccc86e-1b02-4f83-b0c9-1d9592ecd025',
'ext': 'mp4', 'ext': 'mp4',
'title': 'CC:Stand-Up|August 18, 2013|1|0101|Uncensored - Too Good of a Mother', 'title': 'The Daily Show with Trevor Noah|August 28, 2020|25|25149|Doc Rivers and Steve Ballmer - The NBA Player Strike',
'description': 'After a certain point, breastfeeding becomes c**kblocking.', 'description': 'md5:5334307c433892b85f4f5e5ac9ef7498',
'timestamp': 1376798400, 'timestamp': 1598670000,
'upload_date': '20130818', 'upload_date': '20200829',
}, },
}, { }, {
'url': 'http://www.cc.com/shows/the-daily-show-with-trevor-noah/interviews/6yx39d/exclusive-rand-paul-extended-interview', 'url': 'http://www.cc.com/episodes/pnzzci/drawn-together--american-idol--parody-clip-show-season-3-ep-314',
'only_matching': True, 'only_matching': True,
}]
class ComedyCentralFullEpisodesIE(MTVServicesInfoExtractor):
_VALID_URL = r'''(?x)https?://(?:www\.)?cc\.com/
(?:full-episodes|shows(?=/[^/]+/full-episodes))
/(?P<id>[^?]+)'''
_FEED_URL = 'http://comedycentral.com/feeds/mrss/'
_TESTS = [{
'url': 'http://www.cc.com/full-episodes/pv391a/the-daily-show-with-trevor-noah-november-28--2016---ryan-speedo-green-season-22-ep-22028',
'info_dict': {
'description': 'Donald Trump is accused of exploiting his president-elect status for personal gain, Cuban leader Fidel Castro dies, and Ryan Speedo Green discusses "Sing for Your Life."',
'title': 'November 28, 2016 - Ryan Speedo Green',
},
'playlist_count': 4,
}, { }, {
'url': 'http://www.cc.com/shows/the-daily-show-with-trevor-noah/full-episodes', 'url': 'https://www.cc.com/video/k3sdvm/the-daily-show-with-jon-stewart-exclusive-the-fourth-estate',
'only_matching': True,
}]
def _real_extract(self, url):
playlist_id = self._match_id(url)
webpage = self._download_webpage(url, playlist_id)
mgid = self._extract_mgid(webpage, url, data_zone='t2_lc_promo1')
videos_info = self._get_videos_info(mgid)
return videos_info
class ToshIE(MTVServicesInfoExtractor):
IE_DESC = 'Tosh.0'
_VALID_URL = r'^https?://tosh\.cc\.com/video-(?:clips|collections)/[^/]+/(?P<videotitle>[^/?#]+)'
_FEED_URL = 'http://tosh.cc.com/feeds/mrss'
_TESTS = [{
'url': 'http://tosh.cc.com/video-clips/68g93d/twitter-users-share-summer-plans',
'info_dict': {
'description': 'Tosh asked fans to share their summer plans.',
'title': 'Twitter Users Share Summer Plans',
},
'playlist': [{
'md5': 'f269e88114c1805bb6d7653fecea9e06',
'info_dict': {
'id': '90498ec2-ed00-11e0-aca6-0026b9414f30',
'ext': 'mp4',
'title': 'Tosh.0|June 9, 2077|2|211|Twitter Users Share Summer Plans',
'description': 'Tosh asked fans to share their summer plans.',
'thumbnail': r're:^https?://.*\.jpg',
# It's really reported to be published on year 2077
'upload_date': '20770610',
'timestamp': 3390510600,
'subtitles': {
'en': 'mincount:3',
},
},
}]
}, {
'url': 'http://tosh.cc.com/video-collections/x2iz7k/just-plain-foul/m5q4fp',
'only_matching': True, 'only_matching': True,
}] }]
class ComedyCentralTVIE(MTVServicesInfoExtractor): class ComedyCentralTVIE(MTVServicesInfoExtractor):
_VALID_URL = r'https?://(?:www\.)?comedycentral\.tv/(?:staffeln|shows)/(?P<id>[^/?#&]+)' _VALID_URL = r'https?://(?:www\.)?comedycentral\.tv/folgen/(?P<id>[0-9a-z]{6})'
_TESTS = [{ _TESTS = [{
'url': 'http://www.comedycentral.tv/staffeln/7436-the-mindy-project-staffel-4', 'url': 'https://www.comedycentral.tv/folgen/pxdpec/josh-investigates-klimawandel-staffel-1-ep-1',
'info_dict': { 'info_dict': {
'id': 'local_playlist-f99b626bdfe13568579a', 'id': '15907dc3-ec3c-11e8-a442-0e40cf2fc285',
'ext': 'flv', 'ext': 'mp4',
'title': 'Episode_the-mindy-project_shows_season-4_episode-3_full-episode_part1', 'title': 'Josh Investigates',
'description': 'Steht uns das Ende der Welt bevor?',
}, },
'params': {
# rtmp download
'skip_download': True,
},
}, {
'url': 'http://www.comedycentral.tv/shows/1074-workaholics',
'only_matching': True,
}, {
'url': 'http://www.comedycentral.tv/shows/1727-the-mindy-project/bonus',
'only_matching': True,
}] }]
_FEED_URL = 'http://feeds.mtvnservices.com/od/feed/intl-mrss-player-feed'
_GEO_COUNTRIES = ['DE']
def _real_extract(self, url): def _get_feed_query(self, uri):
video_id = self._match_id(url) return {
'accountOverride': 'intl.mtvi.com',
webpage = self._download_webpage(url, video_id) 'arcEp': 'web.cc.tv',
'ep': 'b9032c3a',
mrss_url = self._search_regex( 'imageEp': 'web.cc.tv',
r'data-mrss=(["\'])(?P<url>(?:(?!\1).)+)\1', 'mgid': uri,
webpage, 'mrss url', group='url')
return self._get_videos_info_from_url(mrss_url, video_id)
class ComedyCentralShortnameIE(InfoExtractor):
_VALID_URL = r'^:(?P<id>tds|thedailyshow|theopposition)$'
_TESTS = [{
'url': ':tds',
'only_matching': True,
}, {
'url': ':thedailyshow',
'only_matching': True,
}, {
'url': ':theopposition',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
shortcut_map = {
'tds': 'http://www.cc.com/shows/the-daily-show-with-trevor-noah/full-episodes',
'thedailyshow': 'http://www.cc.com/shows/the-daily-show-with-trevor-noah/full-episodes',
'theopposition': 'http://www.cc.com/shows/the-opposition-with-jordan-klepper/full-episodes',
} }
return self.url_result(shortcut_map[video_id])
+34 -24
View File
@@ -1375,8 +1375,8 @@ class InfoExtractor(object):
'order': ['vp9', '(h265|he?vc?)', '(h264|avc)', 'vp8', '(mp4v|h263)', 'theora', '', None, 'none']}, 'order': ['vp9', '(h265|he?vc?)', '(h264|avc)', 'vp8', '(mp4v|h263)', 'theora', '', None, 'none']},
'acodec': {'type': 'ordered', 'regex': True, 'acodec': {'type': 'ordered', 'regex': True,
'order': ['opus', 'vorbis', 'aac', 'mp?4a?', 'mp3', 'e?a?c-?3', 'dts', '', None, 'none']}, 'order': ['opus', 'vorbis', 'aac', 'mp?4a?', 'mp3', 'e?a?c-?3', 'dts', '', None, 'none']},
'protocol': {'type': 'ordered', 'regex': True, 'proto': {'type': 'ordered', 'regex': True,
'order': ['(ht|f)tps', '(ht|f)tp$', 'm3u8.+', 'm3u8', '.*dash', '', 'mms|rtsp', 'none', 'f4']}, 'order': ['(ht|f)tps', '(ht|f)tp$', 'm3u8.+', 'm3u8', '.*dash', '', 'mms|rtsp', 'none', 'f4']},
'vext': {'type': 'ordered', 'field': 'video_ext', 'vext': {'type': 'ordered', 'field': 'video_ext',
'order': ('mp4', 'webm', 'flv', '', 'none'), 'order': ('mp4', 'webm', 'flv', '', 'none'),
'order_free': ('webm', 'mp4', 'flv', '', 'none')}, 'order_free': ('webm', 'mp4', 'flv', '', 'none')},
@@ -1384,14 +1384,14 @@ class InfoExtractor(object):
'order': ('m4a', 'aac', 'mp3', 'ogg', 'opus', 'webm', '', 'none'), 'order': ('m4a', 'aac', 'mp3', 'ogg', 'opus', 'webm', '', 'none'),
'order_free': ('opus', 'ogg', 'webm', 'm4a', 'mp3', 'aac', '', 'none')}, 'order_free': ('opus', 'ogg', 'webm', 'm4a', 'mp3', 'aac', '', 'none')},
'hidden': {'visible': False, 'forced': True, 'type': 'extractor', 'max': -1000}, 'hidden': {'visible': False, 'forced': True, 'type': 'extractor', 'max': -1000},
'extractor_preference': {'priority': True, 'type': 'extractor'}, 'ie_pref': {'priority': True, 'type': 'extractor'},
'has_video': {'priority': True, 'field': 'vcodec', 'type': 'boolean', 'not_in_list': ('none',)}, 'hasvid': {'priority': True, 'field': 'vcodec', 'type': 'boolean', 'not_in_list': ('none',)},
'has_audio': {'field': 'acodec', 'type': 'boolean', 'not_in_list': ('none',)}, 'hasaud': {'field': 'acodec', 'type': 'boolean', 'not_in_list': ('none',)},
'language_preference': {'priority': True, 'convert': 'ignore'}, 'lang': {'priority': True, 'convert': 'ignore'},
'quality': {'priority': True, 'convert': 'float_none'}, 'quality': {'priority': True, 'convert': 'float_none'},
'filesize': {'convert': 'bytes'}, 'filesize': {'convert': 'bytes'},
'filesize_approx': {'convert': 'bytes'}, 'fs_approx': {'convert': 'bytes'},
'format_id': {'convert': 'string'}, 'id': {'convert': 'string'},
'height': {'convert': 'float_none'}, 'height': {'convert': 'float_none'},
'width': {'convert': 'float_none'}, 'width': {'convert': 'float_none'},
'fps': {'convert': 'float_none'}, 'fps': {'convert': 'float_none'},
@@ -1399,32 +1399,42 @@ class InfoExtractor(object):
'vbr': {'convert': 'float_none'}, 'vbr': {'convert': 'float_none'},
'abr': {'convert': 'float_none'}, 'abr': {'convert': 'float_none'},
'asr': {'convert': 'float_none'}, 'asr': {'convert': 'float_none'},
'source_preference': {'convert': 'ignore'}, 'source': {'convert': 'ignore'},
'codec': {'type': 'combined', 'field': ('vcodec', 'acodec')}, 'codec': {'type': 'combined', 'field': ('vcodec', 'acodec')},
'bitrate': {'type': 'combined', 'field': ('tbr', 'vbr', 'abr'), 'same_limit': True}, 'br': {'type': 'combined', 'field': ('tbr', 'vbr', 'abr'), 'same_limit': True},
'filesize_estimate': {'type': 'combined', 'same_limit': True, 'field': ('filesize', 'filesize_approx')}, 'size': {'type': 'combined', 'same_limit': True, 'field': ('filesize', 'fs_approx')},
'extension': {'type': 'combined', 'field': ('vext', 'aext')}, 'ext': {'type': 'combined', 'field': ('vext', 'aext')},
'dimension': {'type': 'multiple', 'field': ('height', 'width'), 'function': min}, # not named as 'resolution' because such a field exists 'res': {'type': 'multiple', 'field': ('height', 'width'), 'function': min},
'res': {'type': 'alias', 'field': 'dimension'},
'ext': {'type': 'alias', 'field': 'extension'}, # Most of these exist only for compatibility reasons
'br': {'type': 'alias', 'field': 'bitrate'}, 'dimension': {'type': 'alias', 'field': 'res'},
'resolution': {'type': 'alias', 'field': 'res'},
'extension': {'type': 'alias', 'field': 'ext'},
'bitrate': {'type': 'alias', 'field': 'br'},
'total_bitrate': {'type': 'alias', 'field': 'tbr'}, 'total_bitrate': {'type': 'alias', 'field': 'tbr'},
'video_bitrate': {'type': 'alias', 'field': 'vbr'}, 'video_bitrate': {'type': 'alias', 'field': 'vbr'},
'audio_bitrate': {'type': 'alias', 'field': 'abr'}, 'audio_bitrate': {'type': 'alias', 'field': 'abr'},
'framerate': {'type': 'alias', 'field': 'fps'}, 'framerate': {'type': 'alias', 'field': 'fps'},
'lang': {'type': 'alias', 'field': 'language_preference'}, # not named as 'language' because such a field exists 'language_preference': {'type': 'alias', 'field': 'lang'}, # not named as 'language' because such a field exists
'proto': {'type': 'alias', 'field': 'protocol'}, 'protocol': {'type': 'alias', 'field': 'proto'},
'source': {'type': 'alias', 'field': 'source_preference'}, 'source_preference': {'type': 'alias', 'field': 'source'},
'size': {'type': 'alias', 'field': 'filesize_estimate'}, 'filesize_approx': {'type': 'alias', 'field': 'fs_approx'},
'filesize_estimate': {'type': 'alias', 'field': 'size'},
'samplerate': {'type': 'alias', 'field': 'asr'}, 'samplerate': {'type': 'alias', 'field': 'asr'},
'video_ext': {'type': 'alias', 'field': 'vext'}, 'video_ext': {'type': 'alias', 'field': 'vext'},
'audio_ext': {'type': 'alias', 'field': 'aext'}, 'audio_ext': {'type': 'alias', 'field': 'aext'},
'video_codec': {'type': 'alias', 'field': 'vcodec'}, 'video_codec': {'type': 'alias', 'field': 'vcodec'},
'audio_codec': {'type': 'alias', 'field': 'acodec'}, 'audio_codec': {'type': 'alias', 'field': 'acodec'},
'video': {'type': 'alias', 'field': 'has_video'}, 'video': {'type': 'alias', 'field': 'hasvid'},
'audio': {'type': 'alias', 'field': 'has_audio'}, 'has_video': {'type': 'alias', 'field': 'hasvid'},
'extractor': {'type': 'alias', 'field': 'extractor_preference'}, 'audio': {'type': 'alias', 'field': 'hasaud'},
'preference': {'type': 'alias', 'field': 'extractor_preference'}} 'has_audio': {'type': 'alias', 'field': 'hasaud'},
'extractor': {'type': 'alias', 'field': 'ie_pref'},
'preference': {'type': 'alias', 'field': 'ie_pref'},
'extractor_preference': {'type': 'alias', 'field': 'ie_pref'},
'format_id': {'type': 'alias', 'field': 'id'},
}
_order = [] _order = []
+22 -4
View File
@@ -50,7 +50,10 @@ from .animelab import (
AnimeLabIE, AnimeLabIE,
AnimeLabShowsIE, AnimeLabShowsIE,
) )
from .americastestkitchen import AmericasTestKitchenIE from .americastestkitchen import (
AmericasTestKitchenIE,
AmericasTestKitchenSeasonIE,
)
from .animeondemand import AnimeOnDemandIE from .animeondemand import AnimeOnDemandIE
from .anvato import AnvatoIE from .anvato import AnvatoIE
from .aol import AolIE from .aol import AolIE
@@ -244,11 +247,8 @@ from .cnn import (
) )
from .coub import CoubIE from .coub import CoubIE
from .comedycentral import ( from .comedycentral import (
ComedyCentralFullEpisodesIE,
ComedyCentralIE, ComedyCentralIE,
ComedyCentralShortnameIE,
ComedyCentralTVIE, ComedyCentralTVIE,
ToshIE,
) )
from .commonmistakes import CommonMistakesIE, UnicodeBOMIE from .commonmistakes import CommonMistakesIE, UnicodeBOMIE
from .commonprotocols import ( from .commonprotocols import (
@@ -677,6 +677,16 @@ from .microsoftvirtualacademy import (
MicrosoftVirtualAcademyIE, MicrosoftVirtualAcademyIE,
MicrosoftVirtualAcademyCourseIE, MicrosoftVirtualAcademyCourseIE,
) )
from .mildom import (
MildomIE,
MildomVodIE,
MildomUserVodIE,
)
from .minds import (
MindsIE,
MindsChannelIE,
MindsGroupIE,
)
from .ministrygrid import MinistryGridIE from .ministrygrid import MinistryGridIE
from .minoto import MinotoIE from .minoto import MinotoIE
from .miomio import MioMioIE from .miomio import MioMioIE
@@ -1157,6 +1167,10 @@ from .stitcher import StitcherIE
from .sport5 import Sport5IE from .sport5 import Sport5IE
from .sportbox import SportBoxIE from .sportbox import SportBoxIE
from .sportdeutschland import SportDeutschlandIE from .sportdeutschland import SportDeutschlandIE
from .spotify import (
SpotifyIE,
SpotifyShowIE,
)
from .spreaker import ( from .spreaker import (
SpreakerIE, SpreakerIE,
SpreakerPageIE, SpreakerPageIE,
@@ -1265,6 +1279,10 @@ from .toutv import TouTvIE
from .toypics import ToypicsUserIE, ToypicsIE from .toypics import ToypicsUserIE, ToypicsIE
from .traileraddict import TrailerAddictIE from .traileraddict import TrailerAddictIE
from .trilulilu import TriluliluIE from .trilulilu import TriluliluIE
from .trovo import (
TrovoIE,
TrovoVodIE,
)
from .trunews import TruNewsIE from .trunews import TruNewsIE
from .trutv import TruTVIE from .trutv import TruTVIE
from .tube8 import Tube8IE from .tube8 import Tube8IE
+12 -8
View File
@@ -11,7 +11,7 @@ from ..utils import (
class FranceCultureIE(InfoExtractor): class FranceCultureIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?franceculture\.fr/emissions/(?:[^/]+/)*(?P<id>[^/?#&]+)' _VALID_URL = r'https?://(?:www\.)?franceculture\.fr/emissions/(?:[^/]+/)*(?P<id>[^/?#&]+)'
_TEST = { _TESTS = [{
'url': 'http://www.franceculture.fr/emissions/carnet-nomade/rendez-vous-au-pays-des-geeks', 'url': 'http://www.franceculture.fr/emissions/carnet-nomade/rendez-vous-au-pays-des-geeks',
'info_dict': { 'info_dict': {
'id': 'rendez-vous-au-pays-des-geeks', 'id': 'rendez-vous-au-pays-des-geeks',
@@ -20,10 +20,14 @@ class FranceCultureIE(InfoExtractor):
'title': 'Rendez-vous au pays des geeks', 'title': 'Rendez-vous au pays des geeks',
'thumbnail': r're:^https?://.*\.jpg$', 'thumbnail': r're:^https?://.*\.jpg$',
'upload_date': '20140301', 'upload_date': '20140301',
'timestamp': 1393642916, 'timestamp': 1393700400,
'vcodec': 'none', 'vcodec': 'none',
} }
} }, {
# no thumbnail
'url': 'https://www.franceculture.fr/emissions/la-recherche-montre-en-main/la-recherche-montre-en-main-du-mercredi-10-octobre-2018',
'only_matching': True,
}]
def _real_extract(self, url): def _real_extract(self, url):
display_id = self._match_id(url) display_id = self._match_id(url)
@@ -36,19 +40,19 @@ class FranceCultureIE(InfoExtractor):
</h1>| </h1>|
<div[^>]+class="[^"]*?(?:title-zone-diffusion|heading-zone-(?:wrapper|player-button))[^"]*?"[^>]*> <div[^>]+class="[^"]*?(?:title-zone-diffusion|heading-zone-(?:wrapper|player-button))[^"]*?"[^>]*>
).*? ).*?
