mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2026-01-10 17:01:17 +00:00
Compare commits
1 Commits
2021.01.16
...
2021.01.07
| Author | SHA1 | Date | |
|---|---|---|---|
|
0e7f2c7b4d |
10
.github/ISSUE_TEMPLATE/1_broken_site.md
vendored
10
.github/ISSUE_TEMPLATE/1_broken_site.md
vendored
@@ -21,15 +21,15 @@ assignees: ''
|
||||
|
||||
<!--
|
||||
Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dlc:
|
||||
- First of, make sure you are using the latest version of yt-dlp. Run `youtube-dlc --version` and ensure your version is 2021.01.14. 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 Issues with outdated version will be REJECTED.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 youtube-dlc. Run `youtube-dlc --version` and ensure your version is 2021.01.07. If it's not, see https://github.com/pukkandan/yt-dlc on how to update. Issues with outdated version will be REJECTED.
|
||||
- Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser.
|
||||
- Make sure that all URLs and arguments with special characters are properly quoted or escaped as explained in https://github.com/pukkandan/yt-dlp.
|
||||
- Search the bugtracker for similar issues: https://github.com/pukkandan/yt-dlp. DO NOT post duplicates.
|
||||
- Make sure that all URLs and arguments with special characters are properly quoted or escaped as explained in https://github.com/pukkandan/yt-dlc.
|
||||
- Search the bugtracker for similar issues: https://github.com/pukkandan/yt-dlc. DO NOT post duplicates.
|
||||
- Finally, put x into all relevant boxes like this [x] (Dont forget to delete the empty space)
|
||||
-->
|
||||
|
||||
- [ ] I'm reporting a broken site support
|
||||
- [ ] I've verified that I'm running yt-dlp version **2021.01.14**
|
||||
- [ ] I've verified that I'm running youtube-dlc version **2021.01.07**
|
||||
- [ ] I've checked that all provided URLs are alive and playable in a browser
|
||||
- [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped
|
||||
- [ ] I've searched the bugtracker for similar issues including closed ones
|
||||
@@ -44,7 +44,7 @@ Add the `-v` flag to your command line you run youtube-dlc with (`youtube-dlc -v
|
||||
[debug] User config: []
|
||||
[debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
|
||||
[debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
|
||||
[debug] yt-dlp version 2021.01.14
|
||||
[debug] youtube-dlc version 2021.01.07
|
||||
[debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
|
||||
[debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
|
||||
[debug] Proxy map: {}
|
||||
|
||||
@@ -21,15 +21,15 @@ assignees: ''
|
||||
|
||||
<!--
|
||||
Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dlc:
|
||||
- First of, make sure you are using the latest version of yt-dlp. Run `youtube-dlc --version` and ensure your version is 2021.01.14. 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 youtube-dlc. Run `youtube-dlc --version` and ensure your version is 2021.01.07. If it's not, see https://github.com/pukkandan/yt-dlc on how to update. Issues with outdated version will be REJECTED.
|
||||
- Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser.
|
||||
- Make sure that site you are requesting is not dedicated to copyright infringement, see https://github.com/pukkandan/yt-dlp. yt-dlp does not support such sites. In order for site support request to be accepted all provided example URLs should not violate any copyrights.
|
||||
- Search the bugtracker for similar site support requests: https://github.com/pukkandan/yt-dlp. DO NOT post duplicates.
|
||||
- Make sure that site you are requesting is not dedicated to copyright infringement, see https://github.com/pukkandan/yt-dlc. youtube-dlc 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-dlc. DO NOT post duplicates.
|
||||
- Finally, put x into all relevant boxes like this [x] (Dont forget to delete the empty space)
|
||||
-->
|
||||
|
||||
- [ ] I'm reporting a new site support request
|
||||
- [ ] I've verified that I'm running yt-dlp version **2021.01.14**
|
||||
- [ ] I've verified that I'm running youtube-dlc version **2021.01.07**
|
||||
- [ ] I've checked that all provided URLs are alive and playable in a browser
|
||||
- [ ] I've checked that none of provided URLs violate any copyrights
|
||||
- [ ] I've searched the bugtracker for similar site support requests including closed ones
|
||||
|
||||
@@ -21,13 +21,13 @@ assignees: ''
|
||||
|
||||
<!--
|
||||
Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dlc:
|
||||
- First of, make sure you are using the latest version of yt-dlp. Run `youtube-dlc --version` and ensure your version is 2021.01.14. 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.
|
||||
- First of, make sure you are using the latest version of youtube-dlc. Run `youtube-dlc --version` and ensure your version is 2021.01.07. If it's not, see https://github.com/pukkandan/yt-dlc on how to update. Issues with outdated version will be REJECTED.
|
||||
- Search the bugtracker for similar site feature requests: https://github.com/pukkandan/yt-dlc. DO NOT post duplicates.
|
||||
- Finally, put x into all relevant boxes like this [x] (Dont forget to delete the empty space)
|
||||
-->
|
||||
|
||||
- [ ] I'm reporting a site feature request
|
||||
- [ ] I've verified that I'm running yt-dlp version **2021.01.14**
|
||||
- [ ] I've verified that I'm running youtube-dlc version **2021.01.07**
|
||||
- [ ] I've searched the bugtracker for similar site feature requests including closed ones
|
||||
|
||||
|
||||
|
||||
12
.github/ISSUE_TEMPLATE/4_bug_report.md
vendored
12
.github/ISSUE_TEMPLATE/4_bug_report.md
vendored
@@ -21,16 +21,16 @@ assignees: ''
|
||||
|
||||
<!--
|
||||
Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dlc:
|
||||
- First of, make sure you are using the latest version of yt-dlp. Run `youtube-dlc --version` and ensure your version is 2021.01.14. 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 youtube-dlc. Run `youtube-dlc --version` and ensure your version is 2021.01.07. If it's not, see https://github.com/pukkandan/yt-dlc on how to update. Issues with outdated version will be REJECTED.
|
||||
- Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser.
|
||||
- Make sure that all URLs and arguments with special characters are properly quoted or escaped as explained in https://github.com/pukkandan/yt-dlp.
|
||||
- Search the bugtracker for similar issues: https://github.com/pukkandan/yt-dlp. DO NOT post duplicates.
|
||||
- Read bugs section in FAQ: 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-dlc.
|
||||
- Search the bugtracker for similar issues: https://github.com/pukkandan/yt-dlc. DO NOT post duplicates.
|
||||
- Read bugs section in FAQ: https://github.com/pukkandan/yt-dlc
|
||||
- Finally, put x into all relevant boxes like this [x] (Dont forget to delete the empty space)
|
||||
-->
|
||||
|
||||
- [ ] 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 youtube-dlc version **2021.01.07**
|
||||
- [ ] I've checked that all provided URLs are alive and playable in a browser
|
||||
- [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped
|
||||
- [ ] I've searched the bugtracker for similar bug reports including closed ones
|
||||
@@ -46,7 +46,7 @@ Add the `-v` flag to your command line you run youtube-dlc with (`youtube-dlc -v
|
||||
[debug] User config: []
|
||||
[debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
|
||||
[debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
|
||||
[debug] yt-dlp version 2021.01.14
|
||||
[debug] youtube-dlc version 2021.01.07
|
||||
[debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
|
||||
[debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
|
||||
[debug] Proxy map: {}
|
||||
|
||||
6
.github/ISSUE_TEMPLATE/5_feature_request.md
vendored
6
.github/ISSUE_TEMPLATE/5_feature_request.md
vendored
@@ -21,13 +21,13 @@ assignees: ''
|
||||
|
||||
<!--
|
||||
Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dlc:
|
||||
- First of, make sure you are using the latest version of yt-dlp. Run `youtube-dlc --version` and ensure your version is 2021.01.14. 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.
|
||||
- First of, make sure you are using the latest version of youtube-dlc. Run `youtube-dlc --version` and ensure your version is 2021.01.07. If it's not, see https://github.com/pukkandan/yt-dlc on how to update. Issues with outdated version will be REJECTED.
|
||||
- Search the bugtracker for similar feature requests: https://github.com/pukkandan/yt-dlc. DO NOT post duplicates.
|
||||
- Finally, put x into all relevant boxes like this [x] (Dont forget to delete the empty space)
|
||||
-->
|
||||
|
||||
- [ ] I'm reporting a feature request
|
||||
- [ ] I've verified that I'm running yt-dlp version **2021.01.14**
|
||||
- [ ] I've verified that I'm running youtube-dlc version **2021.01.07**
|
||||
- [ ] I've searched the bugtracker for similar feature requests including closed ones
|
||||
|
||||
|
||||
|
||||
4
.github/ISSUE_TEMPLATE/6_question.md
vendored
4
.github/ISSUE_TEMPLATE/6_question.md
vendored
@@ -20,8 +20,8 @@ assignees: ''
|
||||
## Checklist
|
||||
|
||||
<!--
|
||||
Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dlc:
|
||||
- Look through the README (https://github.com/pukkandan/yt-dlp) and FAQ (https://github.com/pukkandan/yt-dlp) for similar questions
|
||||
Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
|
||||
- Look through the README (https://github.com/blackjack4494/yt-dlc) and FAQ (https://github.com/blackjack4494/yt-dlc) for similar questions
|
||||
- Search the bugtracker for similar questions: https://github.com/blackjack4494/yt-dlc
|
||||
- Finally, put x into all relevant boxes like this [x] (Dont forget to delete the empty space)
|
||||
-->
|
||||
|
||||
10
.github/ISSUE_TEMPLATE_tmpl/1_broken_site.md
vendored
10
.github/ISSUE_TEMPLATE_tmpl/1_broken_site.md
vendored
@@ -21,15 +21,15 @@ assignees: ''
|
||||
|
||||
<!--
|
||||
Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dlc:
|
||||
- First of, make sure you are using the latest version of yt-dlp. Run `youtube-dlc --version` and ensure your version is %(version)s. 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 youtube-dlc. Run `youtube-dlc --version` and ensure your version is %(version)s. If it's not, see https://github.com/pukkandan/yt-dlc on how to update. Issues with outdated version will be REJECTED.
|
||||
- Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser.
|
||||
- Make sure that all URLs and arguments with special characters are properly quoted or escaped as explained in https://github.com/pukkandan/yt-dlp.
|
||||
- Search the bugtracker for similar issues: https://github.com/pukkandan/yt-dlp. DO NOT post duplicates.
|
||||
- Make sure that all URLs and arguments with special characters are properly quoted or escaped as explained in https://github.com/pukkandan/yt-dlc.
|
||||
- Search the bugtracker for similar issues: https://github.com/pukkandan/yt-dlc. DO NOT post duplicates.
|
||||
- Finally, put x into all relevant boxes like this [x] (Dont forget to delete the empty space)
|
||||
-->
|
||||
|
||||
- [ ] I'm reporting a broken site support
|
||||
- [ ] I've verified that I'm running yt-dlp version **%(version)s**
|
||||
- [ ] I've verified that I'm running youtube-dlc version **%(version)s**
|
||||
- [ ] I've checked that all provided URLs are alive and playable in a browser
|
||||
- [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped
|
||||
- [ ] I've searched the bugtracker for similar issues including closed ones
|
||||
@@ -44,7 +44,7 @@ Add the `-v` flag to your command line you run youtube-dlc with (`youtube-dlc -v
|
||||
[debug] User config: []
|
||||
[debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
|
||||
[debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
|
||||
[debug] yt-dlp version %(version)s
|
||||
[debug] youtube-dlc version %(version)s
|
||||
[debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
|
||||
[debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
|
||||
[debug] Proxy map: {}
|
||||
|
||||
@@ -21,15 +21,15 @@ assignees: ''
|
||||
|
||||
<!--
|
||||
Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dlc:
|
||||
- First of, make sure you are using the latest version of yt-dlp. Run `youtube-dlc --version` and ensure your version is %(version)s. 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 youtube-dlc. Run `youtube-dlc --version` and ensure your version is %(version)s. If it's not, see https://github.com/pukkandan/yt-dlc on how to update. Issues with outdated version will be REJECTED.
|
||||
- Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser.
|
||||
- Make sure that site you are requesting is not dedicated to copyright infringement, see https://github.com/pukkandan/yt-dlp. yt-dlp does not support such sites. In order for site support request to be accepted all provided example URLs should not violate any copyrights.
|
||||
- Search the bugtracker for similar site support requests: https://github.com/pukkandan/yt-dlp. DO NOT post duplicates.
|
||||
- Make sure that site you are requesting is not dedicated to copyright infringement, see https://github.com/pukkandan/yt-dlc. youtube-dlc 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-dlc. DO NOT post duplicates.
|
||||
- Finally, put x into all relevant boxes like this [x] (Dont forget to delete the empty space)
|
||||
-->
|
||||
|
||||
- [ ] I'm reporting a new site support request
|
||||
- [ ] I've verified that I'm running yt-dlp version **%(version)s**
|
||||
- [ ] I've verified that I'm running youtube-dlc version **%(version)s**
|
||||
- [ ] I've checked that all provided URLs are alive and playable in a browser
|
||||
- [ ] I've checked that none of provided URLs violate any copyrights
|
||||
- [ ] I've searched the bugtracker for similar site support requests including closed ones
|
||||
|
||||
@@ -21,13 +21,13 @@ assignees: ''
|
||||
|
||||
<!--
|
||||
Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dlc:
|
||||
- First of, make sure you are using the latest version of yt-dlp. Run `youtube-dlc --version` and ensure your version is %(version)s. 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.
|
||||
- First of, make sure you are using the latest version of youtube-dlc. Run `youtube-dlc --version` and ensure your version is %(version)s. If it's not, see https://github.com/pukkandan/yt-dlc on how to update. Issues with outdated version will be REJECTED.
|
||||
- Search the bugtracker for similar site feature requests: https://github.com/pukkandan/yt-dlc. DO NOT post duplicates.
|
||||
- Finally, put x into all relevant boxes like this [x] (Dont forget to delete the empty space)
|
||||
-->
|
||||
|
||||
- [ ] I'm reporting a site feature request
|
||||
- [ ] I've verified that I'm running yt-dlp version **%(version)s**
|
||||
- [ ] I've verified that I'm running youtube-dlc version **%(version)s**
|
||||
- [ ] I've searched the bugtracker for similar site feature requests including closed ones
|
||||
|
||||
|
||||
|
||||
12
.github/ISSUE_TEMPLATE_tmpl/4_bug_report.md
vendored
12
.github/ISSUE_TEMPLATE_tmpl/4_bug_report.md
vendored
@@ -21,16 +21,16 @@ assignees: ''
|
||||
|
||||
<!--
|
||||
Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dlc:
|
||||
- First of, make sure you are using the latest version of yt-dlp. Run `youtube-dlc --version` and ensure your version is %(version)s. 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 youtube-dlc. Run `youtube-dlc --version` and ensure your version is %(version)s. If it's not, see https://github.com/pukkandan/yt-dlc on how to update. Issues with outdated version will be REJECTED.
|
||||
- Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser.
|
||||
- Make sure that all URLs and arguments with special characters are properly quoted or escaped as explained in https://github.com/pukkandan/yt-dlp.
|
||||
- Search the bugtracker for similar issues: https://github.com/pukkandan/yt-dlp. DO NOT post duplicates.
|
||||
- Read bugs section in FAQ: 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-dlc.
|
||||
- Search the bugtracker for similar issues: https://github.com/pukkandan/yt-dlc. DO NOT post duplicates.
|
||||
- Read bugs section in FAQ: https://github.com/pukkandan/yt-dlc
|
||||
- Finally, put x into all relevant boxes like this [x] (Dont forget to delete the empty space)
|
||||
-->
|
||||
|
||||
- [ ] I'm reporting a broken site support issue
|
||||
- [ ] I've verified that I'm running yt-dlp version **%(version)s**
|
||||
- [ ] I've verified that I'm running youtube-dlc version **%(version)s**
|
||||
- [ ] I've checked that all provided URLs are alive and playable in a browser
|
||||
- [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped
|
||||
- [ ] I've searched the bugtracker for similar bug reports including closed ones
|
||||
@@ -46,7 +46,7 @@ Add the `-v` flag to your command line you run youtube-dlc with (`youtube-dlc -v
|
||||
[debug] User config: []
|
||||
[debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
|
||||
[debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
|
||||
[debug] yt-dlp version %(version)s
|
||||
[debug] youtube-dlc version %(version)s
|
||||
[debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
|
||||
[debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
|
||||
[debug] Proxy map: {}
|
||||
|
||||
@@ -21,13 +21,13 @@ assignees: ''
|
||||
|
||||
<!--
|
||||
Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dlc:
|
||||
- First of, make sure you are using the latest version of yt-dlp. Run `youtube-dlc --version` and ensure your version is %(version)s. 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.
|
||||
- First of, make sure you are using the latest version of youtube-dlc. Run `youtube-dlc --version` and ensure your version is %(version)s. If it's not, see https://github.com/pukkandan/yt-dlc on how to update. Issues with outdated version will be REJECTED.
|
||||
- Search the bugtracker for similar feature requests: https://github.com/pukkandan/yt-dlc. DO NOT post duplicates.
|
||||
- Finally, put x into all relevant boxes like this [x] (Dont forget to delete the empty space)
|
||||
-->
|
||||
|
||||
- [ ] I'm reporting a feature request
|
||||
- [ ] I've verified that I'm running yt-dlp version **%(version)s**
|
||||
- [ ] I've verified that I'm running youtube-dlc version **%(version)s**
|
||||
- [ ] I've searched the bugtracker for similar feature requests including closed ones
|
||||
|
||||
|
||||
|
||||
2
.github/PULL_REQUEST_TEMPLATE.md
vendored
2
.github/PULL_REQUEST_TEMPLATE.md
vendored
@@ -8,7 +8,7 @@
|
||||
|
||||
### Before submitting a *pull request* make sure you have:
|
||||
- [ ] At least skimmed through [adding new extractor tutorial](https://github.com/ytdl-org/youtube-dl#adding-support-for-a-new-site) and [youtube-dl coding conventions](https://github.com/ytdl-org/youtube-dl#youtube-dl-coding-conventions) sections
|
||||
- [ ] [Searched](https://github.com/pukkandan/yt-dlp/search?q=is%3Apr&type=Issues) the bugtracker for similar pull requests
|
||||
- [ ] [Searched](https://github.com/pukkandan/yt-dlc/search?q=is%3Apr&type=Issues) the bugtracker for similar pull requests
|
||||
- [ ] Checked the code with [flake8](https://pypi.python.org/pypi/flake8)
|
||||
|
||||
### In order to be accepted and merged into youtube-dl each piece of code must be in public domain or released under [Unlicense](http://unlicense.org/). Check one of the following options:
|
||||
|
||||
42
.github/workflows/build.yml
vendored
42
.github/workflows/build.yml
vendored
@@ -37,7 +37,7 @@ jobs:
|
||||
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
|
||||
with:
|
||||
tag_name: ${{ steps.bump_version.outputs.ytdlc_version }}
|
||||
release_name: yt-dlp ${{ steps.bump_version.outputs.ytdlc_version }}
|
||||
release_name: youtube-dlc ${{ steps.bump_version.outputs.ytdlc_version }}
|
||||
body: |
|
||||
Changelog:
|
||||
PLACEHOLDER
|
||||
@@ -58,18 +58,18 @@ jobs:
|
||||
env:
|
||||
SHA2: ${{ hashFiles('youtube-dlc') }}
|
||||
run: echo "::set-output name=sha2_unix::$SHA2"
|
||||
- name: Install dependencies for pypi
|
||||
run: |
|
||||
python -m pip install --upgrade pip
|
||||
pip install setuptools wheel twine
|
||||
- name: Build and publish on pypi
|
||||
env:
|
||||
TWINE_USERNAME: __token__
|
||||
TWINE_PASSWORD: ${{ secrets.PYPI_TOKEN }}
|
||||
run: |
|
||||
rm -rf dist/*
|
||||
python setup.py sdist bdist_wheel
|
||||
twine upload dist/*
|
||||
# - name: Install dependencies for pypi
|
||||
# run: |
|
||||
# python -m pip install --upgrade pip
|
||||
# pip install setuptools wheel twine
|
||||
# - name: Build and publish
|
||||
# env:
|
||||
# TWINE_USERNAME: ${{ secrets.PYPI_USERNAME }}
|
||||
# TWINE_PASSWORD: ${{ secrets.PYPI_PASSWORD }}
|
||||
# run: |
|
||||
# rm -rf dist/*
|
||||
# python setup.py sdist bdist_wheel
|
||||
# twine upload dist/*
|
||||
|
||||
build_windows:
|
||||
|
||||
@@ -161,19 +161,3 @@ jobs:
|
||||
asset_path: ./SHA2-256SUMS
|
||||
asset_name: SHA2-256SUMS
|
||||
asset_content_type: text/plain
|
||||
|
||||
update_version_badge:
|
||||
|
||||
runs-on: ubuntu-latest
|
||||
|
||||
needs: build_unix
|
||||
|
||||
steps:
|
||||
- name: Create Version Badge
|
||||
uses: schneegans/dynamic-badges-action@v1.0.0
|
||||
with:
|
||||
auth: ${{ secrets.GIST_TOKEN }}
|
||||
gistID: c69cb23c3c5b3316248e52022790aa57
|
||||
filename: version.json
|
||||
label: Version
|
||||
message: ${{ needs.build_unix.outputs.ytdlc_version }}
|
||||
|
||||
24
.github/workflows/ci.yml
vendored
24
.github/workflows/ci.yml
vendored
@@ -1,16 +1,16 @@
|
||||
name: Full Test
|
||||
on: [push, pull_request]
|
||||
name: CI
|
||||
on: [push]
|
||||
jobs:
|
||||
tests:
|
||||
name: Tests
|
||||
if: "!contains(github.event.head_commit.message, 'skip ci')"
|
||||
runs-on: ${{ matrix.os }}
|
||||
strategy:
|
||||
fail-fast: true
|
||||
matrix:
|
||||
os: [ubuntu-18.04]
|
||||
os: [ubuntu-latest]
|
||||
# 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]
|
||||
# 3.3, 3.4 are not running
|
||||
python-version: [2.7, 3.5, 3.6, 3.7, 3.8, 3.9, pypy-2.7, pypy-3.6, pypy-3.7]
|
||||
python-impl: [cpython]
|
||||
ytdl-test-set: [core, download]
|
||||
run-tests-ext: [sh]
|
||||
@@ -60,4 +60,16 @@ jobs:
|
||||
env:
|
||||
YTDL_TEST_SET: ${{ matrix.ytdl-test-set }}
|
||||
run: ./devscripts/run_tests.${{ matrix.run-tests-ext }}
|
||||
# flake8 has been moved to quick-test
|
||||
flake8:
|
||||
name: Linter
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- uses: actions/checkout@v2
|
||||
- name: Set up Python
|
||||
uses: actions/setup-python@v2
|
||||
with:
|
||||
python-version: 3.9
|
||||
- name: Install flake8
|
||||
run: pip install flake8
|
||||
- name: Run flake8
|
||||
run: flake8 .
|
||||
33
.github/workflows/python-publish.yml.disable
vendored
Normal file
33
.github/workflows/python-publish.yml.disable
vendored
Normal file
@@ -0,0 +1,33 @@
|
||||
# This workflows will upload a Python Package using Twine when a release is created
|
||||
# For more information see: https://help.github.com/en/actions/language-and-framework-guides/using-python-with-github-actions#publishing-to-package-registries
|
||||
|
||||
name: Upload Python Package
|
||||
|
||||
on:
|
||||
push:
|
||||
branches:
|
||||
- release
|
||||
|
||||
jobs:
|
||||
deploy:
|
||||
|
||||
runs-on: ubuntu-latest
|
||||
|
||||
steps:
|
||||
- uses: actions/checkout@v2
|
||||
- name: Set up Python
|
||||
uses: actions/setup-python@v2
|
||||
with:
|
||||
python-version: '3.x'
|
||||
- name: Install dependencies
|
||||
run: |
|
||||
python -m pip install --upgrade pip
|
||||
pip install setuptools wheel twine
|
||||
- name: Build and publish
|
||||
env:
|
||||
TWINE_USERNAME: ${{ secrets.PYPI_USERNAME }}
|
||||
TWINE_PASSWORD: ${{ secrets.PYPI_PASSWORD }}
|
||||
run: |
|
||||
rm -rf dist/*
|
||||
python setup.py sdist bdist_wheel
|
||||
twine upload dist/*
|
||||
33
.github/workflows/quick-test.yml
vendored
33
.github/workflows/quick-test.yml
vendored
@@ -1,33 +0,0 @@
|
||||
name: Core Test
|
||||
on: [push, pull_request]
|
||||
jobs:
|
||||
tests:
|
||||
name: Core Tests
|
||||
if: "!contains(github.event.head_commit.message, 'skip ci all')"
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- uses: actions/checkout@v2
|
||||
- name: Set up Python 3.9
|
||||
uses: actions/setup-python@v2
|
||||
with:
|
||||
python-version: 3.9
|
||||
- name: Install nose
|
||||
run: pip install nose
|
||||
- name: Run tests
|
||||
env:
|
||||
YTDL_TEST_SET: core
|
||||
run: ./devscripts/run_tests.sh
|
||||
flake8:
|
||||
name: Linter
|
||||
if: "!contains(github.event.head_commit.message, 'skip ci all')"
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- uses: actions/checkout@v2
|
||||
- name: Set up Python
|
||||
uses: actions/setup-python@v2
|
||||
with:
|
||||
python-version: 3.9
|
||||
- name: Install flake8
|
||||
run: pip install flake8
|
||||
- name: Run flake8
|
||||
run: flake8 .
|
||||
1
.gitignore
vendored
1
.gitignore
vendored
@@ -46,7 +46,6 @@ updates_key.pem
|
||||
*.swf
|
||||
*.part
|
||||
*.ytdl
|
||||
*.conf
|
||||
*.swp
|
||||
*.spec
|
||||
test/local_parameters.json
|
||||
|
||||
14
AUTHORS-Fork
14
AUTHORS-Fork
@@ -1,18 +1,8 @@
|
||||
pukkandan (owner)
|
||||
pukkandan
|
||||
h-h-h-h
|
||||
pauldubois98
|
||||
nixxo
|
||||
GreyAlien502
|
||||
kyuyeunk
|
||||
siikamiika
|
||||
jbruchon
|
||||
alexmerkel
|
||||
glenn-slayden
|
||||
Unrud
|
||||
wporr
|
||||
mariuszskon
|
||||
ohnonot
|
||||
samiksome
|
||||
alxnull
|
||||
FelixFrog
|
||||
Zocker1999NET
|
||||
jbruchon
|
||||
146
Changelog.md
146
Changelog.md
@@ -1,146 +0,0 @@
|
||||
# Changelog
|
||||
|
||||
<!--
|
||||
# Instuctions for creating release
|
||||
|
||||
* Run `make doc`
|
||||
* Update Changelog.md and Authors-Fork
|
||||
* Commit to master as `Release <version>`
|
||||
* Push to origin/release - build task will now run
|
||||
* Update version.py and run `make issuetemplates`
|
||||
* Commit to master as `[version] update`
|
||||
* Push to origin/master
|
||||
* Update changelog in /releases
|
||||
|
||||
-->
|
||||
|
||||
|
||||
### 2021.01.16
|
||||
* Update to ytdl-2021.01.16
|
||||
* Portable configuration file: `./yt-dlp.conf`
|
||||
* Changes to configuration file paths. See [this](https://github.com/pukkandan/yt-dlp#configuration) for details
|
||||
* Add PyPI release
|
||||
|
||||
|
||||
### 2021.01.14
|
||||
* Added option `--break-on-reject`
|
||||
* [roosterteeth.com] Fix for bonus episodes by @Zocker1999NET
|
||||
* [tiktok] Fix for when share_info is empty
|
||||
* [EmbedThumbnail] Fix bug due to incorrect function name
|
||||
* [documentation] Changed sponskrub links to point to [pukkandan/sponskrub](https://github.com/pukkandan/SponSkrub) since I am now providing both linux and windows releases
|
||||
* [documentation] Change all links to correctly point to new fork URL
|
||||
* [documentation] Fixes typos
|
||||
|
||||
|
||||
### 2021.01.12
|
||||
* [roosterteeth.com] Add subtitle support by @samiksome
|
||||
* Added `--force-overwrites`, `--no-force-overwrites` by @alxnull
|
||||
* Changed fork name to `yt-dlp`
|
||||
* Fix typos by @FelixFrog
|
||||
* [ci] Option to skip
|
||||
* [changelog] Added unreleased changes in blackjack4494/yt-dlc
|
||||
|
||||
|
||||
### 2021.01.10
|
||||
* [archive.org] Fix extractor and add support for audio and playlists by @wporr
|
||||
* [Animelab] Added by @mariuszskon
|
||||
* [youtube:search] Fix view_count by @ohnonot
|
||||
* [youtube] Show if video is embeddable in info
|
||||
* Update version badge automatically in README
|
||||
* Enable `test_youtube_search_matching`
|
||||
* Create `to_screen` and similar functions in postprocessor/common
|
||||
|
||||
|
||||
### 2021.01.09
|
||||
* [youtube] Fix bug in automatic caption extraction
|
||||
* Add `post_hooks` to YoutubeDL by @alexmerkel
|
||||
* Batch file enumeration improvements by @glenn-slayden
|
||||
* Stop immediately when reaching `--max-downloads` by @glenn-slayden
|
||||
* Fix incorrect ANSI sequence for restoring console-window title by @glenn-slayden
|
||||
* Kill child processes when yt-dlc is killed by @Unrud
|
||||
|
||||
|
||||
### 2021.01.08
|
||||
* **Merge youtube-dl:** Upto [2021.01.08](https://github.com/ytdl-org/youtube-dl/commit/bf6a74c620bd4d5726503c5302906bb36b009026)
|
||||
* 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
|
||||
|
||||
|
||||
### 2021.01.07-1
|
||||
* [Akamai] fix by @nixxo
|
||||
* [Tiktok] merge youtube-dl tiktok extractor by @GreyAlien502
|
||||
* [vlive] add support for playlists by @kyuyeunk
|
||||
* [youtube_live_chat] make sure playerOffsetMs is positive by @siikamiika
|
||||
* Ignore extra data streams in ffmpeg by @jbruchon
|
||||
* Allow passing different arguments to different postprocessors using `--postprocessor-args`
|
||||
* Deprecated `--sponskrub-args`. The same can now be done using `--postprocessor-args "sponskrub:<args>"`
|
||||
* [CI] Split tests into core-test and full-test
|
||||
|
||||
|
||||
### 2021.01.07
|
||||
* Removed priority of `av01` codec in `-S` since most devices don't support it yet
|
||||
* Added `duration_string` to be used in `--output`
|
||||
* Created First Release
|
||||
|
||||
|
||||
### 2021.01.05-1
|
||||
* **Changed defaults:**
|
||||
* Enabled `--ignore`
|
||||
* Disabled `--video-multistreams` and `--audio-multistreams`
|
||||
* Changed default format selection to `bv*+ba/b` when `--audio-multistreams` is disabled
|
||||
* Changed default format sort order to `res,fps,codec,size,br,asr,proto,ext,has_audio,source,format_id`
|
||||
* Changed `webm` to be more preferable than `flv` in format sorting
|
||||
* Changed default output template to `%(title)s [%(id)s].%(ext)s`
|
||||
* Enabled `--list-formats-as-table`
|
||||
|
||||
|
||||
### 2021.01.05
|
||||
* **Format Sort:** Added `--format-sort` (`-S`), `--format-sort-force` (`--S-force`) - See [Sorting Formats](README.md#sorting-formats) for details
|
||||
* **Format Selection:** See [Format Selection](README.md#format-selection) for details
|
||||
* New format selectors: `best*`, `worst*`, `bestvideo*`, `bestaudio*`, `worstvideo*`, `worstaudio*`
|
||||
* Changed video format sorting to show video only files and video+audio files together.