(<button[^>]+data-asset-source="[^"]+"[^>]+>) (<button[^>]+data-(?:url|asset-source)="[^"]+"[^>]+>)
''', ''',
webpage, 'video data')) webpage, 'video data'))
video_url = video_data['data-asset-source'] video_url = video_data.get('data-url') or video_data['data-asset-source']
title = video_data.get('data-asset-title') or self._og_search_title(webpage) title = video_data.get('data-asset-title') or video_data.get('data-diffusion-title') or self._og_search_title(webpage)
description = self._html_search_regex( description = self._html_search_regex(
r'(?s)<div[^>]+class="intro"[^>]*>.*?<h2>(.+?)</h2>', r'(?s)<div[^>]+class="intro"[^>]*>.*?<h2>(.+?)</h2>',
webpage, 'description', default=None) webpage, 'description', default=None)
thumbnail = self._search_regex( thumbnail = self._search_regex(
r'(?s)<figure[^>]+itemtype="https://schema.org/ImageObject"[^>]*>.*?<img[^>]+(?:data-dejavu-)?src="([^"]+)"', r'(?s)<figure[^>]+itemtype="https://schema.org/ImageObject"[^>]*>.*?<img[^>]+(?:data-dejavu-)?src="([^"]+)"',
webpage, 'thumbnail', fatal=False) webpage, 'thumbnail', default=None)
uploader = self._html_search_regex( uploader = self._html_search_regex(
r'(?s)<span class="author">(.*?)</span>', r'(?s)<span class="author">(.*?)</span>',
webpage, 'uploader', default=None) webpage, 'uploader', default=None)
@@ -64,6 +68,6 @@ class FranceCultureIE(InfoExtractor):
'ext': ext, 'ext': ext,
'vcodec': 'none' if ext == 'mp3' else None, 'vcodec': 'none' if ext == 'mp3' else None,
'uploader': uploader, 'uploader': uploader,
'timestamp': int_or_none(video_data.get('data-asset-created-date')), 'timestamp': int_or_none(video_data.get('data-start-time')) or int_or_none(video_data.get('data-asset-created-date')),
'duration': int_or_none(video_data.get('data-duration')), 'duration': int_or_none(video_data.get('data-duration')),
} }
+8 -1
View File
@@ -5,7 +5,10 @@ import functools
import json import json
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import compat_str from ..compat import (
compat_str,
compat_urllib_parse_unquote,
)
from ..utils import ( from ..utils import (
determine_ext, determine_ext,
ExtractorError, ExtractorError,
@@ -131,6 +134,9 @@ class LBRYIE(LBRYBaseIE):
}, { }, {
'url': 'https://lbry.tv/$/download/Episode-1/e7d93d772bd87e2b62d5ab993c1c3ced86ebb396', 'url': 'https://lbry.tv/$/download/Episode-1/e7d93d772bd87e2b62d5ab993c1c3ced86ebb396',
'only_matching': True, 'only_matching': True,
}, {
'url': 'https://lbry.tv/@lacajadepandora:a/TRUMP-EST%C3%81-BIEN-PUESTO-con-Pilar-Baselga,-Carlos-Senra,-Luis-Palacios-(720p_30fps_H264-192kbit_AAC):1',
'only_matching': True,
}] }]
def _real_extract(self, url): def _real_extract(self, url):
@@ -139,6 +145,7 @@ class LBRYIE(LBRYBaseIE):
display_id = display_id.split('/', 2)[-1].replace('/', ':') display_id = display_id.split('/', 2)[-1].replace('/', ':')
else: else:
display_id = display_id.replace(':', '#') display_id = display_id.replace(':', '#')
display_id = compat_urllib_parse_unquote(display_id)
uri = 'lbry://' + display_id uri = 'lbry://' + display_id
result = self._resolve_url(uri, display_id, 'stream') result = self._resolve_url(uri, display_id, 'stream')
result_value = result['value'] result_value = result['value']
+284
View File
@@ -0,0 +1,284 @@
# coding: utf-8
from __future__ import unicode_literals
from datetime import datetime
import itertools
import json
import base64
from .common import InfoExtractor
from ..utils import (
ExtractorError, std_headers,
update_url_query,
random_uuidv4,
try_get,
)
from ..compat import (
compat_urlparse,
compat_urllib_parse_urlencode,
compat_str,
)
class MildomBaseIE(InfoExtractor):
_GUEST_ID = None
_DISPATCHER_CONFIG = None
def _call_api(self, url, video_id, query={}, note='Downloading JSON metadata', init=False):
url = update_url_query(url, self._common_queries(query, init=init))
return self._download_json(url, video_id, note=note)['body']
def _common_queries(self, query={}, init=False):
dc = self._fetch_dispatcher_config()
r = {
'timestamp': self.iso_timestamp(),
'__guest_id': '' if init else self.guest_id(),
'__location': dc['location'],
'__country': dc['country'],
'__cluster': dc['cluster'],
'__platform': 'web',
'__la': self.lang_code(),
'__pcv': 'v2.9.44',
'sfr': 'pc',
'accessToken': '',
}
r.update(query)
return r
def _fetch_dispatcher_config(self):
if not self._DISPATCHER_CONFIG:
try:
tmp = self._download_json(
'https://disp.mildom.com/serverListV2', 'initialization',
note='Downloading dispatcher_config', data=json.dumps({
'protover': 0,
'data': base64.b64encode(json.dumps({
'fr': 'web',
'sfr': 'pc',
'devi': 'Windows',
'la': 'ja',
'gid': None,
'loc': '',
'clu': '',
'wh': '1919*810',
'rtm': self.iso_timestamp(),
'ua': std_headers['User-Agent'],
}).encode('utf8')).decode('utf8').replace('\n', ''),
}).encode('utf8'))
self._DISPATCHER_CONFIG = self._parse_json(base64.b64decode(tmp['data']), 'initialization')
except ExtractorError:
self._DISPATCHER_CONFIG = self._download_json(
'https://bookish-octo-barnacle.vercel.app/api/dispatcher_config', 'initialization',
note='Downloading dispatcher_config fallback')
return self._DISPATCHER_CONFIG
@staticmethod
def iso_timestamp():
'new Date().toISOString()'
return datetime.utcnow().isoformat()[0:-3] + 'Z'
def guest_id(self):
'getGuestId'
if self._GUEST_ID:
return self._GUEST_ID
self._GUEST_ID = try_get(
self, (
lambda x: x._call_api(
'https://cloudac.mildom.com/nonolive/gappserv/guest/h5init', 'initialization',
note='Downloading guest token', init=True)['guest_id'] or None,
lambda x: x._get_cookies('https://www.mildom.com').get('gid').value,
lambda x: x._get_cookies('https://m.mildom.com').get('gid').value,
), compat_str) or ''
return self._GUEST_ID
def lang_code(self):
'getCurrentLangCode'
return 'ja'
class MildomIE(MildomBaseIE):
IE_NAME = 'mildom'
IE_DESC = 'Record ongoing live by specific user in Mildom'
_VALID_URL = r'https?://(?:(?:www|m)\.)mildom\.com/(?P<id>\d+)'
def _real_extract(self, url):
video_id = self._match_id(url)
url = 'https://www.mildom.com/%s' % video_id
webpage = self._download_webpage(url, video_id)
enterstudio = self._call_api(
'https://cloudac.mildom.com/nonolive/gappserv/live/enterstudio', video_id,
note='Downloading live metadata', query={'user_id': video_id})
title = try_get(
enterstudio, (
lambda x: self._html_search_meta('twitter:description', webpage),
lambda x: x['anchor_intro'],
), compat_str)
description = try_get(
enterstudio, (
lambda x: x['intro'],
lambda x: x['live_intro'],
), compat_str)
uploader = try_get(
enterstudio, (
lambda x: self._html_search_meta('twitter:title', webpage),
lambda x: x['loginname'],
), compat_str)
servers = self._call_api(
'https://cloudac.mildom.com/nonolive/gappserv/live/liveserver', video_id,
note='Downloading live server list', query={
'user_id': video_id,
'live_server_type': 'hls',
})
stream_query = self._common_queries({
'streamReqId': random_uuidv4(),
'is_lhls': '0',
})
m3u8_url = update_url_query(servers['stream_server'] + '/%s_master.m3u8' % video_id, stream_query)
formats = self._extract_m3u8_formats(m3u8_url, video_id, 'mp4', headers={
'Referer': 'https://www.mildom.com/',
'Origin': 'https://www.mildom.com',
}, note='Downloading m3u8 information')
del stream_query['streamReqId'], stream_query['timestamp']
for fmt in formats:
# Uses https://github.com/nao20010128nao/bookish-octo-barnacle by @nao20010128nao as a proxy
parsed = compat_urlparse.urlparse(fmt['url'])
parsed = parsed._replace(
netloc='bookish-octo-barnacle.vercel.app',
query=compat_urllib_parse_urlencode(stream_query, True),
path='/api' + parsed.path)
fmt['url'] = compat_urlparse.urlunparse(parsed)
self._sort_formats(formats)
return {
'id': video_id,
'title': title,
'description': description,
'uploader': uploader,
'uploader_id': video_id,
'formats': formats,
'is_live': True,
}
class MildomVodIE(MildomBaseIE):
IE_NAME = 'mildom:vod'
IE_DESC = 'Download a VOD in Mildom'
_VALID_URL = r'https?://(?:(?:www|m)\.)mildom\.com/playback/(?P<user_id>\d+)/(?P<id>(?P=user_id)-[a-zA-Z0-9]+)'
def _real_extract(self, url):
video_id = self._match_id(url)
m = self._VALID_URL_RE.match(url)
user_id = m.group('user_id')
url = 'https://www.mildom.com/playback/%s/%s' % (user_id, video_id)
webpage = self._download_webpage(url, video_id)
autoplay = self._call_api(
'https://cloudac.mildom.com/nonolive/videocontent/playback/getPlaybackDetail', video_id,
note='Downloading playback metadata', query={
'v_id': video_id,
})['playback']
title = try_get(
autoplay, (
lambda x: self._html_search_meta('og:description', webpage),
lambda x: x['title'],
), compat_str)
description = try_get(
autoplay, (
lambda x: x['video_intro'],
), compat_str)
uploader = try_get(
autoplay, (
lambda x: x['author_info']['login_name'],
), compat_str)
audio_formats = [{
'url': autoplay['audio_url'],
'format_id': 'audio',
'protocol': 'm3u8_native',
'vcodec': 'none',
'acodec': 'aac',
}]
video_formats = []
for fmt in autoplay['video_link']:
video_formats.append({
'format_id': 'video-%s' % fmt['name'],
'url': fmt['url'],
'protocol': 'm3u8_native',
'width': fmt['level'] * autoplay['video_width'] // autoplay['video_height'],
'height': fmt['level'],
'vcodec': 'h264',
'acodec': 'aac',
})
stream_query = self._common_queries({
'is_lhls': '0',
})
del stream_query['timestamp']
formats = audio_formats + video_formats
for fmt in formats:
fmt['ext'] = 'mp4'
parsed = compat_urlparse.urlparse(fmt['url'])
stream_query['path'] = parsed.path[5:]
parsed = parsed._replace(
netloc='bookish-octo-barnacle.vercel.app',
query=compat_urllib_parse_urlencode(stream_query, True),
path='/api/vod2/proxy')
fmt['url'] = compat_urlparse.urlunparse(parsed)
self._sort_formats(formats)
return {
'id': video_id,
'title': title,
'description': description,
'uploader': uploader,
'uploader_id': user_id,
'formats': formats,
}
class MildomUserVodIE(MildomBaseIE):
IE_NAME = 'mildom:user:vod'
IE_DESC = 'Download all VODs from specific user in Mildom'
_VALID_URL = r'https?://(?:(?:www|m)\.)mildom\.com/profile/(?P<id>\d+)'
_TESTS = [{
'url': 'https://www.mildom.com/profile/10093333',
'info_dict': {
'id': '10093333',
'title': 'Uploads from ねこばたけ',
},
'playlist_mincount': 351,
}]
def _real_extract(self, url):
user_id = self._match_id(url)
self._downloader.report_warning('To download ongoing live, please use "https://www.mildom.com/%s" instead. This will list up VODs belonging to user.' % user_id)
profile = self._call_api(
'https://cloudac.mildom.com/nonolive/gappserv/user/profileV2', user_id,
query={'user_id': user_id}, note='Downloading user profile')['user_info']
results = []
for page in itertools.count(1):
reply = self._call_api(
'https://cloudac.mildom.com/nonolive/videocontent/profile/playbackList',
user_id, note='Downloading page %d' % page, query={
'user_id': user_id,
'page': page,
'limit': '30',
})
if not reply:
break
results.extend('https://www.mildom.com/playback/%s/%s' % (user_id, x['v_id']) for x in reply)
return self.playlist_result([
self.url_result(u, ie=MildomVodIE.ie_key()) for u in results
], user_id, 'Uploads from %s' % profile['loginname'])
+196
View File
@@ -0,0 +1,196 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
clean_html,
int_or_none,
str_or_none,
strip_or_none,
)
class MindsBaseIE(InfoExtractor):
_VALID_URL_BASE = r'https?://(?:www\.)?minds\.com/'
def _call_api(self, path, video_id, resource, query=None):
api_url = 'https://www.minds.com/api/' + path
token = self._get_cookies(api_url).get('XSRF-TOKEN')
return self._download_json(
api_url, video_id, 'Downloading %s JSON metadata' % resource, headers={
'Referer': 'https://www.minds.com/',
'X-XSRF-TOKEN': token.value if token else '',
}, query=query)
class MindsIE(MindsBaseIE):
IE_NAME = 'minds'
_VALID_URL = MindsBaseIE._VALID_URL_BASE + r'(?:media|newsfeed|archive/view)/(?P<id>[0-9]+)'
_TESTS = [{
'url': 'https://www.minds.com/media/100000000000086822',
'md5': '215a658184a419764852239d4970b045',
'info_dict': {
'id': '100000000000086822',
'ext': 'mp4',
'title': 'Minds intro sequence',
'thumbnail': r're:https?://.+\.png',
'uploader_id': 'ottman',
'upload_date': '20130524',
'timestamp': 1369404826,
'uploader': 'Bill Ottman',
'view_count': int,
'like_count': int,
'dislike_count': int,
'tags': ['animation'],
'comment_count': int,
'license': 'attribution-cc',
},
}, {
# entity.type == 'activity' and empty title
'url': 'https://www.minds.com/newsfeed/798025111988506624',
'md5': 'b2733a74af78d7fd3f541c4cbbaa5950',
'info_dict': {
'id': '798022190320226304',
'ext': 'mp4',
'title': '798022190320226304',
'uploader': 'ColinFlaherty',
'upload_date': '20180111',
'timestamp': 1515639316,
'uploader_id': 'ColinFlaherty',
},
}, {
'url': 'https://www.minds.com/archive/view/715172106794442752',
'only_matching': True,
}, {
# youtube perma_url
'url': 'https://www.minds.com/newsfeed/1197131838022602752',
'only_matching': True,
}]
def _real_extract(self, url):
entity_id = self._match_id(url)
entity = self._call_api(
'v1/entities/entity/' + entity_id, entity_id, 'entity')['entity']
if entity.get('type') == 'activity':
if entity.get('custom_type') == 'video':
video_id = entity['entity_guid']
else:
return self.url_result(entity['perma_url'])
else:
assert(entity['subtype'] == 'video')
video_id = entity_id
# 1080p and webm formats available only on the sources array
video = self._call_api(
'v2/media/video/' + video_id, video_id, 'video')
formats = []
for source in (video.get('sources') or []):
src = source.get('src')
if not src:
continue
formats.append({
'format_id': source.get('label'),
'height': int_or_none(source.get('size')),
'url': src,
})
self._sort_formats(formats)
entity = video.get('entity') or entity
owner = entity.get('ownerObj') or {}
uploader_id = owner.get('username')
tags = entity.get('tags')
if tags and isinstance(tags, compat_str):
tags = [tags]
thumbnail = None
poster = video.get('poster') or entity.get('thumbnail_src')
if poster:
urlh = self._request_webpage(poster, video_id, fatal=False)
if urlh:
thumbnail = urlh.geturl()
return {
'id': video_id,
'title': entity.get('title') or video_id,
'formats': formats,
'description': clean_html(entity.get('description')) or None,
'license': str_or_none(entity.get('license')),
'timestamp': int_or_none(entity.get('time_created')),
'uploader': strip_or_none(owner.get('name')),
'uploader_id': uploader_id,
'uploader_url': 'https://www.minds.com/' + uploader_id if uploader_id else None,
'view_count': int_or_none(entity.get('play:count')),
'like_count': int_or_none(entity.get('thumbs:up:count')),
'dislike_count': int_or_none(entity.get('thumbs:down:count')),
'tags': tags,
'comment_count': int_or_none(entity.get('comments:count')),
'thumbnail': thumbnail,
}
class MindsFeedBaseIE(MindsBaseIE):
_PAGE_SIZE = 150
def _entries(self, feed_id):
query = {'limit': self._PAGE_SIZE, 'sync': 1}
i = 1
while True:
data = self._call_api(
'v2/feeds/container/%s/videos' % feed_id,
feed_id, 'page %s' % i, query)
entities = data.get('entities') or []
for entity in entities:
guid = entity.get('guid')
if not guid:
continue
yield self.url_result(
'https://www.minds.com/newsfeed/' + guid,
MindsIE.ie_key(), guid)
query['from_timestamp'] = data['load-next']
if not (query['from_timestamp'] and len(entities) == self._PAGE_SIZE):
break
i += 1
def _real_extract(self, url):
feed_id = self._match_id(url)
feed = self._call_api(
'v1/%s/%s' % (self._FEED_PATH, feed_id),
feed_id, self._FEED_TYPE)[self._FEED_TYPE]
return self.playlist_result(
self._entries(feed['guid']), feed_id,
strip_or_none(feed.get('name')),
feed.get('briefdescription'))
class MindsChannelIE(MindsFeedBaseIE):
_FEED_TYPE = 'channel'
IE_NAME = 'minds:' + _FEED_TYPE
_VALID_URL = MindsBaseIE._VALID_URL_BASE + r'(?!(?:newsfeed|media|api|archive|groups)/)(?P<id>[^/?&#]+)'
_FEED_PATH = 'channel'
_TEST = {
'url': 'https://www.minds.com/ottman',
'info_dict': {
'id': 'ottman',
'title': 'Bill Ottman',
'description': 'Co-creator & CEO @minds',
},
'playlist_mincount': 54,
}
class MindsGroupIE(MindsFeedBaseIE):
_FEED_TYPE = 'group'
IE_NAME = 'minds:' + _FEED_TYPE
_VALID_URL = MindsBaseIE._VALID_URL_BASE + r'groups/profile/(?P<id>[0-9]+)'
_FEED_PATH = 'groups/group'
_TEST = {
'url': 'https://www.minds.com/groups/profile/785582576369672204/feed/videos',
'info_dict': {
'id': '785582576369672204',
'title': 'Cooking Videos',
},
'playlist_mincount': 1,
}
+11 -12
View File
@@ -255,6 +255,10 @@ class MTVServicesInfoExtractor(InfoExtractor):
return try_get(feed, lambda x: x['result']['data']['id'], compat_str) return try_get(feed, lambda x: x['result']['data']['id'], compat_str)
@staticmethod
def _extract_child_with_type(parent, t):
return next(c for c in parent['children'] if c.get('type') == t)
def _extract_new_triforce_mgid(self, webpage, url='', video_id=None): def _extract_new_triforce_mgid(self, webpage, url='', video_id=None):
if url == '': if url == '':
return return
@@ -332,6 +336,13 @@ class MTVServicesInfoExtractor(InfoExtractor):
if not mgid: if not mgid:
mgid = self._extract_triforce_mgid(webpage, data_zone) mgid = self._extract_triforce_mgid(webpage, data_zone)
if not mgid:
data = self._parse_json(self._search_regex(
r'__DATA__\s*=\s*({.+?});', webpage, 'data'), None)
main_container = self._extract_child_with_type(data, 'MainContainer')
video_player = self._extract_child_with_type(main_container, 'VideoPlayer')
mgid = video_player['props']['media']['video']['config']['uri']
return mgid return mgid
def _real_extract(self, url): def _real_extract(self, url):
@@ -403,18 +414,6 @@ class MTVIE(MTVServicesInfoExtractor):
'only_matching': True, 'only_matching': True,
}] }]
@staticmethod
def extract_child_with_type(parent, t):
children = parent['children']
return next(c for c in children if c.get('type') == t)
def _extract_mgid(self, webpage):
data = self._parse_json(self._search_regex(
r'__DATA__\s*=\s*({.+?});', webpage, 'data'), None)
main_container = self.extract_child_with_type(data, 'MainContainer')
video_player = self.extract_child_with_type(main_container, 'VideoPlayer')
return video_player['props']['media']['video']['config']['uri']
class MTVJapanIE(MTVServicesInfoExtractor): class MTVJapanIE(MTVServicesInfoExtractor):
IE_NAME = 'mtvjapan' IE_NAME = 'mtvjapan'
+105 -84
View File
@@ -1,104 +1,125 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import str_to_int from ..utils import (
determine_ext,
ExtractorError,
int_or_none,
try_get,
url_or_none,
)
class NineGagIE(InfoExtractor): class NineGagIE(InfoExtractor):
IE_NAME = '9gag' IE_NAME = '9gag'
_VALID_URL = r'https?://(?:www\.)?9gag(?:\.com/tv|\.tv)/(?:p|embed)/(?P<id>[a-zA-Z0-9]+)(?:/(?P<display_id>[^?#/]+))?' _VALID_URL = r'https?://(?:www\.)?9gag\.com/gag/(?P<id>[^/?&#]+)'
_TESTS = [{ _TEST = {
'url': 'http://9gag.com/tv/p/Kk2X5/people-are-awesome-2013-is-absolutely-awesome', 'url': 'https://9gag.com/gag/ae5Ag7B',
'info_dict': { 'info_dict': {
'id': 'kXzwOKyGlSA', 'id': 'ae5Ag7B',
'ext': 'mp4', 'ext': 'mp4',
'description': 'This 3-minute video will make you smile and then make you feel untalented and insignificant. Anyway, you should share this awesomeness. (Thanks, Dino!)', 'title': 'Capybara Agility Training',
'title': '\"People Are Awesome 2013\" Is Absolutely Awesome', 'upload_date': '20191108',
'uploader_id': 'UCdEH6EjDKwtTe-sO2f0_1XA', 'timestamp': 1573237208,
'uploader': 'CompilationChannel', 'categories': ['Awesome'],
'upload_date': '20131110', 'tags': ['Weimaraner', 'American Pit Bull Terrier'],
'view_count': int, 'duration': 44,
}, 'like_count': int,
'add_ie': ['Youtube'], 'dislike_count': int,
}, { 'comment_count': int,
'url': 'http://9gag.com/tv/p/aKolP3', }
'info_dict': {
'id': 'aKolP3',
'ext': 'mp4',
'title': 'This Guy Travelled 11 countries In 44 days Just To Make This Amazing Video',
'description': "I just saw more in 1 minute than I've seen in 1 year. This guy's video is epic!!",
'uploader_id': 'rickmereki',
'uploader': 'Rick Mereki',
'upload_date': '20110803',
'view_count': int,
},
'add_ie': ['Vimeo'],
}, {
'url': 'http://9gag.com/tv/p/KklwM',
'only_matching': True,
}, {
'url': 'http://9gag.tv/p/Kk2X5',
'only_matching': True,
}, {
'url': 'http://9gag.com/tv/embed/a5Dmvl',
'only_matching': True,
}]
_EXTERNAL_VIDEO_PROVIDER = {
'1': {
'url': '%s',
'ie_key': 'Youtube',
},
'2': {
'url': 'http://player.vimeo.com/video/%s',
'ie_key': 'Vimeo',
},
'3': {
'url': 'http://instagram.com/p/%s',
'ie_key': 'Instagram',
},
'4': {
'url': 'http://vine.co/v/%s',
'ie_key': 'Vine',
},
} }
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) post_id = self._match_id(url)
video_id = mobj.group('id') post = self._download_json(
display_id = mobj.group('display_id') or video_id 'https://9gag.com/v1/post', post_id, query={
'id': post_id
})['data']['post']
webpage = self._download_webpage(url, display_id) if post.get('type') != 'Animated':
raise ExtractorError(
'The given url does not contain a video',
expected=True)
post_view = self._parse_json( title = post['title']
self._search_regex(
r'var\s+postView\s*=\s*new\s+app\.PostView\({\s*post:\s*({.+?})\s*,\s*posts:\s*prefetchedCurrentPost',
webpage, 'post view'),
display_id)
ie_key = None duration = None
source_url = post_view.get('sourceUrl') formats = []
if not source_url: thumbnails = []
external_video_id = post_view['videoExternalId'] for key, image in (post.get('images') or {}).items():
external_video_provider = post_view['videoExternalProvider'] image_url = url_or_none(image.get('url'))
source_url = self._EXTERNAL_VIDEO_PROVIDER[external_video_provider]['url'] % external_video_id if not image_url:
ie_key = self._EXTERNAL_VIDEO_PROVIDER[external_video_provider]['ie_key'] continue
title = post_view['title'] ext = determine_ext(image_url)
description = post_view.get('description') image_id = key.strip('image')
view_count = str_to_int(post_view.get('externalView')) common = {
thumbnail = post_view.get('thumbnail_700w') or post_view.get('ogImageUrl') or post_view.get('thumbnail_300w') 'url': image_url,
'width': int_or_none(image.get('width')),
'height': int_or_none(image.get('height')),
}
if ext in ('jpg', 'png'):
webp_url = image.get('webpUrl')
if webp_url:
t = common.copy()
t.update({
'id': image_id + '-webp',
'url': webp_url,
})
thumbnails.append(t)
common.update({
'id': image_id,
'ext': ext,
})
thumbnails.append(common)
elif ext in ('webm', 'mp4'):
if not duration:
duration = int_or_none(image.get('duration'))
common['acodec'] = 'none' if image.get('hasAudio') == 0 else None
for vcodec in ('vp8', 'vp9', 'h265'):
c_url = image.get(vcodec + 'Url')
if not c_url:
continue
c_f = common.copy()
c_f.update({
'format_id': image_id + '-' + vcodec,
'url': c_url,
'vcodec': vcodec,
})
formats.append(c_f)
common.update({
'ext': ext,
'format_id': image_id,
})
formats.append(common)
self._sort_formats(formats)
section = try_get(post, lambda x: x['postSection']['name'])
tags = None
post_tags = post.get('tags')
if post_tags:
tags = []
for tag in post_tags:
tag_key = tag.get('key')
if not tag_key:
continue
tags.append(tag_key)
get_count = lambda x: int_or_none(post.get(x + 'Count'))
return { return {
'_type': 'url_transparent', 'id': post_id,
'url': source_url,
'ie_key': ie_key,
'id': video_id,
'display_id': display_id,
'title': title, 'title': title,
'description': description, 'timestamp': int_or_none(post.get('creationTs')),
'view_count': view_count, 'duration': duration,
'thumbnail': thumbnail, 'formats': formats,
'thumbnails': thumbnails,
'like_count': get_count('upVote'),
'dislike_count': get_count('downVote'),
'comment_count': get_count('comments'),
'age_limit': 18 if post.get('nsfw') == 1 else None,
'categories': [section] if section else None,
'tags': tags,
} }
+28 -26
View File
@@ -6,30 +6,40 @@ import re
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import compat_urlparse from ..compat import compat_urlparse
from ..utils import ( from ..utils import (
extract_attributes,
get_element_by_class, get_element_by_class,
urlencode_postdata, urlencode_postdata,
) )
class NJPWWorldIE(InfoExtractor): class NJPWWorldIE(InfoExtractor):
_VALID_URL = r'https?://njpwworld\.com/p/(?P<id>[a-z0-9_]+)' _VALID_URL = r'https?://(front\.)?njpwworld\.com/p/(?P<id>[a-z0-9_]+)'
IE_DESC = '新日本プロレスワールド' IE_DESC = '新日本プロレスワールド'
_NETRC_MACHINE = 'njpwworld' _NETRC_MACHINE = 'njpwworld'
_TEST = { _TESTS = [{
'url': 'http://njpwworld.com/p/s_series_00155_1_9/', 'url': 'http://njpwworld.com/p/s_series_00155_1_9/',
'info_dict': { 'info_dict': {
'id': 's_series_00155_1_9', 'id': 's_series_00155_1_9',
'ext': 'mp4', 'ext': 'mp4',
'title': '第9試合 ランディ・サベージ vs リック・スタイナー', 'title': '闘強導夢2000 2000年1月4日 東京ドーム 第9試合 ランディ・サベージ VS リック・スタイナー',
'tags': list, 'tags': list,
}, },
'params': { 'params': {
'skip_download': True, # AES-encrypted m3u8 'skip_download': True, # AES-encrypted m3u8
}, },
'skip': 'Requires login', 'skip': 'Requires login',
} }, {
'url': 'https://front.njpwworld.com/p/s_series_00563_16_bs',
'info_dict': {
'id': 's_series_00563_16_bs',
'ext': 'mp4',
'title': 'WORLD TAG LEAGUE 2020 & BEST OF THE SUPER Jr.27 2020年12月6日 福岡・福岡国際センター バックステージコメント(字幕あり)',
'tags': ["福岡・福岡国際センター", "バックステージコメント", "2020", "20年代"],
},
'params': {
'skip_download': True,
},
}]
_LOGIN_URL = 'https://front.njpwworld.com/auth/login' _LOGIN_URL = 'https://front.njpwworld.com/auth/login'
@@ -64,35 +74,27 @@ class NJPWWorldIE(InfoExtractor):
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
formats = [] formats = []
for mobj in re.finditer(r'<a[^>]+\bhref=(["\'])/player.+?[^>]*>', webpage): for kind, vid in re.findall(r'if\s+\(\s*imageQualityType\s*==\s*\'([^\']+)\'\s*\)\s*{\s*video_id\s*=\s*"(\d+)"', webpage):
player = extract_attributes(mobj.group(0)) player_path = '/intent?id=%s&type=url' % vid
player_path = player.get('href')
if not player_path:
continue
kind = self._search_regex(
r'(low|high)$', player.get('class') or '', 'kind',
default='low')
player_url = compat_urlparse.urljoin(url, player_path) player_url = compat_urlparse.urljoin(url, player_path)
player_page = self._download_webpage( formats.append({
player_url, video_id, note='Downloading player page') 'url': player_url,
entries = self._parse_html5_media_entries( 'format_id': kind,
player_url, player_page, video_id, m3u8_id='hls-%s' % kind, 'ext': 'mp4',
m3u8_entry_protocol='m3u8_native') 'protocol': 'm3u8',
kind_formats = entries[0]['formats'] 'quality': 2 if kind == 'high' else 1,
for f in kind_formats: })
f['quality'] = 2 if kind == 'high' else 1
formats.extend(kind_formats)
self._sort_formats(formats) self._sort_formats(formats)
post_content = get_element_by_class('post-content', webpage) tag_block = get_element_by_class('tag-block', webpage)
tags = re.findall( tags = re.findall(
r'<li[^>]+class="tag-[^"]+"><a[^>]*>([^<]+)</a></li>', post_content r'<a[^>]+class="tag-[^"]+"[^>]*>([^<]+)</a>', tag_block
) if post_content else None ) if tag_block else None
return { return {
'id': video_id, 'id': video_id,
'title': self._og_search_title(webpage), 'title': get_element_by_class('article-title', webpage) or self._og_search_title(webpage),
'formats': formats, 'formats': formats,
'tags': tags, 'tags': tags,
} }
+4 -1
View File
@@ -75,7 +75,7 @@ class PokemonIE(InfoExtractor):
class PokemonWatchIE(InfoExtractor): class PokemonWatchIE(InfoExtractor):
_VALID_URL = r'https?://watch\.pokemon\.com/[a-z]{2}-[a-z]{2}/player\.html\?id=(?P<id>[a-z0-9]{32})' _VALID_URL = r'https?://watch\.pokemon\.com/[a-z]{2}-[a-z]{2}/(?:#/)?player(?:\.html)?\?id=(?P<id>[a-z0-9]{32})'
_API_URL = 'https://www.pokemon.com/api/pokemontv/v2/channels/{0:}' _API_URL = 'https://www.pokemon.com/api/pokemontv/v2/channels/{0:}'
_TESTS = [{ _TESTS = [{
'url': 'https://watch.pokemon.com/en-us/player.html?id=8309a40969894a8e8d5bc1311e9c5667', 'url': 'https://watch.pokemon.com/en-us/player.html?id=8309a40969894a8e8d5bc1311e9c5667',
@@ -86,6 +86,9 @@ class PokemonWatchIE(InfoExtractor):
'title': 'Lillier and the Staff!', 'title': 'Lillier and the Staff!',
'description': 'md5:338841b8c21b283d24bdc9b568849f04', 'description': 'md5:338841b8c21b283d24bdc9b568849f04',
} }
}, {
'url': 'https://watch.pokemon.com/en-us/#/player?id=3fe7752ba09141f0b0f7756d1981c6b2',
'only_matching': True
}, { }, {
'url': 'https://watch.pokemon.com/de-de/player.html?id=b3c402e111a4459eb47e12160ab0ba07', 'url': 'https://watch.pokemon.com/de-de/player.html?id=b3c402e111a4459eb47e12160ab0ba07',
'only_matching': True 'only_matching': True
+1 -24
View File
@@ -20,19 +20,6 @@ class BellatorIE(MTVServicesInfoExtractor):
_FEED_URL = 'http://www.bellator.com/feeds/mrss/' _FEED_URL = 'http://www.bellator.com/feeds/mrss/'
_GEO_COUNTRIES = ['US'] _GEO_COUNTRIES = ['US']
def _extract_mgid(self, webpage, url):
mgid = None
if not mgid:
mgid = self._extract_triforce_mgid(webpage)
if not mgid:
mgid = self._extract_new_triforce_mgid(webpage, url)
return mgid
# TODO Remove - Reason: Outdated Site
class ParamountNetworkIE(MTVServicesInfoExtractor): class ParamountNetworkIE(MTVServicesInfoExtractor):
_VALID_URL = r'https?://(?:www\.)?paramountnetwork\.com/[^/]+/[\da-z]{6}(?:[/?#&]|$)' _VALID_URL = r'https?://(?:www\.)?paramountnetwork\.com/[^/]+/[\da-z]{6}(?:[/?#&]|$)'
@@ -56,16 +43,6 @@ class ParamountNetworkIE(MTVServicesInfoExtractor):
def _get_feed_query(self, uri): def _get_feed_query(self, uri):
return { return {
'arcEp': 'paramountnetwork.com', 'arcEp': 'paramountnetwork.com',
'imageEp': 'paramountnetwork.com',
'mgid': uri, 'mgid': uri,
} }