|
||||
* Added `--video-multistreams`, `--no-video-multistreams`, `--audio-multistreams`, `--no-audio-multistreams`
|
||||
* Added `b`,`w`,`v`,`a` as alias for `best`, `worst`, `video` and `audio` respectively
|
||||
* **Shortcut Options:** Added `--write-link`, `--write-url-link`, `--write-webloc-link`, `--write-desktop-link` by @h-h-h-h - See [Internet Shortcut Options]README.md(#internet-shortcut-options) for details
|
||||
* **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 `--list-formats-as-table`, `--list-formats-old`
|
||||
* **Negative Options:** Makes it possible to negate most boolean options by adding a `no-` to the switch. Usefull when you want to reverse an option that is defined in a config file
|
||||
* Added `--no-ignore-dynamic-mpd`, `--no-allow-dynamic-mpd`, `--allow-dynamic-mpd`, `--youtube-include-hls-manifest`, `--no-youtube-include-hls-manifest`, `--no-youtube-skip-hls-manifest`, `--no-download`, `--no-download-archive`, `--resize-buffer`, `--part`, `--mtime`, `--no-keep-fragments`, `--no-cookies`, `--no-write-annotations`, `--no-write-info-json`, `--no-write-description`, `--no-write-thumbnail`, `--youtube-include-dash-manifest`, `--post-overwrites`, `--no-keep-video`, `--no-embed-subs`, `--no-embed-thumbnail`, `--no-add-metadata`, `--no-include-ads`, `--no-write-sub`, `--no-write-auto-sub`, `--no-playlist-reverse`, `--no-restrict-filenames`, `--youtube-include-dash-manifest`, `--no-format-sort-force`, `--flat-videos`, `--no-list-formats-as-table`, `--no-sponskrub`, `--no-sponskrub-cut`, `--no-sponskrub-force`
|
||||
* Renamed: `--write-subs`, `--no-write-subs`, `--no-write-auto-subs`, `--write-auto-subs`. Note that these can still be used without the ending "s"
|
||||
* Relaxed validation for format filters so that any arbitrary field can be used
|
||||
* Fix for embedding thumbnail in mp3 by @pauldubois98
|
||||
* Make Twitch Video ID output from Playlist and VOD extractor same. This is only a temporary fix
|
||||
* **Merge youtube-dl:** Upto [2021.01.03](https://github.com/ytdl-org/youtube-dl/commit/8e953dcbb10a1a42f4e12e4e132657cb0100a1f8) - See [blackjack4494/yt-dlc#280](https://github.com/blackjack4494/yt-dlc/pull/280) for details
|
||||
* Extractors [tiktok](https://github.com/ytdl-org/youtube-dl/commit/fb626c05867deab04425bad0c0b16b55473841a2) and [hotstar](https://github.com/ytdl-org/youtube-dl/commit/bb38a1215718cdf36d73ff0a7830a64cd9fa37cc) have not been merged
|
||||
* Cleaned up the fork for public use
|
||||
|
||||
|
||||
### Unreleased changes in [blackjack4494/yt-dlc](https://github.com/blackjack4494/yt-dlc)
|
||||
* Updated to youtube-dl release 2020.11.26
|
||||
* [youtube]
|
||||
* Implemented all Youtube Feeds (ytfav, ytwatchlater, ytsubs, ythistory, ytrec) and SearchURL
|
||||
* Fix ytsearch not returning results sometimes due to promoted content
|
||||
* Temporary fix for automatic captions - disable json3
|
||||
* Fix some improper Youtube URLs
|
||||
* Redirect channel home to /video
|
||||
* Print youtube's warning message
|
||||
* Multiple pages are handled better for feeds
|
||||
* Add --break-on-existing by @gergesh
|
||||
* Pre-check video IDs in the archive before downloading
|
||||
* [bitwave.tv] New extractor
|
||||
* [Gedi] Add extractor
|
||||
* [Rcs] Add new extractor
|
||||
* [skyit] Add support for multiple Sky Italia website and removed old skyitalia extractor
|
||||
* [france.tv] Fix thumbnail URL
|
||||
* [ina] support mobile links
|
||||
* [instagram] Fix extractor
|
||||
* [itv] BTCC new pages' URL update (articles instead of races)
|
||||
* [SouthparkDe] Support for English URLs
|
||||
* [spreaker] fix SpreakerShowIE test URL
|
||||
* [Vlive] Fix playlist handling when downloading a channel
|
||||
* [generic] Detect embedded bitchute videos
|
||||
* [generic] Extract embedded youtube and twitter videos
|
||||
* [ffmpeg] Ensure all streams are copied
|
||||
* Fix for os.rename error when embedding thumbnail to video in a different drive
|
||||
* make_win.bat: don't use UPX to pack vcruntime140.dll
|
||||
13
Makefile
13
Makefile
@@ -1,10 +1,8 @@
|
||||
all: youtube-dlc doc man
|
||||
all: youtube-dlc README.md CONTRIBUTING.md README.txt issuetemplates youtube-dlc.1 youtube-dlc.bash-completion youtube-dlc.zsh youtube-dlc.fish supportedsites
|
||||
doc: README.md CONTRIBUTING.md issuetemplates supportedsites
|
||||
man: README.txt youtube-dlc.1 youtube-dlc.bash-completion youtube-dlc.zsh youtube-dlc.fish
|
||||
|
||||
|
||||
clean:
|
||||
rm -rf youtube-dlc.1.temp.md youtube-dlc.1 youtube-dlc.bash-completion README.txt MANIFEST build/ dist/ .coverage cover/ youtube-dlc.tar.gz youtube-dlc.zsh youtube-dlc.fish youtube_dlc/extractor/lazy_extractors.py *.dump *.part* *.ytdl *.info.json *.mp4 *.m4a *.flv *.mp3 *.avi *.mkv *.webm *.3gp *.wav *.ape *.swf *.jpg *.png *.spec CONTRIBUTING.md.tmp youtube-dlc youtube-dlc.exe
|
||||
rm -rf youtube-dlc.1.temp.md youtube-dlc.1 youtube-dlc.bash-completion README.txt MANIFEST build/ dist/ .coverage cover/ youtube-dlc.tar.gz youtube-dlc.zsh youtube-dlc.fish youtube_dlc/extractor/lazy_extractors.py *.dump *.part* *.ytdl *.info.json *.mp4 *.m4a *.flv *.mp3 *.avi *.mkv *.webm *.3gp *.wav *.ape *.swf *.jpg *.png CONTRIBUTING.md.tmp youtube-dlc youtube-dlc.exe
|
||||
find . -name "*.pyc" -delete
|
||||
find . -name "*.class" -delete
|
||||
|
||||
@@ -12,8 +10,7 @@ PREFIX ?= /usr/local
|
||||
BINDIR ?= $(PREFIX)/bin
|
||||
MANDIR ?= $(PREFIX)/man
|
||||
SHAREDIR ?= $(PREFIX)/share
|
||||
# make_supportedsites.py doesnot work correctly in python2
|
||||
PYTHON ?= /usr/bin/env python3
|
||||
PYTHON ?= /usr/bin/env python
|
||||
|
||||
# set SYSCONFDIR to /etc if PREFIX=/usr or PREFIX=/usr/local
|
||||
SYSCONFDIR = $(shell if [ $(PREFIX) = /usr -o $(PREFIX) = /usr/local ]; then echo /etc; else echo $(PREFIX)/etc; fi)
|
||||
@@ -49,13 +46,11 @@ offlinetest: codetest
|
||||
--exclude test_age_restriction.py \
|
||||
--exclude test_download.py \
|
||||
--exclude test_iqiyi_sdk_interpreter.py \
|
||||
--exclude test_overwrites.py \
|
||||
--exclude test_socks.py \
|
||||
--exclude test_subtitles.py \
|
||||
--exclude test_write_annotations.py \
|
||||
--exclude test_youtube_lists.py \
|
||||
--exclude test_youtube_signature.py \
|
||||
--exclude test_post_hooks.py
|
||||
--exclude test_youtube_signature.py
|
||||
|
||||
tar: youtube-dlc.tar.gz
|
||||
|
||||
|
||||
188
README.md
188
README.md
@@ -1,19 +1,16 @@
|
||||
# YT-DLP
|
||||
[](https://github.com/pukkandan/yt-dlc/actions?query=workflow%3ACI)
|
||||
[](https://github.com/pukkandan/yt-dlc/releases/latest)
|
||||
[](https://github.com/pukkandan/yt-dlc/blob/master/LICENSE)
|
||||
|
||||
<!-- See: https://github.com/marketplace/actions/dynamic-badges -->
|
||||
[](https://github.com/pukkandan/yt-dlp/releases/latest)
|
||||
[](https://github.com/pukkandan/yt-dlp/blob/master/LICENSE)
|
||||
[](https://github.com/pukkandan/yt-dlp/actions?query=workflow%3ACore)
|
||||
[](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)
|
||||
youtube-dlc - download videos from youtube.com and many other [video platforms](docs/supportedsites.md)
|
||||
|
||||
This is a fork of [youtube-dlc](https://github.com/blackjack4494/yt-dlc) which is inturn a fork of [youtube-dl](https://github.com/ytdl-org/youtube-dl)
|
||||
|
||||
* [NEW FEATURES](#new-features)
|
||||
* [CHANGES FROM YOUTUBE-DLC](#changes)
|
||||
* [INSTALLATION](#installation)
|
||||
* [Update](#update)
|
||||
* [Compile](#compile)
|
||||
* [UPDATE](#update)
|
||||
* [COMPILE](#compile)
|
||||
* [YOUTUBE-DLC](#youtube-dlc)
|
||||
* [DESCRIPTION](#description)
|
||||
* [OPTIONS](#options)
|
||||
* [Network Options](#network-options)
|
||||
@@ -41,47 +38,69 @@ This is a fork of [youtube-dlc](https://github.com/blackjack4494/yt-dlc) which i
|
||||
* [Filtering Formats](#filtering-formats)
|
||||
* [Sorting Formats](#sorting-formats)
|
||||
* [Format Selection examples](#format-selection-examples)
|
||||
* [VIDEO SELECTION](#video-selection-1)
|
||||
* [MORE](#more)
|
||||
|
||||
|
||||
# NEW FEATURES
|
||||
The major new features from the latest release of [blackjack4494/yt-dlc](https://github.com/blackjack4494/yt-dlc) are:
|
||||
# CHANGES
|
||||
See [commits](https://github.com/pukkandan/yt-dlc/commits) for more details
|
||||
|
||||
* **[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
|
||||
### 2021.01.05
|
||||
* **Format Sort:** Added `--format-sort` (`-S`), `--format-sort-force` (`--S-force`) - See [Sorting Formats](#sorting-formats) for details
|
||||
* **Format Selection:** See [Format Selection](#format-selection) for details
|
||||
* New format selectors: `best*`, `worst*`, `bestvideo*`, `bestaudio*`, `worstvideo*`, `worstaudio*`
|
||||
* Changed video format sorting to show video only files and video+audio files together.
|
||||
* Added `--video-multistreams`, `--no-video-multistreams`, `--audio-multistreams`, `--no-audio-multistreams`
|
||||
* Added `b`,`w`,`v`,`a` as alias for `best`, `worst`, `video` and `audio` respectively
|
||||
* **Shortcut Options:** Added `--write-link`, `--write-url-link`, `--write-webloc-link`, `--write-desktop-link` by @h-h-h-h - See [Internet Shortcut Options](#internet-shortcut-options) for details
|
||||
* **Sponskrub integration:** Added `--sponskrub`, `--sponskrub-cut`, `--sponskrub-force`, `--sponskrub-location`, `--sponskrub-args` - See [SponSkrub Options](#sponskrub-options-sponsorblock) for details
|
||||
* Added `--force-download-archive` (`--force-write-archive`) by by h-h-h-h
|
||||
* Added `--list-formats-as-table`, `--list-formats-old`
|
||||
* **Negative Options:** Makes it possible to negate boolean options by adding a `no-` to the switch
|
||||
* Added `--no-ignore-dynamic-mpd`, `--no-allow-dynamic-mpd`, `--allow-dynamic-mpd`, `--youtube-include-hls-manifest`, `--no-youtube-include-hls-manifest`, `--no-youtube-skip-hls-manifest`, `--no-download`, `--no-download-archive`, `--resize-buffer`, `--part`, `--mtime`, `--no-keep-fragments`, `--no-cookies`, `--no-write-annotations`, `--no-write-info-json`, `--no-write-description`, `--no-write-thumbnail`, `--youtube-include-dash-manifest`, `--post-overwrites`, `--no-keep-video`, `--no-embed-subs`, `--no-embed-thumbnail`, `--no-add-metadata`, `--no-include-ads`, `--no-write-sub`, `--no-write-auto-sub`, `--no-playlist-reverse`, `--no-restrict-filenames`, `--youtube-include-dash-manifest`, `--no-format-sort-force`, `--flat-videos`, `--no-list-formats-as-table`, `--no-sponskrub`, `--no-sponskrub-cut`, `--no-sponskrub-force`
|
||||
* Renamed: `--write-subs`, `--no-write-subs`, `--no-write-auto-subs`, `--write-auto-subs`. Note that these can still be used without the ending "s"
|
||||
* Relaxed validation for format filters so that any arbitrary field can be used
|
||||
* Fix for embedding thumbnail in mp3 by @pauldubois98
|
||||
* Make Twitch Video ID output from Playlist and VOD extractor same. This is only a temporary fix
|
||||
* **Merge youtube-dl:** Upto [2020.01.03](https://github.com/ytdl-org/youtube-dl/commit/8e953dcbb10a1a42f4e12e4e132657cb0100a1f8) - See [blackjack4494/yt-dlc#280](https://github.com/blackjack4494/yt-dlc/pull/280) for details
|
||||
* Cleaned up the fork for public use
|
||||
|
||||
* **[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))
|
||||
### 2021.01.05-2
|
||||
* **Changed defaults:**
|
||||
* Enabled `--ignore`
|
||||
* Disabled `--video-multistreams` and `--audio-multistreams`
|
||||
* Changed default format selection to `bv*+ba/b` when `--audio-multistreams` is disabled
|
||||
* Changed default format sort order to `res,fps,codec,size,br,asr,proto,ext,has_audio,source,format_id`
|
||||
* Changed `webm` to be more preferable than `flv` in format sorting
|
||||
* Changed default output template to `%(title)s [%(id)s].%(ext)s`
|
||||
* Enabled `--list-formats-as-table`
|
||||
|
||||
* **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)
|
||||
### 2021.01.07
|
||||
* Removed priority of `av01` codec in `-S` since most devices don't support it yet
|
||||
* Added `duration_string` to be used in `--output`
|
||||
* Created First Release
|
||||
|
||||
* **Youtube improvements**:
|
||||
* All Youtube Feeds (`:ytfav`, `:ytwatchlater`, `:ytsubs`, `:ythistory`, `:ytrec`) works correctly and support downloading multiple pages of content
|
||||
* Youtube search works correctly (`ytsearch:`, `ytsearchdate:`) along with Search URLs
|
||||
* Redirect channel's home URL automatically to `/video` to preserve the old behaviour
|
||||
|
||||
* **New extractors**: AnimeLab, Philo MSO, Rcs, Gedi, bitwave.tv
|
||||
|
||||
* **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
|
||||
|
||||
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
|
||||
|
||||
|
||||
**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
|
||||
|
||||
If you are coming from [youtube-dl](https://github.com/ytdl-org/youtube-dl), the amount of changes are very large. Compare [options](#options) and [supported sites](docs/supportedsites.md) with youtube-dl's to get an idea of the massive number of features/patches [youtube-dlc](https://github.com/blackjack4494/yt-dlc) has accumulated.
|
||||
### 2021.01.07-2
|
||||
* [Akamai] fix by @nixxo
|
||||
* [Tiktok] fix extractor by @GreyAlien502
|
||||
* [vlive] add support for playlists by @kyuyeunk
|
||||
* [youtube_live_chat] make sure playerOffsetMs is positive by @siikamiika
|
||||
* Ignore extra data streams in ffmpeg by @jbruchon
|
||||
* Allow passing different arguments to different postprocessors using `--postprocessor-args`
|
||||
* Deprecated `--sponskrub-args`. The same can now be done using `--postprocessor-args "sponskrub:<args>"`
|
||||
|
||||
|
||||
# INSTALLATION
|
||||
|
||||
You can install yt-dlp using one of the following methods:
|
||||
* Use [PyPI package](https://pypi.org/project/yt-dlp/): `python -m pip install --upgrade yt-dlp`
|
||||
* Download the binary from the [latest release](https://github.com/pukkandan/yt-dlp/releases/latest)
|
||||
* Use pip+git: `python -m pip install --upgrade git+https://github.com/pukkandan/yt-dlp.git@release`
|
||||
* Install master branch: `python -m pip install --upgrade git+https://github.com/pukkandan/yt-dlp`
|
||||
To use the latest version, simply download and run the [latest release](https://github.com/pukkandan/yt-dlc/releases/latest).
|
||||
Currently, there is no support for any package managers.
|
||||
|
||||
If you want to install the current master branch
|
||||
|
||||
python -m pip install git+https://github.com/pukkandan/yt-dlc
|
||||
|
||||
### UPDATE
|
||||
`-U` does not work. Simply repeat the install process to update.
|
||||
**DO NOT UPDATE using `-U` !** instead download binaries again
|
||||
|
||||
### COMPILE
|
||||
|
||||
@@ -106,9 +125,9 @@ Then simply type this
|
||||
|
||||
|
||||
# DESCRIPTION
|
||||
**youtube-dlc** is a command-line program to download videos from youtube.com many other [video platforms](docs/supportedsites.md). It requires the Python interpreter, version 2.6, 2.7, or 3.2+, and it is not platform specific. It should work on your Unix box, on Windows or on macOS. It is released to the public domain, which means you can modify it, redistribute it or use it however you like.
|
||||
**youtube-dlc** is a command-line program to download videos from YouTube.com and a few more sites. It requires the Python interpreter, version 2.6, 2.7, or 3.2+, and it is not platform specific. It should work on your Unix box, on Windows or on macOS. It is released to the public domain, which means you can modify it, redistribute it or use it however you like.
|
||||
|
||||
youtube-dlc [OPTIONS] [--] URL [URL...]
|
||||
youtube-dlc [OPTIONS] URL [URL...]
|
||||
|
||||
|
||||
# OPTIONS
|
||||
@@ -141,14 +160,12 @@ Then simply type this
|
||||
an error. The default value "fixup_error"
|
||||
repairs broken URLs, but emits an error if
|
||||
this is not possible instead of searching.
|
||||
--ignore-config, --no-config Disable loading any configuration files
|
||||
except the one provided by --config-
|
||||
location. When given inside a configuration
|
||||
file, no further configuration files are
|
||||
loaded. Additionally, (for backward
|
||||
compatibility) if this option is found
|
||||
inside the system configuration file, the
|
||||
user configuration is not loaded.
|
||||
--ignore-config, --no-config Do not read configuration files. When given
|
||||
in the global configuration file
|
||||
/etc/youtube-dl.conf: Do not read the user
|
||||
configuration in ~/.config/youtube-
|
||||
dl/config (%APPDATA%/youtube-dl/config.txt
|
||||
on Windows)
|
||||
--config-location PATH Location of the configuration file; either
|
||||
the path to the config or its containing
|
||||
directory.
|
||||
@@ -250,10 +267,8 @@ Then simply type this
|
||||
--download-archive FILE Download only videos not listed in the
|
||||
archive file. Record the IDs of all
|
||||
downloaded videos in it.
|
||||
--break-on-existing Stop the download process when encountering
|
||||
a file that's in the archive.
|
||||
--break-on-reject Stop the download process when encountering
|
||||
a file that has been filtered out.
|
||||
--break-on-existing Stop the download process after attempting
|
||||
to download a file that's in the archive.
|
||||
--no-download-archive Do not use archive file (default)
|
||||
--include-ads Download advertisements as well
|
||||
(experimental)
|
||||
@@ -321,11 +336,7 @@ Then simply type this
|
||||
filenames
|
||||
--no-restrict-filenames Allow Unicode characters, "&" and spaces in
|
||||
filenames (default)
|
||||
-w, --no-overwrites Do not overwrite any files
|
||||
--force-overwrites Overwrite all video and metadata files.
|
||||
This option includes --no-continue
|
||||
--no-force-overwrites Do not overwrite the video, but overwrite
|
||||
related files (default)
|
||||
-w, --no-overwrites Do not overwrite files
|
||||
-c, --continue Resume partially downloaded files (default)
|
||||
--no-continue Restart download of partially downloaded
|
||||
files from beginning
|
||||
@@ -418,8 +429,7 @@ Then simply type this
|
||||
files in the current directory to debug
|
||||
problems
|
||||
--print-traffic Display sent and read HTTP traffic
|
||||
-C, --call-home [Broken] Contact the youtube-dlc server for
|
||||
debugging
|
||||
-C, --call-home Contact the youtube-dlc server for debugging
|
||||
--no-call-home Do not contact the youtube-dlc server for
|
||||
debugging (default)
|
||||
|
||||
@@ -470,8 +480,8 @@ Then simply type this
|
||||
--no-audio-multistreams Only one audio stream is downloaded for
|
||||
each output file (default)
|
||||
--all-formats Download all available video formats
|
||||
--prefer-free-formats Prefer free video formats over non-free
|
||||
formats of same quality
|
||||
--prefer-free-formats Prefer free video formats unless a specific
|
||||
one is requested
|
||||
-F, --list-formats List all available formats of requested
|
||||
videos
|
||||
--list-formats-as-table Present the output of -F in a more tabular
|
||||
@@ -558,10 +568,9 @@ Then simply type this
|
||||
ExtractAudio, VideoRemuxer, VideoConvertor,
|
||||
EmbedSubtitle, Metadata, Merger,
|
||||
FixupStretched, FixupM4a, FixupM3u8,
|
||||
SubtitlesConvertor, EmbedThumbnail,
|
||||
XAttrMetadata, SponSkrub and Default. You
|
||||
can use this option multiple times to give
|
||||
different arguments to different
|
||||
SubtitlesConvertor, SponSkrub and Default.
|
||||
You can use this option multiple times to
|
||||
give different arguments to different
|
||||
postprocessors
|
||||
-k, --keep-video Keep the intermediate video file on disk
|
||||
after post-processing
|
||||
@@ -608,7 +617,7 @@ Then simply type this
|
||||
--convert-subs FORMAT Convert the subtitles to other format
|
||||
(currently supported: srt|ass|vtt|lrc)
|
||||
|
||||
## [SponSkrub](https://github.com/pukkandan/SponSkrub) Options ([SponsorBlock](https://sponsor.ajay.app)):
|
||||
## [SponSkrub](https://github.com/faissaloo/SponSkrub) Options ([SponsorBlock](https://sponsor.ajay.app)):
|
||||
--sponskrub Use sponskrub to mark sponsored sections
|
||||
with the data available in SponsorBlock
|
||||
API. This is enabled by default if the
|
||||
@@ -625,6 +634,7 @@ Then simply type this
|
||||
--sponskrub-location PATH Location of the sponskrub binary; either
|
||||
the path to the binary or its containing
|
||||
directory.
|
||||
--sponskrub-args None Give these arguments to sponskrub
|
||||
|
||||
## Extractor Options:
|
||||
--ignore-dynamic-mpd Do not process dynamic DASH manifests
|
||||
@@ -634,22 +644,9 @@ Then simply type this
|
||||
|
||||
# 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. On Linux and macOS, the system wide configuration file is located at `/etc/youtube-dlc.conf` and the user wide configuration file at `~/.config/youtube-dlc/config`. On Windows, the user wide configuration file locations are `%APPDATA%\youtube-dlc\config.txt` or `C:\Users\<user name>\youtube-dlc.conf`. Note that by default configuration file may not exist so you may need to create it yourself.
|
||||
|
||||
1. 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. **User Configuration**:
|
||||
* `%XDG_CONFIG_HOME%/yt-dlp/config` (recommended on Linux/macOS)
|
||||
* `%XDG_CONFIG_HOME%/yt-dlp.conf`
|
||||
* `%APPDATA%/yt-dlp/config` (recommended on Windows)
|
||||
* `%APPDATA%/yt-dlp/config.txt`
|
||||
* `~/yt-dlp.conf`
|
||||
* `~/yt-dlp.conf.txt`
|
||||
|
||||
If none of these files are found, the search is performed again by replacing `yt-dlp` with `youtube-dlc`. Note that `~` points to `C:\Users\<user name>` on windows. Also, `%XDG_CONFIG_HOME%` defaults to `~/.config` if undefined
|
||||
1. **System Configuration**: `/etc/yt-dlp.conf` or `/etc/youtube-dlc.conf`
|
||||
|
||||
For example, with the following configuration file youtube-dlc will always extract the audio, not copy the mtime, use a proxy and save all videos under `YouTube` directory in your home directory:
|
||||
For example, with the following configuration file youtube-dlc will always extract the audio, not copy the mtime, use a proxy and save all videos under `Movies` directory in your home directory:
|
||||
```
|
||||
# Lines starting with # are comments
|
||||
|
||||
@@ -662,13 +659,15 @@ For example, with the following configuration file youtube-dlc will always extra
|
||||
# Use this proxy
|
||||
--proxy 127.0.0.1:3128
|
||||
|
||||
# Save all videos under YouTube directory in your home directory
|
||||
-o ~/YouTube/%(title)s.%(ext)s
|
||||
# Save all videos under Movies directory in your home directory
|
||||
-o ~/Movies/%(title)s.%(ext)s
|
||||
```
|
||||
|
||||
Note that options in configuration file are just the same options aka switches used in regular command line calls; thus there **must be no whitespace** after `-` or `--`, e.g. `-o` or `--proxy` but not `- o` or `-- proxy`.
|
||||
Note that options in configuration file are just the same options aka switches used in regular command line calls thus there **must be no whitespace** after `-` or `--`, e.g. `-o` or `--proxy` but not `- o` or `-- proxy`.
|
||||
|
||||
You can use `--ignore-config` if you want to disable all configuration files for a particular youtube-dlc run. If `--ignore-config` is found inside any configuration file, no further configuration will be loaded. For example, having the option in the portable configuration file prevents loading of user and system configurations. Additionally, (for backward compatibility) if `--ignore-config` is found inside the system configuration file, the user configuration is not loaded.
|
||||
You can use `--ignore-config` if you want to disable the configuration file for a particular youtube-dlc run.
|
||||
|
||||
You can also use `--config-location` if you want to use custom configuration file for a particular youtube-dlc run.
|
||||
|
||||
### Authentication with `.netrc` file
|
||||
|
||||
@@ -954,17 +953,9 @@ $ youtube-dlc -f 'bv*+ba/b'
|
||||
# Same as above
|
||||
$ youtube-dlc
|
||||
|
||||
# Download the best video-only format and the best audio-only format without merging them
|
||||
# For this case, an output template should be used since
|
||||
# by default, bestvideo and bestaudio will have the same file name.
|
||||
$ youtube-dlc -f 'bv,ba' -o '%(title)s.f%(format_id)s.%(ext)s'
|
||||
|
||||
|
||||
|
||||
# The following examples show the old method (without -S) of format selection
|
||||
# and how to use -S to achieve a similar but better result
|
||||
|
||||
# Download the worst video available (old method)
|
||||
# Download the worst video available
|
||||
$ youtube-dlc -f 'wv*+wa/w'
|
||||
|
||||
# Download the best video available but with the smallest resolution
|
||||
@@ -1023,6 +1014,13 @@ $ youtube-dlc -S 'protocol'
|
||||
|
||||
|
||||
|
||||
# Download the best video-only format and the best audio-only format without merging them
|
||||
# For this case, an output template should be used since
|
||||
# by default, bestvideo and bestaudio will have the same file name.
|
||||
$ youtube-dlc -f 'bv,ba' -o '%(title)s.f%(format_id)s.%(ext)s'
|
||||
|
||||
|
||||
|
||||
# Download the best video with h264 codec, or the best video if there is no such video
|
||||
$ youtube-dlc -f '(bv*+ba/b)[vcodec^=avc1] / (bv*+ba/b)'
|
||||
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
@echo off
|
||||
|
||||
rem Keep this list in sync with the `offlinetest` target in Makefile
|
||||
set DOWNLOAD_TESTS="age_restriction^|download^|iqiyi_sdk_interpreter^|socks^|subtitles^|write_annotations^|youtube_lists^|youtube_signature^|post_hooks"
|
||||
set DOWNLOAD_TESTS="age_restriction^|download^|iqiyi_sdk_interpreter^|socks^|subtitles^|write_annotations^|youtube_lists^|youtube_signature"
|
||||
|
||||
if "%YTDL_TEST_SET%" == "core" (
|
||||
set test_set="-I test_("%DOWNLOAD_TESTS%")\.py"
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
#!/bin/bash
|
||||
|
||||
# Keep this list in sync with the `offlinetest` target in Makefile
|
||||
DOWNLOAD_TESTS="age_restriction|download|iqiyi_sdk_interpreter|overwrites|socks|subtitles|write_annotations|youtube_lists|youtube_signature|post_hooks"
|
||||
DOWNLOAD_TESTS="age_restriction|download|iqiyi_sdk_interpreter|socks|subtitles|write_annotations|youtube_lists|youtube_signature"
|
||||
|
||||
test_set=""
|
||||
multiprocess_args=""
|
||||
|
||||
@@ -48,8 +48,6 @@
|
||||
- **AMCNetworks**
|
||||
- **AmericasTestKitchen**
|
||||
- **anderetijden**: npo.nl, ntr.nl, omroepwnl.nl, zapp.nl and npo3.nl
|
||||
- **AnimeLab**
|
||||
- **AnimeLabShows**
|
||||
- **AnimeOnDemand**
|
||||
- **Anvato**
|
||||
- **aol.com**
|
||||
@@ -57,10 +55,9 @@
|
||||
- **Aparat**
|
||||
- **AppleConnect**
|
||||
- **AppleDaily**: 臺灣蘋果日報
|
||||
- **ApplePodcasts**
|
||||
- **appletrailers**
|
||||
- **appletrailers:section**
|
||||
- **archive.org**: archive.org video and audio
|
||||
- **archive.org**: archive.org videos
|
||||
- **ArcPublishing**
|
||||
- **ARD**
|
||||
- **ARD:mediathek**
|
||||
@@ -102,10 +99,6 @@
|
||||
- **BellMedia**
|
||||
- **Bet**
|
||||
- **bfi:player**
|
||||
- **bfmtv**
|
||||
- **bfmtv:article**
|
||||
- **bfmtv:live**
|
||||
- **BibelTV**
|
||||
- **Bigflix**
|
||||
- **Bild**: Bild.de
|
||||
- **BiliBili**
|
||||
@@ -353,8 +346,6 @@
|
||||
- **Go**
|
||||
- **GodTube**
|
||||
- **Golem**
|
||||
- **google:podcasts**
|
||||
- **google:podcasts:feed**
|
||||
- **GoogleDrive**
|
||||
- **Goshgay**
|
||||
- **GPUTechConf**
|
||||
@@ -390,8 +381,6 @@
|
||||
- **HungamaSong**
|
||||
- **Hypem**
|
||||
- **ign.com**
|
||||
- **IHeartRadio**
|
||||
- **iheartradio:podcast**
|
||||
- **imdb**: Internet Movie Database trailers
|
||||
- **imdb:list**: Internet Movie Database lists
|
||||
- **Imgur**
|
||||
@@ -431,8 +420,7 @@
|
||||
- **Katsomo**
|
||||
- **KeezMovies**
|
||||
- **Ketnet**
|
||||
- **khanacademy**
|
||||
- **khanacademy:unit**
|
||||
- **KhanAcademy**
|
||||
- **KickStarter**
|
||||
- **KinjaEmbed**
|
||||
- **KinoPoisk**
|
||||
@@ -718,6 +706,7 @@
|
||||
- **Playwire**
|
||||
- **pluralsight**
|
||||
- **pluralsight:course**
|
||||
- **plus.google**: Google Plus
|
||||
- **podomatic**
|
||||
- **Pokemon**
|
||||
- **PokemonWatch**
|
||||
@@ -1157,7 +1146,7 @@
|
||||
- **WWE**
|
||||
- **XBef**
|
||||
- **XboxClips**
|
||||
- **XFileShare**: XFileShare based sites: Aparat, ClipWatching, GoUnlimited, GoVid, HolaVid, Streamty, TheVideoBee, Uqload, VidBom, vidlo, VidLocker, VidShare, VUp, XVideoSharing
|
||||
- **XFileShare**: XFileShare based sites: ClipWatching, GoUnlimited, GoVid, HolaVid, Streamty, TheVideoBee, Uqload, VidBom, vidlo, VidLocker, VidShare, VUp, XVideoSharing
|
||||
- **XHamster**
|
||||
- **XHamsterEmbed**
|
||||
- **XHamsterUser**
|
||||
|
||||
@@ -74,7 +74,7 @@ version_file = VSVersionInfo(
|
||||
),
|
||||
StringStruct("OriginalFilename", "youtube-dlc.exe"),
|
||||
StringStruct("ProductName", "Youtube-dlc"),
|
||||
StringStruct("ProductVersion", version + " | git.io/JLh7K"),
|
||||
StringStruct("ProductVersion", version + " | git.io/JUGsM"),
|
||||
],
|
||||
)
|
||||
]
|
||||
|
||||
28
setup.py
28
setup.py
@@ -11,12 +11,8 @@ from distutils.spawn import spawn
|
||||
exec(compile(open('youtube_dlc/version.py').read(),
|
||||
'youtube_dlc/version.py', 'exec'))
|
||||
|
||||
DESCRIPTION = 'Command-line program to download videos from YouTube.com and many other other video platforms.'
|
||||
|
||||
LONG_DESCRIPTION = '\n\n'.join((
|
||||
'Official repository: <https://github.com/pukkandan/yt-dlp>',
|
||||
'**PS**: Many links in this document will not work since this is a copy of the README.md from Github',
|
||||
open("README.md", "r", encoding="utf-8").read()))
|
||||
DESCRIPTION = 'Media downloader supporting various sites such as youtube'
|
||||
LONG_DESCRIPTION = 'Command-line program to download videos from YouTube.com and other video sites. Based on a more active community fork.'
|
||||
|
||||
if len(sys.argv) >= 2 and sys.argv[1] == 'py2exe':
|
||||
print("inv")
|
||||
@@ -63,21 +59,19 @@ class build_lazy_extractors(Command):
|
||||
)
|
||||
|
||||
setup(
|
||||
name="yt-dlp",
|
||||
name="youtube_dlc",
|
||||
version=__version__,
|
||||
maintainer="pukkandan",
|
||||
maintainer_email="pukkandan@gmail.com",
|
||||
maintainer="Tom-Oliver Heidel",
|
||||
maintainer_email="theidel@uni-bremen.de",
|
||||
description=DESCRIPTION,
|
||||
long_description=LONG_DESCRIPTION,
|
||||
long_description_content_type="text/markdown",
|
||||
url="https://github.com/pukkandan/yt-dlp",
|
||||
# long_description_content_type="text/markdown",
|
||||
url="https://github.com/pukkandan/yt-dlc",
|
||||
packages=find_packages(exclude=("youtube_dl","test",)),
|
||||
project_urls={
|
||||
'Documentation': 'https://github.com/pukkandan/yt-dlp#yt-dlp',
|
||||
'Source': 'https://github.com/pukkandan/yt-dlp',
|
||||
'Tracker': 'https://github.com/pukkandan/yt-dlp/issues',
|
||||
#'Funding': 'https://donate.pypi.org',
|
||||
},
|
||||
#packages=[
|
||||
# 'youtube_dlc',
|
||||
# 'youtube_dlc.extractor', 'youtube_dlc.downloader',
|
||||
# 'youtube_dlc.postprocessor'],
|
||||
classifiers=[
|
||||
"Topic :: Multimedia :: Video",
|
||||
"Development Status :: 5 - Production/Stable",
|
||||
|
||||
@@ -14,7 +14,7 @@
|
||||
"logtostderr": false,
|
||||
"matchtitle": null,
|
||||
"max_downloads": null,
|
||||
"overwrites": null,
|
||||
"nooverwrites": false,
|
||||
"nopart": false,
|
||||
"noprogress": false,
|
||||
"outtmpl": "%(id)s.%(ext)s",
|
||||
|
||||
@@ -69,9 +69,9 @@ class TestAllURLsMatching(unittest.TestCase):
|
||||
self.assertMatch('https://www.youtube.com/feed/watch_later', ['youtube:tab'])
|
||||
self.assertMatch('https://www.youtube.com/feed/subscriptions', ['youtube:tab'])
|
||||
|
||||
def test_youtube_search_matching(self):
|
||||
self.assertMatch('http://www.youtube.com/results?search_query=making+mustard', ['youtube:search_url'])
|
||||
self.assertMatch('https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video', ['youtube:search_url'])
|
||||
# def test_youtube_search_matching(self):
|
||||
# self.assertMatch('http://www.youtube.com/results?search_query=making+mustard', ['youtube:search_url'])
|
||||
# self.assertMatch('https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video', ['youtube:search_url'])
|
||||
|
||||
def test_youtube_extract(self):
|
||||
assertExtractId = lambda url, id: self.assertEqual(YoutubeIE.extract_id(url), id)
|
||||
|
||||
@@ -1,52 +0,0 @@
|
||||
#!/usr/bin/env python
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import os
|
||||
from os.path import join
|
||||
import subprocess
|
||||
import sys
|
||||
import unittest
|
||||
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
|
||||
|
||||
from test.helper import try_rm
|
||||
|
||||
|
||||
root_dir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
|
||||
download_file = join(root_dir, 'test.webm')
|
||||
|
||||
|
||||
class TestOverwrites(unittest.TestCase):
|
||||
def setUp(self):
|
||||
# create an empty file
|
||||
open(download_file, 'a').close()
|
||||
|
||||
def test_default_overwrites(self):
|
||||
outp = subprocess.Popen(
|
||||
[
|
||||
sys.executable, 'youtube_dlc/__main__.py',
|
||||
'-o', 'test.webm',
|
||||
'https://www.youtube.com/watch?v=jNQXAC9IVRw'
|
||||
], cwd=root_dir, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
|
||||
sout, serr = outp.communicate()
|
||||
self.assertTrue(b'has already been downloaded' in sout)
|
||||
# if the file has no content, it has not been redownloaded
|
||||
self.assertTrue(os.path.getsize(download_file) < 1)
|
||||
|
||||
def test_yes_overwrites(self):
|
||||
outp = subprocess.Popen(
|
||||
[
|
||||
sys.executable, 'youtube_dlc/__main__.py', '--yes-overwrites',
|
||||
'-o', 'test.webm',
|
||||
'https://www.youtube.com/watch?v=jNQXAC9IVRw'
|
||||
], cwd=root_dir, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
|
||||
sout, serr = outp.communicate()
|
||||
self.assertTrue(b'has already been downloaded' not in sout)
|
||||
# if the file has no content, it has not been redownloaded
|
||||
self.assertTrue(os.path.getsize(download_file) > 1)
|
||||
|
||||
def tearDown(self):
|
||||
try_rm(join(root_dir, 'test.webm'))
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
unittest.main()
|
||||
@@ -1,68 +0,0 @@
|
||||
#!/usr/bin/env python
|
||||
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import os
|
||||
import sys
|
||||
import unittest
|
||||
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
|
||||
|
||||
from test.helper import get_params, try_rm
|
||||
import youtube_dl.YoutubeDL
|
||||
from youtube_dl.utils import DownloadError
|
||||
|
||||
|
||||
class YoutubeDL(youtube_dl.YoutubeDL):
|
||||
def __init__(self, *args, **kwargs):
|
||||
super(YoutubeDL, self).__init__(*args, **kwargs)
|
||||
self.to_stderr = self.to_screen
|
||||
|
||||
|
||||
TEST_ID = 'gr51aVj-mLg'
|
||||
EXPECTED_NAME = 'gr51aVj-mLg'
|
||||
|
||||
|
||||
class TestPostHooks(unittest.TestCase):
|
||||
def setUp(self):
|
||||
self.stored_name_1 = None
|
||||
self.stored_name_2 = None
|
||||
self.params = get_params({
|
||||
'skip_download': False,
|
||||
'writeinfojson': False,
|
||||
'quiet': True,
|
||||
'verbose': False,
|
||||
'cachedir': False,
|
||||
})
|
||||
self.files = []
|
||||
|
||||
def test_post_hooks(self):
|
||||
self.params['post_hooks'] = [self.hook_one, self.hook_two]
|
||||
ydl = YoutubeDL(self.params)
|
||||
ydl.download([TEST_ID])
|
||||
self.assertEqual(self.stored_name_1, EXPECTED_NAME, 'Not the expected name from hook 1')
|
||||
self.assertEqual(self.stored_name_2, EXPECTED_NAME, 'Not the expected name from hook 2')
|
||||
|
||||
def test_post_hook_exception(self):
|
||||
self.params['post_hooks'] = [self.hook_three]
|
||||
ydl = YoutubeDL(self.params)
|
||||
self.assertRaises(DownloadError, ydl.download, [TEST_ID])
|
||||
|
||||
def hook_one(self, filename):
|
||||
self.stored_name_1, _ = os.path.splitext(os.path.basename(filename))
|
||||
self.files.append(filename)
|
||||
|
||||
def hook_two(self, filename):
|
||||
self.stored_name_2, _ = os.path.splitext(os.path.basename(filename))
|
||||
self.files.append(filename)
|
||||
|
||||
def hook_three(self, filename):
|
||||
self.files.append(filename)
|
||||
raise Exception('Test exception for \'%s\'' % filename)
|
||||
|
||||
def tearDown(self):
|
||||
for f in self.files:
|
||||
try_rm(f)
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
unittest.main()
|
||||
@@ -264,24 +264,16 @@ class TestNRKSubtitles(BaseTestSubtitles):
|
||||
|
||||
|
||||
class TestRaiPlaySubtitles(BaseTestSubtitles):
|
||||
url = 'http://www.raiplay.it/video/2014/04/Report-del-07042014-cb27157f-9dd0-4aee-b788-b1f67643a391.html'
|
||||
IE = RaiPlayIE
|
||||
|
||||
def test_subtitles_key(self):
|
||||
self.url = 'http://www.raiplay.it/video/2014/04/Report-del-07042014-cb27157f-9dd0-4aee-b788-b1f67643a391.html'
|
||||
def test_allsubtitles(self):
|
||||
self.DL.params['writesubtitles'] = True
|
||||
self.DL.params['allsubtitles'] = True
|
||||
subtitles = self.getSubtitles()
|
||||
self.assertEqual(set(subtitles.keys()), set(['it']))
|
||||
self.assertEqual(md5(subtitles['it']), 'b1d90a98755126b61e667567a1f6680a')
|
||||
|
||||
def test_subtitles_array_key(self):
|
||||
self.url = 'https://www.raiplay.it/video/2020/12/Report---04-01-2021-2e90f1de-8eee-4de4-ac0e-78d21db5b600.html'
|
||||
self.DL.params['writesubtitles'] = True
|
||||
self.DL.params['allsubtitles'] = True
|
||||
subtitles = self.getSubtitles()
|
||||
self.assertEqual(set(subtitles.keys()), set(['it']))
|
||||
self.assertEqual(md5(subtitles['it']), '4b3264186fbb103508abe5311cfcb9cd')
|
||||
|
||||
|
||||
class TestVikiSubtitles(BaseTestSubtitles):
|
||||
url = 'http://www.viki.com/videos/1060846v-punch-episode-18'
|
||||
|
||||
@@ -21,7 +21,6 @@ from youtube_dlc.utils import (
|
||||
encode_base_n,
|
||||
caesar,
|
||||
clean_html,
|
||||
clean_podcast_url,
|
||||
date_from_str,
|
||||
DateRange,
|
||||
detect_exe_version,
|
||||
@@ -1498,10 +1497,6 @@ Line 1
|
||||
iri_to_uri('http://导航.中国/'),
|
||||
'http://xn--fet810g.xn--fiqs8s/')
|
||||
|
||||
def test_clean_podcast_url(self):
|
||||
self.assertEqual(clean_podcast_url('https://www.podtrac.com/pts/redirect.mp3/chtbl.com/track/5899E/traffic.megaphone.fm/HSW7835899191.mp3'), 'https://traffic.megaphone.fm/HSW7835899191.mp3')
|
||||
self.assertEqual(clean_podcast_url('https://play.podtrac.com/npr-344098539/edge1.pod.npr.org/anon.npr-podcasts/podcast/npr/waitwait/2020/10/20201003_waitwait_wwdtmpodcast201003-015621a5-f035-4eca-a9a1-7c118d90bc3c.mp3'), 'https://edge1.pod.npr.org/anon.npr-podcasts/podcast/npr/waitwait/2020/10/20201003_waitwait_wwdtmpodcast201003-015621a5-f035-4eca-a9a1-7c118d90bc3c.mp3')
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
unittest.main()
|
||||
|
||||
@@ -1 +1 @@
|
||||
py "%~dp0youtube_dlc\__main__.py" %*
|
||||
py "%~dp0\youtube_dl\__main__.py"
|
||||
@@ -58,7 +58,6 @@ from .utils import (
|
||||
encode_compat_str,
|
||||
encodeFilename,
|
||||
error_to_compat_str,
|
||||
ExistingVideoReached,
|
||||
expand_path,
|
||||
ExtractorError,
|
||||
format_bytes,
|
||||
@@ -82,7 +81,6 @@ from .utils import (
|
||||
register_socks_protocols,
|
||||
render_table,
|
||||
replace_extension,
|
||||
RejectedVideoReached,
|
||||
SameFileError,
|
||||
sanitize_filename,
|
||||
sanitize_path,
|
||||
@@ -101,7 +99,6 @@ from .utils import (
|
||||
YoutubeDLCookieProcessor,
|
||||
YoutubeDLHandler,
|
||||
YoutubeDLRedirectHandler,
|
||||
process_communicate_or_kill,
|
||||
)
|
||||
from .cache import Cache
|
||||
from .extractor import get_info_extractor, gen_extractor_classes, _LAZY_LOADER
|
||||
@@ -181,11 +178,9 @@ class YoutubeDL(object):
|
||||
outtmpl: Template for output names.
|
||||
restrictfilenames: Do not allow "&" and spaces in file names.
|
||||
trim_file_name: Limit length of filename (extension excluded).
|
||||
ignoreerrors: Do not stop on download errors. (Default True when running youtube-dlc, but False when directly accessing YoutubeDL class)
|
||||
ignoreerrors: Do not stop on download errors. (Default False when running youtube-dlc, but True when directly accessing YoutubeDL class)
|
||||
force_generic_extractor: Force downloader to use the generic extractor
|
||||
overwrites: Overwrite all video and metadata files if True,
|
||||
overwrite only non-video files if None
|
||||
and don't overwrite any file if False
|
||||
nooverwrites: Prevent overwriting files.
|
||||
playliststart: Playlist item to start at.
|
||||
playlistend: Playlist item to end at.
|
||||
playlist_items: Specific indices of playlist to download.
|
||||
@@ -234,7 +229,6 @@ class YoutubeDL(object):
|
||||
again.
|
||||
break_on_existing: Stop the download process after attempting to download a file that's
|
||||
in the archive.
|
||||
break_on_reject: Stop the download process when encountering a video that has been filtered out.
|
||||
cookiefile: File name where cookies should be read from and dumped to.
|
||||
nocheckcertificate:Do not verify SSL certificates
|
||||
prefer_insecure: Use HTTP instead of HTTPS to retrieve information.
|
||||
@@ -258,9 +252,6 @@ class YoutubeDL(object):
|
||||
youtube_dlc/postprocessor/__init__.py for a list.
|
||||
as well as any further keyword arguments for the
|
||||
postprocessor.
|
||||
post_hooks: A list of functions that get called as the final step
|
||||
for each video file, after all postprocessors have been
|
||||
called. The filename will be passed as the only argument.
|
||||
progress_hooks: A list of functions that get called on download
|
||||
progress, with a dictionary with the entries
|
||||
* status: One of "downloading", "error", or "finished".
|
||||
@@ -369,8 +360,6 @@ class YoutubeDL(object):
|
||||
_pps = []
|
||||
_download_retcode = None
|
||||
_num_downloads = None
|
||||
_playlist_level = 0
|
||||
_playlist_urls = set()
|
||||
_screen_file = None
|
||||
|
||||
def __init__(self, params=None, auto_init=True):
|
||||
@@ -380,7 +369,6 @@ class YoutubeDL(object):
|
||||
self._ies = []
|
||||
self._ies_instances = {}
|
||||
self._pps = []
|
||||
self._post_hooks = []
|
||||
self._progress_hooks = []
|
||||
self._download_retcode = 0
|
||||
self._num_downloads = 0
|
||||
@@ -484,9 +472,6 @@ class YoutubeDL(object):
|
||||
pp = pp_class(self, **compat_kwargs(pp_def))
|
||||
self.add_post_processor(pp)
|
||||
|
||||
for ph in self.params.get('post_hooks', []):
|
||||
self.add_post_hook(ph)
|
||||
|
||||
for ph in self.params.get('progress_hooks', []):
|
||||
self.add_progress_hook(ph)
|
||||
|
||||
@@ -539,10 +524,6 @@ class YoutubeDL(object):
|
||||
self._pps.append(pp)
|
||||
pp.set_downloader(self)
|
||||
|
||||
def add_post_hook(self, ph):
|
||||
"""Add the post hook"""
|
||||
self._post_hooks.append(ph)
|
||||
|
||||
def add_progress_hook(self, ph):
|
||||
"""Add the progress hook (currently only for the file downloader)"""
|
||||
self._progress_hooks.append(ph)
|
||||
@@ -597,7 +578,7 @@ class YoutubeDL(object):
|
||||
# already of type unicode()
|
||||
ctypes.windll.kernel32.SetConsoleTitleW(ctypes.c_wchar_p(message))
|
||||
elif 'TERM' in os.environ:
|
||||
self._write_string('\033[0;%s\007' % message, self._screen_file)
|
||||
self._write_string('\033]0;%s\007' % message, self._screen_file)
|
||||
|
||||
def save_console_title(self):
|
||||
if not self.params.get('consoletitle', False):
|
||||
@@ -693,13 +674,6 @@ class YoutubeDL(object):
|
||||
except UnicodeEncodeError:
|
||||
self.to_screen('[download] The file has already been downloaded')
|
||||
|
||||
def report_file_delete(self, file_name):
|
||||
"""Report that existing file will be deleted."""
|
||||
try:
|
||||
self.to_screen('Deleting already existent file %s' % file_name)
|
||||
except UnicodeEncodeError:
|
||||
self.to_screen('Deleting already existent file')
|
||||
|
||||
def prepare_filename(self, info_dict):
|
||||
"""Generate the output filename."""
|
||||
try:
|
||||
@@ -802,53 +776,44 @@ class YoutubeDL(object):
|
||||
def _match_entry(self, info_dict, incomplete):
|
||||
""" Returns None if the file should be downloaded """
|
||||
|
||||
def check_filter():
|
||||
video_title = info_dict.get('title', info_dict.get('id', 'video'))
|
||||
if 'title' in info_dict:
|
||||
# This can happen when we're just evaluating the playlist
|
||||
title = info_dict['title']
|
||||
matchtitle = self.params.get('matchtitle', False)
|
||||
if matchtitle:
|
||||
if not re.search(matchtitle, title, re.IGNORECASE):
|
||||
return '"' + title + '" title did not match pattern "' + matchtitle + '"'
|
||||
rejecttitle = self.params.get('rejecttitle', False)
|
||||
if rejecttitle:
|
||||
if re.search(rejecttitle, title, re.IGNORECASE):
|
||||
return '"' + title + '" title matched reject pattern "' + rejecttitle + '"'
|
||||
date = info_dict.get('upload_date')
|
||||
if date is not None:
|
||||
dateRange = self.params.get('daterange', DateRange())
|
||||
if date not in dateRange:
|
||||
return '%s upload date is not in range %s' % (date_from_str(date).isoformat(), dateRange)
|
||||
view_count = info_dict.get('view_count')
|
||||
if view_count is not None:
|
||||
min_views = self.params.get('min_views')
|
||||
if min_views is not None and view_count < min_views:
|
||||
return 'Skipping %s, because it has not reached minimum view count (%d/%d)' % (video_title, view_count, min_views)
|
||||
max_views = self.params.get('max_views')
|
||||
if max_views is not None and view_count > max_views:
|
||||
return 'Skipping %s, because it has exceeded the maximum view count (%d/%d)' % (video_title, view_count, max_views)
|
||||
if age_restricted(info_dict.get('age_limit'), self.params.get('age_limit')):
|
||||
return 'Skipping "%s" because it is age restricted' % video_title
|
||||
if self.in_download_archive(info_dict):
|
||||
return '%s has already been recorded in archive' % video_title
|
||||
video_title = info_dict.get('title', info_dict.get('id', 'video'))
|
||||
if 'title' in info_dict:
|
||||
# This can happen when we're just evaluating the playlist
|
||||
title = info_dict['title']
|
||||
matchtitle = self.params.get('matchtitle', False)
|
||||
if matchtitle:
|
||||
if not re.search(matchtitle, title, re.IGNORECASE):
|
||||
return '"' + title + '" title did not match pattern "' + matchtitle + '"'
|
||||
rejecttitle = self.params.get('rejecttitle', False)
|
||||
if rejecttitle:
|
||||
if re.search(rejecttitle, title, re.IGNORECASE):
|
||||
return '"' + title + '" title matched reject pattern "' + rejecttitle + '"'
|
||||
date = info_dict.get('upload_date')
|
||||
if date is not None:
|
||||
dateRange = self.params.get('daterange', DateRange())
|
||||
if date not in dateRange:
|
||||
return '%s upload date is not in range %s' % (date_from_str(date).isoformat(), dateRange)
|
||||
view_count = info_dict.get('view_count')
|
||||
if view_count is not None:
|
||||
min_views = self.params.get('min_views')
|
||||
if min_views is not None and view_count < min_views:
|
||||
return 'Skipping %s, because it has not reached minimum view count (%d/%d)' % (video_title, view_count, min_views)
|
||||
max_views = self.params.get('max_views')
|
||||
if max_views is not None and view_count > max_views:
|
||||
return 'Skipping %s, because it has exceeded the maximum view count (%d/%d)' % (video_title, view_count, max_views)
|
||||
if age_restricted(info_dict.get('age_limit'), self.params.get('age_limit')):
|
||||
return 'Skipping "%s" because it is age restricted' % video_title
|
||||
if self.in_download_archive(info_dict):
|
||||
return '%s has already been recorded in archive' % video_title
|
||||
|
||||
if not incomplete:
|
||||
match_filter = self.params.get('match_filter')
|
||||
if match_filter is not None:
|
||||
ret = match_filter(info_dict)
|
||||
if ret is not None:
|
||||
return ret
|
||||
return None
|
||||
if not incomplete:
|
||||
match_filter = self.params.get('match_filter')
|
||||
if match_filter is not None:
|
||||
ret = match_filter(info_dict)
|
||||
if ret is not None:
|
||||
return ret
|
||||
|
||||
reason = check_filter()
|
||||
if reason is not None:
|
||||
self.to_screen('[download] ' + reason)
|
||||
if reason.endswith('has already been recorded in the archive') and self.params.get('break_on_existing', False):
|
||||
raise ExistingVideoReached()
|
||||
elif self.params.get('break_on_reject', False):
|
||||
raise RejectedVideoReached()
|
||||
return reason
|
||||
return None
|
||||
|
||||
@staticmethod
|
||||
def add_extra_info(info_dict, extra_info):
|
||||
@@ -909,7 +874,7 @@ class YoutubeDL(object):
|
||||
self.report_error(msg)
|
||||
except ExtractorError as e: # An error we somewhat expected
|
||||
self.report_error(compat_str(e), e.format_traceback())
|
||||
except (MaxDownloadsReached, ExistingVideoReached, RejectedVideoReached):
|
||||
except MaxDownloadsReached:
|
||||
raise
|
||||
except Exception as e:
|
||||
if self.params.get('ignoreerrors', False):
|
||||
@@ -1014,23 +979,119 @@ class YoutubeDL(object):
|
||||
return self.process_ie_result(
|
||||
new_result, download=download, extra_info=extra_info)
|
||||
elif result_type in ('playlist', 'multi_video'):
|
||||
# Protect from infinite recursion due to recursively nested playlists
|
||||
# (see https://github.com/ytdl-org/youtube-dl/issues/27833)
|
||||
webpage_url = ie_result['webpage_url']
|
||||
if webpage_url in self._playlist_urls:
|
||||
self.to_screen(
|
||||
'[download] Skipping already downloaded playlist: %s'
|
||||
% ie_result.get('title') or ie_result.get('id'))
|
||||
return
|
||||
# We process each entry in the playlist
|
||||
playlist = ie_result.get('title') or ie_result.get('id')
|
||||
self.to_screen('[download] Downloading playlist: %s' % playlist)
|
||||
|
||||
self._playlist_level += 1
|
||||
self._playlist_urls.add(webpage_url)
|
||||
try:
|
||||
return self.__process_playlist(ie_result, download)
|
||||
finally:
|
||||
self._playlist_level -= 1
|
||||
if not self._playlist_level:
|
||||
self._playlist_urls.clear()
|
||||
playlist_results = []
|
||||
|
||||
playliststart = self.params.get('playliststart', 1) - 1
|
||||
playlistend = self.params.get('playlistend')
|
||||
# For backwards compatibility, interpret -1 as whole list
|
||||
if playlistend == -1:
|
||||
playlistend = None
|
||||
|
||||
playlistitems_str = self.params.get('playlist_items')
|
||||
playlistitems = None
|
||||
if playlistitems_str is not None:
|
||||
def iter_playlistitems(format):
|
||||
for string_segment in format.split(','):
|
||||
if '-' in string_segment:
|
||||
start, end = string_segment.split('-')
|
||||
for item in range(int(start), int(end) + 1):
|
||||
yield int(item)
|
||||
else:
|
||||
yield int(string_segment)
|
||||
playlistitems = orderedSet(iter_playlistitems(playlistitems_str))
|
||||
|
||||
ie_entries = ie_result['entries']
|
||||
|
||||
def make_playlistitems_entries(list_ie_entries):
|
||||
num_entries = len(list_ie_entries)
|
||||
return [
|
||||
list_ie_entries[i - 1] for i in playlistitems
|
||||
if -num_entries <= i - 1 < num_entries]
|
||||
|
||||
def report_download(num_entries):
|
||||
self.to_screen(
|
||||
'[%s] playlist %s: Downloading %d videos' %
|
||||
(ie_result['extractor'], playlist, num_entries))
|
||||
|
||||
if isinstance(ie_entries, list):
|
||||
n_all_entries = len(ie_entries)
|
||||
if playlistitems:
|
||||
entries = make_playlistitems_entries(ie_entries)
|
||||
else:
|
||||
entries = ie_entries[playliststart:playlistend]
|
||||
n_entries = len(entries)
|
||||
self.to_screen(
|
||||
'[%s] playlist %s: Collected %d video ids (downloading %d of them)' %
|
||||
(ie_result['extractor'], playlist, n_all_entries, n_entries))
|
||||
elif isinstance(ie_entries, PagedList):
|
||||
if playlistitems:
|
||||
entries = []
|
||||
for item in playlistitems:
|
||||
entries.extend(ie_entries.getslice(
|
||||
item - 1, item
|
||||
))
|
||||
else:
|
||||
entries = ie_entries.getslice(
|
||||
playliststart, playlistend)
|
||||
n_entries = len(entries)
|
||||
report_download(n_entries)
|
||||
else: # iterable
|
||||
if playlistitems:
|
||||
entries = make_playlistitems_entries(list(itertools.islice(
|
||||
ie_entries, 0, max(playlistitems))))
|
||||
else:
|
||||
entries = list(itertools.islice(
|
||||
ie_entries, playliststart, playlistend))
|
||||
n_entries = len(entries)
|
||||
report_download(n_entries)
|
||||
|
||||
if self.params.get('playlistreverse', False):
|
||||
entries = entries[::-1]
|
||||
|
||||
if self.params.get('playlistrandom', False):
|
||||
random.shuffle(entries)
|
||||
|
||||
x_forwarded_for = ie_result.get('__x_forwarded_for_ip')
|
||||
|
||||
for i, entry in enumerate(entries, 1):
|
||||
self.to_screen('[download] Downloading video %s of %s' % (i, n_entries))
|
||||
# This __x_forwarded_for_ip thing is a bit ugly but requires
|
||||
# minimal changes
|
||||
if x_forwarded_for:
|
||||
entry['__x_forwarded_for_ip'] = x_forwarded_for
|
||||
extra = {
|
||||
'n_entries': n_entries,
|
||||
'playlist': playlist,
|
||||
'playlist_id': ie_result.get('id'),
|
||||
'playlist_title': ie_result.get('title'),
|
||||
'playlist_uploader': ie_result.get('uploader'),
|
||||
'playlist_uploader_id': ie_result.get('uploader_id'),
|
||||
'playlist_index': playlistitems[i - 1] if playlistitems else i + playliststart,
|
||||
'extractor': ie_result['extractor'],
|
||||
'webpage_url': ie_result['webpage_url'],
|
||||
'webpage_url_basename': url_basename(ie_result['webpage_url']),
|
||||
'extractor_key': ie_result['extractor_key'],
|
||||
}
|
||||
|
||||
reason = self._match_entry(entry, incomplete=True)
|
||||
if reason is not None:
|
||||
if reason.endswith('has already been recorded in the archive') and self.params.get('break_on_existing'):
|
||||
print('[download] tried downloading a file that\'s already in the archive, stopping since --break-on-existing is set.')