def _extract_mgid(self, webpage, url):
root_data = self._parse_json(self._search_regex(
r'window\.__DATA__\s*=\s*({.+})',
webpage, 'data'), None)
def find_sub_data(data, data_type):
return next(c for c in data['children'] if c.get('type') == data_type)
c = find_sub_data(find_sub_data(root_data, 'MainContainer'), 'VideoPlayer')
return c['props']['media']['video']['config']['uri']
+156
View File
@@ -0,0 +1,156 @@
# coding: utf-8
from __future__ import unicode_literals
import json
import re
from .common import InfoExtractor
from ..utils import (
clean_podcast_url,
float_or_none,
int_or_none,
strip_or_none,
try_get,
unified_strdate,
)
class SpotifyBaseIE(InfoExtractor):
_ACCESS_TOKEN = None
_OPERATION_HASHES = {
'Episode': '8276d4423d709ae9b68ec1b74cc047ba0f7479059a37820be730f125189ac2bf',
'MinimalShow': '13ee079672fad3f858ea45a55eb109553b4fb0969ed793185b2e34cbb6ee7cc0',
'ShowEpisodes': 'e0e5ce27bd7748d2c59b4d44ba245a8992a05be75d6fabc3b20753fc8857444d',
}
_VALID_URL_TEMPL = r'https?://open\.spotify\.com/%s/(?P<id>[^/?&#]+)'
def _real_initialize(self):
self._ACCESS_TOKEN = self._download_json(
'https://open.spotify.com/get_access_token', None)['accessToken']
def _call_api(self, operation, video_id, variables):
return self._download_json(
'https://api-partner.spotify.com/pathfinder/v1/query', video_id, query={
'operationName': 'query' + operation,
'variables': json.dumps(variables),
'extensions': json.dumps({
'persistedQuery': {
'sha256Hash': self._OPERATION_HASHES[operation],
},
})
}, headers={'authorization': 'Bearer ' + self._ACCESS_TOKEN})['data']
def _extract_episode(self, episode, series):
episode_id = episode['id']
title = episode['name'].strip()
formats = []
audio_preview = episode.get('audioPreview') or {}
audio_preview_url = audio_preview.get('url')
if audio_preview_url:
f = {
'url': audio_preview_url.replace('://p.scdn.co/mp3-preview/', '://anon-podcast.scdn.co/'),
'vcodec': 'none',
}
audio_preview_format = audio_preview.get('format')
if audio_preview_format:
f['format_id'] = audio_preview_format
mobj = re.match(r'([0-9A-Z]{3})_(?:[A-Z]+_)?(\d+)', audio_preview_format)
if mobj:
f.update({
'abr': int(mobj.group(2)),
'ext': mobj.group(1).lower(),
})
formats.append(f)
for item in (try_get(episode, lambda x: x['audio']['items']) or []):
item_url = item.get('url')
if not (item_url and item.get('externallyHosted')):
continue
formats.append({
'url': clean_podcast_url(item_url),
'vcodec': 'none',
})
thumbnails = []
for source in (try_get(episode, lambda x: x['coverArt']['sources']) or []):
source_url = source.get('url')
if not source_url:
continue
thumbnails.append({
'url': source_url,
'width': int_or_none(source.get('width')),
'height': int_or_none(source.get('height')),
})
return {
'id': episode_id,
'title': title,
'formats': formats,
'thumbnails': thumbnails,
'description': strip_or_none(episode.get('description')),
'duration': float_or_none(try_get(
episode, lambda x: x['duration']['totalMilliseconds']), 1000),
'release_date': unified_strdate(try_get(
episode, lambda x: x['releaseDate']['isoString'])),
'series': series,
}
class SpotifyIE(SpotifyBaseIE):
IE_NAME = 'spotify'
_VALID_URL = SpotifyBaseIE._VALID_URL_TEMPL % 'episode'
_TEST = {
'url': 'https://open.spotify.com/episode/4Z7GAJ50bgctf6uclHlWKo',
'md5': '74010a1e3fa4d9e1ab3aa7ad14e42d3b',
'info_dict': {
'id': '4Z7GAJ50bgctf6uclHlWKo',
'ext': 'mp3',
'title': 'From the archive: Why time management is ruining our lives',
'description': 'md5:b120d9c4ff4135b42aa9b6d9cde86935',
'duration': 2083.605,
'release_date': '20201217',
'series': "The Guardian's Audio Long Reads",
}
}
def _real_extract(self, url):
episode_id = self._match_id(url)
episode = self._call_api('Episode', episode_id, {
'uri': 'spotify:episode:' + episode_id
})['episode']
return self._extract_episode(
episode, try_get(episode, lambda x: x['podcast']['name']))
class SpotifyShowIE(SpotifyBaseIE):
IE_NAME = 'spotify:show'
_VALID_URL = SpotifyBaseIE._VALID_URL_TEMPL % 'show'
_TEST = {
'url': 'https://open.spotify.com/show/4PM9Ke6l66IRNpottHKV9M',
'info_dict': {
'id': '4PM9Ke6l66IRNpottHKV9M',
'title': 'The Story from the Guardian',
'description': 'The Story podcast is dedicated to our finest audio documentaries, investigations and long form stories',
},
'playlist_mincount': 36,
}
def _real_extract(self, url):
show_id = self._match_id(url)
podcast = self._call_api('ShowEpisodes', show_id, {
'limit': 1000000000,
'offset': 0,
'uri': 'spotify:show:' + show_id,
})['podcast']
podcast_name = podcast.get('name')
entries = []
for item in (try_get(podcast, lambda x: x['episodes']['items']) or []):
episode = item.get('episode')
if not episode:
continue
entries.append(self._extract_episode(episode, podcast_name))
return self.playlist_result(
entries, show_id, podcast_name, podcast.get('description'))
+193
View File
@@ -0,0 +1,193 @@
# coding: utf-8
from __future__ import unicode_literals
import json
from .common import InfoExtractor
from ..utils import (
ExtractorError,
int_or_none,
str_or_none,
try_get,
)
class TrovoBaseIE(InfoExtractor):
_VALID_URL_BASE = r'https?://(?:www\.)?trovo\.live/'
def _extract_streamer_info(self, data):
streamer_info = data.get('streamerInfo') or {}
username = streamer_info.get('userName')
return {
'uploader': streamer_info.get('nickName'),
'uploader_id': str_or_none(streamer_info.get('uid')),
'uploader_url': 'https://trovo.live/' + username if username else None,
}
class TrovoIE(TrovoBaseIE):
_VALID_URL = TrovoBaseIE._VALID_URL_BASE + r'(?!(?:clip|video)/)(?P<id>[^/?&#]+)'
def _real_extract(self, url):
username = self._match_id(url)
live_info = self._download_json(
'https://gql.trovo.live/', username, query={
'query': '''{
getLiveInfo(params: {userName: "%s"}) {
isLive
programInfo {
coverUrl
id
streamInfo {
desc
playUrl
}
title
}
streamerInfo {
nickName
uid
userName
}
}
}''' % username,
})['data']['getLiveInfo']
if live_info.get('isLive') == 0:
raise ExtractorError('%s is offline' % username, expected=True)
program_info = live_info['programInfo']
program_id = program_info['id']
title = self._live_title(program_info['title'])
formats = []
for stream_info in (program_info.get('streamInfo') or []):
play_url = stream_info.get('playUrl')
if not play_url:
continue
format_id = stream_info.get('desc')
formats.append({
'format_id': format_id,
'height': int_or_none(format_id[:-1]) if format_id else None,
'url': play_url,
})
self._sort_formats(formats)
info = {
'id': program_id,
'title': title,
'formats': formats,
'thumbnail': program_info.get('coverUrl'),
'is_live': True,
}
info.update(self._extract_streamer_info(live_info))
return info
class TrovoVodIE(TrovoBaseIE):
_VALID_URL = TrovoBaseIE._VALID_URL_BASE + r'(?:clip|video)/(?P<id>[^/?&#]+)'
_TESTS = [{
'url': 'https://trovo.live/video/ltv-100095501_100095501_1609596043',
'info_dict': {
'id': 'ltv-100095501_100095501_1609596043',
'ext': 'mp4',
'title': 'Spontaner 12 Stunden Stream! - Ok Boomer!',
'uploader': 'Exsl',
'timestamp': 1609640305,
'upload_date': '20210103',
'uploader_id': '100095501',
'duration': 43977,
'view_count': int,
'like_count': int,
'comment_count': int,
'comments': 'mincount:8',
'categories': ['Grand Theft Auto V'],
},
}, {
'url': 'https://trovo.live/clip/lc-5285890810184026005',
'only_matching': True,
}]
def _real_extract(self, url):
vid = self._match_id(url)
resp = self._download_json(
'https://gql.trovo.live/', vid, data=json.dumps([{
'query': '''{
batchGetVodDetailInfo(params: {vids: ["%s"]}) {
VodDetailInfos
}
}''' % vid,
}, {
'query': '''{
getCommentList(params: {appInfo: {postID: "%s"}, pageSize: 1000000000, preview: {}}) {
commentList {
author {
nickName
uid
}
commentID
content
createdAt
parentID
}
}
}''' % vid,
}]).encode(), headers={
'Content-Type': 'application/json',
})
vod_detail_info = resp[0]['data']['batchGetVodDetailInfo']['VodDetailInfos'][vid]
vod_info = vod_detail_info['vodInfo']
title = vod_info['title']
language = vod_info.get('languageName')
formats = []
for play_info in (vod_info.get('playInfos') or []):
play_url = play_info.get('playUrl')
if not play_url:
continue
format_id = play_info.get('desc')
formats.append({
'ext': 'mp4',
'filesize': int_or_none(play_info.get('fileSize')),
'format_id': format_id,
'height': int_or_none(format_id[:-1]) if format_id else None,
'language': language,
'protocol': 'm3u8_native',
'tbr': int_or_none(play_info.get('bitrate')),
'url': play_url,
})
self._sort_formats(formats)
category = vod_info.get('categoryName')
get_count = lambda x: int_or_none(vod_info.get(x + 'Num'))
comment_list = try_get(resp, lambda x: x[1]['data']['getCommentList']['commentList'], list) or []
comments = []
for comment in comment_list:
content = comment.get('content')
if not content:
continue
author = comment.get('author') or {}
parent = comment.get('parentID')
comments.append({
'author': author.get('nickName'),
'author_id': str_or_none(author.get('uid')),
'id': str_or_none(comment.get('commentID')),
'text': content,
'timestamp': int_or_none(comment.get('createdAt')),
'parent': 'root' if parent == 0 else str_or_none(parent),
})
info = {
'id': vid,
'title': title,
'formats': formats,
'thumbnail': vod_info.get('coverUrl'),
'timestamp': int_or_none(vod_info.get('publishTs')),
'duration': int_or_none(vod_info.get('duration')),
'view_count': get_count('watch'),
'like_count': get_count('like'),
'comment_count': get_count('comment'),
'comments': comments,
'categories': [category] if category else None,
}
info.update(self._extract_streamer_info(vod_detail_info))
return info
+111
View File
@@ -0,0 +1,111 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
js_to_json,
try_get,
int_or_none,
str_or_none,
url_or_none,
)
from ..compat import compat_str
class TrovoLiveIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?trovo\.live/video/(?P<id>[\w-]+)'
_TEST = {
'url': 'https://trovo.live/video/ltv-100759829_100759829_1610625308',
'md5': 'ea7b58427910e9af66a462d895201a30',
'info_dict': {
'id': 'ltv-100759829_100759829_1610625308',
'ext': 'ts',
'title': 'GTA RP ASTERIX doa najjaca',
'uploader': 'Peroo42',
'duration': 5872,
'view_count': int,
'like_count': int,
'comment_count': int,
'categories': list,
'is_live': False,
'thumbnail': r're:^https?://.*\.jpg$',
'uploader_id': '100759829',
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
nuxt = self._search_regex(r'\bwindow\.__NUXT__\s*=\s*(.+?);?\s*</script>', webpage, 'nuxt', default='')
mobj = re.search(r'\((?P<arg_names>[^(]+)\)\s*{\s*return\s+(?P<json>{.+})\s*\((?P<args>.+?)\)\s*\)$', nuxt)
vod_details = vod_info = {}
if mobj:
vod_details = self._parse_json(
js_to_json(
self._search_regex(r'VodDetailInfos\s*:({.+?}),\s*_', webpage, 'VodDetailInfos'),
dict(zip(
(i.strip() for i in mobj.group('arg_names').split(',')),
(i.strip() for i in mobj.group('args').split(','))))),
video_id)
vod_info = try_get(vod_details, lambda x: x['json'][video_id]['vodInfo'], dict) or {}
player_info = self._parse_json(
self._search_regex(
r'_playerInfo\s*=\s*({.+?})\s*</script>', webpage, 'player info'),
video_id)
title = (
vod_info.get('title')
or self._html_search_regex(r'<h3>(.+?)</h3>', webpage, 'title', fatal=False)
or self._og_search_title(webpage))
uploader = (
try_get(vod_details, lambda x: x['json'][video_id]['streamerInfo']['userName'], compat_str)
or self._search_regex(r'<div[^>]+userName\s=\s[\'"](.+?)[\'"]', webpage, 'uploader', fatal=False))
format_dicts = vod_info.get('playInfos') or player_info.get('urlArray') or []
def _extract_format_data(format_dict):
res = format_dict.get('desc')
enc = str_or_none(format_dict.get('encodeType'))
if enc:
notes = [enc.replace('VOD_ENCODE_TYPE_', '')]
level = str_or_none(format_dict.get('levelType'))
if level:
notes.append('level %s' % level)
height = int_or_none(res[:-1]) if res else None
bitrate = format_dict.get('bitrate')
fid = res or ('%sk' % str_or_none(bitrate) if bitrate else None) or ' '.join(notes)
return {
'url': format_dict['playUrl'],
'format_id': fid,
'format_note': ' '.join(notes),
'height': height,
'resolution': str_or_none(res),
'tbr': int_or_none(bitrate),
'filesize': int_or_none(format_dict.get('fileSize')),
'vcodec': 'avc3',
'acodec': 'aac',
'ext': 'ts'
}
formats = [_extract_format_data(f) for f in format_dicts]
self._sort_formats(formats)
return {
'id': video_id,
'title': title,
'uploader': uploader,
'duration': int_or_none(vod_info.get('duration')),
'formats': formats,
'view_count': int_or_none(vod_info.get('watchNum')),
'like_count': int_or_none(vod_info.get('likeNum')),
'comment_count': int_or_none(vod_info.get('commentNum')),
'categories': [str_or_none(vod_info.get('categoryName'))],
'is_live': try_get(player_info, lambda x: x['isLive'], bool),
'thumbnail': url_or_none(vod_info.get('coverUrl')),
'uploader_id': str_or_none(try_get(vod_details, lambda x: x['json'][video_id]['streamerInfo']['uid'])),
}
+13 -51
View File
@@ -1,12 +1,9 @@
# coding: utf-8 # coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
import re
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import compat_str from ..compat import compat_str
from ..utils import ( from ..utils import (
ExtractorError,
unified_strdate, unified_strdate,
HEADRequest, HEADRequest,
int_or_none, int_or_none,
@@ -46,15 +43,6 @@ class WatIE(InfoExtractor):
}, },
] ]
_FORMATS = (
(200, 416, 234),
(400, 480, 270),
(600, 640, 360),
(1200, 640, 360),
(1800, 960, 540),
(2500, 1280, 720),
)
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
video_id = video_id if video_id.isdigit() and len(video_id) > 6 else compat_str(int(video_id, 36)) video_id = video_id if video_id.isdigit() and len(video_id) > 6 else compat_str(int(video_id, 36))
@@ -97,46 +85,20 @@ class WatIE(InfoExtractor):
return red_url return red_url
return None return None
def remove_bitrate_limit(manifest_url):
return re.sub(r'(?:max|min)_bitrate=\d+&?', '', manifest_url)
formats = [] formats = []
try: manifest_urls = self._download_json(
alt_urls = lambda manifest_url: [re.sub(r'(?:wdv|ssm)?\.ism/', repl + '.ism/', manifest_url) for repl in ('', 'ssm')] 'http://www.wat.tv/get/webhtml/' + video_id, video_id)
manifest_urls = self._download_json( m3u8_url = manifest_urls.get('hls')
'http://www.wat.tv/get/webhtml/' + video_id, video_id) if m3u8_url:
m3u8_url = manifest_urls.get('hls') formats.extend(self._extract_m3u8_formats(
if m3u8_url: m3u8_url, video_id, 'mp4',
m3u8_url = remove_bitrate_limit(m3u8_url) 'm3u8_native', m3u8_id='hls', fatal=False))
for m3u8_alt_url in alt_urls(m3u8_url): mpd_url = manifest_urls.get('mpd')
formats.extend(self._extract_m3u8_formats( if mpd_url:
m3u8_alt_url, video_id, 'mp4', formats.extend(self._extract_mpd_formats(
'm3u8_native', m3u8_id='hls', fatal=False)) mpd_url.replace('://das-q1.tf1.fr/', '://das-q1-ssl.tf1.fr/'),
formats.extend(self._extract_f4m_formats( video_id, mpd_id='dash', fatal=False))
m3u8_alt_url.replace('ios', 'web').replace('.m3u8', '.f4m'), self._sort_formats(formats)
video_id, f4m_id='hds', fatal=False))
mpd_url = manifest_urls.get('mpd')
if mpd_url:
mpd_url = remove_bitrate_limit(mpd_url)
for mpd_alt_url in alt_urls(mpd_url):
formats.extend(self._extract_mpd_formats(
mpd_alt_url, video_id, mpd_id='dash', fatal=False))
self._sort_formats(formats)
except ExtractorError:
abr = 64
for vbr, width, height in self._FORMATS:
tbr = vbr + abr
format_id = 'http-%s' % tbr
fmt_url = 'http://dnl.adv.tf1.fr/2/USP-0x0/%s/%s/%s/ssm/%s-%s-64k.mp4' % (video_id[-4:-2], video_id[-2:], video_id, video_id, vbr)
if self._is_valid_url(fmt_url, video_id, format_id):
formats.append({
'format_id': format_id,
'url': fmt_url,
'vbr': vbr,
'abr': abr,
'width': width,
'height': height,
})
date_diffusion = first_chapter.get('date_diffusion') or video_data.get('configv4', {}).get('estatS4') date_diffusion = first_chapter.get('date_diffusion') or video_data.get('configv4', {}).get('estatS4')
upload_date = unified_strdate(date_diffusion) if date_diffusion else None upload_date = unified_strdate(date_diffusion) if date_diffusion else None
+40 -40
View File
@@ -177,46 +177,9 @@ class YahooIE(InfoExtractor):
'only_matching': True, 'only_matching': True,
}] }]
def _real_extract(self, url): def _extract_yahoo_video(self, video_id, country):
url, country, display_id = re.match(self._VALID_URL, url).groups()
if not country:
country = 'us'
else:
country = country.split('-')[0]
api_base = 'https://%s.yahoo.com/_td/api/resource/' % country
for i, uuid in enumerate(['url=' + url, 'ymedia-alias=' + display_id]):
content = self._download_json(
api_base + 'content;getDetailView=true;uuids=["%s"]' % uuid,
display_id, 'Downloading content JSON metadata', fatal=i == 1)
if content:
item = content['items'][0]
break
if item.get('type') != 'video':
entries = []
cover = item.get('cover') or {}
if cover.get('type') == 'yvideo':
cover_url = cover.get('url')
if cover_url:
entries.append(self.url_result(
cover_url, 'Yahoo', cover.get('uuid')))
for e in item.get('body', []):
if e.get('type') == 'videoIframe':
iframe_url = e.get('url')
if not iframe_url:
continue
entries.append(self.url_result(iframe_url))
return self.playlist_result(
entries, item.get('uuid'),
item.get('title'), item.get('summary'))
video_id = item['uuid']
video = self._download_json( video = self._download_json(
api_base + 'VideoService.videos;view=full;video_ids=["%s"]' % video_id, 'https://%s.yahoo.com/_td/api/resource/VideoService.videos;view=full;video_ids=["%s"]' % (country, video_id),
video_id, 'Downloading video JSON metadata')[0] video_id, 'Downloading video JSON metadata')[0]
title = video['title'] title = video['title']
@@ -298,7 +261,6 @@ class YahooIE(InfoExtractor):
'id': video_id, 'id': video_id,
'title': self._live_title(title) if is_live else title, 'title': self._live_title(title) if is_live else title,
'formats': formats, 'formats': formats,
'display_id': display_id,
'thumbnails': thumbnails, 'thumbnails': thumbnails,
'description': clean_html(video.get('description')), 'description': clean_html(video.get('description')),
'timestamp': parse_iso8601(video.get('publish_time')), 'timestamp': parse_iso8601(video.get('publish_time')),
@@ -311,6 +273,44 @@ class YahooIE(InfoExtractor):
'episode_number': int_or_none(series_info.get('episode_number')), 'episode_number': int_or_none(series_info.get('episode_number')),
} }
def _real_extract(self, url):
url, country, display_id = re.match(self._VALID_URL, url).groups()
if not country:
country = 'us'
else:
country = country.split('-')[0]
item = self._download_json(
'https://%s.yahoo.com/caas/content/article' % country, display_id,
'Downloading content JSON metadata', query={
'url': url
})['items'][0]['data']['partnerData']
if item.get('type') != 'video':
entries = []
cover = item.get('cover') or {}
if cover.get('type') == 'yvideo':
cover_url = cover.get('url')
if cover_url:
entries.append(self.url_result(
cover_url, 'Yahoo', cover.get('uuid')))
for e in (item.get('body') or []):
if e.get('type') == 'videoIframe':
iframe_url = e.get('url')
if not iframe_url:
continue
entries.append(self.url_result(iframe_url))
return self.playlist_result(
entries, item.get('uuid'),
item.get('title'), item.get('summary'))
info = self._extract_yahoo_video(item['uuid'], country)
info['display_id'] = display_id
return info
class YahooSearchIE(SearchInfoExtractor): class YahooSearchIE(SearchInfoExtractor):
IE_DESC = 'Yahoo screen search' IE_DESC = 'Yahoo screen search'
+171 -104
View File
@@ -14,6 +14,8 @@ from .compat import (
compat_shlex_split, compat_shlex_split,
) )
from .utils import ( from .utils import (
expand_path,
get_executable_path,
preferredencoding, preferredencoding,
write_string, write_string,
) )
@@ -62,7 +64,7 @@ def parseOpts(overrideArguments=None):
userConfFile = os.path.join(xdg_config_home, '%s.conf' % package_name) userConfFile = os.path.join(xdg_config_home, '%s.conf' % package_name)
userConf = _readOptions(userConfFile, default=None) userConf = _readOptions(userConfFile, default=None)
if userConf is not None: if userConf is not None:
return userConf return userConf, userConfFile
# appdata # appdata
appdata_dir = compat_getenv('appdata') appdata_dir = compat_getenv('appdata')
@@ -70,19 +72,21 @@ def parseOpts(overrideArguments=None):
userConfFile = os.path.join(appdata_dir, package_name, 'config') userConfFile = os.path.join(appdata_dir, package_name, 'config')
userConf = _readOptions(userConfFile, default=None) userConf = _readOptions(userConfFile, default=None)
if userConf is None: if userConf is None:
userConf = _readOptions('%s.txt' % userConfFile, default=None) userConfFile += '.txt'
userConf = _readOptions(userConfFile, default=None)
if userConf is not None: if userConf is not None:
return userConf return userConf, userConfFile
# home # home
userConfFile = os.path.join(compat_expanduser('~'), '%s.conf' % package_name) userConfFile = os.path.join(compat_expanduser('~'), '%s.conf' % package_name)
userConf = _readOptions(userConfFile, default=None) userConf = _readOptions(userConfFile, default=None)
if userConf is None: if userConf is None:
userConf = _readOptions('%s.txt' % userConfFile, default=None) userConfFile += '.txt'
userConf = _readOptions(userConfFile, default=None)
if userConf is not None: if userConf is not None:
return userConf return userConf, userConfFile
return default return default, None
def _format_option_string(option): def _format_option_string(option):
''' ('-o', '--option') -> -o, --format METAVAR''' ''' ('-o', '--option') -> -o, --format METAVAR'''
@@ -104,6 +108,20 @@ def parseOpts(overrideArguments=None):
def _comma_separated_values_options_callback(option, opt_str, value, parser): def _comma_separated_values_options_callback(option, opt_str, value, parser):
setattr(parser.values, option.dest, value.split(',')) setattr(parser.values, option.dest, value.split(','))
def _dict_from_multiple_values_options_callback(
option, opt_str, value, parser, allowed_keys=r'[\w-]+', delimiter=':', default_key=None, process=None):
out_dict = getattr(parser.values, option.dest)
mobj = re.match(r'(?i)(?P<key>%s)%s(?P<val>.*)$' % (allowed_keys, delimiter), value)
if mobj is not None:
key, val = mobj.group('key').lower(), mobj.group('val')
elif default_key is not None:
key, val = default_key, value
else:
raise optparse.OptionValueError(
'wrong %s formatting; it should be %s, not "%s"' % (opt_str, option.metavar, value))
out_dict[key] = process(val) if callable(process) else val
# No need to wrap help messages if we're on a wide console # No need to wrap help messages if we're on a wide console
columns = compat_get_terminal_size().columns columns = compat_get_terminal_size().columns
max_width = columns if columns else 80 max_width = columns if columns else 80
@@ -137,11 +155,11 @@ def parseOpts(overrideArguments=None):
general.add_option( general.add_option(
'-i', '--ignore-errors', '--no-abort-on-error', '-i', '--ignore-errors', '--no-abort-on-error',
action='store_true', dest='ignoreerrors', default=True, action='store_true', dest='ignoreerrors', default=True,
help='Continue on download errors, for example to skip unavailable videos in a playlist (default)') help='Continue on download errors, for example to skip unavailable videos in a playlist (default) (Alias: --no-abort-on-error)')
general.add_option( general.add_option(
'--abort-on-error', '--no-ignore-errors', '--abort-on-error', '--no-ignore-errors',
action='store_false', dest='ignoreerrors', action='store_false', dest='ignoreerrors',
help='Abort downloading of further videos if an error occurs') help='Abort downloading of further videos if an error occurs (Alias: --no-ignore-errors)')
general.add_option( general.add_option(
'--dump-user-agent', '--dump-user-agent',
action='store_true', dest='dump_user_agent', default=False, action='store_true', dest='dump_user_agent', default=False,
@@ -161,7 +179,7 @@ def parseOpts(overrideArguments=None):
general.add_option( general.add_option(
'--default-search', '--default-search',
dest='default_search', metavar='PREFIX', dest='default_search', metavar='PREFIX',
help='Use this prefix for unqualified URLs. For example "gvsearch2:" downloads two videos from google videos for youtube-dl "large apple". Use the value "auto" to let youtube-dl guess ("auto_warning" to emit a warning when guessing). "error" just throws an error. The default value "fixup_error" repairs broken URLs, but emits an error if this is not possible instead of searching.') help='Use this prefix for unqualified URLs. For example "gvsearch2:" downloads two videos from google videos for youtube-dl "large apple". Use the value "auto" to let youtube-dl guess ("auto_warning" to emit a warning when guessing). "error" just throws an error. The default value "fixup_error" repairs broken URLs, but emits an error if this is not possible instead of searching')
general.add_option( general.add_option(
'--ignore-config', '--no-config', '--ignore-config', '--no-config',
action='store_true', action='store_true',
@@ -169,15 +187,15 @@ def parseOpts(overrideArguments=None):
'Disable loading any configuration files except the one provided by --config-location. ' 'Disable loading any configuration files except the one provided by --config-location. '
'When given inside a configuration file, no further configuration files are loaded. ' 'When given inside a configuration file, no further configuration files are loaded. '
'Additionally, (for backward compatibility) if this option is found inside the ' 'Additionally, (for backward compatibility) if this option is found inside the '
'system configuration file, the user configuration is not loaded.')) 'system configuration file, the user configuration is not loaded'))
general.add_option( general.add_option(
'--config-location', '--config-location',
dest='config_location', metavar='PATH', dest='config_location', metavar='PATH',
help='Location of the configuration file; either the path to the config or its containing directory.') help='Location of the main configuration file; either the path to the config or its containing directory')
general.add_option( general.add_option(
'--flat-playlist', '--flat-playlist',
action='store_const', dest='extract_flat', const='in_playlist', default=False, action='store_const', dest='extract_flat', const='in_playlist', default=False,
help='Do not extract the videos of a playlist, only list them.') help='Do not extract the videos of a playlist, only list them')
general.add_option( general.add_option(
'--flat-videos', '--flat-videos',
action='store_true', dest='extract_flat', action='store_true', dest='extract_flat',
@@ -195,7 +213,7 @@ def parseOpts(overrideArguments=None):
action='store_false', dest='mark_watched', default=False, action='store_false', dest='mark_watched', default=False,
help='Do not mark videos watched') help='Do not mark videos watched')
general.add_option( general.add_option(
'--no-color', '--no-colors', '--no-colors',
action='store_true', dest='no_color', action='store_true', dest='no_color',
default=False, default=False,
help='Do not emit color codes in output') help='Do not emit color codes in output')
@@ -235,7 +253,7 @@ def parseOpts(overrideArguments=None):
dest='geo_verification_proxy', default=None, metavar='URL', dest='geo_verification_proxy', default=None, metavar='URL',
help=( help=(
'Use this proxy to verify the IP address for some geo-restricted sites. ' 'Use this proxy to verify the IP address for some geo-restricted sites. '
'The default proxy specified by --proxy (or none, if the option is not present) is used for the actual downloading.')) 'The default proxy specified by --proxy (or none, if the option is not present) is used for the actual downloading'))
geo.add_option( geo.add_option(
'--cn-verification-proxy', '--cn-verification-proxy',
dest='cn_verification_proxy', default=None, metavar='URL', dest='cn_verification_proxy', default=None, metavar='URL',
@@ -269,7 +287,7 @@ def parseOpts(overrideArguments=None):
selection.add_option( selection.add_option(
'--playlist-items', '--playlist-items',
dest='playlist_items', metavar='ITEM_SPEC', default=None, dest='playlist_items', metavar='ITEM_SPEC', default=None,
help='Playlist video items to download. Specify indices of the videos in the playlist separated by commas like: "--playlist-items 1,2,5,8" if you want to download videos indexed 1, 2, 5, 8 in the playlist. You can specify range: "--playlist-items 1-3,7,10-13", it will download the videos at index 1, 2, 3, 7, 10, 11, 12 and 13.') help='Playlist video items to download. Specify indices of the videos in the playlist separated by commas like: "--playlist-items 1,2,5,8" if you want to download videos indexed 1, 2, 5, 8 in the playlist. You can specify range: "--playlist-items 1-3,7,10-13", it will download the videos at index 1, 2, 3, 7, 10, 11, 12 and 13')
selection.add_option( selection.add_option(
'--match-title', '--match-title',
dest='matchtitle', metavar='REGEX', dest='matchtitle', metavar='REGEX',
@@ -294,8 +312,8 @@ def parseOpts(overrideArguments=None):
'--date', '--date',
metavar='DATE', dest='date', default=None, metavar='DATE', dest='date', default=None,
help=( help=(
'Download only videos uploaded in this date.' 'Download only videos uploaded in this date. '
'The date can be "YYYYMMDD" or in the format' 'The date can be "YYYYMMDD" or in the format '
'"(now|today)[+-][0-9](day|week|month|year)(s)?"')) '"(now|today)[+-][0-9](day|week|month|year)(s)?"'))