|
||||
break
|
||||
else:
|
||||
self.to_screen('[download] ' + reason)
|
||||
continue
|
||||
|
||||
entry_result = self.__process_iterable_entry(entry, download, extra)
|
||||
# TODO: skip failed (empty) entries?
|
||||
playlist_results.append(entry_result)
|
||||
ie_result['entries'] = playlist_results
|
||||
self.to_screen('[download] Finished downloading playlist: %s' % playlist)
|
||||
return ie_result
|
||||
elif result_type == 'compat_list':
|
||||
self.report_warning(
|
||||
'Extractor %s returned a compat_list result. '
|
||||
@@ -1055,115 +1116,6 @@ class YoutubeDL(object):
|
||||
else:
|
||||
raise Exception('Invalid result type: %s' % result_type)
|
||||
|
||||
def __process_playlist(self, ie_result, download):
|
||||
# We process each entry in the playlist
|
||||
playlist = ie_result.get('title') or ie_result.get('id')
|
||||
self.to_screen('[download] Downloading playlist: %s' % playlist)
|
||||
|
||||
playlist_results = []
|
||||
|
||||
playliststart = self.params.get('playliststart', 1) - 1
|
||||
playlistend = self.params.get('playlistend')
|
||||
# For backwards compatibility, interpret -1 as whole list
|
||||
if playlistend == -1:
|
||||
playlistend = None
|
||||
|
||||
playlistitems_str = self.params.get('playlist_items')
|
||||
playlistitems = None
|
||||
if playlistitems_str is not None:
|
||||
def iter_playlistitems(format):
|
||||
for string_segment in format.split(','):
|
||||
if '-' in string_segment:
|
||||
start, end = string_segment.split('-')
|
||||
for item in range(int(start), int(end) + 1):
|
||||
yield int(item)
|
||||
else:
|
||||
yield int(string_segment)
|
||||
playlistitems = orderedSet(iter_playlistitems(playlistitems_str))
|
||||
|
||||
ie_entries = ie_result['entries']
|
||||
|
||||
def make_playlistitems_entries(list_ie_entries):
|
||||
num_entries = len(list_ie_entries)
|
||||
return [
|
||||
list_ie_entries[i - 1] for i in playlistitems
|
||||
if -num_entries <= i - 1 < num_entries]
|
||||
|
||||
def report_download(num_entries):
|
||||
self.to_screen(
|
||||
'[%s] playlist %s: Downloading %d videos' %
|
||||
(ie_result['extractor'], playlist, num_entries))
|
||||
|
||||
if isinstance(ie_entries, list):
|
||||
n_all_entries = len(ie_entries)
|
||||
if playlistitems:
|
||||
entries = make_playlistitems_entries(ie_entries)
|
||||
else:
|
||||
entries = ie_entries[playliststart:playlistend]
|
||||
n_entries = len(entries)
|
||||
self.to_screen(
|
||||
'[%s] playlist %s: Collected %d video ids (downloading %d of them)' %
|
||||
(ie_result['extractor'], playlist, n_all_entries, n_entries))
|
||||
elif isinstance(ie_entries, PagedList):
|
||||
if playlistitems:
|
||||
entries = []
|
||||
for item in playlistitems:
|
||||
entries.extend(ie_entries.getslice(
|
||||
item - 1, item
|
||||
))
|
||||
else:
|
||||
entries = ie_entries.getslice(
|
||||
playliststart, playlistend)
|
||||
n_entries = len(entries)
|
||||
report_download(n_entries)
|
||||
else: # iterable
|
||||
if playlistitems:
|
||||
entries = make_playlistitems_entries(list(itertools.islice(
|
||||
ie_entries, 0, max(playlistitems))))
|
||||
else:
|
||||
entries = list(itertools.islice(
|
||||
ie_entries, playliststart, playlistend))
|
||||
n_entries = len(entries)
|
||||
report_download(n_entries)
|
||||
|
||||
if self.params.get('playlistreverse', False):
|
||||
entries = entries[::-1]
|
||||
|
||||
if self.params.get('playlistrandom', False):
|
||||
random.shuffle(entries)
|
||||
|
||||
x_forwarded_for = ie_result.get('__x_forwarded_for_ip')
|
||||
|
||||
for i, entry in enumerate(entries, 1):
|
||||
self.to_screen('[download] Downloading video %s of %s' % (i, n_entries))
|
||||
# This __x_forwarded_for_ip thing is a bit ugly but requires
|
||||
# minimal changes
|
||||
if x_forwarded_for:
|
||||
entry['__x_forwarded_for_ip'] = x_forwarded_for
|
||||
extra = {
|
||||
'n_entries': n_entries,
|
||||
'playlist': playlist,
|
||||
'playlist_id': ie_result.get('id'),
|
||||
'playlist_title': ie_result.get('title'),
|
||||
'playlist_uploader': ie_result.get('uploader'),
|
||||
'playlist_uploader_id': ie_result.get('uploader_id'),
|
||||
'playlist_index': playlistitems[i - 1] if playlistitems else i + playliststart,
|
||||
'extractor': ie_result['extractor'],
|
||||
'webpage_url': ie_result['webpage_url'],
|
||||
'webpage_url_basename': url_basename(ie_result['webpage_url']),
|
||||
'extractor_key': ie_result['extractor_key'],
|
||||
}
|
||||
|
||||
if self._match_entry(entry, incomplete=True) is not None:
|
||||
continue
|
||||
|
||||
entry_result = self.__process_iterable_entry(entry, download, extra)
|
||||
# TODO: skip failed (empty) entries?
|
||||
playlist_results.append(entry_result)
|
||||
ie_result['entries'] = playlist_results
|
||||
self.to_screen('[download] Finished downloading playlist: %s' % playlist)
|
||||
return ie_result
|
||||
|
||||
@__handle_extraction_exceptions
|
||||
def __process_iterable_entry(self, entry, download, extra_info):
|
||||
return self.process_ie_result(
|
||||
@@ -1897,7 +1849,9 @@ class YoutubeDL(object):
|
||||
if 'format' not in info_dict:
|
||||
info_dict['format'] = info_dict['ext']
|
||||
|
||||
if self._match_entry(info_dict, incomplete=False) is not None:
|
||||
reason = self._match_entry(info_dict, incomplete=False)
|
||||
if reason is not None:
|
||||
self.to_screen('[download] ' + reason)
|
||||
return
|
||||
|
||||
self._num_downloads += 1
|
||||
@@ -1932,7 +1886,7 @@ class YoutubeDL(object):
|
||||
|
||||
if self.params.get('writedescription', False):
|
||||
descfn = replace_extension(filename, 'description', info_dict.get('ext'))
|
||||
if not self.params.get('overwrites', True) and os.path.exists(encodeFilename(descfn)):
|
||||
if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(descfn)):
|
||||
self.to_screen('[info] Video description is already present')
|
||||
elif info_dict.get('description') is None:
|
||||
self.report_warning('There\'s no description to write.')
|
||||
@@ -1947,7 +1901,7 @@ class YoutubeDL(object):
|
||||
|
||||
if self.params.get('writeannotations', False):
|
||||
annofn = replace_extension(filename, 'annotations.xml', info_dict.get('ext'))
|
||||
if not self.params.get('overwrites', True) and os.path.exists(encodeFilename(annofn)):
|
||||
if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(annofn)):
|
||||
self.to_screen('[info] Video annotations are already present')
|
||||
elif not info_dict.get('annotations'):
|
||||
self.report_warning('There are no annotations to write.')
|
||||
@@ -1981,7 +1935,7 @@ class YoutubeDL(object):
|
||||
for sub_lang, sub_info in subtitles.items():
|
||||
sub_format = sub_info['ext']
|
||||
sub_filename = subtitles_filename(filename, sub_lang, sub_format, info_dict.get('ext'))
|
||||
if not self.params.get('overwrites', True) and os.path.exists(encodeFilename(sub_filename)):
|
||||
if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(sub_filename)):
|
||||
self.to_screen('[info] Video subtitle %s.%s is already present' % (sub_lang, sub_format))
|
||||
else:
|
||||
self.to_screen('[info] Writing video subtitles to: ' + sub_filename)
|
||||
@@ -2036,7 +1990,7 @@ class YoutubeDL(object):
|
||||
|
||||
if self.params.get('writeinfojson', False):
|
||||
infofn = replace_extension(filename, 'info.json', info_dict.get('ext'))
|
||||
if not self.params.get('overwrites', True) and os.path.exists(encodeFilename(infofn)):
|
||||
if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(infofn)):
|
||||
self.to_screen('[info] Video description metadata is already present')
|
||||
else:
|
||||
self.to_screen('[info] Writing video description metadata as JSON to: ' + infofn)
|
||||
@@ -2144,15 +2098,11 @@ class YoutubeDL(object):
|
||||
'Requested formats are incompatible for merge and will be merged into mkv.')
|
||||
# Ensure filename always has a correct extension for successful merge
|
||||
filename = '%s.%s' % (filename_wo_ext, info_dict['ext'])
|
||||
file_exists = os.path.exists(encodeFilename(filename))
|
||||
if not self.params.get('overwrites', False) and file_exists:
|
||||
if os.path.exists(encodeFilename(filename)):
|
||||
self.to_screen(
|
||||
'[download] %s has already been downloaded and '
|
||||
'merged' % filename)
|
||||
else:
|
||||
if file_exists:
|
||||
self.report_file_delete(filename)
|
||||
os.remove(encodeFilename(filename))
|
||||
for f in requested_formats:
|
||||
new_info = dict(info_dict)
|
||||
new_info.update(f)
|
||||
@@ -2169,11 +2119,6 @@ class YoutubeDL(object):
|
||||
# Even if there were no downloads, it is being merged only now
|
||||
info_dict['__real_download'] = True
|
||||
else:
|
||||
# Delete existing file with --yes-overwrites
|
||||
if self.params.get('overwrites', False):
|
||||
if os.path.exists(encodeFilename(filename)):
|
||||
self.report_file_delete(filename)
|
||||
os.remove(encodeFilename(filename))
|
||||
# Just a single file
|
||||
success, real_download = dl(filename, info_dict)
|
||||
info_dict['__real_download'] = real_download
|
||||
@@ -2254,19 +2199,10 @@ class YoutubeDL(object):
|
||||
except (PostProcessingError) as err:
|
||||
self.report_error('postprocessing: %s' % str(err))
|
||||
return
|
||||
try:
|
||||
for ph in self._post_hooks:
|
||||
ph(filename)
|
||||
except Exception as err:
|
||||
self.report_error('post hooks: %s' % str(err))
|
||||
return
|
||||
must_record_download_archive = True
|
||||
|
||||
if must_record_download_archive or self.params.get('force_write_download_archive', False):
|
||||
self.record_download_archive(info_dict)
|
||||
max_downloads = self.params.get('max_downloads')
|
||||
if max_downloads is not None and self._num_downloads >= int(max_downloads):
|
||||
raise MaxDownloadsReached()
|
||||
|
||||
def download(self, url_list):
|
||||
"""Download a given list of URLs."""
|
||||
@@ -2285,13 +2221,7 @@ class YoutubeDL(object):
|
||||
except UnavailableVideoError:
|
||||
self.report_error('unable to download video')
|
||||
except MaxDownloadsReached:
|
||||
self.to_screen('[info] Maximum number of downloaded files reached')
|
||||
raise
|
||||
except ExistingVideoReached:
|
||||
self.to_screen('[info] Encountered a file that is already in the archive, stopping due to --break-on-existing')
|
||||
raise
|
||||
except RejectedVideoReached:
|
||||
self.to_screen('[info] Encountered a file that did not match filter, stopping due to --break-on-reject')
|
||||
self.to_screen('[info] Maximum number of downloaded files reached.')
|
||||
raise
|
||||
else:
|
||||
if self.params.get('dump_single_json', False):
|
||||
@@ -2563,7 +2493,7 @@ class YoutubeDL(object):
|
||||
self.get_encoding()))
|
||||
write_string(encoding_str, encoding=None)
|
||||
|
||||
self._write_string('[debug] yt-dlp version ' + __version__ + '\n')
|
||||
self._write_string('[debug] youtube-dlc version ' + __version__ + '\n')
|
||||
if _LAZY_LOADER:
|
||||
self._write_string('[debug] Lazy loading extractors enabled' + '\n')
|
||||
try:
|
||||
@@ -2571,7 +2501,7 @@ class YoutubeDL(object):
|
||||
['git', 'rev-parse', '--short', 'HEAD'],
|
||||
stdout=subprocess.PIPE, stderr=subprocess.PIPE,
|
||||
cwd=os.path.dirname(os.path.abspath(__file__)))
|
||||
out, err = process_communicate_or_kill(sp)
|
||||
out, err = sp.communicate()
|
||||
out = out.decode().strip()
|
||||
if re.match('[0-9a-f]+', out):
|
||||
self._write_string('[debug] Git HEAD: ' + out + '\n')
|
||||
@@ -2612,7 +2542,6 @@ class YoutubeDL(object):
|
||||
if self.params.get('call_home', False):
|
||||
ipaddr = self.urlopen('https://yt-dl.org/ip').read().decode('utf-8')
|
||||
self._write_string('[debug] Public IP address: %s\n' % ipaddr)
|
||||
return
|
||||
latest_version = self.urlopen(
|
||||
'https://yt-dl.org/latest/version').read().decode('utf-8')
|
||||
if version_tuple(latest_version) > version_tuple(__version__):
|
||||
@@ -2710,7 +2639,7 @@ class YoutubeDL(object):
|
||||
thumb_display_id = '%s ' % t['id'] if len(thumbnails) > 1 else ''
|
||||
t['filename'] = thumb_filename = replace_extension(filename + suffix, thumb_ext, info_dict.get('ext'))
|
||||
|
||||
if not self.params.get('overwrites', True) and os.path.exists(encodeFilename(thumb_filename)):
|
||||
if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(thumb_filename)):
|
||||
self.to_screen('[%s] %s: Thumbnail %sis already present' %
|
||||
(info_dict['extractor'], info_dict['id'], thumb_display_id))
|
||||
else:
|
||||
|
||||
@@ -26,13 +26,11 @@ from .utils import (
|
||||
decodeOption,
|
||||
DEFAULT_OUTTMPL,
|
||||
DownloadError,
|
||||
ExistingVideoReached,
|
||||
expand_path,
|
||||
match_filter_func,
|
||||
MaxDownloadsReached,
|
||||
preferredencoding,
|
||||
read_batch_urls,
|
||||
RejectedVideoReached,
|
||||
SameFileError,
|
||||
setproctitle,
|
||||
std_headers,
|
||||
@@ -178,9 +176,6 @@ def _real_main(argv=None):
|
||||
opts.max_sleep_interval = opts.sleep_interval
|
||||
if opts.ap_mso and opts.ap_mso not in MSO_INFO:
|
||||
parser.error('Unsupported TV Provider, use --ap-list-mso to get a list of supported TV Providers')
|
||||
if opts.overwrites:
|
||||
# --yes-overwrites implies --no-continue
|
||||
opts.continue_dl = False
|
||||
|
||||
def parse_retries(retries):
|
||||
if retries in ('inf', 'infinite'):
|
||||
@@ -396,7 +391,7 @@ def _real_main(argv=None):
|
||||
'ignoreerrors': opts.ignoreerrors,
|
||||
'force_generic_extractor': opts.force_generic_extractor,
|
||||
'ratelimit': opts.ratelimit,
|
||||
'overwrites': opts.overwrites,
|
||||
'nooverwrites': opts.nooverwrites,
|
||||
'retries': opts.retries,
|
||||
'fragment_retries': opts.fragment_retries,
|
||||
'skip_unavailable_fragments': opts.skip_unavailable_fragments,
|
||||
@@ -451,7 +446,6 @@ def _real_main(argv=None):
|
||||
'age_limit': opts.age_limit,
|
||||
'download_archive': download_archive_fn,
|
||||
'break_on_existing': opts.break_on_existing,
|
||||
'break_on_reject': opts.break_on_reject,
|
||||
'cookiefile': opts.cookiefile,
|
||||
'nocheckcertificate': opts.no_check_certificate,
|
||||
'prefer_insecure': opts.prefer_insecure,
|
||||
@@ -522,8 +516,8 @@ def _real_main(argv=None):
|
||||
retcode = ydl.download_with_info_file(expand_path(opts.load_info_filename))
|
||||
else:
|
||||
retcode = ydl.download(all_urls)
|
||||
except (MaxDownloadsReached, ExistingVideoReached, RejectedVideoReached):
|
||||
ydl.to_screen('Aborting remaining downloads')
|
||||
except MaxDownloadsReached:
|
||||
ydl.to_screen('--max-download limit reached, aborting.')
|
||||
retcode = 101
|
||||
|
||||
sys.exit(retcode)
|
||||
|
||||
@@ -2896,7 +2896,6 @@ else:
|
||||
_terminal_size = collections.namedtuple('terminal_size', ['columns', 'lines'])
|
||||
|
||||
def compat_get_terminal_size(fallback=(80, 24)):
|
||||
from .utils import process_communicate_or_kill
|
||||
columns = compat_getenv('COLUMNS')
|
||||
if columns:
|
||||
columns = int(columns)
|
||||
@@ -2913,7 +2912,7 @@ else:
|
||||
sp = subprocess.Popen(
|
||||
['stty', 'size'],
|
||||
stdout=subprocess.PIPE, stderr=subprocess.PIPE)
|
||||
out, err = process_communicate_or_kill(sp)
|
||||
out, err = sp.communicate()
|
||||
_lines, _columns = map(int, out.split())
|
||||
except Exception:
|
||||
_columns, _lines = _terminal_size(*fallback)
|
||||
|
||||
@@ -332,7 +332,7 @@ class FileDownloader(object):
|
||||
"""
|
||||
|
||||
nooverwrites_and_exists = (
|
||||
not self.params.get('overwrites', True)
|
||||
self.params.get('nooverwrites', False)
|
||||
and os.path.exists(encodeFilename(filename))
|
||||
)
|
||||
|
||||
|
||||
@@ -22,7 +22,6 @@ from ..utils import (
|
||||
handle_youtubedl_headers,
|
||||
check_executable,
|
||||
is_outdated_version,
|
||||
process_communicate_or_kill,
|
||||
)
|
||||
|
||||
|
||||
@@ -105,7 +104,7 @@ class ExternalFD(FileDownloader):
|
||||
|
||||
p = subprocess.Popen(
|
||||
cmd, stderr=subprocess.PIPE)
|
||||
_, stderr = process_communicate_or_kill(p)
|
||||
_, stderr = p.communicate()
|
||||
if p.returncode != 0:
|
||||
self.to_stderr(stderr.decode('utf-8', 'replace'))
|
||||
return p.returncode
|
||||
@@ -144,7 +143,7 @@ class CurlFD(ExternalFD):
|
||||
|
||||
# curl writes the progress to stderr so don't capture it.
|
||||
p = subprocess.Popen(cmd)
|
||||
process_communicate_or_kill(p)
|
||||
p.communicate()
|
||||
return p.returncode
|
||||
|
||||
|
||||
@@ -344,17 +343,14 @@ class FFmpegFD(ExternalFD):
|
||||
proc = subprocess.Popen(args, stdin=subprocess.PIPE, env=env)
|
||||
try:
|
||||
retval = proc.wait()
|
||||
except BaseException as e:
|
||||
except KeyboardInterrupt:
|
||||
# subprocces.run would send the SIGKILL signal to ffmpeg and the
|
||||
# mp4 file couldn't be played, but if we ask ffmpeg to quit it
|
||||
# produces a file that is playable (this is mostly useful for live
|
||||
# streams). Note that Windows is not affected and produces playable
|
||||
# files (see https://github.com/ytdl-org/youtube-dl/issues/8300).
|
||||
if isinstance(e, KeyboardInterrupt) and sys.platform != 'win32':
|
||||
process_communicate_or_kill(proc, b'q')
|
||||
else:
|
||||
proc.kill()
|
||||
proc.wait()
|
||||
if sys.platform != 'win32':
|
||||
proc.communicate(b'q')
|
||||
raise
|
||||
return retval
|
||||
|
||||
|
||||
@@ -172,12 +172,8 @@ class HlsFD(FragmentFD):
|
||||
iv = decrypt_info.get('IV') or compat_struct_pack('>8xq', media_sequence)
|
||||
decrypt_info['KEY'] = decrypt_info.get('KEY') or self.ydl.urlopen(
|
||||
self._prepare_url(info_dict, info_dict.get('_decryption_key_url') or decrypt_info['URI'])).read()
|
||||
# Don't decrypt the content in tests since the data is explicitly truncated and it's not to a valid block
|
||||
# size (see https://github.com/ytdl-org/youtube-dl/pull/27660). Tests only care that the correct data downloaded,
|
||||
# not what it decrypts to.
|
||||
if not test:
|
||||
frag_content = AES.new(
|
||||
decrypt_info['KEY'], AES.MODE_CBC, iv).decrypt(frag_content)
|
||||
frag_content = AES.new(
|
||||
decrypt_info['KEY'], AES.MODE_CBC, iv).decrypt(frag_content)
|
||||
self._append_fragment(ctx, frag_content)
|
||||
# We only download the first fragment during the test
|
||||
if test:
|
||||
|
||||
@@ -89,13 +89,11 @@ class RtmpFD(FileDownloader):
|
||||
self.to_screen('')
|
||||
cursor_in_new_line = True
|
||||
self.to_screen('[rtmpdump] ' + line)
|
||||
if not cursor_in_new_line:
|
||||
self.to_screen('')
|
||||
return proc.wait()
|
||||
except BaseException: # Including KeyboardInterrupt
|
||||
proc.kill()
|
||||
finally:
|
||||
proc.wait()
|
||||
raise
|
||||
if not cursor_in_new_line:
|
||||
self.to_screen('')
|
||||
return proc.returncode
|
||||
|
||||
url = info_dict['url']
|
||||
player_url = info_dict.get('player_url')
|
||||
|
||||
@@ -6,7 +6,6 @@ import re
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
clean_html,
|
||||
clean_podcast_url,
|
||||
int_or_none,
|
||||
parse_iso8601,
|
||||
)
|
||||
@@ -18,7 +17,7 @@ class ACastBaseIE(InfoExtractor):
|
||||
info = {
|
||||
'id': episode['id'],
|
||||
'display_id': episode.get('episodeUrl'),
|
||||
'url': clean_podcast_url(episode['url']),
|
||||
'url': episode['url'],
|
||||
'title': title,
|
||||
'description': clean_html(episode.get('description') or episode.get('summary')),
|
||||
'thumbnail': episode.get('image'),
|
||||
|
||||
@@ -10,7 +10,6 @@ import random
|
||||
from .common import InfoExtractor
|
||||
from ..aes import aes_cbc_decrypt
|
||||
from ..compat import (
|
||||
compat_HTTPError,
|
||||
compat_b64decode,
|
||||
compat_ord,
|
||||
)
|
||||
@@ -19,13 +18,11 @@ from ..utils import (
|
||||
bytes_to_long,
|
||||
ExtractorError,
|
||||
float_or_none,
|
||||
int_or_none,
|
||||
intlist_to_bytes,
|
||||
long_to_bytes,
|
||||
pkcs1pad,
|
||||
strip_or_none,
|
||||
try_get,
|
||||
unified_strdate,
|
||||
urljoin,
|
||||
)
|
||||
|
||||
|
||||
@@ -34,27 +31,16 @@ class ADNIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?animedigitalnetwork\.fr/video/[^/]+/(?P<id>\d+)'
|
||||
_TEST = {
|
||||
'url': 'http://animedigitalnetwork.fr/video/blue-exorcist-kyoto-saga/7778-episode-1-debut-des-hostilites',
|
||||
'md5': '0319c99885ff5547565cacb4f3f9348d',
|
||||
'md5': 'e497370d847fd79d9d4c74be55575c7a',
|
||||
'info_dict': {
|
||||
'id': '7778',
|
||||
'ext': 'mp4',
|
||||
'title': 'Blue Exorcist - Kyôto Saga - Episode 1',
|
||||
'title': 'Blue Exorcist - Kyôto Saga - Épisode 1',
|
||||
'description': 'md5:2f7b5aa76edbc1a7a92cedcda8a528d5',
|
||||
'series': 'Blue Exorcist - Kyôto Saga',
|
||||
'duration': 1467,
|
||||
'release_date': '20170106',
|
||||
'comment_count': int,
|
||||
'average_rating': float,
|
||||
'season_number': 2,
|
||||
'episode': 'Début des hostilités',
|
||||
'episode_number': 1,
|
||||
}
|
||||
}
|
||||
|
||||
_BASE_URL = 'http://animedigitalnetwork.fr'
|
||||
_API_BASE_URL = 'https://gw.api.animedigitalnetwork.fr/'
|
||||
_PLAYER_BASE_URL = _API_BASE_URL + 'player/'
|
||||
_RSA_KEY = (0x9B42B08905199A5CCE2026274399CA560ECB209EE9878A708B1C0812E1BB8CB5D1FB7441861147C1A1F2F3A0476DD63A9CAC20D3E983613346850AA6CB38F16DC7D720FD7D86FC6E5B3D5BBC72E14CD0BF9E869F2CEA2CCAD648F1DCE38F1FF916CEFB2D339B64AA0264372344BC775E265E8A852F88144AB0BD9AA06C1A4ABB, 65537)
|
||||
_RSA_KEY = (0xc35ae1e4356b65a73b551493da94b8cb443491c0aa092a357a5aee57ffc14dda85326f42d716e539a34542a0d3f363adf16c5ec222d713d5997194030ee2e4f0d1fb328c01a81cf6868c090d50de8e169c6b13d1675b9eeed1cbc51e1fffca9b38af07f37abd790924cd3bee59d0257cfda4fe5f3f0534877e21ce5821447d1b, 65537)
|
||||
_POS_ALIGN_MAP = {
|
||||
'start': 1,
|
||||
'end': 3,
|
||||
@@ -68,24 +54,26 @@ class ADNIE(InfoExtractor):
|
||||
def _ass_subtitles_timecode(seconds):
|
||||
return '%01d:%02d:%02d.%02d' % (seconds / 3600, (seconds % 3600) / 60, seconds % 60, (seconds % 1) * 100)
|
||||
|
||||
def _get_subtitles(self, sub_url, video_id):
|
||||
if not sub_url:
|
||||
def _get_subtitles(self, sub_path, video_id):
|
||||
if not sub_path:
|
||||
return None
|
||||
|
||||
enc_subtitles = self._download_webpage(
|
||||
sub_url, video_id, 'Downloading subtitles location', fatal=False) or '{}'
|
||||
urljoin(self._BASE_URL, sub_path),
|
||||
video_id, 'Downloading subtitles location', fatal=False) or '{}'
|
||||
subtitle_location = (self._parse_json(enc_subtitles, video_id, fatal=False) or {}).get('location')
|
||||
if subtitle_location:
|
||||
enc_subtitles = self._download_webpage(
|
||||
subtitle_location, video_id, 'Downloading subtitles data',
|
||||
fatal=False, headers={'Origin': 'https://animedigitalnetwork.fr'})
|
||||
urljoin(self._BASE_URL, subtitle_location),
|
||||
video_id, 'Downloading subtitles data', fatal=False,
|
||||
headers={'Origin': 'https://animedigitalnetwork.fr'})
|
||||
if not enc_subtitles:
|
||||
return None
|
||||
|
||||
# http://animedigitalnetwork.fr/components/com_vodvideo/videojs/adn-vjs.min.js
|
||||
dec_subtitles = intlist_to_bytes(aes_cbc_decrypt(
|
||||
bytes_to_intlist(compat_b64decode(enc_subtitles[24:])),
|
||||
bytes_to_intlist(binascii.unhexlify(self._K + 'ab9f52f5baae7c72')),
|
||||
bytes_to_intlist(binascii.unhexlify(self._K + '4b8ef13ec1872730')),
|
||||
bytes_to_intlist(compat_b64decode(enc_subtitles[:24]))
|
||||
))
|
||||
subtitles_json = self._parse_json(
|
||||
@@ -131,76 +119,59 @@ Format: Marked,Start,End,Style,Name,MarginL,MarginR,MarginV,Effect,Text'''
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
video_base_url = self._PLAYER_BASE_URL + 'video/%s/' % video_id
|
||||
player = self._download_json(
|
||||
video_base_url + 'configuration', video_id,
|
||||
'Downloading player config JSON metadata')['player']
|
||||
options = player['options']
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
player_config = self._parse_json(self._search_regex(
|
||||
r'playerConfig\s*=\s*({.+});', webpage,
|
||||
'player config', default='{}'), video_id, fatal=False)
|
||||
if not player_config:
|
||||
config_url = urljoin(self._BASE_URL, self._search_regex(
|
||||
r'(?:id="player"|class="[^"]*adn-player-container[^"]*")[^>]+data-url="([^"]+)"',
|
||||
webpage, 'config url'))
|
||||
player_config = self._download_json(
|
||||
config_url, video_id,
|
||||
'Downloading player config JSON metadata')['player']
|
||||
|
||||
user = options['user']
|
||||
if not user.get('hasAccess'):
|
||||
raise ExtractorError(
|
||||
'This video is only available for paying users', expected=True)
|
||||
# self.raise_login_required() # FIXME: Login is not implemented
|
||||
video_info = {}
|
||||
video_info_str = self._search_regex(
|
||||
r'videoInfo\s*=\s*({.+});', webpage,
|
||||
'video info', fatal=False)
|
||||
if video_info_str:
|
||||
video_info = self._parse_json(
|
||||
video_info_str, video_id, fatal=False) or {}
|
||||
|
||||
token = self._download_json(
|
||||
user.get('refreshTokenUrl') or (self._PLAYER_BASE_URL + 'refresh/token'),
|
||||
video_id, 'Downloading access token', headers={
|
||||
'x-player-refresh-token': user['refreshToken']
|
||||
}, data=b'')['token']
|
||||
|
||||
links_url = try_get(options, lambda x: x['video']['url']) or (video_base_url + 'link')
|
||||
self._K = ''.join([random.choice('0123456789abcdef') for _ in range(16)])
|
||||
message = bytes_to_intlist(json.dumps({
|
||||
'k': self._K,
|
||||
't': token,
|
||||
}))
|
||||
|
||||
# Sometimes authentication fails for no good reason, retry with
|
||||
# a different random padding
|
||||
links_data = None
|
||||
for _ in range(3):
|
||||
options = player_config.get('options') or {}
|
||||
metas = options.get('metas') or {}
|
||||
links = player_config.get('links') or {}
|
||||
sub_path = player_config.get('subtitles')
|
||||
error = None
|
||||
if not links:
|
||||
links_url = player_config.get('linksurl') or options['videoUrl']
|
||||
token = options['token']
|
||||
self._K = ''.join([random.choice('0123456789abcdef') for _ in range(16)])
|
||||
message = bytes_to_intlist(json.dumps({
|
||||
'k': self._K,
|
||||
'e': 60,
|
||||
't': token,
|
||||
}))
|
||||
padded_message = intlist_to_bytes(pkcs1pad(message, 128))
|
||||
n, e = self._RSA_KEY
|
||||
encrypted_message = long_to_bytes(pow(bytes_to_long(padded_message), e, n))
|
||||
authorization = base64.b64encode(encrypted_message).decode()
|
||||
|
||||
try:
|
||||
links_data = self._download_json(
|
||||
links_url, video_id, 'Downloading links JSON metadata', headers={
|
||||
'X-Player-Token': authorization
|
||||
}, query={
|
||||
'freeWithAds': 'true',
|
||||
'adaptive': 'false',
|
||||
'withMetadata': 'true',
|
||||
'source': 'Web'
|
||||
})
|
||||
break
|
||||
except ExtractorError as e:
|
||||
if not isinstance(e.cause, compat_HTTPError):
|
||||
raise e
|
||||
|
||||
if e.cause.code == 401:
|
||||
# This usually goes away with a different random pkcs1pad, so retry
|
||||
continue
|
||||
|
||||
error = self._parse_json(e.cause.read(), video_id)
|
||||
message = error.get('message')
|
||||
if e.cause.code == 403 and error.get('code') == 'player-bad-geolocation-country':
|
||||
self.raise_geo_restricted(msg=message)
|
||||
else:
|
||||
raise ExtractorError(message)
|
||||
else:
|
||||
raise ExtractorError('Giving up retrying')
|
||||
|
||||
links = links_data.get('links') or {}
|
||||
metas = links_data.get('metadata') or {}
|
||||
sub_url = (links.get('subtitles') or {}).get('all')
|
||||
video_info = links_data.get('video') or {}
|
||||
title = metas['title']
|
||||
links_data = self._download_json(
|
||||
urljoin(self._BASE_URL, links_url), video_id,
|
||||
'Downloading links JSON metadata', headers={
|
||||
'Authorization': 'Bearer ' + authorization,
|
||||
})
|
||||
links = links_data.get('links') or {}
|
||||
metas = metas or links_data.get('meta') or {}
|
||||
sub_path = sub_path or links_data.get('subtitles') or \
|
||||
'index.php?option=com_vodapi&task=subtitles.getJSON&format=json&id=' + video_id
|
||||
sub_path += '&token=' + token
|
||||
error = links_data.get('error')
|
||||
title = metas.get('title') or video_info['title']
|
||||
|
||||
formats = []
|
||||
for format_id, qualities in (links.get('streaming') or {}).items():
|
||||
for format_id, qualities in links.items():
|
||||
if not isinstance(qualities, dict):
|
||||
continue
|
||||
for quality, load_balancer_url in qualities.items():
|
||||
@@ -218,26 +189,19 @@ Format: Marked,Start,End,Style,Name,MarginL,MarginR,MarginV,Effect,Text'''
|
||||
for f in m3u8_formats:
|
||||
f['language'] = 'fr'
|
||||
formats.extend(m3u8_formats)
|
||||
if not error:
|
||||
error = options.get('error')
|
||||
if not formats and error:
|
||||
raise ExtractorError('%s said: %s' % (self.IE_NAME, error), expected=True)
|
||||
self._sort_formats(formats)
|
||||
|
||||
video = (self._download_json(
|
||||
self._API_BASE_URL + 'video/%s' % video_id, video_id,
|
||||
'Downloading additional video metadata', fatal=False) or {}).get('video') or {}
|
||||
show = video.get('show') or {}
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'description': strip_or_none(metas.get('summary') or video.get('summary')),
|
||||
'thumbnail': video_info.get('image') or player.get('image'),
|
||||
'description': strip_or_none(metas.get('summary') or video_info.get('resume')),
|
||||
'thumbnail': video_info.get('image'),
|
||||
'formats': formats,
|
||||
'subtitles': self.extract_subtitles(sub_url, video_id),
|
||||
'episode': metas.get('subtitle') or video.get('name'),
|
||||
'episode_number': int_or_none(video.get('shortNumber')),
|
||||
'series': show.get('title'),
|
||||
'season_number': int_or_none(video.get('season')),
|
||||
'duration': int_or_none(video_info.get('duration') or video.get('duration')),
|
||||
'release_date': unified_strdate(video.get('releaseDate')),
|
||||
'average_rating': float_or_none(video.get('rating') or metas.get('rating')),
|
||||
'comment_count': int_or_none(video.get('commentsCount')),
|
||||
'subtitles': self.extract_subtitles(sub_path, video_id),
|
||||
'episode': metas.get('subtitle') or video_info.get('videoTitle'),
|
||||
'series': video_info.get('playlistTitle'),
|
||||
}
|
||||
|
||||
@@ -9,7 +9,6 @@ from .common import InfoExtractor
|
||||
from ..compat import (
|
||||
compat_kwargs,
|
||||
compat_urlparse,
|
||||
compat_getpass
|
||||
)
|
||||
from ..utils import (
|
||||
unescapeHTML,
|
||||
@@ -61,10 +60,6 @@ MSO_INFO = {
|
||||
'username_field': 'IDToken1',
|
||||
'password_field': 'IDToken2',
|
||||
},
|
||||
'Philo': {
|
||||
'name': 'Philo',
|
||||
'username_field': 'ident'
|
||||
},
|
||||
'Verizon': {
|
||||
'name': 'Verizon FiOS',
|
||||
'username_field': 'IDToken1',
|
||||
@@ -1472,22 +1467,6 @@ class AdobePassIE(InfoExtractor):
|
||||
mvpd_confirm_page, urlh = mvpd_confirm_page_res
|
||||
if '<button class="submit" value="Resume">Resume</button>' in mvpd_confirm_page:
|
||||
post_form(mvpd_confirm_page_res, 'Confirming Login')
|
||||
elif mso_id == 'Philo':
|
||||
# Philo has very unique authentication method
|
||||
self._download_webpage(
|
||||
'https://idp.philo.com/auth/init/login_code', video_id, 'Requesting auth code', data=urlencode_postdata({
|
||||
'ident': username,
|
||||
'device': 'web',
|
||||
'send_confirm_link': False,
|
||||
'send_token': True
|
||||
}))
|
||||
philo_code = compat_getpass('Type auth code you have received [Return]: ')
|
||||
self._download_webpage(
|
||||
'https://idp.philo.com/auth/update/login_code', video_id, 'Submitting token', data=urlencode_postdata({
|
||||
'token': philo_code
|
||||
}))
|
||||
mvpd_confirm_page_res = self._download_webpage_handle('https://idp.philo.com/idp/submit', video_id, 'Confirming Philo Login')
|
||||
post_form(mvpd_confirm_page_res, 'Confirming Login')
|
||||
elif mso_id == 'Verizon':
|
||||
# In general, if you're connecting from a Verizon-assigned IP,
|
||||
# you will not actually pass your credentials.
|
||||
|
||||
@@ -1,285 +0,0 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
urlencode_postdata,
|
||||
int_or_none,
|
||||
str_or_none,
|
||||
determine_ext,
|
||||
)
|
||||
|
||||
from ..compat import compat_HTTPError
|
||||
|
||||
|
||||
class AnimeLabBaseIE(InfoExtractor):
|
||||
_LOGIN_REQUIRED = True
|
||||
_LOGIN_URL = 'https://www.animelab.com/login'
|
||||
_NETRC_MACHINE = 'animelab'
|
||||
|
||||
def _login(self):
|
||||
def is_logged_in(login_webpage):
|
||||
return 'Sign In' not in login_webpage
|
||||
|
||||
login_page = self._download_webpage(
|
||||
self._LOGIN_URL, None, 'Downloading login page')
|
||||
|
||||
# Check if already logged in
|
||||
if is_logged_in(login_page):
|
||||
return
|
||||
|
||||
(username, password) = self._get_login_info()
|
||||
if username is None and self._LOGIN_REQUIRED:
|
||||
self.raise_login_required('Login is required to access any AnimeLab content')
|
||||
|
||||
login_form = {
|
||||
'email': username,
|
||||
'password': password,
|
||||
}
|
||||
|
||||
try:
|
||||
response = self._download_webpage(
|
||||
self._LOGIN_URL, None, 'Logging in', 'Wrong login info',
|
||||
data=urlencode_postdata(login_form),
|
||||
headers={'Content-Type': 'application/x-www-form-urlencoded'})
|
||||
except ExtractorError as e:
|
||||
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 400:
|
||||
raise ExtractorError('Unable to log in (wrong credentials?)', expected=True)
|
||||
else:
|
||||
raise
|
||||
|
||||
# if login was successful
|
||||
if is_logged_in(response):
|
||||
return
|
||||
|
||||
raise ExtractorError('Unable to login (cannot verify if logged in)')
|
||||
|
||||
def _real_initialize(self):
|
||||
self._login()
|
||||
|
||||
|
||||
class AnimeLabIE(AnimeLabBaseIE):
|
||||
_VALID_URL = r'https?://(?:www\.)?animelab\.com/player/(?P<id>[^/]+)'
|
||||
|
||||
# the following tests require authentication, but a free account will suffice
|
||||
# just set 'usenetrc' to true in test/local_parameters.json if you use a .netrc file
|
||||
# or you can set 'username' and 'password' there
|
||||
# the tests also select a specific format so that the same video is downloaded
|
||||
# regardless of whether the user is premium or not (needs testing on a premium account)
|
||||
_TEST = {
|
||||
'url': 'https://www.animelab.com/player/fullmetal-alchemist-brotherhood-episode-42',
|
||||
'md5': '05bde4b91a5d1ff46ef5b94df05b0f7f',
|
||||
'info_dict': {
|
||||
'id': '383',
|
||||
'ext': 'mp4',
|
||||
'display_id': 'fullmetal-alchemist-brotherhood-episode-42',
|
||||
'title': 'Fullmetal Alchemist: Brotherhood - Episode 42 - Signs of a Counteroffensive',
|
||||
'description': 'md5:103eb61dd0a56d3dfc5dbf748e5e83f4',
|
||||
'series': 'Fullmetal Alchemist: Brotherhood',
|
||||
'episode': 'Signs of a Counteroffensive',
|
||||
'episode_number': 42,
|
||||
'duration': 1469,
|
||||
'season': 'Season 1',
|
||||
'season_number': 1,
|
||||
'season_id': '38',
|
||||
},
|
||||
'params': {
|
||||
'format': '[format_id=21711_yeshardsubbed_ja-JP][height=480]',
|
||||
},
|
||||
'skip': 'All AnimeLab content requires authentication',
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
display_id = self._match_id(url)
|
||||
|
||||
# unfortunately we can get different URLs for the same formats
|
||||
# e.g. if we are using a "free" account so no dubs available
|
||||
# (so _remove_duplicate_formats is not effective)
|
||||
# so we use a dictionary as a workaround
|
||||
formats = {}
|
||||
for language_option_url in ('https://www.animelab.com/player/%s/subtitles',
|
||||
'https://www.animelab.com/player/%s/dubbed'):
|
||||
actual_url = language_option_url % display_id
|
||||
webpage = self._download_webpage(actual_url, display_id, 'Downloading URL ' + actual_url)
|
||||
|
||||
video_collection = self._parse_json(self._search_regex(r'new\s+?AnimeLabApp\.VideoCollection\s*?\((.*?)\);', webpage, 'AnimeLab VideoCollection'), display_id)
|
||||
position = int_or_none(self._search_regex(r'playlistPosition\s*?=\s*?(\d+)', webpage, 'Playlist Position'))
|
||||
|
||||
raw_data = video_collection[position]['videoEntry']
|
||||
|
||||
video_id = str_or_none(raw_data['id'])
|
||||
|
||||
# create a title from many sources (while grabbing other info)
|
||||
# TODO use more fallback sources to get some of these
|
||||
series = raw_data.get('showTitle')
|
||||
video_type = raw_data.get('videoEntryType', {}).get('name')
|
||||
episode_number = raw_data.get('episodeNumber')
|
||||
episode_name = raw_data.get('name')
|
||||
|
||||
title_parts = (series, video_type, episode_number, episode_name)
|
||||
if None not in title_parts:
|
||||
title = '%s - %s %s - %s' % title_parts
|
||||
else:
|
||||
title = episode_name
|
||||
|
||||
description = raw_data.get('synopsis') or self._og_search_description(webpage, default=None)
|
||||
|
||||
duration = int_or_none(raw_data.get('duration'))
|
||||
|
||||
thumbnail_data = raw_data.get('images', [])
|
||||
thumbnails = []
|
||||
for thumbnail in thumbnail_data:
|
||||
for instance in thumbnail['imageInstances']:
|
||||
image_data = instance.get('imageInfo', {})
|
||||
thumbnails.append({
|
||||
'id': str_or_none(image_data.get('id')),
|
||||
'url': image_data.get('fullPath'),
|
||||
'width': image_data.get('width'),
|
||||
'height': image_data.get('height'),
|
||||
})
|
||||
|
||||
season_data = raw_data.get('season', {}) or {}
|
||||
season = str_or_none(season_data.get('name'))
|
||||
season_number = int_or_none(season_data.get('seasonNumber'))
|
||||
season_id = str_or_none(season_data.get('id'))
|
||||
|
||||
for video_data in raw_data['videoList']:
|
||||
current_video_list = {}
|
||||
current_video_list['language'] = video_data.get('language', {}).get('languageCode')
|
||||
|
||||
is_hardsubbed = video_data.get('hardSubbed')
|
||||
|
||||
for video_instance in video_data['videoInstances']:
|
||||
httpurl = video_instance.get('httpUrl')
|
||||
url = httpurl if httpurl else video_instance.get('rtmpUrl')
|
||||
if url is None:
|
||||
# this video format is unavailable to the user (not premium etc.)
|
||||
continue
|
||||
|
||||
current_format = current_video_list.copy()
|
||||
|
||||
format_id_parts = []
|
||||
|
||||
format_id_parts.append(str_or_none(video_instance.get('id')))
|
||||
|
||||
if is_hardsubbed is not None:
|
||||
if is_hardsubbed:
|
||||
format_id_parts.append('yeshardsubbed')
|
||||
else:
|
||||
format_id_parts.append('nothardsubbed')
|
||||
|
||||
format_id_parts.append(current_format['language'])
|
||||
|
||||
format_id = '_'.join([x for x in format_id_parts if x is not None])
|
||||
|
||||
ext = determine_ext(url)
|
||||
if ext == 'm3u8':
|
||||
for format_ in self._extract_m3u8_formats(
|
||||
url, video_id, m3u8_id=format_id, fatal=False):
|
||||
formats[format_['format_id']] = format_
|
||||
continue
|
||||
elif ext == 'mpd':
|
||||
for format_ in self._extract_mpd_formats(
|
||||
url, video_id, mpd_id=format_id, fatal=False):
|
||||
formats[format_['format_id']] = format_
|
||||
continue
|
||||
|
||||
current_format['url'] = url
|
||||
quality_data = video_instance.get('videoQuality')
|
||||
if quality_data:
|
||||
quality = quality_data.get('name') or quality_data.get('description')
|
||||
else:
|
||||
quality = None
|
||||
|
||||
height = None
|
||||
if quality:
|
||||
height = int_or_none(self._search_regex(r'(\d+)p?$', quality, 'Video format height', default=None))
|
||||
|
||||
if height is None:
|
||||
self.report_warning('Could not get height of video')
|
||||
else:
|
||||
current_format['height'] = height
|
||||
current_format['format_id'] = format_id
|
||||
|
||||
formats[current_format['format_id']] = current_format
|
||||
|
||||
formats = list(formats.values())
|
||||
self._sort_formats(formats)
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'display_id': display_id,
|
||||
'title': title,
|
||||
'description': description,
|
||||
'series': series,
|
||||
'episode': episode_name,
|
||||
'episode_number': int_or_none(episode_number),
|
||||
'thumbnails': thumbnails,
|
||||
'duration': duration,
|
||||
'formats': formats,
|
||||
'season': season,
|
||||
'season_number': season_number,
|
||||
'season_id': season_id,
|
||||
}
|
||||
|
||||
|
||||
class AnimeLabShowsIE(AnimeLabBaseIE):
|
||||
_VALID_URL = r'https?://(?:www\.)?animelab\.com/shows/(?P<id>[^/]+)'
|
||||
|
||||
_TEST = {
|
||||
'url': 'https://www.animelab.com/shows/attack-on-titan',
|
||||
'info_dict': {
|
||||
'id': '45',
|
||||
'title': 'Attack on Titan',
|
||||
'description': 'md5:989d95a2677e9309368d5cf39ba91469',
|
||||
},
|
||||
'playlist_count': 59,
|
||||
'skip': 'All AnimeLab content requires authentication',
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
_BASE_URL = 'http://www.animelab.com'
|
||||
_SHOWS_API_URL = '/api/videoentries/show/videos/'
|
||||
display_id = self._match_id(url)
|
||||
|
||||
webpage = self._download_webpage(url, display_id, 'Downloading requested URL')
|
||||
|
||||
show_data_str = self._search_regex(r'({"id":.*}),\svideoEntry', webpage, 'AnimeLab show data')
|
||||
show_data = self._parse_json(show_data_str, display_id)
|
||||
|
||||
show_id = str_or_none(show_data.get('id'))
|
||||
title = show_data.get('name')
|
||||
description = show_data.get('shortSynopsis') or show_data.get('longSynopsis')
|
||||
|
||||
entries = []
|
||||
for season in show_data['seasons']:
|
||||
season_id = season['id']
|
||||
get_data = urlencode_postdata({
|
||||
'seasonId': season_id,
|
||||
'limit': 1000,
|
||||
})
|
||||
# despite using urlencode_postdata, we are sending a GET request
|
||||
target_url = _BASE_URL + _SHOWS_API_URL + show_id + "?" + get_data.decode('utf-8')
|
||||
response = self._download_webpage(
|
||||
target_url,
|
||||
None, 'Season id %s' % season_id)
|
||||
|
||||
season_data = self._parse_json(response, display_id)
|
||||
|
||||
for video_data in season_data['list']:
|
||||
entries.append(self.url_result(
|
||||
_BASE_URL + '/player/' + video_data['slug'], 'AnimeLab',
|
||||
str_or_none(video_data.get('id')), video_data.get('name')
|
||||
))
|
||||
|
||||
return {
|
||||
'_type': 'playlist',
|
||||
'id': show_id,
|
||||
'title': title,
|
||||
'description': description,
|
||||
'entries': entries,
|
||||
}
|
||||
|
||||
# TODO implement myqueue
|
||||
@@ -116,6 +116,8 @@ class AnimeOnDemandIE(InfoExtractor):
|
||||
r'(?s)<div[^>]+itemprop="description"[^>]*>(.+?)</div>',
|
||||
webpage, 'anime description', default=None)
|
||||
|
||||
entries = []
|
||||
|
||||
def extract_info(html, video_id, num=None):
|
||||
title, description = [None] * 2
|
||||
formats = []
|
||||
@@ -231,7 +233,7 @@ class AnimeOnDemandIE(InfoExtractor):
|
||||
self._sort_formats(info['formats'])
|
||||
f = common_info.copy()
|
||||
f.update(info)
|
||||
yield f
|
||||
entries.append(f)
|
||||
|
||||
# Extract teaser/trailer only when full episode is not available
|
||||
if not info['formats']:
|
||||
@@ -245,7 +247,7 @@ class AnimeOnDemandIE(InfoExtractor):
|
||||
'title': m.group('title'),
|
||||
'url': urljoin(url, m.group('href')),
|
||||
})
|
||||
yield f
|
||||
entries.append(f)
|
||||
|
||||
def extract_episodes(html):
|
||||
for num, episode_html in enumerate(re.findall(
|
||||
@@ -273,8 +275,7 @@ class AnimeOnDemandIE(InfoExtractor):
|
||||
'episode_number': episode_number,
|
||||
}
|
||||
|
||||
for e in extract_entries(episode_html, video_id, common_info):
|
||||
yield e
|
||||
extract_entries(episode_html, video_id, common_info)
|
||||
|
||||
def extract_film(html, video_id):
|
||||
common_info = {
|
||||
@@ -282,18 +283,11 @@ class AnimeOnDemandIE(InfoExtractor):
|
||||
'title': anime_title,
|
||||
'description': anime_description,
|
||||
}
|
||||
for e in extract_entries(html, video_id, common_info):
|
||||
yield e
|
||||
extract_entries(html, video_id, common_info)
|
||||
|
||||
def entries():
|
||||
has_episodes = False
|
||||
for e in extract_episodes(webpage):
|
||||
has_episodes = True
|
||||
yield e
|
||||
extract_episodes(webpage)
|
||||
|
||||
if not has_episodes:
|
||||
for e in extract_film(webpage, anime_id):
|
||||
yield e
|
||||
if not entries:
|
||||
extract_film(webpage, anime_id)
|
||||
|
||||
return self.playlist_result(
|
||||
entries(), anime_id, anime_title, anime_description)
|
||||
return self.playlist_result(entries, anime_id, anime_title, anime_description)
|
||||
|
||||
@@ -1,61 +0,0 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
clean_podcast_url,
|
||||
int_or_none,
|
||||
parse_iso8601,
|
||||
try_get,
|
||||
)
|
||||
|
||||
|
||||
class ApplePodcastsIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://podcasts\.apple\.com/(?:[^/]+/)?podcast(?:/[^/]+){1,2}.*?\bi=(?P<id>\d+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://podcasts.apple.com/us/podcast/207-whitney-webb-returns/id1135137367?i=1000482637777',
|
||||
'md5': 'df02e6acb11c10e844946a39e7222b08',
|
||||
'info_dict': {
|
||||
'id': '1000482637777',
|
||||
'ext': 'mp3',
|
||||
'title': '207 - Whitney Webb Returns',
|
||||
'description': 'md5:13a73bade02d2e43737751e3987e1399',
|
||||
'upload_date': '20200705',
|
||||
'timestamp': 1593921600,
|
||||
'duration': 6425,
|
||||
'series': 'The Tim Dillon Show',
|
||||
}
|
||||
}, {
|
||||
'url': 'https://podcasts.apple.com/podcast/207-whitney-webb-returns/id1135137367?i=1000482637777',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://podcasts.apple.com/podcast/207-whitney-webb-returns?i=1000482637777',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://podcasts.apple.com/podcast/id1135137367?i=1000482637777',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
episode_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, episode_id)
|
||||
ember_data = self._parse_json(self._search_regex(
|
||||
r'id="shoebox-ember-data-store"[^>]*>\s*({.+?})\s*<',
|
||||
webpage, 'ember data'), episode_id)
|
||||
episode = ember_data['data']['attributes']
|
||||
description = episode.get('description') or {}
|
||||
|
||||
series = None
|
||||
for inc in (ember_data.get('included') or []):
|
||||
if inc.get('type') == 'media/podcast':
|
||||
series = try_get(inc, lambda x: x['attributes']['name'])
|
||||
|
||||
return {
|
||||
'id': episode_id,
|
||||
'title': episode['name'],
|
||||
'url': clean_podcast_url(episode['assetUrl']),
|
||||
'description': description.get('standard') or description.get('short'),
|
||||
'timestamp': parse_iso8601(episode.get('releaseDateTime')),
|
||||
'duration': int_or_none(episode.get('durationInMilliseconds'), 1000),
|
||||
'series': series,
|
||||
}
|
||||
@@ -1,43 +1,27 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
import json
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import compat_urllib_parse_unquote_plus
|
||||
from ..utils import (
|
||||
KNOWN_EXTENSIONS,
|
||||
|
||||
extract_attributes,
|
||||
unified_strdate,
|
||||
unified_timestamp,
|
||||
clean_html,
|
||||
dict_get,
|
||||
parse_duration,
|
||||
int_or_none,
|
||||
str_or_none,
|
||||
merge_dicts,
|
||||
)
|
||||
|
||||
|
||||
class ArchiveOrgIE(InfoExtractor):
|
||||
IE_NAME = 'archive.org'
|
||||
IE_DESC = 'archive.org video and audio'
|
||||
_VALID_URL = r'https?://(?:www\.)?archive\.org/(?:details|embed)/(?P<id>[^?#]+)(?:[?].*)?$'
|
||||
IE_DESC = 'archive.org videos'
|
||||
_VALID_URL = r'https?://(?:www\.)?archive\.org/(?:details|embed)/(?P<id>[^/?#]+)(?:[?].*)?$'
|
||||
_TESTS = [{
|
||||
'url': 'http://archive.org/details/XD300-23_68HighlightsAResearchCntAugHumanIntellect',
|
||||
'md5': '8af1d4cf447933ed3c7f4871162602db',
|
||||
'info_dict': {
|
||||
'id': 'XD300-23_68HighlightsAResearchCntAugHumanIntellect',
|
||||
'ext': 'ogv',
|
||||
'ext': 'ogg',
|
||||
'title': '1968 Demo - FJCC Conference Presentation Reel #1',
|
||||
'description': 'md5:da45c349df039f1cc8075268eb1b5c25',
|
||||
'release_date': '19681210',
|
||||
'timestamp': 1268695290,
|
||||
'upload_date': '20100315',
|
||||
'creator': 'SRI International',
|
||||
'uploader': 'laura@archive.org',
|
||||
},
|
||||
'upload_date': '19681210',
|
||||
'uploader': 'SRI International'
|
||||
}
|
||||
}, {
|
||||
'url': 'https://archive.org/details/Cops1922',
|
||||
'md5': '0869000b4ce265e8ca62738b336b268a',
|
||||
@@ -45,199 +29,37 @@ class ArchiveOrgIE(InfoExtractor):
|
||||
'id': 'Cops1922',
|
||||
'ext': 'mp4',
|
||||
'title': 'Buster Keaton\'s "Cops" (1922)',
|
||||
'description': 'md5:43a603fd6c5b4b90d12a96b921212b9c',
|
||||
'uploader': 'yorkmba99@hotmail.com',
|
||||
'timestamp': 1387699629,
|
||||
'upload_date': "20131222",
|
||||
},
|
||||
'description': 'md5:89e7c77bf5d965dd5c0372cfb49470f6',
|
||||
}
|
||||
}, {
|
||||
'url': 'http://archive.org/embed/XD300-23_68HighlightsAResearchCntAugHumanIntellect',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://archive.org/details/Election_Ads',
|
||||
'md5': '284180e857160cf866358700bab668a3',
|
||||
'info_dict': {
|
||||
'id': 'Election_Ads/Commercial-JFK1960ElectionAdCampaignJingle.mpg',
|
||||
'title': 'Commercial-JFK1960ElectionAdCampaignJingle.mpg',
|
||||
'ext': 'mp4',
|
||||
},
|
||||
}, {
|
||||
'url': 'https://archive.org/details/Election_Ads/Commercial-Nixon1960ElectionAdToughonDefense.mpg',
|
||||
'md5': '7915213ef02559b5501fe630e1a53f59',
|
||||
'info_dict': {
|
||||
'id': 'Election_Ads/Commercial-Nixon1960ElectionAdToughonDefense.mpg',
|
||||
'title': 'Commercial-Nixon1960ElectionAdToughonDefense.mpg',
|
||||
'ext': 'mp4',
|
||||
'timestamp': 1205588045,
|
||||
'uploader': 'mikedavisstripmaster@yahoo.com',
|
||||
'description': '1960 Presidential Campaign Election Commercials John F Kennedy, Richard M Nixon',
|
||||
'upload_date': '20080315',
|
||||
},
|
||||
}, {
|
||||
'url': 'https://archive.org/details/gd1977-05-08.shure57.stevenson.29303.flac16',
|
||||
'md5': '7d07ffb42aba6537c28e053efa4b54c9',
|
||||
'info_dict': {
|
||||
'id': 'gd1977-05-08.shure57.stevenson.29303.flac16/gd1977-05-08d01t01.flac',
|
||||
'title': 'Turning',
|
||||
'ext': 'flac',
|
||||
},
|
||||
}, {
|
||||
'url': 'https://archive.org/details/gd1977-05-08.shure57.stevenson.29303.flac16/gd1977-05-08d01t07.flac',
|
||||
'md5': 'a07cd8c6ab4ee1560f8a0021717130f3',
|
||||
'info_dict': {
|
||||
'id': 'gd1977-05-08.shure57.stevenson.29303.flac16/gd1977-05-08d01t07.flac',
|
||||
'title': 'Deal',
|
||||
'ext': 'flac',
|
||||
'timestamp': 1205895624,
|
||||
'uploader': 'mvernon54@yahoo.com',
|
||||
'description': 'md5:6a31f1996db0aa0fc9da6d6e708a1bb0',
|
||||
'upload_date': '20080319',
|
||||
'location': 'Barton Hall - Cornell University',
|
||||
},
|
||||
}, {
|
||||
'url': 'https://archive.org/details/lp_the-music-of-russia_various-artists-a-askaryan-alexander-melik',
|
||||
'md5': '7cb019baa9b332e82ea7c10403acd180',
|
||||
'info_dict': {
|
||||
'id': 'lp_the-music-of-russia_various-artists-a-askaryan-alexander-melik/disc1/01.01. Bells Of Rostov.mp3',
|
||||
'title': 'Bells Of Rostov',
|
||||
'ext': 'mp3',
|
||||
},
|
||||
}, {
|
||||
'url': 'https://archive.org/details/lp_the-music-of-russia_various-artists-a-askaryan-alexander-melik/disc1/02.02.+Song+And+Chorus+In+The+Polovetsian+Camp+From+%22Prince+Igor%22+(Act+2%2C+Scene+1).mp3',
|
||||
'md5': '1d0aabe03edca83ca58d9ed3b493a3c3',
|
||||
'info_dict': {
|
||||
'id': 'lp_the-music-of-russia_various-artists-a-askaryan-alexander-melik/disc1/02.02. Song And Chorus In The Polovetsian Camp From "Prince Igor" (Act 2, Scene 1).mp3',
|
||||
'title': 'Song And Chorus In The Polovetsian Camp From "Prince Igor" (Act 2, Scene 1)',
|
||||
'ext': 'mp3',
|
||||
'timestamp': 1569662587,
|
||||
'uploader': 'associate-joygen-odiongan@archive.org',
|
||||
'description': 'md5:012b2d668ae753be36896f343d12a236',
|
||||
'upload_date': '20190928',
|
||||
},
|
||||
}]
|
||||
|
||||
@staticmethod
|
||||
def _playlist_data(webpage):
|
||||
element = re.findall(r'''(?xs)
|
||||
<input
|
||||
(?:\s+[a-zA-Z0-9:._-]+(?:=[a-zA-Z0-9:._-]*|="[^"]*"|='[^']*'|))*?
|
||||
\s+class=['"]?js-play8-playlist['"]?
|
||||
(?:\s+[a-zA-Z0-9:._-]+(?:=[a-zA-Z0-9:._-]*|="[^"]*"|='[^']*'|))*?
|
||||
\s*/>
|
||||
''', webpage)[0]
|
||||
|
||||
return json.loads(extract_attributes(element)['value'])
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = compat_urllib_parse_unquote_plus(self._match_id(url))
|
||||
identifier, entry_id = (video_id.split('/', 1) + [None])[:2]
|
||||
video_id = self._match_id(url)
|
||||
webpage = self._download_webpage(
|
||||
'http://archive.org/embed/' + video_id, video_id)
|
||||
jwplayer_playlist = self._parse_json(self._search_regex(
|
||||
r"(?s)Play\('[^']+'\s*,\s*(\[.+\])\s*,\s*{.*?}\)",
|
||||
webpage, 'jwplayer playlist'), video_id)
|
||||
info = self._parse_jwplayer_data(
|
||||
{'playlist': jwplayer_playlist}, video_id, base_url=url)
|
||||
|
||||
# Archive.org metadata API doesn't clearly demarcate playlist entries
|
||||
# or subtitle tracks, so we get them from the embeddable player.
|
||||
embed_page = self._download_webpage(
|
||||
'https://archive.org/embed/' + identifier, identifier)
|
||||
playlist = self._playlist_data(embed_page)
|
||||
|
||||
entries = {}
|
||||
for p in playlist:
|
||||
# If the user specified a playlist entry in the URL, ignore the
|
||||
# rest of the playlist.
|
||||
if entry_id and p['orig'] != entry_id:
|
||||
continue
|
||||
|
||||
entries[p['orig']] = {
|
||||
'formats': [],
|
||||
'thumbnails': [],
|
||||
'artist': p.get('artist'),
|
||||
'track': p.get('title'),
|
||||
'subtitles': {}}
|
||||
|
||||
for track in p.get('tracks', []):
|
||||
if track['kind'] != 'subtitles':
|
||||
continue
|
||||
|
||||
entries[p['orig']][track['label']] = {
|
||||
'url': 'https://archive.org/' + track['file'].lstrip('/')}
|
||||
def get_optional(metadata, field):
|
||||
return metadata.get(field, [None])[0]
|
||||
|
||||
metadata = self._download_json(
|
||||
'http://archive.org/metadata/' + identifier, identifier)
|
||||
m = metadata['metadata']
|
||||
identifier = m['identifier']
|
||||
|
||||
info = {
|
||||
'id': identifier,
|
||||
'title': m['title'],
|
||||
'description': clean_html(m.get('description')),
|
||||
'uploader': dict_get(m, ['uploader', 'adder']),
|
||||
'creator': m.get('creator'),
|
||||
'license': m.get('licenseurl'),
|
||||
'release_date': unified_strdate(m.get('date')),
|
||||
'timestamp': unified_timestamp(dict_get(m, ['publicdate', 'addeddate'])),
|
||||
'webpage_url': 'https://archive.org/details/' + identifier,
|
||||
'location': m.get('venue'),
|
||||
'release_year': int_or_none(m.get('year'))}
|
||||
|
||||
for f in metadata['files']:
|
||||
if f['name'] in entries:
|
||||
entries[f['name']] = merge_dicts(entries[f['name']], {
|
||||
'id': identifier + '/' + f['name'],
|
||||
'title': f.get('title') or f['name'],
|
||||
'display_id': f['name'],
|
||||
'description': clean_html(f.get('description')),
|
||||
'creator': f.get('creator'),
|
||||
'duration': parse_duration(f.get('length')),
|
||||
'track_number': int_or_none(f.get('track')),
|
||||
'album': f.get('album'),
|
||||
'discnumber': int_or_none(f.get('disc')),
|
||||
'release_year': int_or_none(f.get('year'))})
|
||||
entry = entries[f['name']]
|
||||
elif f.get('original') in entries:
|
||||
entry = entries[f['original']]
|
||||
else:
|
||||
continue
|
||||
|
||||
if f.get('format') == 'Thumbnail':
|
||||
entry['thumbnails'].append({
|
||||
'id': f['name'],
|
||||
'url': 'https://archive.org/download/' + identifier + '/' + f['name'],
|
||||
'width': int_or_none(f.get('width')),
|
||||
'height': int_or_none(f.get('width')),
|
||||
'filesize': int_or_none(f.get('size'))})
|
||||
|
||||
extension = (f['name'].rsplit('.', 1) + [None])[1]
|
||||
if extension in KNOWN_EXTENSIONS:
|
||||
entry['formats'].append({
|
||||
'url': 'https://archive.org/download/' + identifier + '/' + f['name'],
|
||||
'format': f.get('format'),
|
||||
'width': int_or_none(f.get('width')),
|
||||
'height': int_or_none(f.get('height')),
|
||||
'filesize': int_or_none(f.get('size')),
|
||||
'protocol': 'https'})
|
||||
|
||||
# Sort available formats by filesize
|
||||
for entry in entries.values():
|
||||
entry['formats'] = list(sorted(entry['formats'], key=lambda x: x.get('filesize', -1)))
|
||||
|
||||
if len(entries) == 1:
|
||||
# If there's only one item, use it as the main info dict
|
||||
only_video = entries[list(entries.keys())[0]]
|
||||
if entry_id:
|
||||
info = merge_dicts(only_video, info)
|
||||
else:
|
||||
info = merge_dicts(info, only_video)
|
||||
else:
|
||||
# Otherwise, we have a playlist.
|
||||
info['_type'] = 'playlist'
|
||||
info['entries'] = list(entries.values())
|
||||
|
||||
if metadata.get('reviews'):
|
||||
info['comments'] = []
|
||||
for review in metadata['reviews']:
|
||||
info['comments'].append({
|
||||
'id': review.get('review_id'),
|
||||
'author': review.get('reviewer'),
|
||||
'text': str_or_none(review.get('reviewtitle'), '') + '\n\n' + review.get('reviewbody'),
|
||||
'timestamp': unified_timestamp(review.get('createdate')),
|
||||
'parent': 'root'})
|
||||
|
||||
'http://archive.org/details/' + video_id, video_id, query={
|
||||
'output': 'json',
|
||||
})['metadata']
|
||||
info.update({
|
||||
'title': get_optional(metadata, 'title') or info.get('title'),
|
||||
'description': clean_html(get_optional(metadata, 'description')),
|
||||
})
|
||||
if info.get('_type') != 'playlist':
|
||||
info.update({
|
||||
'uploader': get_optional(metadata, 'creator'),
|
||||
'upload_date': unified_strdate(get_optional(metadata, 'date')),
|
||||
})
|
||||
return info
|
||||
|
||||
@@ -1,103 +0,0 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import extract_attributes
|
||||
|
||||
|
||||
class BFMTVBaseIE(InfoExtractor):
|
||||
_VALID_URL_BASE = r'https?://(?:www\.)?bfmtv\.com/'
|
||||
_VALID_URL_TMPL = _VALID_URL_BASE + r'(?:[^/]+/)*[^/?&#]+_%s[A-Z]-(?P<id>\d{12})\.html'
|
||||
_VIDEO_BLOCK_REGEX = r'(<div[^>]+class="video_block"[^>]*>)'
|
||||
BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/%s/%s_default/index.html?videoId=%s'
|
||||
|
||||
def _brightcove_url_result(self, video_id, video_block):
|
||||
account_id = video_block.get('accountid') or '876450612001'
|
||||
player_id = video_block.get('playerid') or 'I2qBTln4u'
|
||||
return self.url_result(
|
||||
self.BRIGHTCOVE_URL_TEMPLATE % (account_id, player_id, video_id),
|
||||
'BrightcoveNew', video_id)
|
||||
|
||||
|
||||
class BFMTVIE(BFMTVBaseIE):
|
||||
IE_NAME = 'bfmtv'
|
||||
_VALID_URL = BFMTVBaseIE._VALID_URL_TMPL % 'V'
|
||||
_TESTS = [{
|
||||
'url': 'https://www.bfmtv.com/politique/emmanuel-macron-l-islam-est-une-religion-qui-vit-une-crise-aujourd-hui-partout-dans-le-monde_VN-202010020146.html',
|
||||
'info_dict': {
|
||||
'id': '6196747868001',
|
||||
'ext': 'mp4',
|
||||
'title': 'Emmanuel Macron: "L\'Islam est une religion qui vit une crise aujourd’hui, partout dans le monde"',
|
||||
'description': 'Le Président s\'exprime sur la question du séparatisme depuis les Mureaux, dans les Yvelines.',
|
||||
'uploader_id': '876450610001',
|
||||
'upload_date': '20201002',
|
||||
'timestamp': 1601629620,
|
||||
},
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
bfmtv_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, bfmtv_id)
|
||||
video_block = extract_attributes(self._search_regex(
|
||||
self._VIDEO_BLOCK_REGEX, webpage, 'video block'))
|
||||
return self._brightcove_url_result(video_block['videoid'], video_block)
|
||||
|
||||
|
||||
class BFMTVLiveIE(BFMTVIE):
|
||||
IE_NAME = 'bfmtv:live'
|
||||
_VALID_URL = BFMTVBaseIE._VALID_URL_BASE + '(?P<id>(?:[^/]+/)?en-direct)'
|
||||
_TESTS = [{
|
||||
'url': 'https://www.bfmtv.com/en-direct/',
|
||||
'info_dict': {
|
||||
'id': '5615950982001',
|
||||
'ext': 'mp4',
|
||||
'title': r're:^le direct BFMTV WEB \d{4}-\d{2}-\d{2} \d{2}:\d{2}$',
|
||||
'uploader_id': '876450610001',
|
||||
'upload_date': '20171018',
|
||||
'timestamp': 1508329950,
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
}, {
|
||||
'url': 'https://www.bfmtv.com/economie/en-direct/',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
|
||||
class BFMTVArticleIE(BFMTVBaseIE):
|
||||
IE_NAME = 'bfmtv:article'
|
||||
_VALID_URL = BFMTVBaseIE._VALID_URL_TMPL % 'A'
|
||||
_TESTS = [{
|
||||
'url': 'https://www.bfmtv.com/sante/covid-19-un-responsable-de-l-institut-pasteur-se-demande-quand-la-france-va-se-reconfiner_AV-202101060198.html',
|
||||
'info_dict': {
|
||||
'id': '202101060198',
|
||||
'title': 'Covid-19: un responsable de l\'Institut Pasteur se demande "quand la France va se reconfiner"',
|
||||
'description': 'md5:947974089c303d3ac6196670ae262843',
|
||||
},
|
||||
'playlist_count': 2,
|
||||
}, {
|
||||
'url': 'https://www.bfmtv.com/international/pour-bolsonaro-le-bresil-est-en-faillite-mais-il-ne-peut-rien-faire_AD-202101060232.html',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.bfmtv.com/sante/covid-19-oui-le-vaccin-de-pfizer-distribue-en-france-a-bien-ete-teste-sur-des-personnes-agees_AN-202101060275.html',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
bfmtv_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, bfmtv_id)
|
||||
|
||||
entries = []
|
||||
for video_block_el in re.findall(self._VIDEO_BLOCK_REGEX, webpage):
|
||||
video_block = extract_attributes(video_block_el)
|
||||
video_id = video_block.get('videoid')
|
||||
if not video_id:
|
||||
continue
|
||||
entries.append(self._brightcove_url_result(video_id, video_block))
|
||||
|
||||
return self.playlist_result(
|
||||
entries, bfmtv_id, self._og_search_title(webpage, fatal=False),
|
||||
self._html_search_meta(['og:description', 'description'], webpage))
|
||||
@@ -1,30 +0,0 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
|
||||
|
||||
class BibelTVIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?bibeltv\.de/mediathek/videos/(?:crn/)?(?P<id>\d+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://www.bibeltv.de/mediathek/videos/329703-sprachkurs-in-malaiisch',
|
||||
'md5': '252f908192d611de038b8504b08bf97f',
|
||||
'info_dict': {
|
||||
'id': 'ref:329703',
|
||||
'ext': 'mp4',
|
||||
'title': 'Sprachkurs in Malaiisch',
|
||||
'description': 'md5:3e9f197d29ee164714e67351cf737dfe',
|
||||
'timestamp': 1608316701,
|
||||
'uploader_id': '5840105145001',
|
||||
'upload_date': '20201218',
|
||||
}
|
||||
}, {
|
||||
'url': 'https://www.bibeltv.de/mediathek/videos/crn/326374',
|
||||
'only_matching': True,
|
||||
}]
|
||||
BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/5840105145001/default_default/index.html?videoId=ref:%s'
|
||||
|
||||
def _real_extract(self, url):
|
||||
crn_id = self._match_id(url)
|
||||
return self.url_result(
|
||||
self.BRIGHTCOVE_URL_TEMPLATE % crn_id, 'BrightcoveNew')
|
||||
@@ -7,12 +7,12 @@ from .common import InfoExtractor
|
||||
from .gigya import GigyaBaseIE
|
||||
from ..compat import compat_HTTPError
|
||||
from ..utils import (
|
||||
extract_attributes,
|
||||
ExtractorError,
|
||||
strip_or_none,
|
||||
float_or_none,
|
||||
int_or_none,
|
||||
merge_dicts,
|
||||
parse_iso8601,
|
||||
str_or_none,
|
||||
url_or_none,
|
||||
)
|
||||
@@ -37,7 +37,6 @@ class CanvasIE(InfoExtractor):
|
||||
'url': 'https://mediazone.vrt.be/api/v1/canvas/assets/mz-ast-5e5f90b6-2d72-4c40-82c2-e134f884e93e',
|
||||
'only_matching': True,
|
||||
}]
|
||||
_GEO_BYPASS = False
|
||||
_HLS_ENTRY_PROTOCOLS_MAP = {
|
||||
'HLS': 'm3u8_native',
|
||||
'HLS_AES': 'm3u8',
|
||||
@@ -48,34 +47,29 @@ class CanvasIE(InfoExtractor):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
site_id, video_id = mobj.group('site_id'), mobj.group('id')
|
||||
|
||||
data = None
|
||||
if site_id != 'vrtvideo':
|
||||
# Old API endpoint, serves more formats but may fail for some videos
|
||||
data = self._download_json(
|
||||
'https://mediazone.vrt.be/api/v1/%s/assets/%s'
|
||||
% (site_id, video_id), video_id, 'Downloading asset JSON',
|
||||
'Unable to download asset JSON', fatal=False)
|
||||
# Old API endpoint, serves more formats but may fail for some videos
|
||||
data = self._download_json(
|
||||
'https://mediazone.vrt.be/api/v1/%s/assets/%s'
|
||||
% (site_id, video_id), video_id, 'Downloading asset JSON',
|
||||
'Unable to download asset JSON', fatal=False)
|
||||
|
||||
# New API endpoint
|
||||
if not data:
|
||||
headers = self.geo_verification_headers()
|
||||
headers.update({'Content-Type': 'application/json'})
|
||||
token = self._download_json(
|
||||
'%s/tokens' % self._REST_API_BASE, video_id,
|
||||
'Downloading token', data=b'', headers=headers)['vrtPlayerToken']
|
||||
'Downloading token', data=b'',
|
||||
headers={'Content-Type': 'application/json'})['vrtPlayerToken']
|
||||
data = self._download_json(
|
||||
'%s/videos/%s' % (self._REST_API_BASE, video_id),
|
||||
video_id, 'Downloading video JSON', query={
|
||||
video_id, 'Downloading video JSON', fatal=False, query={
|
||||
'vrtPlayerToken': token,
|
||||
'client': '%s@PROD' % site_id,
|
||||
}, expected_status=400)
|
||||
if not data.get('title'):
|
||||
code = data.get('code')
|
||||
if code == 'AUTHENTICATION_REQUIRED':
|
||||
self.raise_login_required()
|
||||
elif code == 'INVALID_LOCATION':
|
||||
self.raise_geo_restricted(countries=['BE'])
|
||||
raise ExtractorError(data.get('message') or code, expected=True)
|
||||
message = data.get('message')
|
||||
if message and not data.get('title'):
|
||||
if data.get('code') == 'AUTHENTICATION_REQUIRED':
|
||||
self.raise_login_required(message)
|
||||
raise ExtractorError(message, expected=True)
|
||||
|
||||
title = data['title']
|
||||
description = data.get('description')
|
||||
@@ -211,24 +205,20 @@ class CanvasEenIE(InfoExtractor):
|
||||
|
||||
class VrtNUIE(GigyaBaseIE):
|
||||
IE_DESC = 'VrtNU.be'
|
||||
_VALID_URL = r'https?://(?:www\.)?vrt\.be/vrtnu/a-z/(?:[^/]+/){2}(?P<id>[^/?#&]+)'
|
||||
_VALID_URL = r'https?://(?:www\.)?vrt\.be/(?P<site_id>vrtnu)/(?:[^/]+/)*(?P<id>[^/?#&]+)'
|
||||
_TESTS = [{
|
||||
# Available via old API endpoint
|
||||
'url': 'https://www.vrt.be/vrtnu/a-z/postbus-x/1989/postbus-x-s1989a1/',
|
||||
'url': 'https://www.vrt.be/vrtnu/a-z/postbus-x/1/postbus-x-s1a1/',
|
||||
'info_dict': {
|
||||
'id': 'pbs-pub-e8713dac-899e-41de-9313-81269f4c04ac$vid-90c932b1-e21d-4fb8-99b1-db7b49cf74de',
|
||||
'id': 'pbs-pub-2e2d8c27-df26-45c9-9dc6-90c78153044d$vid-90c932b1-e21d-4fb8-99b1-db7b49cf74de',
|
||||
'ext': 'mp4',
|
||||
'title': 'Postbus X - Aflevering 1 (Seizoen 1989)',
|
||||
'description': 'md5:b704f669eb9262da4c55b33d7c6ed4b7',
|
||||
'title': 'De zwarte weduwe',
|
||||
'description': 'md5:db1227b0f318c849ba5eab1fef895ee4',
|
||||
'duration': 1457.04,
|
||||
'thumbnail': r're:^https?://.*\.jpg$',
|
||||
'series': 'Postbus X',
|
||||
'season': 'Seizoen 1989',
|
||||
'season_number': 1989,
|
||||
'episode': 'De zwarte weduwe',
|
||||
'season': 'Season 1',
|
||||
'season_number': 1,
|
||||
'episode_number': 1,
|
||||
'timestamp': 1595822400,
|
||||
'upload_date': '20200727',
|
||||
},
|
||||
'skip': 'This video is only available for registered users',
|
||||
'params': {
|
||||
@@ -310,25 +300,69 @@ class VrtNUIE(GigyaBaseIE):
|
||||
def _real_extract(self, url):
|
||||
display_id = self._match_id(url)
|
||||
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
|
||||
attrs = extract_attributes(self._search_regex(
|
||||
r'(<nui-media[^>]+>)', webpage, 'media element'))
|
||||
video_id = attrs['videoid']
|
||||
publication_id = attrs.get('publicationid')
|
||||
if publication_id:
|
||||
video_id = publication_id + '$' + video_id
|
||||
|
||||
page = (self._parse_json(self._search_regex(
|
||||
r'digitalData\s*=\s*({.+?});', webpage, 'digial data',
|
||||
default='{}'), video_id, fatal=False) or {}).get('page') or {}
|
||||
webpage, urlh = self._download_webpage_handle(url, display_id)
|
||||
|
||||
info = self._search_json_ld(webpage, display_id, default={})
|
||||
|
||||
# title is optional here since it may be extracted by extractor
|
||||
# that is delegated from here
|
||||
title = strip_or_none(self._html_search_regex(
|
||||
r'(?ms)<h1 class="content__heading">(.+?)</h1>',
|
||||
webpage, 'title', default=None))
|
||||
|
||||
description = self._html_search_regex(
|
||||
r'(?ms)<div class="content__description">(.+?)</div>',
|
||||
webpage, 'description', default=None)
|
||||
|
||||
season = self._html_search_regex(
|
||||
[r'''(?xms)<div\ class="tabs__tab\ tabs__tab--active">\s*
|
||||
<span>seizoen\ (.+?)</span>\s*
|
||||
</div>''',
|
||||
r'<option value="seizoen (\d{1,3})" data-href="[^"]+?" selected>'],
|
||||
webpage, 'season', default=None)
|
||||
|
||||
season_number = int_or_none(season)
|
||||
|
||||
episode_number = int_or_none(self._html_search_regex(
|
||||
r'''(?xms)<div\ class="content__episode">\s*
|
||||
<abbr\ title="aflevering">afl</abbr>\s*<span>(\d+)</span>
|
||||
</div>''',
|
||||
webpage, 'episode_number', default=None))
|
||||
|
||||
release_date = parse_iso8601(self._html_search_regex(
|
||||
r'(?ms)<div class="content__broadcastdate">\s*<time\ datetime="(.+?)"',
|
||||
webpage, 'release_date', default=None))
|
||||
|
||||
# If there's a ? or a # in the URL, remove them and everything after
|
||||
clean_url = urlh.geturl().split('?')[0].split('#')[0].strip('/')
|
||||
securevideo_url = clean_url + '.mssecurevideo.json'
|
||||
|
||||
try:
|
||||
video = self._download_json(securevideo_url, display_id)
|
||||
except ExtractorError as e:
|
||||
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
|
||||
self.raise_login_required()
|
||||
raise
|
||||
|
||||
# We are dealing with a '../<show>.relevant' URL
|
||||
redirect_url = video.get('url')
|
||||
if redirect_url:
|
||||
return self.url_result(self._proto_relative_url(redirect_url, 'https:'))
|
||||
|
||||
# There is only one entry, but with an unknown key, so just get
|
||||
# the first one
|
||||
video_id = list(video.values())[0].get('videoid')
|
||||
|
||||
return merge_dicts(info, {
|
||||
'_type': 'url_transparent',
|
||||
'url': 'https://mediazone.vrt.be/api/v1/vrtvideo/assets/%s' % video_id,
|
||||
'ie_key': CanvasIE.ie_key(),
|
||||
'id': video_id,
|
||||
'display_id': display_id,
|
||||
'season_number': int_or_none(page.get('episode_season')),
|
||||
'title': title,
|
||||
'description': description,
|
||||
'season': season,
|
||||
'season_number': season_number,
|
||||
'episode_number': episode_number,
|
||||
'release_date': release_date,
|
||||
})
|
||||
|
||||
@@ -8,14 +8,11 @@ from ..utils import (
|
||||
ExtractorError,
|
||||
extract_attributes,
|
||||
find_xpath_attr,
|
||||
get_element_by_attribute,
|
||||
get_element_by_class,
|
||||
int_or_none,
|
||||
js_to_json,
|
||||
merge_dicts,
|
||||
parse_iso8601,
|
||||
smuggle_url,
|
||||
str_to_int,
|
||||
unescapeHTML,
|
||||
)
|
||||
from .senateisvp import SenateISVPIE
|
||||
@@ -119,30 +116,8 @@ class CSpanIE(InfoExtractor):
|
||||
jwsetup, video_id, require_title=False, m3u8_id='hls',
|
||||
base_url=url)
|
||||
add_referer(info['formats'])
|
||||
for subtitles in info['subtitles'].values():
|
||||
for subtitle in subtitles:
|
||||
ext = determine_ext(subtitle['url'])
|
||||
if ext == 'php':
|
||||
ext = 'vtt'
|
||||
subtitle['ext'] = ext
|
||||
ld_info = self._search_json_ld(webpage, video_id, default={})
|
||||
title = get_element_by_class('video-page-title', webpage) or \
|
||||
self._og_search_title(webpage)
|
||||
description = get_element_by_attribute('itemprop', 'description', webpage) or \
|
||||
self._html_search_meta(['og:description', 'description'], webpage)
|
||||
return merge_dicts(info, ld_info, {
|
||||
'title': title,
|
||||
'thumbnail': get_element_by_attribute('itemprop', 'thumbnailUrl', webpage),
|
||||
'description': description,
|
||||
'timestamp': parse_iso8601(get_element_by_attribute('itemprop', 'uploadDate', webpage)),
|
||||
'location': get_element_by_attribute('itemprop', 'contentLocation', webpage),
|
||||
'duration': int_or_none(self._search_regex(
|
||||
r'jwsetup\.seclength\s*=\s*(\d+);',
|
||||
webpage, 'duration', fatal=False)),
|
||||
'view_count': str_to_int(self._search_regex(
|
||||
r"<span[^>]+class='views'[^>]*>([\d,]+)\s+Views</span>",
|
||||
webpage, 'views', fatal=False)),
|
||||
})
|
||||
return merge_dicts(info, ld_info)
|
||||
|
||||
# Obsolete
|
||||
# We first look for clipid, because clipprog always appears before
|
||||
|
||||
@@ -17,12 +17,7 @@ from ..utils import (
|
||||
class DPlayIE(InfoExtractor):
|
||||
_VALID_URL = r'''(?x)https?://
|
||||
(?P<domain>
|
||||
(?:www\.)?(?P<host>d
|
||||
(?:
|
||||
play\.(?P<country>dk|fi|jp|se|no)|
|
||||
iscoveryplus\.(?P<plus_country>dk|es|fi|it|se|no)
|
||||
)
|
||||
)|
|
||||
(?:www\.)?(?P<host>dplay\.(?P<country>dk|fi|jp|se|no))|
|
||||
(?P<subdomain_country>es|it)\.dplay\.com
|
||||
)/[^/]+/(?P<id>[^/]+/[^/?#]+)'''
|
||||
|
||||
@@ -131,24 +126,6 @@ class DPlayIE(InfoExtractor):
|
||||
}, {
|
||||
'url': 'https://www.dplay.jp/video/gold-rush/24086',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.discoveryplus.se/videos/nugammalt-77-handelser-som-format-sverige/nugammalt-77-handelser-som-format-sverige-101',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.discoveryplus.dk/videoer/ted-bundy-mind-of-a-monster/ted-bundy-mind-of-a-monster',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.discoveryplus.no/videoer/i-kongens-klr/sesong-1-episode-7',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.discoveryplus.it/videos/biografie-imbarazzanti/luigi-di-maio-la-psicosi-di-stanislawskij',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.discoveryplus.es/videos/la-fiebre-del-oro/temporada-8-episodio-1',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.discoveryplus.fi/videot/shifting-gears-with-aaron-kaufman/episode-16',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _get_disco_api_info(self, url, display_id, disco_host, realm, country):
|
||||
@@ -264,7 +241,7 @@ class DPlayIE(InfoExtractor):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
display_id = mobj.group('id')
|
||||
domain = mobj.group('domain').lstrip('www.')
|
||||
country = mobj.group('country') or mobj.group('subdomain_country') or mobj.group('plus_country')
|
||||
host = 'disco-api.' + domain if domain[0] == 'd' else 'eu2-prod.disco-api.com'
|
||||
country = mobj.group('country') or mobj.group('subdomain_country')
|
||||
host = 'disco-api.' + domain if domain.startswith('dplay.') else 'eu2-prod.disco-api.com'
|
||||
return self._get_disco_api_info(
|
||||
url, display_id, host, 'dplay' + country, country)
|
||||
|
||||
@@ -46,10 +46,6 @@ from .alura import (
|
||||
AluraCourseIE
|
||||
)
|
||||
from .amcnetworks import AMCNetworksIE
|
||||
from .animelab import (
|
||||
AnimeLabIE,
|
||||
AnimeLabShowsIE,
|
||||
)
|
||||
from .americastestkitchen import AmericasTestKitchenIE
|
||||
from .animeondemand import AnimeOnDemandIE
|
||||
from .anvato import AnvatoIE
|
||||
@@ -63,7 +59,6 @@ from .appletrailers import (
|
||||
AppleTrailersIE,
|
||||
AppleTrailersSectionIE,
|
||||
)
|
||||
from .applepodcasts import ApplePodcastsIE
|
||||
from .archiveorg import ArchiveOrgIE
|
||||
from .arcpublishing import ArcPublishingIE
|
||||
from .arkena import ArkenaIE
|
||||
@@ -109,12 +104,6 @@ from .bellmedia import BellMediaIE
|
||||
from .beatport import BeatportIE
|
||||
from .bet import BetIE
|
||||
from .bfi import BFIPlayerIE
|
||||
from .bfmtv import (
|
||||
BFMTVIE,
|
||||
BFMTVLiveIE,
|
||||
BFMTVArticleIE,
|
||||
)
|
||||
from .bibeltv import BibelTVIE
|
||||
from .bigflix import BigflixIE
|
||||
from .bild import BildIE
|
||||
from .bilibili import (
|
||||
@@ -453,10 +442,7 @@ from .go import GoIE
|
||||
from .godtube import GodTubeIE
|
||||
from .golem import GolemIE
|
||||
from .googledrive import GoogleDriveIE
|
||||
from .googlepodcasts import (
|
||||
GooglePodcastsIE,
|
||||
GooglePodcastsFeedIE,
|
||||
)
|
||||
from .googleplus import GooglePlusIE
|
||||
from .googlesearch import GoogleSearchIE
|
||||
from .goshgay import GoshgayIE
|
||||
from .gputechconf import GPUTechConfIE
|
||||
@@ -498,10 +484,6 @@ from .ign import (
|
||||
OneUPIE,
|
||||
PCMagIE,
|
||||
)
|
||||
from .iheart import (
|
||||
IHeartRadioIE,
|
||||
IHeartRadioPodcastIE,
|
||||
)
|
||||
from .imdb import (
|
||||
ImdbIE,
|
||||
ImdbListIE
|
||||
@@ -551,10 +533,7 @@ from .karaoketv import KaraoketvIE
|
||||
from .karrierevideos import KarriereVideosIE
|
||||
from .keezmovies import KeezMoviesIE
|
||||
from .ketnet import KetnetIE
|
||||
from .khanacademy import (
|
||||
KhanAcademyIE,
|
||||
KhanAcademyUnitIE,
|
||||
)
|
||||
from .khanacademy import KhanAcademyIE
|
||||
from .kickstarter import KickStarterIE
|
||||
from .kinja import KinjaEmbedIE
|
||||
from .kinopoisk import KinoPoiskIE
|
||||
|
||||
73
youtube_dlc/extractor/googleplus.py
Normal file
73
youtube_dlc/extractor/googleplus.py
Normal file
@@ -0,0 +1,73 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
import codecs
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import unified_strdate
|
||||
|
||||
|
||||
class GooglePlusIE(InfoExtractor):
|
||||
IE_DESC = 'Google Plus'
|
||||
_VALID_URL = r'https?://plus\.google\.com/(?:[^/]+/)*?posts/(?P<id>\w+)'
|
||||
IE_NAME = 'plus.google'
|
||||
_TEST = {
|
||||
'url': 'https://plus.google.com/u/0/108897254135232129896/posts/ZButuJc6CtH',
|
||||
'info_dict': {
|
||||
'id': 'ZButuJc6CtH',
|
||||
'ext': 'flv',
|
||||
'title': '嘆きの天使 降臨',
|
||||
'upload_date': '20120613',
|
||||
'uploader': '井上ヨシマサ',
|
||||
}
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
# Step 1, Retrieve post webpage to extract further information
|
||||
webpage = self._download_webpage(url, video_id, 'Downloading entry webpage')
|
||||
|
||||
title = self._og_search_description(webpage).splitlines()[0]
|
||||
upload_date = unified_strdate(self._html_search_regex(
|
||||
r'''(?x)<a.+?class="o-U-s\s[^"]+"\s+style="display:\s*none"\s*>
|
||||
([0-9]{4}-[0-9]{2}-[0-9]{2})</a>''',
|
||||
webpage, 'upload date', fatal=False, flags=re.VERBOSE))
|
||||
uploader = self._html_search_regex(
|
||||
r'rel="author".*?>(.*?)</a>', webpage, 'uploader', fatal=False)
|
||||
|
||||
# Step 2, Simulate clicking the image box to launch video
|
||||
DOMAIN = 'https://plus.google.com/'
|
||||
video_page = self._search_regex(
|
||||
r'<a href="((?:%s)?photos/.*?)"' % re.escape(DOMAIN),
|
||||
webpage, 'video page URL')
|
||||
if not video_page.startswith(DOMAIN):
|
||||
video_page = DOMAIN + video_page
|
||||
|
||||
webpage = self._download_webpage(video_page, video_id, 'Downloading video page')
|
||||
|
||||
def unicode_escape(s):
|
||||
decoder = codecs.getdecoder('unicode_escape')
|
||||
return re.sub(
|
||||
r'\\u[0-9a-fA-F]{4,}',
|
||||
lambda m: decoder(m.group(0))[0],
|
||||
s)
|
||||
|
||||
# Extract video links all sizes
|
||||
formats = [{
|
||||
'url': unicode_escape(video_url),
|
||||
'ext': 'flv',
|
||||
'width': int(width),
|
||||
'height': int(height),
|
||||
} for width, height, video_url in re.findall(
|
||||
r'\d+,(\d+),(\d+),"(https?://[^.]+\.googleusercontent\.com.*?)"', webpage)]
|
||||
self._sort_formats(formats)
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'uploader': uploader,
|
||||
'upload_date': upload_date,
|
||||
'formats': formats,
|
||||
}
|
||||
@@ -1,88 +0,0 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import json
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
clean_podcast_url,
|
||||
int_or_none,
|
||||
try_get,
|
||||
urlencode_postdata,
|
||||
)
|
||||
|
||||
|
||||
class GooglePodcastsBaseIE(InfoExtractor):
|
||||
_VALID_URL_BASE = r'https?://podcasts\.google\.com/feed/'
|
||||
|
||||
def _batch_execute(self, func_id, video_id, params):
|
||||
return json.loads(self._download_json(
|
||||
'https://podcasts.google.com/_/PodcastsUi/data/batchexecute',
|
||||
video_id, data=urlencode_postdata({
|
||||
'f.req': json.dumps([[[func_id, json.dumps(params), None, '1']]]),
|
||||
}), transform_source=lambda x: self._search_regex(r'(?s)(\[.+\])', x, 'data'))[0][2])
|
||||
|
||||
def _extract_episode(self, episode):
|
||||
return {
|
||||
'id': episode[4][3],
|
||||
'title': episode[8],
|
||||
'url': clean_podcast_url(episode[13]),
|
||||
'thumbnail': episode[2],
|
||||
'description': episode[9],
|
||||
'creator': try_get(episode, lambda x: x[14]),
|
||||
'timestamp': int_or_none(episode[11]),
|
||||
'duration': int_or_none(episode[12]),
|
||||
'series': episode[1],
|
||||
}
|
||||
|
||||
|
||||
class GooglePodcastsIE(GooglePodcastsBaseIE):
|
||||
IE_NAME = 'google:podcasts'
|
||||
_VALID_URL = GooglePodcastsBaseIE._VALID_URL_BASE + r'(?P<feed_url>[^/]+)/episode/(?P<id>[^/?&#]+)'
|
||||
_TEST = {
|
||||
'url': 'https://podcasts.google.com/feed/aHR0cHM6Ly9mZWVkcy5ucHIub3JnLzM0NDA5ODUzOS9wb2RjYXN0LnhtbA/episode/MzBlNWRlN2UtOWE4Yy00ODcwLTk2M2MtM2JlMmUyNmViOTRh',
|
||||
'md5': 'fa56b2ee8bd0703e27e42d4b104c4766',
|
||||
'info_dict': {
|
||||
'id': '30e5de7e-9a8c-4870-963c-3be2e26eb94a',
|
||||
'ext': 'mp3',
|
||||
'title': 'WWDTM New Year 2021',
|
||||
'description': 'We say goodbye to 2020 with Christine Baranksi, Doug Jones, Jonna Mendez, and Kellee Edwards.',
|
||||
'upload_date': '20210102',
|
||||
'timestamp': 1609606800,
|
||||
'duration': 2901,
|
||||
'series': "Wait Wait... Don't Tell Me!",
|
||||
}
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
b64_feed_url, b64_guid = re.match(self._VALID_URL, url).groups()
|
||||
episode = self._batch_execute(
|
||||
'oNjqVe', b64_guid, [b64_feed_url, b64_guid])[1]
|
||||
return self._extract_episode(episode)
|
||||
|
||||
|
||||
class GooglePodcastsFeedIE(GooglePodcastsBaseIE):
|
||||
IE_NAME = 'google:podcasts:feed'
|
||||
_VALID_URL = GooglePodcastsBaseIE._VALID_URL_BASE + r'(?P<id>[^/?&#]+)/?(?:[?#&]|$)'
|
||||
_TEST = {
|
||||
'url': 'https://podcasts.google.com/feed/aHR0cHM6Ly9mZWVkcy5ucHIub3JnLzM0NDA5ODUzOS9wb2RjYXN0LnhtbA',
|
||||
'info_dict': {
|
||||
'title': "Wait Wait... Don't Tell Me!",
|
||||
'description': "NPR's weekly current events quiz. Have a laugh and test your news knowledge while figuring out what's real and what we've made up.",
|
||||
},
|
||||
'playlist_mincount': 20,
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
b64_feed_url = self._match_id(url)
|
||||
data = self._batch_execute('ncqJEe', b64_feed_url, [b64_feed_url])
|
||||
|
||||