selection.add_option( selection.add_option(
'--datebefore', '--datebefore',
@@ -322,10 +340,10 @@ def parseOpts(overrideArguments=None):
metavar='FILTER', dest='match_filter', default=None, metavar='FILTER', dest='match_filter', default=None,
help=( help=(
'Generic video filter. ' 'Generic video filter. '
'Specify any key (see the "OUTPUT TEMPLATE" for a list of available keys) to ' 'Specify any key (see "OUTPUT TEMPLATE" for a list of available keys) to '
'match if the key is present, ' 'match if the key is present, '
'!key to check if the key is not present, ' '!key to check if the key is not present, '
'key > NUMBER (like "comment_count > 12", also works with ' 'key>NUMBER (like "comment_count > 12", also works with '
'>=, <, <=, !=, =) to compare against a number, ' '>=, <, <=, !=, =) to compare against a number, '
'key = \'LITERAL\' (like "uploader = \'Mike Smith\'", also works with !=) ' 'key = \'LITERAL\' (like "uploader = \'Mike Smith\'", also works with !=) '
'to match against a string literal ' 'to match against a string literal '
@@ -336,7 +354,7 @@ def parseOpts(overrideArguments=None):
'100 times and disliked less than 50 times (or the dislike ' '100 times and disliked less than 50 times (or the dislike '
'functionality is not available at the given service), but who ' 'functionality is not available at the given service), but who '
'also have a description, use --match-filter ' 'also have a description, use --match-filter '
'"like_count > 100 & dislike_count <? 50 & description" .')) '"like_count > 100 & dislike_count <? 50 & description"'))
selection.add_option( selection.add_option(
'--no-match-filter', '--no-match-filter',
metavar='FILTER', dest='match_filter', action='store_const', const=None, metavar='FILTER', dest='match_filter', action='store_const', const=None,
@@ -344,11 +362,11 @@ def parseOpts(overrideArguments=None):
selection.add_option( selection.add_option(
'--no-playlist', '--no-playlist',
action='store_true', dest='noplaylist', default=False, action='store_true', dest='noplaylist', default=False,
help='Download only the video, if the URL refers to a video and a playlist.') help='Download only the video, if the URL refers to a video and a playlist')
selection.add_option( selection.add_option(
'--yes-playlist', '--yes-playlist',
action='store_false', dest='noplaylist', default=False, action='store_false', dest='noplaylist', default=False,
help='Download the playlist, if the URL refers to a video and a playlist.') help='Download the playlist, if the URL refers to a video and a playlist')
selection.add_option( selection.add_option(
'--age-limit', '--age-limit',
metavar='YEARS', dest='age_limit', default=None, type=int, metavar='YEARS', dest='age_limit', default=None, type=int,
@@ -356,15 +374,15 @@ def parseOpts(overrideArguments=None):
selection.add_option( selection.add_option(
'--download-archive', metavar='FILE', '--download-archive', metavar='FILE',
dest='download_archive', dest='download_archive',
help='Download only videos not listed in the archive file. Record the IDs of all downloaded videos in it.') help='Download only videos not listed in the archive file. Record the IDs of all downloaded videos in it')
selection.add_option( selection.add_option(
'--break-on-existing', '--break-on-existing',
action='store_true', dest='break_on_existing', default=False, action='store_true', dest='break_on_existing', default=False,
help="Stop the download process when encountering a file that's in the archive.") help='Stop the download process when encountering a file that is in the archive')
selection.add_option( selection.add_option(
'--break-on-reject', '--break-on-reject',
action='store_true', dest='break_on_reject', default=False, action='store_true', dest='break_on_reject', default=False,
help="Stop the download process when encountering a file that has been filtered out.") help='Stop the download process when encountering a file that has been filtered out')
selection.add_option( selection.add_option(
'--no-download-archive', '--no-download-archive',
dest='download_archive', action="store_const", const=None, dest='download_archive', action="store_const", const=None,
@@ -386,7 +404,7 @@ def parseOpts(overrideArguments=None):
authentication.add_option( authentication.add_option(
'-p', '--password', '-p', '--password',
dest='password', metavar='PASSWORD', dest='password', metavar='PASSWORD',
help='Account password. If this option is left out, youtube-dlc will ask interactively.') help='Account password. If this option is left out, youtube-dlc will ask interactively')
authentication.add_option( authentication.add_option(
'-2', '--twofactor', '-2', '--twofactor',
dest='twofactor', metavar='TWOFACTOR', dest='twofactor', metavar='TWOFACTOR',
@@ -412,7 +430,7 @@ def parseOpts(overrideArguments=None):
adobe_pass.add_option( adobe_pass.add_option(
'--ap-password', '--ap-password',
dest='ap_password', metavar='PASSWORD', dest='ap_password', metavar='PASSWORD',
help='Multiple-system operator account password. If this option is left out, youtube-dlc will ask interactively.') help='Multiple-system operator account password. If this option is left out, youtube-dlc will ask interactively')
adobe_pass.add_option( adobe_pass.add_option(
'--ap-list-mso', '--ap-list-mso',
action='store_true', dest='ap_list_mso', default=False, action='store_true', dest='ap_list_mso', default=False,
@@ -471,27 +489,27 @@ def parseOpts(overrideArguments=None):
video_format.add_option( video_format.add_option(
'--list-formats-as-table', '--list-formats-as-table',
action='store_true', dest='listformats_table', default=True, action='store_true', dest='listformats_table', default=True,
help='Present the output of -F in a more tabular form (default)') help='Present the output of -F in tabular form (default)')
video_format.add_option( video_format.add_option(
'--list-formats-old', '--no-list-formats-as-table', '--list-formats-old', '--no-list-formats-as-table',
action='store_false', dest='listformats_table', action='store_false', dest='listformats_table',
help='Present the output of -F in the old form') help='Present the output of -F in the old form (Alias: --no-list-formats-as-table)')
video_format.add_option( video_format.add_option(
'--youtube-include-dash-manifest', '--no-youtube-skip-dash-manifest', '--youtube-include-dash-manifest', '--no-youtube-skip-dash-manifest',
action='store_true', dest='youtube_include_dash_manifest', default=True, action='store_true', dest='youtube_include_dash_manifest', default=True,
help='Download the DASH manifests and related data on YouTube videos (default)') help='Download the DASH manifests and related data on YouTube videos (default) (Alias: --no-youtube-skip-dash-manifest)')
video_format.add_option( video_format.add_option(
'--youtube-skip-dash-manifest', '--no-youtube-include-dash-manifest', '--youtube-skip-dash-manifest', '--no-youtube-include-dash-manifest',
action='store_false', dest='youtube_include_dash_manifest', action='store_false', dest='youtube_include_dash_manifest',
help='Do not download the DASH manifests and related data on YouTube videos') help='Do not download the DASH manifests and related data on YouTube videos (Alias: --no-youtube-include-dash-manifest)')
video_format.add_option( video_format.add_option(
'--youtube-include-hls-manifest', '--no-youtube-skip-hls-manifest', '--youtube-include-hls-manifest', '--no-youtube-skip-hls-manifest',
action='store_true', dest='youtube_include_hls_manifest', default=True, action='store_true', dest='youtube_include_hls_manifest', default=True,
help='Download the HLS manifests and related data on YouTube videos (default)') help='Download the HLS manifests and related data on YouTube videos (default) (Alias: --no-youtube-skip-hls-manifest)')
video_format.add_option( video_format.add_option(
'--youtube-skip-hls-manifest', '--no-youtube-include-hls-manifest', '--youtube-skip-hls-manifest', '--no-youtube-include-hls-manifest',
action='store_false', dest='youtube_include_hls_manifest', action='store_false', dest='youtube_include_hls_manifest',
help='Do not download the HLS manifests and related data on YouTube videos') help='Do not download the HLS manifests and related data on YouTube videos (Alias: --no-youtube-include-hls-manifest)')
video_format.add_option( video_format.add_option(
'--merge-output-format', '--merge-output-format',
action='store', dest='merge_output_format', metavar='FORMAT', default=None, action='store', dest='merge_output_format', metavar='FORMAT', default=None,
@@ -543,7 +561,7 @@ def parseOpts(overrideArguments=None):
downloader.add_option( downloader.add_option(
'-R', '--retries', '-R', '--retries',
dest='retries', metavar='RETRIES', default=10, dest='retries', metavar='RETRIES', default=10,
help='Number of retries (default is %default), or "infinite".') help='Number of retries (default is %default), or "infinite"')
downloader.add_option( downloader.add_option(
'--fragment-retries', '--fragment-retries',
dest='fragment_retries', metavar='RETRIES', default=10, dest='fragment_retries', metavar='RETRIES', default=10,
@@ -551,11 +569,11 @@ def parseOpts(overrideArguments=None):
downloader.add_option( downloader.add_option(
'--skip-unavailable-fragments', '--no-abort-on-unavailable-fragment', '--skip-unavailable-fragments', '--no-abort-on-unavailable-fragment',
action='store_true', dest='skip_unavailable_fragments', default=True, action='store_true', dest='skip_unavailable_fragments', default=True,
help='Skip unavailable fragments for DASH, hlsnative and ISM (default)') help='Skip unavailable fragments for DASH, hlsnative and ISM (default) (Alias: --no-abort-on-unavailable-fragment)')
downloader.add_option( downloader.add_option(
'--abort-on-unavailable-fragment', '--no-skip-unavailable-fragments', '--abort-on-unavailable-fragment', '--no-skip-unavailable-fragments',
action='store_false', dest='skip_unavailable_fragments', action='store_false', dest='skip_unavailable_fragments',
help='Abort downloading when some fragment is unavailable') help='Abort downloading if a fragment is unavailable (Alias: --no-skip-unavailable-fragments)')
downloader.add_option( downloader.add_option(
'--keep-fragments', '--keep-fragments',
action='store_true', dest='keep_fragments', default=False, action='store_true', dest='keep_fragments', default=False,
@@ -618,14 +636,21 @@ def parseOpts(overrideArguments=None):
'video while downloading (some players may not be able to play it)')) 'video while downloading (some players may not be able to play it)'))
downloader.add_option( downloader.add_option(
'--external-downloader', '--external-downloader',
dest='external_downloader', metavar='COMMAND', dest='external_downloader', metavar='NAME',
help=( help=(
'Use the specified external downloader. ' 'Use the specified external downloader. '
'Currently supports %s' % ','.join(list_external_downloaders()))) 'Currently supports %s' % ', '.join(list_external_downloaders())))
downloader.add_option( downloader.add_option(
'--external-downloader-args', '--downloader-args', '--external-downloader-args',
dest='external_downloader_args', metavar='ARGS', metavar='NAME:ARGS', dest='external_downloader_args', default={}, type='str',
help='Give these arguments to the external downloader') action='callback', callback=_dict_from_multiple_values_options_callback,
callback_kwargs={
'allowed_keys': '|'.join(list_external_downloaders()),
'default_key': 'default', 'process': compat_shlex_split},
help=(
'Give these arguments to the external downloader. '
'Specify the downloader name and the arguments separated by a colon ":". '
'You can use this option multiple times (Alias: --external-downloader-args)'))
workarounds = optparse.OptionGroup(parser, 'Workarounds') workarounds = optparse.OptionGroup(parser, 'Workarounds')
workarounds.add_option( workarounds.add_option(
@@ -651,8 +676,9 @@ def parseOpts(overrideArguments=None):
) )
workarounds.add_option( workarounds.add_option(
'--add-header', '--add-header',
metavar='FIELD:VALUE', dest='headers', action='append', metavar='FIELD:VALUE', dest='headers', default={}, type='str',
help='Specify a custom HTTP header and its value, separated by a colon \':\'. You can use this option multiple times', action='callback', callback=_dict_from_multiple_values_options_callback,
help='Specify a custom HTTP header and its value, separated by a colon ":". You can use this option multiple times',
) )
workarounds.add_option( workarounds.add_option(
'--bidi-workaround', '--bidi-workaround',
@@ -665,14 +691,14 @@ def parseOpts(overrideArguments=None):
'Number of seconds to sleep before each download when used alone ' 'Number of seconds to sleep before each download when used alone '
'or a lower bound of a range for randomized sleep before each download ' 'or a lower bound of a range for randomized sleep before each download '
'(minimum possible number of seconds to sleep) when used along with ' '(minimum possible number of seconds to sleep) when used along with '
'--max-sleep-interval.')) '--max-sleep-interval'))
workarounds.add_option( workarounds.add_option(
'--max-sleep-interval', metavar='SECONDS', '--max-sleep-interval', metavar='SECONDS',
dest='max_sleep_interval', type=float, dest='max_sleep_interval', type=float,
help=( help=(
'Upper bound of a range for randomized sleep before each download ' 'Upper bound of a range for randomized sleep before each download '
'(maximum possible number of seconds to sleep). Must only be used ' '(maximum possible number of seconds to sleep). Must only be used '
'along with --min-sleep-interval.')) 'along with --min-sleep-interval'))
workarounds.add_option( workarounds.add_option(
'--sleep-subtitles', metavar='SECONDS', '--sleep-subtitles', metavar='SECONDS',
dest='sleep_interval_subtitles', default=0, type=int, dest='sleep_interval_subtitles', default=0, type=int,
@@ -730,23 +756,23 @@ def parseOpts(overrideArguments=None):
verbosity.add_option( verbosity.add_option(
'-j', '--dump-json', '-j', '--dump-json',
action='store_true', dest='dumpjson', default=False, action='store_true', dest='dumpjson', default=False,
help='Simulate, quiet but print JSON information. See the "OUTPUT TEMPLATE" for a description of available keys.') help='Simulate, quiet but print JSON information. See "OUTPUT TEMPLATE" for a description of available keys')
verbosity.add_option( verbosity.add_option(
'-J', '--dump-single-json', '-J', '--dump-single-json',
action='store_true', dest='dump_single_json', default=False, action='store_true', dest='dump_single_json', default=False,
help=( help=(
'Simulate, quiet but print JSON information for each command-line argument. ' 'Simulate, quiet but print JSON information for each command-line argument. '
'If the URL refers to a playlist, dump the whole playlist information in a single line.')) 'If the URL refers to a playlist, dump the whole playlist information in a single line'))
verbosity.add_option( verbosity.add_option(
'--print-json', '--print-json',
action='store_true', dest='print_json', default=False, action='store_true', dest='print_json', default=False,
help='Be quiet and print the video information as JSON (video is still being downloaded).') help='Be quiet and print the video information as JSON (video is still being downloaded)')
verbosity.add_option( verbosity.add_option(
'--force-write-archive', '--force-write-download-archive', '--force-download-archive', '--force-write-archive', '--force-write-download-archive', '--force-download-archive',
action='store_true', dest='force_write_download_archive', default=False, action='store_true', dest='force_write_download_archive', default=False,
help=( help=(
'Force download archive entries to be written as far as no errors occur,' 'Force download archive entries to be written as far as no errors occur,'
'even if -s or another simulation switch is used.')) 'even if -s or another simulation switch is used (Alias: --force-download-archive)'))
verbosity.add_option( verbosity.add_option(
'--newline', '--newline',
action='store_true', dest='progress_with_newline', default=False, action='store_true', dest='progress_with_newline', default=False,
@@ -793,14 +819,33 @@ def parseOpts(overrideArguments=None):
'-a', '--batch-file', '-a', '--batch-file',
dest='batchfile', metavar='FILE', dest='batchfile', metavar='FILE',
help="File containing URLs to download ('-' for stdin), one URL per line. " help="File containing URLs to download ('-' for stdin), one URL per line. "
"Lines starting with '#', ';' or ']' are considered as comments and ignored.") "Lines starting with '#', ';' or ']' are considered as comments and ignored")
filesystem.add_option( filesystem.add_option(
'--id', default=False, '--id', default=False,
action='store_true', dest='useid', help=optparse.SUPPRESS_HELP) action='store_true', dest='useid', help=optparse.SUPPRESS_HELP)
filesystem.add_option(
'-P', '--paths',
metavar='TYPE:PATH', dest='paths', default={}, type='str',
action='callback', callback=_dict_from_multiple_values_options_callback,
callback_kwargs={
'allowed_keys': 'home|temp|config|description|annotation|subtitle|infojson|thumbnail',
'process': lambda x: x.strip()},
help=(
'The paths where the files should be downloaded. '
'Specify the type of file and the path separated by a colon ":" '
'(supported: description|annotation|subtitle|infojson|thumbnail). '
'Additionally, you can also provide "home" and "temp" paths. '
'All intermediary files are first downloaded to the temp path and '
'then the final files are moved over to the home path after download is finished. '
'Note that this option is ignored if --output is an absolute path'))
filesystem.add_option( filesystem.add_option(
'-o', '--output', '-o', '--output',
dest='outtmpl', metavar='TEMPLATE', dest='outtmpl', metavar='TEMPLATE',
help='Output filename template, see the "OUTPUT TEMPLATE" for details') help='Output filename template, see "OUTPUT TEMPLATE" for details')
filesystem.add_option(
'--output-na-placeholder',
dest='outtmpl_na_placeholder', metavar='TEXT', default='NA',
help=('Placeholder value for unavailable meta fields in output filename template (default: "%default")'))
filesystem.add_option( filesystem.add_option(
'--autonumber-size', '--autonumber-size',
dest='autonumber_size', metavar='NUMBER', type=int, dest='autonumber_size', metavar='NUMBER', type=int,
@@ -903,7 +948,7 @@ def parseOpts(overrideArguments=None):
help='Do not read/dump cookies (default)') help='Do not read/dump cookies (default)')
filesystem.add_option( filesystem.add_option(
'--cache-dir', dest='cachedir', default=None, metavar='DIR', '--cache-dir', dest='cachedir', default=None, metavar='DIR',
help='Location in the filesystem where youtube-dl can store some downloaded information permanently. By default $XDG_CACHE_HOME/youtube-dl or ~/.cache/youtube-dl . At the moment, only YouTube player files (for videos with obfuscated signatures) are cached, but that may change.') help='Location in the filesystem where youtube-dl can store some downloaded information permanently. By default $XDG_CACHE_HOME/youtube-dl or ~/.cache/youtube-dl . At the moment, only YouTube player files (for videos with obfuscated signatures) are cached, but that may change')
filesystem.add_option( filesystem.add_option(
'--no-cache-dir', action='store_false', dest='cachedir', '--no-cache-dir', action='store_false', dest='cachedir',