entries = []
|
||||
for episode in (try_get(data, lambda x: x[1][0]) or []):
|
||||
entries.append(self._extract_episode(episode))
|
||||
|
||||
feed = try_get(data, lambda x: x[3]) or []
|
||||
return self.playlist_result(
|
||||
entries, playlist_title=try_get(feed, lambda x: x[0]),
|
||||
playlist_description=try_get(feed, lambda x: x[2]))
|
||||
@@ -1,97 +0,0 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
clean_html,
|
||||
clean_podcast_url,
|
||||
int_or_none,
|
||||
str_or_none,
|
||||
)
|
||||
|
||||
|
||||
class IHeartRadioBaseIE(InfoExtractor):
|
||||
def _call_api(self, path, video_id, fatal=True, query=None):
|
||||
return self._download_json(
|
||||
'https://api.iheart.com/api/v3/podcast/' + path,
|
||||
video_id, fatal=fatal, query=query)
|
||||
|
||||
def _extract_episode(self, episode):
|
||||
return {
|
||||
'thumbnail': episode.get('imageUrl'),
|
||||
'description': clean_html(episode.get('description')),
|
||||
'timestamp': int_or_none(episode.get('startDate'), 1000),
|
||||
'duration': int_or_none(episode.get('duration')),
|
||||
}
|
||||
|
||||
|
||||
class IHeartRadioIE(IHeartRadioBaseIE):
|
||||
IENAME = 'iheartradio'
|
||||
_VALID_URL = r'(?:https?://(?:www\.)?iheart\.com/podcast/[^/]+/episode/(?P<display_id>[^/?&#]+)-|iheartradio:)(?P<id>\d+)'
|
||||
_TEST = {
|
||||
'url': 'https://www.iheart.com/podcast/105-behind-the-bastards-29236323/episode/part-one-alexander-lukashenko-the-dictator-70346499/?embed=true',
|
||||
'md5': 'c8609c92c8688dcb69d8541042b8abca',
|
||||
'info_dict': {
|
||||
'id': '70346499',
|
||||
'ext': 'mp3',
|
||||
'title': 'Part One: Alexander Lukashenko: The Dictator of Belarus',
|
||||
'description': 'md5:96cc7297b3a5a9ebae28643801c96fae',
|
||||
'timestamp': 1597741200,
|
||||
'upload_date': '20200818',
|
||||
}
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
episode_id = self._match_id(url)
|
||||
episode = self._call_api(
|
||||
'episodes/' + episode_id, episode_id)['episode']
|
||||
info = self._extract_episode(episode)
|
||||
info.update({
|
||||
'id': episode_id,
|
||||
'title': episode['title'],
|
||||
'url': clean_podcast_url(episode['mediaUrl']),
|
||||
})
|
||||
return info
|
||||
|
||||
|
||||
class IHeartRadioPodcastIE(IHeartRadioBaseIE):
|
||||
IE_NAME = 'iheartradio:podcast'
|
||||
_VALID_URL = r'https?://(?:www\.)?iheart(?:podcastnetwork)?\.com/podcast/[^/?&#]+-(?P<id>\d+)/?(?:[?#&]|$)'
|
||||
_TESTS = [{
|
||||
'url': 'https://www.iheart.com/podcast/1119-it-could-happen-here-30717896/',
|
||||
'info_dict': {
|
||||
'id': '30717896',
|
||||
'title': 'It Could Happen Here',
|
||||
'description': 'md5:5842117412a967eb0b01f8088eb663e2',
|
||||
},
|
||||
'playlist_mincount': 11,
|
||||
}, {
|
||||
'url': 'https://www.iheartpodcastnetwork.com/podcast/105-stuff-you-should-know-26940277',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
podcast_id = self._match_id(url)
|
||||
path = 'podcasts/' + podcast_id
|
||||
episodes = self._call_api(
|
||||
path + '/episodes', podcast_id, query={'limit': 1000000000})['data']
|
||||
|
||||
entries = []
|
||||
for episode in episodes:
|
||||
episode_id = str_or_none(episode.get('id'))
|
||||
if not episode_id:
|
||||
continue
|
||||
info = self._extract_episode(episode)
|
||||
info.update({
|
||||
'_type': 'url',
|
||||
'id': episode_id,
|
||||
'title': episode.get('title'),
|
||||
'url': 'iheartradio:' + episode_id,
|
||||
'ie_key': IHeartRadioIE.ie_key(),
|
||||
})
|
||||
entries.append(info)
|
||||
|
||||
podcast = self._call_api(path, podcast_id, False) or {}
|
||||
|
||||
return self.playlist_result(
|
||||
entries, podcast_id, podcast.get('title'), podcast.get('description'))
|
||||
@@ -2,71 +2,92 @@ from __future__ import unicode_literals
|
||||
|
||||
from .canvas import CanvasIE
|
||||
from .common import InfoExtractor
|
||||
from ..compat import compat_urllib_parse_unquote
|
||||
from ..utils import (
|
||||
int_or_none,
|
||||
parse_iso8601,
|
||||
)
|
||||
|
||||
|
||||
class KetnetIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?ketnet\.be/(?P<id>(?:[^/]+/)*[^/?#&]+)'
|
||||
_VALID_URL = r'https?://(?:www\.)?ketnet\.be/(?:[^/]+/)*(?P<id>[^/?#&]+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://www.ketnet.be/kijken/n/nachtwacht/3/nachtwacht-s3a1-de-greystook',
|
||||
'md5': '37b2b7bb9b3dcaa05b67058dc3a714a9',
|
||||
'url': 'https://www.ketnet.be/kijken/zomerse-filmpjes',
|
||||
'md5': '6bdeb65998930251bbd1c510750edba9',
|
||||
'info_dict': {
|
||||
'id': 'pbs-pub-aef8b526-115e-4006-aa24-e59ff6c6ef6f$vid-ddb815bf-c8e7-467b-8879-6bad7a32cebd',
|
||||
'id': 'zomerse-filmpjes',
|
||||
'ext': 'mp4',
|
||||
'title': 'Nachtwacht - Reeks 3: Aflevering 1',
|
||||
'description': 'De Nachtwacht krijgt te maken met een parasiet',
|
||||
'title': 'Gluur mee op de filmset en op Pennenzakkenrock',
|
||||
'description': 'Gluur mee met Ghost Rockers op de filmset',
|
||||
'thumbnail': r're:^https?://.*\.jpg$',
|
||||
'duration': 1468.02,
|
||||
'timestamp': 1609225200,
|
||||
'upload_date': '20201229',
|
||||
'series': 'Nachtwacht',
|
||||
'season': 'Reeks 3',
|
||||
'episode': 'De Greystook',
|
||||
'episode_number': 1,
|
||||
}
|
||||
}, {
|
||||
# mzid in playerConfig instead of sources
|
||||
'url': 'https://www.ketnet.be/kijken/nachtwacht/de-greystook',
|
||||
'md5': '90139b746a0a9bd7bb631283f6e2a64e',
|
||||
'info_dict': {
|
||||
'id': 'md-ast-4ac54990-ce66-4d00-a8ca-9eac86f4c475',
|
||||
'display_id': 'md-ast-4ac54990-ce66-4d00-a8ca-9eac86f4c475',
|
||||
'ext': 'flv',
|
||||
'title': 'Nachtwacht: De Greystook',
|
||||
'description': 'md5:1db3f5dc4c7109c821261e7512975be7',
|
||||
'thumbnail': r're:^https?://.*\.jpg$',
|
||||
'duration': 1468.03,
|
||||
},
|
||||
'expected_warnings': ['is not a supported codec', 'Unknown MIME type'],
|
||||
}, {
|
||||
'url': 'https://www.ketnet.be/themas/karrewiet/jaaroverzicht-20200/karrewiet-het-jaar-van-black-mamba',
|
||||
'url': 'https://www.ketnet.be/kijken/karrewiet/uitzending-8-september-2016',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.ketnet.be/achter-de-schermen/sien-repeteert-voor-stars-for-life',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# mzsource, geo restricted to Belgium
|
||||
'url': 'https://www.ketnet.be/kijken/nachtwacht/de-bermadoe',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
display_id = self._match_id(url)
|
||||
video_id = self._match_id(url)
|
||||
|
||||
video = self._download_json(
|
||||
'https://senior-bff.ketnet.be/graphql', display_id, query={
|
||||
'query': '''{
|
||||
video(id: "content/ketnet/nl/%s.model.json") {
|
||||
description
|
||||
episodeNr
|
||||
imageUrl
|
||||
mediaReference
|
||||
programTitle
|
||||
publicationDate
|
||||
seasonTitle
|
||||
subtitleVideodetail
|
||||
titleVideodetail
|
||||
}
|
||||
}''' % display_id,
|
||||
})['data']['video']
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
mz_id = compat_urllib_parse_unquote(video['mediaReference'])
|
||||
config = self._parse_json(
|
||||
self._search_regex(
|
||||
r'(?s)playerConfig\s*=\s*({.+?})\s*;', webpage,
|
||||
'player config'),
|
||||
video_id)
|
||||
|
||||
mzid = config.get('mzid')
|
||||
if mzid:
|
||||
return self.url_result(
|
||||
'https://mediazone.vrt.be/api/v1/ketnet/assets/%s' % mzid,
|
||||
CanvasIE.ie_key(), video_id=mzid)
|
||||
|
||||
title = config['title']
|
||||
|
||||
formats = []
|
||||
for source_key in ('', 'mz'):
|
||||
source = config.get('%ssource' % source_key)
|
||||
if not isinstance(source, dict):
|
||||
continue
|
||||
for format_id, format_url in source.items():
|
||||
if format_id == 'hls':
|
||||
formats.extend(self._extract_m3u8_formats(
|
||||
format_url, video_id, 'mp4',
|
||||
entry_protocol='m3u8_native', m3u8_id=format_id,
|
||||
fatal=False))
|
||||
elif format_id == 'hds':
|
||||
formats.extend(self._extract_f4m_formats(
|
||||
format_url, video_id, f4m_id=format_id, fatal=False))
|
||||
else:
|
||||
formats.append({
|
||||
'url': format_url,
|
||||
'format_id': format_id,
|
||||
})
|
||||
self._sort_formats(formats)
|
||||
|
||||
return {
|
||||
'_type': 'url_transparent',
|
||||
'id': mz_id,
|
||||
'title': video['titleVideodetail'],
|
||||
'url': 'https://mediazone.vrt.be/api/v1/ketnet/assets/' + mz_id,
|
||||
'thumbnail': video.get('imageUrl'),
|
||||
'description': video.get('description'),
|
||||
'timestamp': parse_iso8601(video.get('publicationDate')),
|
||||
'series': video.get('programTitle'),
|
||||
'season': video.get('seasonTitle'),
|
||||
'episode': video.get('subtitleVideodetail'),
|
||||
'episode_number': int_or_none(video.get('episodeNr')),
|
||||
'ie_key': CanvasIE.ie_key(),
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'description': config.get('description'),
|
||||
'thumbnail': config.get('image'),
|
||||
'series': config.get('program'),
|
||||
'episode': config.get('episode'),
|
||||
'formats': formats,
|
||||
}
|
||||
|
||||
@@ -1,107 +1,82 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import json
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
int_or_none,
|
||||
parse_iso8601,
|
||||
try_get,
|
||||
unified_strdate,
|
||||
)
|
||||
|
||||
|
||||
class KhanAcademyBaseIE(InfoExtractor):
|
||||
_VALID_URL_TEMPL = r'https?://(?:www\.)?khanacademy\.org/(?P<id>(?:[^/]+/){%s}%s[^?#/&]+)'
|
||||
class KhanAcademyIE(InfoExtractor):
|
||||
_VALID_URL = r'^https?://(?:(?:www|api)\.)?khanacademy\.org/(?P<key>[^/]+)/(?:[^/]+/){,2}(?P<id>[^?#/]+)(?:$|[?#])'
|
||||
IE_NAME = 'KhanAcademy'
|
||||
|
||||
def _parse_video(self, video):
|
||||
return {
|
||||
'_type': 'url_transparent',
|
||||
'url': video['youtubeId'],
|
||||
'id': video.get('slug'),
|
||||
'title': video.get('title'),
|
||||
'thumbnail': video.get('imageUrl') or video.get('thumbnailUrl'),
|
||||
'duration': int_or_none(video.get('duration')),
|
||||
'description': video.get('description'),
|
||||
'ie_key': 'Youtube',
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
display_id = self._match_id(url)
|
||||
component_props = self._parse_json(self._download_json(
|
||||
'https://www.khanacademy.org/api/internal/graphql',
|
||||
display_id, query={
|
||||
'hash': 1604303425,
|
||||
'variables': json.dumps({
|
||||
'path': display_id,
|
||||
'queryParams': '',
|
||||
}),
|
||||
})['data']['contentJson'], display_id)['componentProps']
|
||||
return self._parse_component_props(component_props)
|
||||
|
||||
|
||||
class KhanAcademyIE(KhanAcademyBaseIE):
|
||||
IE_NAME = 'khanacademy'
|
||||
_VALID_URL = KhanAcademyBaseIE._VALID_URL_TEMPL % ('4', 'v/')
|
||||
_TEST = {
|
||||
'url': 'https://www.khanacademy.org/computing/computer-science/cryptography/crypt/v/one-time-pad',
|
||||
'md5': '9c84b7b06f9ebb80d22a5c8dedefb9a0',
|
||||
_TESTS = [{
|
||||
'url': 'http://www.khanacademy.org/video/one-time-pad',
|
||||
'md5': '7b391cce85e758fb94f763ddc1bbb979',
|
||||
'info_dict': {
|
||||
'id': 'FlIG3TvQCBQ',
|
||||
'ext': 'mp4',
|
||||
'id': 'one-time-pad',
|
||||
'ext': 'webm',
|
||||
'title': 'The one-time pad',
|
||||
'description': 'The perfect cipher',
|
||||
'duration': 176,
|
||||
'uploader': 'Brit Cruise',
|
||||
'uploader_id': 'khanacademy',
|
||||
'upload_date': '20120411',
|
||||
'timestamp': 1334170113,
|
||||
'license': 'cc-by-nc-sa',
|
||||
},
|
||||
'add_ie': ['Youtube'],
|
||||
}
|
||||
|
||||
def _parse_component_props(self, component_props):
|
||||
video = component_props['tutorialPageData']['contentModel']
|
||||
info = self._parse_video(video)
|
||||
author_names = video.get('authorNames')
|
||||
info.update({
|
||||
'uploader': ', '.join(author_names) if author_names else None,
|
||||
'timestamp': parse_iso8601(video.get('dateAdded')),
|
||||
'license': video.get('kaUserLicense'),
|
||||
})
|
||||
return info
|
||||
|
||||
|
||||
class KhanAcademyUnitIE(KhanAcademyBaseIE):
|
||||
IE_NAME = 'khanacademy:unit'
|
||||
_VALID_URL = (KhanAcademyBaseIE._VALID_URL_TEMPL % ('2', '')) + '/?(?:[?#&]|$)'
|
||||
_TEST = {
|
||||
'url': 'https://www.khanacademy.org/computing/computer-science/cryptography',
|
||||
}, {
|
||||
'url': 'https://www.khanacademy.org/math/applied-math/cryptography',
|
||||
'info_dict': {
|
||||
'id': 'cryptography',
|
||||
'title': 'Cryptography',
|
||||
'title': 'Journey into cryptography',
|
||||
'description': 'How have humans protected their secret messages through history? What has changed today?',
|
||||
},
|
||||
'playlist_mincount': 31,
|
||||
}
|
||||
'playlist_mincount': 3,
|
||||
}]
|
||||
|
||||
def _parse_component_props(self, component_props):
|
||||
curation = component_props['curation']
|
||||
def _real_extract(self, url):
|
||||
m = re.match(self._VALID_URL, url)
|
||||
video_id = m.group('id')
|
||||
|
||||
entries = []
|
||||
tutorials = try_get(curation, lambda x: x['tabs'][0]['modules'][0]['tutorials'], list) or []
|
||||
for tutorial_number, tutorial in enumerate(tutorials, 1):
|
||||
chapter_info = {
|
||||
'chapter': tutorial.get('title'),
|
||||
'chapter_number': tutorial_number,
|
||||
'chapter_id': tutorial.get('id'),
|
||||
if m.group('key') == 'video':
|
||||
data = self._download_json(
|
||||
'http://api.khanacademy.org/api/v1/videos/' + video_id,
|
||||
video_id, 'Downloading video info')
|
||||
|
||||
upload_date = unified_strdate(data['date_added'])
|
||||
uploader = ', '.join(data['author_names'])
|
||||
return {
|
||||
'_type': 'url_transparent',
|
||||
'url': data['url'],
|
||||
'id': video_id,
|
||||
'title': data['title'],
|
||||
'thumbnail': data['image_url'],
|
||||
'duration': data['duration'],
|
||||
'description': data['description'],
|
||||
'uploader': uploader,
|
||||
'upload_date': upload_date,
|
||||
}
|
||||
for content_item in (tutorial.get('contentItems') or []):
|
||||
if content_item.get('kind') == 'Video':
|
||||
info = self._parse_video(content_item)
|
||||
info.update(chapter_info)
|
||||
entries.append(info)
|
||||
else:
|
||||
# topic
|
||||
data = self._download_json(
|
||||
'http://api.khanacademy.org/api/v1/topic/' + video_id,
|
||||
video_id, 'Downloading topic info')
|
||||
|
||||
return self.playlist_result(
|
||||
entries, curation.get('unit'), curation.get('title'),
|
||||
curation.get('description'))
|
||||
entries = [
|
||||
{
|
||||
'_type': 'url',
|
||||
'url': c['url'],
|
||||
'id': c['id'],
|
||||
'title': c['title'],
|
||||
}
|
||||
for c in data['children'] if c['kind'] in ('Video', 'Topic')]
|
||||
|
||||
return {
|
||||
'_type': 'playlist',
|
||||
'id': video_id,
|
||||
'title': data['title'],
|
||||
'description': data['description'],
|
||||
'entries': entries,
|
||||
}
|
||||
|
||||
@@ -251,11 +251,8 @@ class MixcloudPlaylistBaseIE(MixcloudBaseIE):
|
||||
cloudcast_url = cloudcast.get('url')
|
||||
if not cloudcast_url:
|
||||
continue
|
||||
slug = try_get(cloudcast, lambda x: x['slug'], compat_str)
|
||||
owner_username = try_get(cloudcast, lambda x: x['owner']['username'], compat_str)
|
||||
video_id = '%s_%s' % (owner_username, slug) if slug and owner_username else None
|
||||
entries.append(self.url_result(
|
||||
cloudcast_url, MixcloudIE.ie_key(), video_id))
|
||||
cloudcast_url, MixcloudIE.ie_key(), cloudcast.get('slug')))
|
||||
|
||||
page_info = items['pageInfo']
|
||||
has_next_page = page_info['hasNextPage']
|
||||
@@ -324,8 +321,7 @@ class MixcloudUserIE(MixcloudPlaylistBaseIE):
|
||||
_DESCRIPTION_KEY = 'biog'
|
||||
_ROOT_TYPE = 'user'
|
||||
_NODE_TEMPLATE = '''slug
|
||||
url
|
||||
owner { username }'''
|
||||
url'''
|
||||
|
||||
def _get_playlist_title(self, title, slug):
|
||||
return '%s (%s)' % (title, slug)
|
||||
@@ -349,7 +345,6 @@ class MixcloudPlaylistIE(MixcloudPlaylistBaseIE):
|
||||
_NODE_TEMPLATE = '''cloudcast {
|
||||
slug
|
||||
url
|
||||
owner { username }
|
||||
}'''
|
||||
|
||||
def _get_cloudcast(self, node):
|
||||
|
||||
@@ -61,23 +61,6 @@ class MotherlessIE(InfoExtractor):
|
||||
# no keywords
|
||||
'url': 'http://motherless.com/8B4BBC1',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# see https://motherless.com/videos/recent for recent videos with
|
||||
# uploaded date in "ago" format
|
||||
'url': 'https://motherless.com/3C3E2CF',
|
||||
'info_dict': {
|
||||
'id': '3C3E2CF',
|
||||
'ext': 'mp4',
|
||||
'title': 'a/ Hot Teens',
|
||||
'categories': list,
|
||||
'upload_date': '20210104',
|
||||
'uploader_id': 'yonbiw',
|
||||
'thumbnail': r're:https?://.*\.jpg',
|
||||
'age_limit': 18,
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
@@ -102,28 +85,20 @@ class MotherlessIE(InfoExtractor):
|
||||
or 'http://cdn4.videos.motherlessmedia.com/videos/%s.mp4?fs=opencloud' % video_id)
|
||||
age_limit = self._rta_search(webpage)
|
||||
view_count = str_to_int(self._html_search_regex(
|
||||
(r'>([\d,.]+)\s+Views<', r'<strong>Views</strong>\s+([^<]+)<'),
|
||||
(r'>(\d+)\s+Views<', r'<strong>Views</strong>\s+([^<]+)<'),
|
||||
webpage, 'view count', fatal=False))
|
||||
like_count = str_to_int(self._html_search_regex(
|
||||
(r'>([\d,.]+)\s+Favorites<',
|
||||
r'<strong>Favorited</strong>\s+([^<]+)<'),
|
||||
(r'>(\d+)\s+Favorites<', r'<strong>Favorited</strong>\s+([^<]+)<'),
|
||||
webpage, 'like count', fatal=False))
|
||||
|
||||
upload_date = unified_strdate(self._search_regex(
|
||||
r'class=["\']count[^>]+>(\d+\s+[a-zA-Z]{3}\s+\d{4})<', webpage,
|
||||
'upload date', default=None))
|
||||
if not upload_date:
|
||||
uploaded_ago = self._search_regex(
|
||||
r'>\s*(\d+[hd])\s+[aA]go\b', webpage, 'uploaded ago',
|
||||
default=None)
|
||||
if uploaded_ago:
|
||||
delta = int(uploaded_ago[:-1])
|
||||
_AGO_UNITS = {
|
||||
'h': 'hours',
|
||||
'd': 'days',
|
||||
}
|
||||
kwargs = {_AGO_UNITS.get(uploaded_ago[-1]): delta}
|
||||
upload_date = (datetime.datetime.utcnow() - datetime.timedelta(**kwargs)).strftime('%Y%m%d')
|
||||
upload_date = self._html_search_regex(
|
||||
(r'class=["\']count[^>]+>(\d+\s+[a-zA-Z]{3}\s+\d{4})<',
|
||||
r'<strong>Uploaded</strong>\s+([^<]+)<'), webpage, 'upload date')
|
||||
if 'Ago' in upload_date:
|
||||
days = int(re.search(r'([0-9]+)', upload_date).group(1))
|
||||
upload_date = (datetime.datetime.now() - datetime.timedelta(days=days)).strftime('%Y%m%d')
|
||||
else:
|
||||
upload_date = unified_strdate(upload_date)
|
||||
|
||||
comment_count = webpage.count('class="media-comment-contents"')
|
||||
uploader_id = self._html_search_regex(
|
||||
|
||||
@@ -223,12 +223,12 @@ class NRKIE(NRKBaseIE):
|
||||
legal_age = try_get(
|
||||
data, lambda x: x['legalAge']['body']['rating']['code'], compat_str)
|
||||
# https://en.wikipedia.org/wiki/Norwegian_Media_Authority
|
||||
age_limit = None
|
||||
if legal_age:
|
||||
if legal_age == 'A':
|
||||
age_limit = 0
|
||||
elif legal_age.isdigit():
|
||||
age_limit = int_or_none(legal_age)
|
||||
if legal_age == 'A':
|
||||
age_limit = 0
|
||||
elif legal_age.isdigit():
|
||||
age_limit = int_or_none(legal_age)
|
||||
else:
|
||||
age_limit = None
|
||||
|
||||
is_series = try_get(data, lambda x: x['_links']['series']['name']) == 'series'
|
||||
|
||||
@@ -298,14 +298,6 @@ class NRKTVIE(InfoExtractor):
|
||||
'description': 'md5:46923a6e6510eefcce23d5ef2a58f2ce',
|
||||
'duration': 2223.44,
|
||||
'age_limit': 6,
|
||||
'subtitles': {
|
||||
'nb-nor': [{
|
||||
'ext': 'vtt',
|
||||
}],
|
||||
'nb-ttv': [{
|
||||
'ext': 'vtt',
|
||||
}]
|
||||
},
|
||||
},
|
||||
}, {
|
||||
'url': 'https://tv.nrk.no/serie/20-spoersmaal-tv/MUHH48000314/23-05-2014',
|
||||
|
||||
@@ -17,7 +17,6 @@ from ..utils import (
|
||||
get_exe_version,
|
||||
is_outdated_version,
|
||||
std_headers,
|
||||
process_communicate_or_kill,
|
||||
)
|
||||
|
||||
|
||||
@@ -227,7 +226,7 @@ class PhantomJSwrapper(object):
|
||||
self.exe, '--ssl-protocol=any',
|
||||
self._TMP_FILES['script'].name
|
||||
], stdout=subprocess.PIPE, stderr=subprocess.PIPE)
|
||||
out, err = process_communicate_or_kill(p)
|
||||
out, err = p.communicate()
|
||||
if p.returncode != 0:
|
||||
raise ExtractorError(
|
||||
'Executing JS failed\n:' + encodeArgument(err))
|
||||
|
||||
@@ -450,18 +450,6 @@ class PeerTubeIE(InfoExtractor):
|
||||
'tags': ['framasoft', 'peertube'],
|
||||
'categories': ['Science & Technology'],
|
||||
}
|
||||
}, {
|
||||
# Issue #26002
|
||||
'url': 'peertube:spacepub.space:d8943b2d-8280-497b-85ec-bc282ec2afdc',
|
||||
'info_dict': {
|
||||
'id': 'd8943b2d-8280-497b-85ec-bc282ec2afdc',
|
||||
'ext': 'mp4',
|
||||
'title': 'Dot matrix printer shell demo',
|
||||
'uploader_id': '3',
|
||||
'timestamp': 1587401293,
|
||||
'upload_date': '20200420',
|
||||
'uploader': 'Drew DeVault',
|
||||
}
|
||||
}, {
|
||||
'url': 'https://peertube.tamanoir.foucry.net/videos/watch/0b04f13d-1e18-4f1d-814e-4979aa7c9c44',
|
||||
'only_matching': True,
|
||||
@@ -538,15 +526,7 @@ class PeerTubeIE(InfoExtractor):
|
||||
title = video['name']
|
||||
|
||||
formats = []
|
||||
files = video.get('files') or []
|
||||
for playlist in (video.get('streamingPlaylists') or []):
|
||||
if not isinstance(playlist, dict):
|
||||
continue
|
||||
playlist_files = playlist.get('files')
|
||||
if not (playlist_files and isinstance(playlist_files, list)):
|
||||
continue
|
||||
files.extend(playlist_files)
|
||||
for file_ in files:
|
||||
for file_ in video['files']:
|
||||
if not isinstance(file_, dict):
|
||||
continue
|
||||
file_url = url_or_none(file_.get('fileUrl'))
|
||||
|
||||
@@ -103,28 +103,22 @@ class RaiBaseIE(InfoExtractor):
|
||||
}.items() if v is not None)
|
||||
|
||||
@staticmethod
|
||||
def _extract_subtitles(url, video_data):
|
||||
STL_EXT = 'stl'
|
||||
SRT_EXT = 'srt'
|
||||
def _extract_subtitles(url, subtitle_url):
|
||||
subtitles = {}
|
||||
subtitles_array = video_data.get('subtitlesArray') or []
|
||||
for k in ('subtitles', 'subtitlesUrl'):
|
||||
subtitles_array.append({'url': video_data.get(k)})
|
||||
for subtitle in subtitles_array:
|
||||
sub_url = subtitle.get('url')
|
||||
if sub_url and isinstance(sub_url, compat_str):
|
||||
sub_lang = subtitle.get('language') or 'it'
|
||||
sub_url = urljoin(url, sub_url)
|
||||
sub_ext = determine_ext(sub_url, SRT_EXT)
|
||||
subtitles.setdefault(sub_lang, []).append({
|
||||
'ext': sub_ext,
|
||||
'url': sub_url,
|
||||
if subtitle_url and isinstance(subtitle_url, compat_str):
|
||||
subtitle_url = urljoin(url, subtitle_url)
|
||||
STL_EXT = '.stl'
|
||||
SRT_EXT = '.srt'
|
||||
subtitles['it'] = [{
|
||||
'ext': 'stl',
|
||||
'url': subtitle_url,
|
||||
}]
|
||||
if subtitle_url.endswith(STL_EXT):
|
||||
srt_url = subtitle_url[:-len(STL_EXT)] + SRT_EXT
|
||||
subtitles['it'].append({
|
||||
'ext': 'srt',
|
||||
'url': srt_url,
|
||||
})
|
||||
if STL_EXT == sub_ext:
|
||||
subtitles[sub_lang].append({
|
||||
'ext': SRT_EXT,
|
||||
'url': sub_url[:-len(STL_EXT)] + SRT_EXT,
|
||||
})
|
||||
return subtitles
|
||||
|
||||
|
||||
@@ -144,9 +138,6 @@ class RaiPlayIE(RaiBaseIE):
|
||||
'duration': 6160,
|
||||
'series': 'Report',
|
||||
'season': '2013/14',
|
||||
'subtitles': {
|
||||
'it': 'count:2',
|
||||
},
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
@@ -154,10 +145,6 @@ class RaiPlayIE(RaiBaseIE):
|
||||
}, {
|
||||
'url': 'http://www.raiplay.it/video/2016/11/gazebotraindesi-efebe701-969c-4593-92f3-285f0d1ce750.html?',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# subtitles at 'subtitlesArray' key (see #27698)
|
||||
'url': 'https://www.raiplay.it/video/2020/12/Report---04-01-2021-2e90f1de-8eee-4de4-ac0e-78d21db5b600.html',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
@@ -184,7 +171,7 @@ class RaiPlayIE(RaiBaseIE):
|
||||
if date_published and time_published:
|
||||
date_published += ' ' + time_published
|
||||
|
||||
subtitles = self._extract_subtitles(url, video)
|
||||
subtitles = self._extract_subtitles(url, video.get('subtitles'))
|
||||
|
||||
program_info = media.get('program_info') or {}
|
||||
season = media.get('season')
|
||||
@@ -338,22 +325,6 @@ class RaiIE(RaiBaseIE):
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
}, {
|
||||
# ContentItem in iframe (see #12652) and subtitle at 'subtitlesUrl' key
|
||||
'url': 'http://www.presadiretta.rai.it/dl/portali/site/puntata/ContentItem-3ed19d13-26c2-46ff-a551-b10828262f1b.html',
|
||||
'info_dict': {
|
||||
'id': '1ad6dc64-444a-42a4-9bea-e5419ad2f5fd',
|
||||
'ext': 'mp4',
|
||||
'title': 'Partiti acchiappavoti - Presa diretta del 13/09/2015',
|
||||
'description': 'md5:d291b03407ec505f95f27970c0b025f4',
|
||||
'upload_date': '20150913',
|
||||
'subtitles': {
|
||||
'it': 'count:2',
|
||||
},
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
}, {
|
||||
# Direct MMS URL
|
||||
'url': 'http://www.rai.it/dl/RaiTV/programmi/media/ContentItem-b63a4089-ac28-48cf-bca5-9f5b5bc46df5.html',
|
||||
@@ -394,7 +365,7 @@ class RaiIE(RaiBaseIE):
|
||||
'url': compat_urlparse.urljoin(url, thumbnail_url),
|
||||
})
|
||||
|
||||
subtitles = self._extract_subtitles(url, media)
|
||||
subtitles = self._extract_subtitles(url, media.get('subtitlesUrl'))
|
||||
|
||||
info = {
|
||||
'id': content_id,
|
||||
@@ -431,8 +402,7 @@ class RaiIE(RaiBaseIE):
|
||||
r'''(?x)
|
||||
(?:
|
||||
(?:initEdizione|drawMediaRaiTV)\(|
|
||||
<(?:[^>]+\bdata-id|var\s+uniquename)=|
|
||||
<iframe[^>]+\bsrc=
|
||||
<(?:[^>]+\bdata-id|var\s+uniquename)=
|
||||
)
|
||||
(["\'])
|
||||
(?:(?!\1).)*\bContentItem-(?P<id>%s)
|
||||
|
||||
@@ -30,19 +30,6 @@ class RoosterTeethIE(InfoExtractor):
|
||||
'series': 'Million Dollars, But...',
|
||||
'episode': 'Million Dollars, But... The Game Announcement',
|
||||
},
|
||||
}, {
|
||||
'url': 'https://roosterteeth.com/watch/rwby-bonus-25',
|
||||
'md5': 'fe8d9d976b272c18a24fe7f1f5830084',
|
||||
'info_dict': {
|
||||
'id': '31',
|
||||
'display_id': 'rwby-bonus-25',
|
||||
'title': 'Volume 2, World of Remnant 3',
|
||||
'description': 'md5:8d58d3270292ea11da00ea712bbfb009',
|
||||
'episode': 'Volume 2, World of Remnant 3',