help='Disable filesystem caching') help='Disable filesystem caching')
@@ -938,25 +983,25 @@ def parseOpts(overrideArguments=None):
link.add_option( link.add_option(
'--write-link', '--write-link',
action='store_true', dest='writelink', default=False, action='store_true', dest='writelink', default=False,
help='Write an internet shortcut file, depending on the current platform (.url/.webloc/.desktop). The URL may be cached by the OS.') help='Write an internet shortcut file, depending on the current platform (.url, .webloc or .desktop). The URL may be cached by the OS')
link.add_option( link.add_option(
'--write-url-link', '--write-url-link',
action='store_true', dest='writeurllink', default=False, action='store_true', dest='writeurllink', default=False,
help='Write a Windows internet shortcut file (.url). Note that the OS caches the URL based on the file path.') help='Write a .url Windows internet shortcut. The OS caches the URL based on the file path')
link.add_option( link.add_option(
'--write-webloc-link', '--write-webloc-link',
action='store_true', dest='writewebloclink', default=False, action='store_true', dest='writewebloclink', default=False,
help='Write a macOS internet shortcut file (.webloc)') help='Write a .webloc macOS internet shortcut')
link.add_option( link.add_option(
'--write-desktop-link', '--write-desktop-link',
action='store_true', dest='writedesktoplink', default=False, action='store_true', dest='writedesktoplink', default=False,
help='Write a Linux internet shortcut file (.desktop)') help='Write a .desktop Linux internet shortcut')
postproc = optparse.OptionGroup(parser, 'Post-Processing Options') postproc = optparse.OptionGroup(parser, 'Post-Processing Options')
postproc.add_option( postproc.add_option(
'-x', '--extract-audio', '-x', '--extract-audio',
action='store_true', dest='extractaudio', default=False, action='store_true', dest='extractaudio', default=False,
help='Convert video files to audio-only files (requires ffmpeg or avconv and ffprobe or avprobe)') help='Convert video files to audio-only files (requires ffmpeg/avconv and ffprobe/avprobe)')
postproc.add_option( postproc.add_option(
'--audio-format', metavar='FORMAT', dest='audioformat', default='best', '--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') help='Specify audio format: "best", "aac", "flac", "mp3", "m4a", "opus", "vorbis", or "wav"; "%default" by default; No effect without -x')
@@ -975,15 +1020,21 @@ def parseOpts(overrideArguments=None):
metavar='FORMAT', dest='recodevideo', default=None, 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 (currently supported: mp4|flv|ogg|webm|mkv|avi)')
postproc.add_option( postproc.add_option(
'--postprocessor-args', metavar='NAME:ARGS', '--postprocessor-args', '--ppa',
dest='postprocessor_args', action='append', metavar='NAME:ARGS', dest='postprocessor_args', default={}, type='str',
action='callback', callback=_dict_from_multiple_values_options_callback,
callback_kwargs={'default_key': 'default-compat', 'allowed_keys': r'\w+(?:\+\w+)?', 'process': compat_shlex_split},
help=( help=(
'Give these arguments to the postprocessors. ' 'Give these arguments to the postprocessors. '
"Specify the postprocessor name and the arguments separated by a colon ':' " 'Specify the postprocessor/executable name and the arguments separated by a colon ":" '
'to give the argument to only the specified postprocessor. Supported names are ' 'to give the argument to the specified postprocessor/executable. Supported postprocessors are: '
'ExtractAudio, VideoRemuxer, VideoConvertor, EmbedSubtitle, Metadata, Merger, FixupStretched, ' 'SponSkrub, ExtractAudio, VideoRemuxer, VideoConvertor, EmbedSubtitle, Metadata, Merger, '
'FixupM4a, FixupM3u8, SubtitlesConvertor, EmbedThumbnail, XAttrMetadata, SponSkrub and Default. ' 'FixupStretched, FixupM4a, FixupM3u8, SubtitlesConvertor and EmbedThumbnail. '
'You can use this option multiple times to give different arguments to different postprocessors')) '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)'))
postproc.add_option( postproc.add_option(
'-k', '--keep-video', '-k', '--keep-video',
action='store_true', dest='keepvideo', default=False, action='store_true', dest='keepvideo', default=False,
@@ -1049,15 +1100,15 @@ def parseOpts(overrideArguments=None):
postproc.add_option( postproc.add_option(
'--prefer-avconv', '--no-prefer-ffmpeg', '--prefer-avconv', '--no-prefer-ffmpeg',
action='store_false', dest='prefer_ffmpeg', action='store_false', dest='prefer_ffmpeg',
help='Prefer avconv over ffmpeg for running the postprocessors') help='Prefer avconv over ffmpeg for running the postprocessors (Alias: --no-prefer-ffmpeg)')
postproc.add_option( postproc.add_option(
'--prefer-ffmpeg', '--no-prefer-avconv', '--prefer-ffmpeg', '--no-prefer-avconv',
action='store_true', dest='prefer_ffmpeg', action='store_true', dest='prefer_ffmpeg',
help='Prefer ffmpeg over avconv for running the postprocessors (default)') help='Prefer ffmpeg over avconv for running the postprocessors (default) (Alias: --no-prefer-avconv)')
postproc.add_option( postproc.add_option(
'--ffmpeg-location', '--avconv-location', metavar='PATH', '--ffmpeg-location', '--avconv-location', metavar='PATH',
dest='ffmpeg_location', dest='ffmpeg_location',
help='Location of the ffmpeg/avconv binary; either the path to the binary or its containing directory.') help='Location of the ffmpeg/avconv binary; either the path to the binary or its containing directory (Alias: --avconv-location)')
postproc.add_option( postproc.add_option(
'--exec', '--exec',
metavar='CMD', dest='exec_cmd', metavar='CMD', dest='exec_cmd',
@@ -1067,12 +1118,14 @@ def parseOpts(overrideArguments=None):
metavar='FORMAT', dest='convertsubtitles', default=None, metavar='FORMAT', dest='convertsubtitles', default=None,
help='Convert the subtitles to other format (currently supported: srt|ass|vtt|lrc)') help='Convert the subtitles to other format (currently supported: srt|ass|vtt|lrc)')
sponskrub = optparse.OptionGroup(parser, 'SponSkrub Options (SponsorBlock)') sponskrub = optparse.OptionGroup(parser, 'SponSkrub (SponsorBlock) Options', description=(
'SponSkrub (https://github.com/pukkandan/SponSkrub) is a utility to mark/remove sponsor segments '
'from downloaded YouTube videos using SponsorBlock API (https://sponsor.ajay.app)'))
sponskrub.add_option( sponskrub.add_option(
'--sponskrub', '--sponskrub',
action='store_true', dest='sponskrub', default=None, action='store_true', dest='sponskrub', default=None,
help=( help=(
'Use sponskrub to mark sponsored sections with the data available in SponsorBlock API. ' 'Use sponskrub to mark sponsored sections. '
'This is enabled by default if the sponskrub binary exists (Youtube only)')) 'This is enabled by default if the sponskrub binary exists (Youtube only)'))
sponskrub.add_option( sponskrub.add_option(
'--no-sponskrub', '--no-sponskrub',
@@ -1097,7 +1150,7 @@ def parseOpts(overrideArguments=None):
sponskrub.add_option( sponskrub.add_option(
'--sponskrub-location', metavar='PATH', '--sponskrub-location', metavar='PATH',
dest='sponskrub_path', default='', dest='sponskrub_path', default='',
help='Location of the sponskrub binary; either the path to the binary or its containing directory.') help='Location of the sponskrub binary; either the path to the binary or its containing directory')
sponskrub.add_option( sponskrub.add_option(
'--sponskrub-args', dest='sponskrub_args', metavar='ARGS', '--sponskrub-args', dest='sponskrub_args', metavar='ARGS',
help=optparse.SUPPRESS_HELP) help=optparse.SUPPRESS_HELP)
@@ -1106,11 +1159,11 @@ def parseOpts(overrideArguments=None):
extractor.add_option( extractor.add_option(
'--allow-dynamic-mpd', '--no-ignore-dynamic-mpd', '--allow-dynamic-mpd', '--no-ignore-dynamic-mpd',
action='store_true', dest='dynamic_mpd', default=True, action='store_true', dest='dynamic_mpd', default=True,
help='Process dynamic DASH manifests (default)') help='Process dynamic DASH manifests (default) (Alias: --no-ignore-dynamic-mpd)')
extractor.add_option( extractor.add_option(
'--ignore-dynamic-mpd', '--no-allow-dynamic-mpd', '--ignore-dynamic-mpd', '--no-allow-dynamic-mpd',
action='store_false', dest='dynamic_mpd', action='store_false', dest='dynamic_mpd',
help='Do not process dynamic DASH manifests') help='Do not process dynamic DASH manifests (Alias: --no-allow-dynamic-mpd)')
parser.add_option_group(general) parser.add_option_group(general)
parser.add_option_group(network) parser.add_option_group(network)
@@ -1141,59 +1194,73 @@ def parseOpts(overrideArguments=None):
return conf return conf
configs = { configs = {
'command_line': compat_conf(sys.argv[1:]), 'command-line': compat_conf(sys.argv[1:]),
'custom': [], 'portable': [], 'user': [], 'system': []} 'custom': [], 'home': [], 'portable': [], 'user': [], 'system': []}
opts, args = parser.parse_args(configs['command_line']) paths = {'command-line': False}
opts, args = parser.parse_args(configs['command-line'])
def get_configs(): def get_configs():
if '--config-location' in configs['command_line']: if '--config-location' in configs['command-line']:
location = compat_expanduser(opts.config_location) location = compat_expanduser(opts.config_location)
if os.path.isdir(location): if os.path.isdir(location):
location = os.path.join(location, 'youtube-dlc.conf') location = os.path.join(location, 'youtube-dlc.conf')
if not os.path.exists(location): if not os.path.exists(location):
parser.error('config-location %s does not exist.' % location) parser.error('config-location %s does not exist.' % location)
configs['custom'] = _readOptions(location) configs['custom'] = _readOptions(location, default=None)
if configs['custom'] is None:
if '--ignore-config' in configs['command_line']: configs['custom'] = []
else:
paths['custom'] = location
if '--ignore-config' in configs['command-line']:
return return
if '--ignore-config' in configs['custom']: if '--ignore-config' in configs['custom']:
return return
def get_portable_path(): def read_options(path, user=False):
path = os.path.dirname(sys.argv[0]) func = _readUserConf if user else _readOptions
if os.path.abspath(sys.argv[0]) != os.path.abspath(sys.executable): # Not packaged current_path = os.path.join(path, 'yt-dlp.conf')
path = os.path.join(path, '..') config = func(current_path, default=None)
return os.path.abspath(path) if user:
config, current_path = config
run_path = get_portable_path() if config is None:
configs['portable'] = _readOptions(os.path.join(run_path, 'yt-dlp.conf'), default=None) current_path = os.path.join(path, 'youtube-dlc.conf')
if configs['portable'] is None: config = func(current_path, default=None)
configs['portable'] = _readOptions(os.path.join(run_path, 'youtube-dlc.conf')) if user:
config, current_path = config
if config is None:
return [], None
return config, current_path
configs['portable'], paths['portable'] = read_options(get_executable_path())
if '--ignore-config' in configs['portable']: if '--ignore-config' in configs['portable']:
return return
configs['system'] = _readOptions('/etc/yt-dlp.conf', default=None)
if configs['system'] is None:
configs['system'] = _readOptions('/etc/youtube-dlc.conf')
def get_home_path():
opts = parser.parse_args(configs['portable'] + configs['custom'] + configs['command-line'])[0]
return expand_path(opts.paths.get('home', '')).strip()
configs['home'], paths['home'] = read_options(get_home_path())
if '--ignore-config' in configs['home']:
return
configs['system'], paths['system'] = read_options('/etc')
if '--ignore-config' in configs['system']: if '--ignore-config' in configs['system']:
return return
configs['user'] = _readUserConf('yt-dlp', default=None)
if configs['user'] is None: configs['user'], paths['user'] = read_options('', True)
configs['user'] = _readUserConf('youtube-dlc')
if '--ignore-config' in configs['user']: if '--ignore-config' in configs['user']:
configs['system'] = [] configs['system'], paths['system'] = [], None
get_configs() get_configs()
argv = configs['system'] + configs['user'] + configs['portable'] + configs['custom'] + configs['command_line'] argv = configs['system'] + configs['user'] + configs['home'] + configs['portable'] + configs['custom'] + configs['command-line']
opts, args = parser.parse_args(argv) opts, args = parser.parse_args(argv)
if opts.verbose: if opts.verbose:
for conf_label, conf in ( for label in ('System', 'User', 'Portable', 'Home', 'Custom', 'Command-line'):
('System config', configs['system']), key = label.lower()
('User config', configs['user']), if paths.get(key) is None:
('Portable config', configs['portable']), continue
('Custom config', configs['custom']), if paths[key]:
('Command-line args', configs['command_line'])): write_string('[debug] %s config file: %s\n' % (label, paths[key]))
write_string('[debug] %s: %s\n' % (conf_label, repr(_hide_login_info(conf)))) write_string('[debug] %s config: %s\n' % (label, repr(_hide_login_info(configs[key]))))
return parser, opts, args return parser, opts, args
+2
View File
@@ -17,6 +17,7 @@ from .ffmpeg import (
from .xattrpp import XAttrMetadataPP from .xattrpp import XAttrMetadataPP
from .execafterdownload import ExecAfterDownloadPP from .execafterdownload import ExecAfterDownloadPP
from .metadatafromtitle import MetadataFromTitlePP from .metadatafromtitle import MetadataFromTitlePP
from .movefilesafterdownload import MoveFilesAfterDownloadPP
from .sponskrub import SponSkrubPP from .sponskrub import SponSkrubPP
@@ -39,6 +40,7 @@ __all__ = [
'FFmpegVideoConvertorPP', 'FFmpegVideoConvertorPP',
'FFmpegVideoRemuxerPP', 'FFmpegVideoRemuxerPP',
'MetadataFromTitlePP', 'MetadataFromTitlePP',
'MoveFilesAfterDownloadPP',
'SponSkrubPP', 'SponSkrubPP',
'XAttrMetadataPP', 'XAttrMetadataPP',
] ]
+19 -12
View File
@@ -2,10 +2,11 @@ from __future__ import unicode_literals
import os import os
from ..compat import compat_str
from ..utils import ( from ..utils import (
PostProcessingError,
cli_configuration_args, cli_configuration_args,
encodeFilename, encodeFilename,
PostProcessingError,
) )
@@ -33,12 +34,17 @@ class PostProcessor(object):
def __init__(self, downloader=None): def __init__(self, downloader=None):
self._downloader = downloader self._downloader = downloader
if not hasattr(self, 'PP_NAME'): self.PP_NAME = self.pp_key()
self.PP_NAME = self.__class__.__name__[:-2]
def to_screen(self, text, *args, **kwargs): @classmethod
def pp_key(cls):
name = cls.__name__[:-2]
return compat_str(name[6:]) if name[:6].lower() == 'ffmpeg' else name
def to_screen(self, text, prefix=True, *args, **kwargs):
tag = '[%s] ' % self.PP_NAME if prefix else ''
if self._downloader: if self._downloader:
return self._downloader.to_screen('[%s] %s' % (self.PP_NAME, text), *args, **kwargs) return self._downloader.to_screen('%s%s' % (tag, text), *args, **kwargs)
def report_warning(self, text, *args, **kwargs): def report_warning(self, text, *args, **kwargs):
if self._downloader: if self._downloader:
@@ -48,9 +54,10 @@ class PostProcessor(object):
if self._downloader: if self._downloader:
return self._downloader.report_error(text, *args, **kwargs) return self._downloader.report_error(text, *args, **kwargs)
def write_debug(self, text, *args, **kwargs): 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):
return self._downloader.to_screen('[debug] %s' % text, *args, **kwargs) return self._downloader.to_screen('%s%s' % (tag, text), *args, **kwargs)
def get_param(self, name, default=None, *args, **kwargs): def get_param(self, name, default=None, *args, **kwargs):
if self._downloader: if self._downloader:
@@ -84,11 +91,11 @@ class PostProcessor(object):
except Exception: except Exception:
self.report_warning(errnote) self.report_warning(errnote)
def _configuration_args(self, default=[]): def _configuration_args(self, default=[], exe=None):
args = self.get_param('postprocessor_args', {}) key = self.pp_key().lower()
if isinstance(args, list): # for backward compatibility args, is_compat = cli_configuration_args(
args = {'default': args, 'sponskrub': []} self._downloader.params, 'postprocessor_args', key, default, exe)
return cli_configuration_args(args, self.PP_NAME.lower(), args.get('default', [])) return args if not is_compat or key != 'sponskrub' else default
class AudioConversionError(PostProcessingError): class AudioConversionError(PostProcessingError):
+12 -31
View File
@@ -24,7 +24,6 @@ class EmbedThumbnailPPError(PostProcessingError):
class EmbedThumbnailPP(FFmpegPostProcessor): class EmbedThumbnailPP(FFmpegPostProcessor):
PP_NAME = 'EmbedThumbnail'
def __init__(self, downloader=None, already_have_thumbnail=False): def __init__(self, downloader=None, already_have_thumbnail=False):
super(EmbedThumbnailPP, self).__init__(downloader) super(EmbedThumbnailPP, self).__init__(downloader)
@@ -75,42 +74,23 @@ class EmbedThumbnailPP(FFmpegPostProcessor):
os.rename(encodeFilename(escaped_thumbnail_jpg_filename), encodeFilename(thumbnail_jpg_filename)) os.rename(encodeFilename(escaped_thumbnail_jpg_filename), encodeFilename(thumbnail_jpg_filename))
thumbnail_filename = thumbnail_jpg_filename thumbnail_filename = thumbnail_jpg_filename
success = True
if info['ext'] == 'mp3': if info['ext'] == 'mp3':
options = [ options = [
'-c', 'copy', '-map', '0:0', '-map', '1:0', '-id3v2_version', '3', '-c', 'copy', '-map', '0:0', '-map', '1:0', '-id3v2_version', '3',
'-metadata:s:v', 'title="Album cover"', '-metadata:s:v', 'comment="Cover (front)"'] '-metadata:s:v', 'title="Album cover"', '-metadata:s:v', 'comment="Cover (front)"']
self.to_screen('Adding thumbnail to "%s"' % filename) self.to_screen('Adding thumbnail to "%s"' % filename)
self.run_ffmpeg_multiple_files([filename, thumbnail_filename], temp_filename, options) self.run_ffmpeg_multiple_files([filename, thumbnail_filename], temp_filename, options)
if not self._already_have_thumbnail:
os.remove(encodeFilename(thumbnail_filename))
os.remove(encodeFilename(filename))
os.rename(encodeFilename(temp_filename), encodeFilename(filename))
elif info['ext'] == 'mkv': elif info['ext'] == 'mkv':
old_thumbnail_filename = thumbnail_filename
thumbnail_filename = os.path.join(os.path.dirname(old_thumbnail_filename), 'cover.jpg')
if os.path.exists(thumbnail_filename):
os.remove(encodeFilename(thumbnail_filename))
os.rename(encodeFilename(old_thumbnail_filename), encodeFilename(thumbnail_filename))
options = [ options = [
'-c', 'copy', '-map', '0', '-dn', '-c', 'copy', '-map', '0', '-dn', '-attach', thumbnail_filename,
'-attach', thumbnail_filename, '-metadata:s:t', 'mimetype=image/jpeg'] '-metadata:s:t', 'mimetype=image/jpeg', '-metadata:s:t', 'filename=cover.jpg']
self.to_screen('Adding thumbnail to "%s"' % filename) self.to_screen('Adding thumbnail to "%s"' % filename)
self.run_ffmpeg_multiple_files([filename], temp_filename, options) self.run_ffmpeg_multiple_files([filename], temp_filename, options)
if not self._already_have_thumbnail:
os.remove(encodeFilename(thumbnail_filename))
else:
os.rename(encodeFilename(thumbnail_filename), encodeFilename(old_thumbnail_filename))
os.remove(encodeFilename(filename))
os.rename(encodeFilename(temp_filename), encodeFilename(filename))
elif info['ext'] in ['m4a', 'mp4']: elif info['ext'] in ['m4a', 'mp4']:
if not check_executable('AtomicParsley', ['-v']): if not check_executable('AtomicParsley', ['-v']):
raise EmbedThumbnailPPError('AtomicParsley was not found. Please install.') raise EmbedThumbnailPPError('AtomicParsley was not found. Please install.')
@@ -121,9 +101,9 @@ class EmbedThumbnailPP(FFmpegPostProcessor):
encodeFilename(thumbnail_filename, True), encodeFilename(thumbnail_filename, True),
encodeArgument('-o'), encodeArgument('-o'),
encodeFilename(temp_filename, True)] encodeFilename(temp_filename, True)]
cmd += [encodeArgument(o) for o in self._configuration_args(exe='AtomicParsley')]
self.to_screen('Adding thumbnail to "%s"' % filename) self.to_screen('Adding thumbnail to "%s"' % filename)
self.write_debug('AtomicParsley command line: %s' % shell_quote(cmd)) self.write_debug('AtomicParsley command line: %s' % shell_quote(cmd))
p = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE) p = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
@@ -132,17 +112,18 @@ class EmbedThumbnailPP(FFmpegPostProcessor):
if p.returncode != 0: if p.returncode != 0:
msg = stderr.decode('utf-8', 'replace').strip() msg = stderr.decode('utf-8', 'replace').strip()
raise EmbedThumbnailPPError(msg) raise EmbedThumbnailPPError(msg)
if not self._already_have_thumbnail:
os.remove(encodeFilename(thumbnail_filename))
# for formats that don't support thumbnails (like 3gp) AtomicParsley # for formats that don't support thumbnails (like 3gp) AtomicParsley
# won't create to the temporary file # won't create to the temporary file
if b'No changes' in stdout: if b'No changes' in stdout:
self.report_warning('The file format doesn\'t support embedding a thumbnail') self.report_warning('The file format doesn\'t support embedding a thumbnail')
else: success = False
os.remove(encodeFilename(filename))
os.rename(encodeFilename(temp_filename), encodeFilename(filename))
else: else:
raise EmbedThumbnailPPError('Only mp3, mkv, m4a and mp4 are supported for thumbnail embedding for now.') raise EmbedThumbnailPPError('Only mp3, mkv, m4a and mp4 are supported for thumbnail embedding for now.')
return [], info if success:
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
@@ -11,12 +11,15 @@ from ..utils import (
class ExecAfterDownloadPP(PostProcessor): class ExecAfterDownloadPP(PostProcessor):
PP_NAME = 'Exec'
def __init__(self, downloader, exec_cmd): def __init__(self, downloader, exec_cmd):
super(ExecAfterDownloadPP, self).__init__(downloader) super(ExecAfterDownloadPP, self).__init__(downloader)
self.exec_cmd = exec_cmd self.exec_cmd = exec_cmd
@classmethod
def pp_key(cls):
return 'Exec'
def run(self, information): def run(self, information):
cmd = self.exec_cmd cmd = self.exec_cmd
if '{}' not in cmd: if '{}' not in cmd:
+1 -3
View File
@@ -54,8 +54,6 @@ class FFmpegPostProcessorError(PostProcessingError):
class FFmpegPostProcessor(PostProcessor): class FFmpegPostProcessor(PostProcessor):
def __init__(self, downloader=None): def __init__(self, downloader=None):
if not hasattr(self, 'PP_NAME'):
self.PP_NAME = self.__class__.__name__[6:-2] # Remove ffmpeg from the front
PostProcessor.__init__(self, downloader) PostProcessor.__init__(self, downloader)
self._determine_executables() self._determine_executables()
@@ -209,7 +207,7 @@ class FFmpegPostProcessor(PostProcessor):
oldest_mtime = min( oldest_mtime = min(
os.stat(encodeFilename(path)).st_mtime for path in input_paths) os.stat(encodeFilename(path)).st_mtime for path in input_paths)
opts += self._configuration_args() opts += self._configuration_args(exe=self.basename)
files_cmd = [] files_cmd = []
for path in input_paths: for path in input_paths:
@@ -0,0 +1,53 @@
from __future__ import unicode_literals
import os
import shutil
from .common import PostProcessor
from ..utils import (
encodeFilename,
make_dir,
PostProcessingError,
)
from ..compat import compat_str
class MoveFilesAfterDownloadPP(PostProcessor):
def __init__(self, downloader, files_to_move):
PostProcessor.__init__(self, downloader)
self.files_to_move = files_to_move
@classmethod
def pp_key(cls):
return 'MoveFiles'
def run(self, info):
dl_path, dl_name = os.path.split(encodeFilename(info['filepath']))
finaldir = info.get('__finaldir', dl_path)
finalpath = os.path.join(finaldir, dl_name)
self.files_to_move[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 os.path.exists(encodeFilename(newfile)):
if self.get_param('overwrites', True):
self.report_warning('Replacing existing file "%s"' % newfile)
os.path.remove(encodeFilename(newfile))
else:
self.report_warning(
'Cannot move file "%s" out of temporary directory since "%s" already exists. '
% (oldfile, newfile))
continue
make_dir(newfile, PostProcessingError)
self.to_screen('Moving file "%s" to "%s"' % (oldfile, newfile))
shutil.move(oldfile, newfile) # os.rename cannot move between volumes
info['filepath'] = compat_str(finalpath)
return [], info
+18 -15
View File
@@ -7,22 +7,23 @@ from ..compat import compat_shlex_split
from ..utils import ( from ..utils import (
check_executable, check_executable,
encodeArgument, encodeArgument,
encodeFilename,
shell_quote, shell_quote,
str_or_none,
PostProcessingError, PostProcessingError,
prepend_extension,
) )
class SponSkrubPP(PostProcessor): class SponSkrubPP(PostProcessor):
_temp_ext = 'spons' _temp_ext = 'spons'
_def_args = []
_exe_name = 'sponskrub' _exe_name = 'sponskrub'
def __init__(self, downloader, path='', args=None, ignoreerror=False, cut=False, force=False): def __init__(self, downloader, path='', args=None, ignoreerror=False, cut=False, force=False):
PostProcessor.__init__(self, downloader) PostProcessor.__init__(self, downloader)
self.force = force self.force = force
self.cutout = cut self.cutout = cut
self.args = ['-chapter'] if not cut else [] self.args = str_or_none(args) or '' # For backward compatibility
self.args += self._configuration_args(self._def_args) if args is None else compat_shlex_split(args)
self.path = self.get_exe(path) self.path = self.get_exe(path)
if not ignoreerror and self.path is None: if not ignoreerror and self.path is None:
@@ -58,13 +59,15 @@ class SponSkrubPP(PostProcessor):
self.report_warning('If sponskrub is run multiple times, unintended parts of the video could be cut out.') self.report_warning('If sponskrub is run multiple times, unintended parts of the video could be cut out.')
filename = information['filepath'] filename = information['filepath']
temp_filename = filename + '.' + self._temp_ext + os.path.splitext(filename)[1] temp_filename = prepend_extension(filename, self._temp_ext)
if os.path.exists(temp_filename): if os.path.exists(encodeFilename(temp_filename)):
os.remove(temp_filename) os.remove(encodeFilename(temp_filename))
cmd = [self.path] cmd = [self.path]
if self.args: if not self.cutout:
cmd += self.args cmd += ['-chapter']
cmd += compat_shlex_split(self.args) # For backward compatibility
cmd += self._configuration_args(exe=self._exe_name)
cmd += ['--', information['id'], filename, temp_filename] cmd += ['--', information['id'], filename, temp_filename]
cmd = [encodeArgument(i) for i in cmd] cmd = [encodeArgument(i) for i in cmd]
@@ -73,15 +76,15 @@ class SponSkrubPP(PostProcessor):
stdout, stderr = p.communicate() stdout, stderr = p.communicate()
if p.returncode == 0: if p.returncode == 0:
os.remove(filename) os.remove(encodeFilename(filename))
os.rename(temp_filename, filename) os.rename(encodeFilename(temp_filename), encodeFilename(filename))
self.to_screen('Sponsor sections have been %s' % ('removed' if self.cutout else 'marked')) self.to_screen('Sponsor sections have been %s' % ('removed' if self.cutout else 'marked'))
elif p.returncode == 3: elif p.returncode == 3:
self.to_screen('No segments in the SponsorBlock database') self.to_screen('No segments in the SponsorBlock database')
else: else:
stderr = stderr.decode('utf-8', 'replace') msg = stderr.decode('utf-8', 'replace').strip() or stdout.decode('utf-8', 'replace').strip()
msg = stderr.strip() self.write_debug(msg, prefix=False)
if not self.get_param('verbose', False): line = 0 if msg[:12].lower() == 'unrecognised' else -1
msg = msg.split('\n')[-1] msg = msg.split('\n')[line]
raise PostProcessingError(msg if msg else 'sponskrub failed with error code %s!' % p.returncode) raise PostProcessingError(msg if msg else 'sponskrub failed with error code %s' % p.returncode)
return [], information return [], information
+82 -7
View File
@@ -16,6 +16,7 @@ import email.header
import errno import errno
import functools import functools
import gzip import gzip
import imp
import io import io
import itertools import itertools
import json import json
@@ -4099,7 +4100,8 @@ def strip_jsonp(code):
r'\g<callback_data>', code) r'\g<callback_data>', code)
def js_to_json(code): def js_to_json(code, vars={}):
# vars is a dict of var, val pairs to substitute
COMMENT_RE = r'/\*(?:(?!\*/).)*?\*/|//[^\n]*' COMMENT_RE = r'/\*(?:(?!\*/).)*?\*/|//[^\n]*'
SKIP_RE = r'\s*(?:{comment})?\s*'.format(comment=COMMENT_RE) SKIP_RE = r'\s*(?:{comment})?\s*'.format(comment=COMMENT_RE)
INTEGER_TABLE = ( INTEGER_TABLE = (
@@ -4128,6 +4130,9 @@ def js_to_json(code):
i = int(im.group(1), base) i = int(im.group(1), base)
return '"%d":' % i if v.endswith(':') else '%d' % i return '"%d":' % i if v.endswith(':') else '%d' % i
if v in vars:
return vars[v]
return '"%s"' % v return '"%s"' % v
return re.sub(r'''(?sx) return re.sub(r'''(?sx)
@@ -4652,12 +4657,35 @@ def cli_valueless_option(params, command_option, param, expected_value=True):
return [command_option] if param == expected_value else [] return [command_option] if param == expected_value else []
def cli_configuration_args(params, param, default=[]): def cli_configuration_args(params, arg_name, key, default=[], exe=None): # returns arg, for_compat
ex_args = params.get(param) argdict = params.get(arg_name, {})
if ex_args is None: if isinstance(argdict, (list, tuple)): # for backward compatibility
return default return argdict, True
assert isinstance(ex_args, list)
return ex_args if argdict is None:
return default, False
assert isinstance(argdict, dict)
assert isinstance(key, compat_str)
key = key.lower()
args = exe_args = None
if exe is not None:
assert isinstance(exe, compat_str)
exe = exe.lower()
args = argdict.get('%s+%s' % (key, exe))
if args is None:
exe_args = argdict.get(exe)
if args is None:
args = argdict.get(key) if key != exe else None
if args is None and exe_args is None:
args = argdict.get('default', default)
args, exe_args = args or [], exe_args or []
assert isinstance(args, (list, tuple))
assert isinstance(exe_args, (list, tuple))
return args + exe_args, False
class ISO639Utils(object): class ISO639Utils(object):
@@ -5859,3 +5887,50 @@ def clean_podcast_url(url):
st\.fm # https://podsights.com/docs/ st\.fm # https://podsights.com/docs/
)/e )/e
)/''', '', url) )/''', '', url)
_HEX_TABLE = '0123456789abcdef'
def random_uuidv4():
return re.sub(r'[xy]', lambda x: _HEX_TABLE[random.randint(0, 15)], 'xxxxxxxx-xxxx-4xxx-yxxx-xxxxxxxxxxxx')
def make_dir(path, to_screen=None):
try:
dn = os.path.dirname(path)
if dn and not os.path.exists(dn):
os.makedirs(dn)
return True
except (OSError, IOError) as err:
if callable(to_screen) is not None:
to_screen('unable to create directory ' + error_to_compat_str(err))
return False
def get_executable_path():
path = os.path.dirname(sys.argv[0])
if os.path.abspath(sys.argv[0]) != os.path.abspath(sys.executable): # Not packaged
path = os.path.join(path, '..')
return os.path.abspath(path)
def load_plugins(name, type, namespace):
plugin_info = [None]
classes = []
try:
plugin_info = imp.find_module(
name, [os.path.join(get_executable_path(), 'ytdlp_plugins')])
plugins = imp.load_module(name, *plugin_info)
for name in dir(plugins):
if not name.endswith(type):
continue
klass = getattr(plugins, name)
classes.append(klass)
namespace[name] = klass
except ImportError:
pass
finally:
if plugin_info[0] is not None:
plugin_info[0].close()
return classes
+1 -1
View File
@@ -1,3 +1,3 @@
from __future__ import unicode_literals from __future__ import unicode_literals
__version__ = '2021.01.14' __version__ = '2021.01.20'
+2
View File
@@ -0,0 +1,2 @@
# flake8: noqa
from .sample import SamplePluginIE
+12
View File
@@ -0,0 +1,12 @@
from __future__ import unicode_literals
from youtube_dlc.extractor.common import InfoExtractor
class SamplePluginIE(InfoExtractor):
_WORKING = False
IE_DESC = False
_VALID_URL = r'^sampleplugin:'
def _real_extract(self, url):
self.to_screen('URL "%s" sucessfully captured' % url)