|
||||
'channel_id': 'fab60c1c-29cb-43bc-9383-5c3538d9e246',
|
||||
'thumbnail': r're:^https?://.*\.(png|jpe?g)$',
|
||||
'ext': 'mp4',
|
||||
},
|
||||
}, {
|
||||
'url': 'http://achievementhunter.roosterteeth.com/episode/off-topic-the-achievement-hunter-podcast-2016-i-didn-t-think-it-would-pass-31',
|
||||
'only_matching': True,
|
||||
@@ -63,7 +50,7 @@ class RoosterTeethIE(InfoExtractor):
|
||||
'url': 'https://roosterteeth.com/watch/million-dollars-but-season-2-million-dollars-but-the-game-announcement',
|
||||
'only_matching': True,
|
||||
}]
|
||||
_EPISODE_BASE_URL = 'https://svod-be.roosterteeth.com/api/v1/watch/'
|
||||
_EPISODE_BASE_URL = 'https://svod-be.roosterteeth.com/api/v1/episodes/'
|
||||
|
||||
def _login(self):
|
||||
username, password = self._get_login_info()
|
||||
@@ -99,11 +86,9 @@ class RoosterTeethIE(InfoExtractor):
|
||||
api_episode_url = self._EPISODE_BASE_URL + display_id
|
||||
|
||||
try:
|
||||
video_data = self._download_json(
|
||||
m3u8_url = self._download_json(
|
||||
api_episode_url + '/videos', display_id,
|
||||
'Downloading video JSON metadata')['data'][0]
|
||||
m3u8_url = video_data['attributes']['url']
|
||||
subtitle_m3u8_url = video_data['links']['download']
|
||||
'Downloading video JSON metadata')['data'][0]['attributes']['url']
|
||||
except ExtractorError as e:
|
||||
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
|
||||
if self._parse_json(e.cause.read().decode(), display_id).get('access') is False:
|
||||
@@ -124,7 +109,7 @@ class RoosterTeethIE(InfoExtractor):
|
||||
|
||||
thumbnails = []
|
||||
for image in episode.get('included', {}).get('images', []):
|
||||
if image.get('type') in ('episode_image', 'bonus_feature_image'):
|
||||
if image.get('type') == 'episode_image':
|
||||
img_attributes = image.get('attributes') or {}
|
||||
for k in ('thumb', 'small', 'medium', 'large'):
|
||||
img_url = img_attributes.get(k)
|
||||
@@ -134,33 +119,6 @@ class RoosterTeethIE(InfoExtractor):
|
||||
'url': img_url,
|
||||
})
|
||||
|
||||
subtitles = {}
|
||||
res = self._download_webpage_handle(
|
||||
subtitle_m3u8_url, display_id,
|
||||
'Downloading m3u8 information',
|
||||
'Failed to download m3u8 information',
|
||||
fatal=True, data=None, headers={}, query={})
|
||||
if res is not False:
|
||||
subtitle_m3u8_doc, _ = res
|
||||
for line in subtitle_m3u8_doc.split('\n'):
|
||||
if 'EXT-X-MEDIA:TYPE=SUBTITLES' in line:
|
||||
parts = line.split(',')
|
||||
for part in parts:
|
||||
if 'LANGUAGE' in part:
|
||||
lang = part[part.index('=') + 2:-1]
|
||||
elif 'URI' in part:
|
||||
uri = part[part.index('=') + 2:-1]
|
||||
res = self._download_webpage_handle(
|
||||
uri, display_id,
|
||||
'Downloading m3u8 information',
|
||||
'Failed to download m3u8 information',
|
||||
fatal=True, data=None, headers={}, query={})
|
||||
doc, _ = res
|
||||
for l in doc.split('\n'):
|
||||
if not l.startswith('#'):
|
||||
subtitles[lang] = [{'url': uri[:-uri[::-1].index('/')] + l}]
|
||||
break
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'display_id': display_id,
|
||||
@@ -176,5 +134,4 @@ class RoosterTeethIE(InfoExtractor):
|
||||
'formats': formats,
|
||||
'channel_id': attributes.get('channel_id'),
|
||||
'duration': int_or_none(attributes.get('length')),
|
||||
'subtitles': subtitles
|
||||
}
|
||||
|
||||
@@ -10,7 +10,7 @@ from ..utils import (
|
||||
|
||||
class SBSIE(InfoExtractor):
|
||||
IE_DESC = 'sbs.com.au'
|
||||
_VALID_URL = r'https?://(?:www\.)?sbs\.com\.au/(?:ondemand(?:/video/(?:single/)?|.*?\bplay=)|news/(?:embeds/)?video/)(?P<id>[0-9]+)'
|
||||
_VALID_URL = r'https?://(?:www\.)?sbs\.com\.au/(?:ondemand|news)/video/(?:single/)?(?P<id>[0-9]+)'
|
||||
|
||||
_TESTS = [{
|
||||
# Original URL is handled by the generic IE which finds the iframe:
|
||||
@@ -18,7 +18,7 @@ class SBSIE(InfoExtractor):
|
||||
'url': 'http://www.sbs.com.au/ondemand/video/single/320403011771/?source=drupal&vertical=thefeed',
|
||||
'md5': '3150cf278965eeabb5b4cea1c963fe0a',
|
||||
'info_dict': {
|
||||
'id': '_rFBPRPO4pMR',
|
||||
'id': '320403011771',
|
||||
'ext': 'mp4',
|
||||
'title': 'Dingo Conservation (The Feed)',
|
||||
'description': 'md5:f250a9856fca50d22dec0b5b8015f8a5',
|
||||
@@ -34,15 +34,6 @@ class SBSIE(InfoExtractor):
|
||||
}, {
|
||||
'url': 'http://www.sbs.com.au/news/video/471395907773/The-Feed-July-9',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.sbs.com.au/ondemand/?play=1836638787723',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.sbs.com.au/ondemand/program/inside-windsor-castle?play=1283505731842',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.sbs.com.au/news/embeds/video/1840778819866',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
|
||||
@@ -50,15 +50,9 @@ class ParamountNetworkIE(MTVServicesInfoExtractor):
|
||||
},
|
||||
}]
|
||||
|
||||
_FEED_URL = 'http://feeds.mtvnservices.com/od/feed/intl-mrss-player-feed'
|
||||
_FEED_URL = 'http://www.paramountnetwork.com/feeds/mrss/'
|
||||
_GEO_COUNTRIES = ['US']
|
||||
|
||||
def _get_feed_query(self, uri):
|
||||
return {
|
||||
'arcEp': 'paramountnetwork.com',
|
||||
'mgid': uri,
|
||||
}
|
||||
|
||||
def _extract_mgid(self, webpage, url):
|
||||
root_data = self._parse_json(self._search_regex(
|
||||
r'window\.__DATA__\s*=\s*({.+})',
|
||||
|
||||
@@ -8,17 +8,13 @@ from ..utils import (
|
||||
compat_str,
|
||||
float_or_none,
|
||||
int_or_none,
|
||||
smuggle_url,
|
||||
str_or_none,
|
||||
try_get,
|
||||
)
|
||||
|
||||
|
||||
class STVPlayerIE(InfoExtractor):
|
||||
IE_NAME = 'stv:player'
|
||||
_VALID_URL = r'https?://player\.stv\.tv/(?P<type>episode|video)/(?P<id>[a-z0-9]{4})'
|
||||
_TESTS = [{
|
||||
# shortform
|
||||
_TEST = {
|
||||
'url': 'https://player.stv.tv/video/4gwd/emmerdale/60-seconds-on-set-with-laura-norton/',
|
||||
'md5': '5adf9439c31d554f8be0707c7abe7e0a',
|
||||
'info_dict': {
|
||||
@@ -31,11 +27,7 @@ class STVPlayerIE(InfoExtractor):
|
||||
'uploader_id': '1486976045',
|
||||
},
|
||||
'skip': 'this resource is unavailable outside of the UK',
|
||||
}, {
|
||||
# episodes
|
||||
'url': 'https://player.stv.tv/episode/4125/jennifer-saunders-memory-lane',
|
||||
'only_matching': True,
|
||||
}]
|
||||
}
|
||||
BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/1486976045/default_default/index.html?videoId=%s'
|
||||
_PTYPE_MAP = {
|
||||
'episode': 'episodes',
|
||||
@@ -44,31 +36,11 @@ class STVPlayerIE(InfoExtractor):
|
||||
|
||||
def _real_extract(self, url):
|
||||
ptype, video_id = re.match(self._VALID_URL, url).groups()
|
||||
resp = self._download_json(
|
||||
'https://player.api.stv.tv/v1/%s/%s' % (self._PTYPE_MAP[ptype], video_id),
|
||||
video_id)
|
||||
|
||||
webpage = self._download_webpage(url, video_id, fatal=False) or ''
|
||||
props = (self._parse_json(self._search_regex(
|
||||
r'<script[^>]+id="__NEXT_DATA__"[^>]*>({.+?})</script>',
|
||||
webpage, 'next data', default='{}'), video_id,
|
||||
fatal=False) or {}).get('props') or {}
|
||||
player_api_cache = try_get(
|
||||
props, lambda x: x['initialReduxState']['playerApiCache']) or {}
|
||||
|
||||
api_path, resp = None, {}
|
||||
for k, v in player_api_cache.items():
|
||||
if k.startswith('/episodes/') or k.startswith('/shortform/'):
|
||||
api_path, resp = k, v
|
||||
break
|
||||
else:
|
||||
episode_id = str_or_none(try_get(
|
||||
props, lambda x: x['pageProps']['episodeId']))
|
||||
api_path = '/%s/%s' % (self._PTYPE_MAP[ptype], episode_id or video_id)
|
||||
|
||||
result = resp.get('results')
|
||||
if not result:
|
||||
resp = self._download_json(
|
||||
'https://player.api.stv.tv/v1' + api_path, video_id)
|
||||
result = resp['results']
|
||||
|
||||
result = resp['results']
|
||||
video = result['video']
|
||||
video_id = compat_str(video['id'])
|
||||
|
||||
@@ -85,7 +57,7 @@ class STVPlayerIE(InfoExtractor):
|
||||
return {
|
||||
'_type': 'url_transparent',
|
||||
'id': video_id,
|
||||
'url': smuggle_url(self.BRIGHTCOVE_URL_TEMPLATE % video_id, {'geo_countries': ['GB']}),
|
||||
'url': self.BRIGHTCOVE_URL_TEMPLATE % video_id,
|
||||
'description': result.get('summary'),
|
||||
'duration': float_or_none(video.get('length'), 1000),
|
||||
'subtitles': subtitles,
|
||||
|
||||
@@ -3,13 +3,10 @@ from __future__ import unicode_literals
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import compat_HTTPError
|
||||
from ..utils import (
|
||||
determine_ext,
|
||||
ExtractorError,
|
||||
float_or_none,
|
||||
int_or_none,
|
||||
parse_iso8601,
|
||||
js_to_json,
|
||||
mimetype2ext,
|
||||
)
|
||||
|
||||
|
||||
@@ -18,35 +15,29 @@ class ThreeQSDNIE(InfoExtractor):
|
||||
IE_DESC = '3Q SDN'
|
||||
_VALID_URL = r'https?://playout\.3qsdn\.com/(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})'
|
||||
_TESTS = [{
|
||||
# https://player.3qsdn.com/demo.html
|
||||
'url': 'https://playout.3qsdn.com/7201c779-6b3c-11e7-a40e-002590c750be',
|
||||
'md5': '64a57396b16fa011b15e0ea60edce918',
|
||||
# ondemand from http://www.philharmonie.tv/veranstaltung/26/
|
||||
'url': 'http://playout.3qsdn.com/0280d6b9-1215-11e6-b427-0cc47a188158?protocol=http',
|
||||
'md5': 'ab040e37bcfa2e0c079f92cb1dd7f6cd',
|
||||
'info_dict': {
|
||||
'id': '7201c779-6b3c-11e7-a40e-002590c750be',
|
||||
'id': '0280d6b9-1215-11e6-b427-0cc47a188158',
|
||||
'ext': 'mp4',
|
||||
'title': 'Video Ads',
|
||||
'title': '0280d6b9-1215-11e6-b427-0cc47a188158',
|
||||
'is_live': False,
|
||||
'description': 'Video Ads Demo',
|
||||
'timestamp': 1500334803,
|
||||
'upload_date': '20170717',
|
||||
'duration': 888.032,
|
||||
'subtitles': {
|
||||
'eng': 'count:1',
|
||||
},
|
||||
},
|
||||
'expected_warnings': ['Unknown MIME type application/mp4 in DASH manifest'],
|
||||
'expected_warnings': ['Failed to download MPD manifest', 'Failed to parse JSON'],
|
||||
}, {
|
||||
# live video stream
|
||||
'url': 'https://playout.3qsdn.com/66e68995-11ca-11e8-9273-002590c750be',
|
||||
'url': 'https://playout.3qsdn.com/d755d94b-4ab9-11e3-9162-0025907ad44f?js=true',
|
||||
'info_dict': {
|
||||
'id': '66e68995-11ca-11e8-9273-002590c750be',
|
||||
'id': 'd755d94b-4ab9-11e3-9162-0025907ad44f',
|
||||
'ext': 'mp4',
|
||||
'title': 're:^66e68995-11ca-11e8-9273-002590c750be [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
|
||||
'title': 're:^d755d94b-4ab9-11e3-9162-0025907ad44f [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
|
||||
'is_live': True,
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True, # m3u8 downloads
|
||||
},
|
||||
'expected_warnings': ['Failed to download MPD manifest'],
|
||||
}, {
|
||||
# live audio stream
|
||||
'url': 'http://playout.3qsdn.com/9edf36e0-6bf2-11e2-a16a-9acf09e2db48',
|
||||
@@ -67,14 +58,6 @@ class ThreeQSDNIE(InfoExtractor):
|
||||
# live video with rtmp link
|
||||
'url': 'https://playout.3qsdn.com/6092bb9e-8f72-11e4-a173-002590c750be',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# ondemand from http://www.philharmonie.tv/veranstaltung/26/
|
||||
'url': 'http://playout.3qsdn.com/0280d6b9-1215-11e6-b427-0cc47a188158?protocol=http',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# live video stream
|
||||
'url': 'https://playout.3qsdn.com/d755d94b-4ab9-11e3-9162-0025907ad44f?js=true',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
@staticmethod
|
||||
@@ -87,78 +70,73 @@ class ThreeQSDNIE(InfoExtractor):
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
try:
|
||||
config = self._download_json(
|
||||
url.replace('://playout.3qsdn.com/', '://playout.3qsdn.com/config/'), video_id)
|
||||
except ExtractorError as e:
|
||||
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
|
||||
self.raise_geo_restricted()
|
||||
raise
|
||||
js = self._download_webpage(
|
||||
'http://playout.3qsdn.com/%s' % video_id, video_id,
|
||||
query={'js': 'true'})
|
||||
|
||||
live = config.get('streamContent') == 'live'
|
||||
aspect = float_or_none(config.get('aspect'))
|
||||
if any(p in js for p in (
|
||||
'>This content is not available in your country',
|
||||
'playout.3qsdn.com/forbidden')):
|
||||
self.raise_geo_restricted()
|
||||
|
||||
stream_content = self._search_regex(
|
||||
r'streamContent\s*:\s*(["\'])(?P<content>.+?)\1', js,
|
||||
'stream content', default='demand', group='content')
|
||||
|
||||
live = stream_content == 'live'
|
||||
|
||||
stream_type = self._search_regex(
|
||||
r'streamType\s*:\s*(["\'])(?P<type>audio|video)\1', js,
|
||||
'stream type', default='video', group='type')
|
||||
|
||||
formats = []
|
||||
for source_type, source in (config.get('sources') or {}).items():
|
||||
if not source:
|
||||
continue
|
||||
if source_type == 'dash':
|
||||
urls = set()
|
||||
|
||||
def extract_formats(item_url, item={}):
|
||||
if not item_url or item_url in urls:
|
||||
return
|
||||
urls.add(item_url)
|
||||
ext = mimetype2ext(item.get('type')) or determine_ext(item_url, default_ext=None)
|
||||
if ext == 'mpd':
|
||||
formats.extend(self._extract_mpd_formats(
|
||||
source, video_id, mpd_id='mpd', fatal=False))
|
||||
elif source_type == 'hls':
|
||||
item_url, video_id, mpd_id='mpd', fatal=False))
|
||||
elif ext == 'm3u8':
|
||||
formats.extend(self._extract_m3u8_formats(
|
||||
source, video_id, 'mp4', 'm3u8' if live else 'm3u8_native',
|
||||
item_url, video_id, 'mp4',
|
||||
entry_protocol='m3u8' if live else 'm3u8_native',
|
||||
m3u8_id='hls', fatal=False))
|
||||
elif source_type == 'progressive':
|
||||
for s in source:
|
||||
src = s.get('src')
|
||||
if not (src and self._is_valid_url(src, video_id)):
|
||||
continue
|
||||
width = None
|
||||
format_id = ['http']
|
||||
ext = determine_ext(src)
|
||||
if ext:
|
||||
format_id.append(ext)
|
||||
height = int_or_none(s.get('height'))
|
||||
if height:
|
||||
format_id.append('%dp' % height)
|
||||
if aspect:
|
||||
width = int(height * aspect)
|
||||
formats.append({
|
||||
'ext': ext,
|
||||
'format_id': '-'.join(format_id),
|
||||
'height': height,
|
||||
'source_preference': 0,
|
||||
'url': src,
|
||||
'vcodec': 'none' if height == 0 else None,
|
||||
'width': width,
|
||||
})
|
||||
for f in formats:
|
||||
if f.get('acodec') == 'none':
|
||||
f['preference'] = -40
|
||||
elif f.get('vcodec') == 'none':
|
||||
f['preference'] = -50
|
||||
self._sort_formats(formats, ('preference', 'width', 'height', 'source_preference', 'tbr', 'vbr', 'abr', 'ext', 'format_id'))
|
||||
elif ext == 'f4m':
|
||||
formats.extend(self._extract_f4m_formats(
|
||||
item_url, video_id, f4m_id='hds', fatal=False))
|
||||
else:
|
||||
if not self._is_valid_url(item_url, video_id):
|
||||
return
|
||||
formats.append({
|
||||
'url': item_url,
|
||||
'format_id': item.get('quality'),
|
||||
'ext': 'mp4' if item_url.startswith('rtsp') else ext,
|
||||
'vcodec': 'none' if stream_type == 'audio' else None,
|
||||
})
|
||||
|
||||
subtitles = {}
|
||||
for subtitle in (config.get('subtitles') or []):
|
||||
src = subtitle.get('src')
|
||||
if not src:
|
||||
for item_js in re.findall(r'({[^{]*?\b(?:src|source)\s*:\s*["\'].+?})', js):
|
||||
f = self._parse_json(
|
||||
item_js, video_id, transform_source=js_to_json, fatal=False)
|
||||
if not f:
|
||||
continue
|
||||
subtitles.setdefault(subtitle.get('label') or 'eng', []).append({
|
||||
'url': src,
|
||||
})
|
||||
extract_formats(f.get('src'), f)
|
||||
|
||||
title = config.get('title') or video_id
|
||||
# More relaxed version to collect additional URLs and acting
|
||||
# as a future-proof fallback
|
||||
for _, src in re.findall(r'\b(?:src|source)\s*:\s*(["\'])((?:https?|rtsp)://.+?)\1', js):
|
||||
extract_formats(src)
|
||||
|
||||
self._sort_formats(formats)
|
||||
|
||||
title = self._live_title(video_id) if live else video_id
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': self._live_title(title) if live else title,
|
||||
'thumbnail': config.get('poster') or None,
|
||||
'description': config.get('description') or None,
|
||||
'timestamp': parse_iso8601(config.get('upload_date')),
|
||||
'duration': float_or_none(config.get('vlength')) or None,
|
||||
'title': title,
|
||||
'is_live': live,
|
||||
'formats': formats,
|
||||
'subtitles': subtitles,
|
||||
}
|
||||
|
||||
@@ -17,8 +17,8 @@ class TikTokBaseIE(InfoExtractor):
|
||||
video_info = try_get(
|
||||
video_data, lambda x: x['itemInfo']['itemStruct'], dict)
|
||||
author_info = try_get(
|
||||
video_data, lambda x: x['itemInfo']['itemStruct']['author'], dict) or {}
|
||||
share_info = try_get(video_data, lambda x: x['itemInfo']['shareMeta'], dict) or {}
|
||||
video_data, lambda x: x['itemInfo']['itemStruct']['author'], dict)
|
||||
share_info = try_get(video_data, lambda x: x['itemInfo']['shareMeta'], dict)
|
||||
|
||||
unique_id = str_or_none(author_info.get('uniqueId'))
|
||||
timestamp = try_get(video_info, lambda x: int(x['createTime']), int)
|
||||
|
||||
@@ -9,6 +9,7 @@ import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import (
|
||||
compat_kwargs,
|
||||
compat_parse_qs,
|
||||
compat_str,
|
||||
compat_urlparse,
|
||||
@@ -17,7 +18,6 @@ from ..compat import (
|
||||
)
|
||||
from ..utils import (
|
||||
clean_html,
|
||||
dict_get,
|
||||
ExtractorError,
|
||||
float_or_none,
|
||||
int_or_none,
|
||||
@@ -42,16 +42,30 @@ class TwitchBaseIE(InfoExtractor):
|
||||
_CLIENT_ID = 'kimne78kx3ncx6brgo4mv6wki5h1ko'
|
||||
_NETRC_MACHINE = 'twitch'
|
||||
|
||||
_OPERATION_HASHES = {
|
||||
'CollectionSideBar': '27111f1b382effad0b6def325caef1909c733fe6a4fbabf54f8d491ef2cf2f14',
|
||||
'FilterableVideoTower_Videos': 'a937f1d22e269e39a03b509f65a7490f9fc247d7f83d6ac1421523e3b68042cb',
|
||||
'ClipsCards__User': 'b73ad2bfaecfd30a9e6c28fada15bd97032c83ec77a0440766a56fe0bd632777',
|
||||
'ChannelCollectionsContent': '07e3691a1bad77a36aba590c351180439a40baefc1c275356f40fc7082419a84',
|
||||
'StreamMetadata': '1c719a40e481453e5c48d9bb585d971b8b372f8ebb105b17076722264dfa5b3e',
|
||||
'ComscoreStreamingQuery': 'e1edae8122517d013405f237ffcc124515dc6ded82480a88daef69c83b53ac01',
|
||||
'VideoPreviewOverlay': '3006e77e51b128d838fa4e835723ca4dc9a05c5efd4466c1085215c6e437e65c',
|
||||
'VideoMetadata': '226edb3e692509f727fd56821f5653c05740242c82b0388883e0c0e75dcbf687',
|
||||
}
|
||||
def _handle_error(self, response):
|
||||
if not isinstance(response, dict):
|
||||
return
|
||||
error = response.get('error')
|
||||
if error:
|
||||
raise ExtractorError(
|
||||
'%s returned error: %s - %s' % (self.IE_NAME, error, response.get('message')),
|
||||
expected=True)
|
||||
|
||||
def _call_api(self, path, item_id, *args, **kwargs):
|
||||
headers = kwargs.get('headers', {}).copy()
|
||||
headers.update({
|
||||
'Accept': 'application/vnd.twitchtv.v5+json; charset=UTF-8',
|
||||
'Client-ID': self._CLIENT_ID,
|
||||
})
|
||||
kwargs.update({
|
||||
'headers': headers,
|
||||
'expected_status': (400, 410),
|
||||
})
|
||||
response = self._download_json(
|
||||
'%s/%s' % (self._API_BASE, path), item_id,
|
||||
*args, **compat_kwargs(kwargs))
|
||||
self._handle_error(response)
|
||||
return response
|
||||
|
||||
def _real_initialize(self):
|
||||
self._login()
|
||||
@@ -77,14 +91,14 @@ class TwitchBaseIE(InfoExtractor):
|
||||
|
||||
headers = {
|
||||
'Referer': page_url,
|
||||
'Origin': 'https://www.twitch.tv',
|
||||
'Origin': page_url,
|
||||
'Content-Type': 'text/plain;charset=UTF-8',
|
||||
}
|
||||
|
||||
response = self._download_json(
|
||||
post_url, None, note, data=json.dumps(form).encode(),
|
||||
headers=headers, expected_status=400)
|
||||
error = dict_get(response, ('error', 'error_description', 'error_code'))
|
||||
error = response.get('error_description') or response.get('error_code')
|
||||
if error:
|
||||
fail(error)
|
||||
|
||||
@@ -137,50 +151,13 @@ class TwitchBaseIE(InfoExtractor):
|
||||
})
|
||||
self._sort_formats(formats)
|
||||
|
||||
def _download_base_gql(self, video_id, ops, note, fatal=True):
|
||||
headers = {
|
||||
'Content-Type': 'text/plain;charset=UTF-8',
|
||||
'Client-ID': self._CLIENT_ID,
|
||||
}
|
||||
gql_auth = self._get_cookies('https://gql.twitch.tv').get('auth-token')
|
||||
if gql_auth:
|
||||
headers['Authorization'] = 'OAuth ' + gql_auth.value
|
||||
return self._download_json(
|
||||
'https://gql.twitch.tv/gql', video_id, note,
|
||||
data=json.dumps(ops).encode(),
|
||||
headers=headers, fatal=fatal)
|
||||
def _download_access_token(self, channel_name):
|
||||
return self._call_api(
|
||||
'api/channels/%s/access_token' % channel_name, channel_name,
|
||||
'Downloading access token JSON')
|
||||
|
||||
def _download_gql(self, video_id, ops, note, fatal=True):
|
||||
for op in ops:
|
||||
op['extensions'] = {
|
||||
'persistedQuery': {
|
||||
'version': 1,
|
||||
'sha256Hash': self._OPERATION_HASHES[op['operationName']],
|
||||
}
|
||||
}
|
||||
return self._download_base_gql(video_id, ops, note)
|
||||
|
||||
def _download_access_token(self, video_id, token_kind, param_name):
|
||||
method = '%sPlaybackAccessToken' % token_kind
|
||||
ops = {
|
||||
'query': '''{
|
||||
%s(
|
||||
%s: "%s",
|
||||
params: {
|
||||
platform: "web",
|
||||
playerBackend: "mediaplayer",
|
||||
playerType: "site"
|
||||
}
|
||||
)
|
||||
{
|
||||
value
|
||||
signature
|
||||
}
|
||||
}''' % (method, param_name, video_id),
|
||||
}
|
||||
return self._download_base_gql(
|
||||
video_id, ops,
|
||||
'Downloading %s access token GraphQL' % token_kind)['data'][method]
|
||||
def _extract_channel_id(self, token, channel_name):
|
||||
return compat_str(self._parse_json(token, channel_name)['channel_id'])
|
||||
|
||||
|
||||
class TwitchVodIE(TwitchBaseIE):
|
||||
@@ -193,6 +170,8 @@ class TwitchVodIE(TwitchBaseIE):
|
||||
)
|
||||
(?P<id>\d+)
|
||||
'''
|
||||
_ITEM_TYPE = 'vod'
|
||||
_ITEM_SHORTCUT = 'v'
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'http://www.twitch.tv/riotgames/v/6528877?t=5m10s',
|
||||
@@ -202,7 +181,7 @@ class TwitchVodIE(TwitchBaseIE):
|
||||
'title': 'LCK Summer Split - Week 6 Day 1',
|
||||
'thumbnail': r're:^https?://.*\.jpg$',
|
||||
'duration': 17208,
|
||||
'timestamp': 1435131734,
|
||||
'timestamp': 1435131709,
|
||||
'upload_date': '20150624',
|
||||
'uploader': 'Riot Games',
|
||||
'uploader_id': 'riotgames',
|
||||
@@ -251,20 +230,10 @@ class TwitchVodIE(TwitchBaseIE):
|
||||
}]
|
||||
|
||||
def _download_info(self, item_id):
|
||||
data = self._download_gql(
|
||||
item_id, [{
|
||||
'operationName': 'VideoMetadata',
|
||||
'variables': {
|
||||
'channelLogin': '',
|
||||
'videoID': item_id,
|
||||
},
|
||||
}],
|
||||
'Downloading stream metadata GraphQL')[0]['data']
|
||||
video = data.get('video')
|
||||
if video is None:
|
||||
raise ExtractorError(
|
||||
'Video %s does not exist' % item_id, expected=True)
|
||||
return self._extract_info_gql(video, item_id)
|
||||
return self._extract_info(
|
||||
self._call_api(
|
||||
'kraken/videos/%s' % item_id, item_id,
|
||||
'Downloading video info JSON'))
|
||||
|
||||
@staticmethod
|
||||
def _extract_info(info):
|
||||
@@ -303,33 +272,13 @@ class TwitchVodIE(TwitchBaseIE):
|
||||
'is_live': is_live,
|
||||
}
|
||||
|
||||
@staticmethod
|
||||
def _extract_info_gql(info, item_id):
|
||||
vod_id = info.get('id') or item_id
|
||||
# id backward compatibility for download archives
|
||||
if vod_id[0] != 'v':
|
||||
vod_id = 'v%s' % vod_id
|
||||
thumbnail = url_or_none(info.get('previewThumbnailURL'))
|
||||
if thumbnail:
|
||||
for p in ('width', 'height'):
|
||||
thumbnail = thumbnail.replace('{%s}' % p, '0')
|
||||
return {
|
||||
'id': vod_id,
|
||||
'title': info.get('title') or 'Untitled Broadcast',
|
||||
'description': info.get('description'),
|
||||
'duration': int_or_none(info.get('lengthSeconds')),
|
||||
'thumbnail': thumbnail,
|
||||
'uploader': try_get(info, lambda x: x['owner']['displayName'], compat_str),
|
||||
'uploader_id': try_get(info, lambda x: x['owner']['login'], compat_str),
|
||||
'timestamp': unified_timestamp(info.get('publishedAt')),
|
||||
'view_count': int_or_none(info.get('viewCount')),
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
vod_id = self._match_id(url)
|
||||
|
||||
info = self._download_info(vod_id)
|
||||
access_token = self._download_access_token(vod_id, 'video', 'id')
|
||||
access_token = self._call_api(
|
||||
'api/vods/%s/access_token' % vod_id, vod_id,
|
||||
'Downloading %s access token' % self._ITEM_TYPE)
|
||||
|
||||
formats = self._extract_m3u8_formats(
|
||||
'%s/vod/%s.m3u8?%s' % (
|
||||
@@ -340,8 +289,8 @@ class TwitchVodIE(TwitchBaseIE):
|
||||
'allow_spectre': 'true',
|
||||
'player': 'twitchweb',
|
||||
'playlist_include_framerate': 'true',
|
||||
'nauth': access_token['value'],
|
||||
'nauthsig': access_token['signature'],
|
||||
'nauth': access_token['token'],
|
||||
'nauthsig': access_token['sig'],
|
||||
})),
|
||||
vod_id, 'mp4', entry_protocol='m3u8_native')
|
||||
|
||||
@@ -384,7 +333,37 @@ def _make_video_result(node):
|
||||
}
|
||||
|
||||
|
||||
class TwitchCollectionIE(TwitchBaseIE):
|
||||
class TwitchGraphQLBaseIE(TwitchBaseIE):
|
||||
_PAGE_LIMIT = 100
|
||||
|
||||
_OPERATION_HASHES = {
|
||||
'CollectionSideBar': '27111f1b382effad0b6def325caef1909c733fe6a4fbabf54f8d491ef2cf2f14',
|
||||
'FilterableVideoTower_Videos': 'a937f1d22e269e39a03b509f65a7490f9fc247d7f83d6ac1421523e3b68042cb',
|
||||
'ClipsCards__User': 'b73ad2bfaecfd30a9e6c28fada15bd97032c83ec77a0440766a56fe0bd632777',
|
||||
'ChannelCollectionsContent': '07e3691a1bad77a36aba590c351180439a40baefc1c275356f40fc7082419a84',
|
||||
'StreamMetadata': '1c719a40e481453e5c48d9bb585d971b8b372f8ebb105b17076722264dfa5b3e',
|
||||
'ComscoreStreamingQuery': 'e1edae8122517d013405f237ffcc124515dc6ded82480a88daef69c83b53ac01',
|
||||
'VideoPreviewOverlay': '3006e77e51b128d838fa4e835723ca4dc9a05c5efd4466c1085215c6e437e65c',
|
||||
}
|
||||
|
||||
def _download_gql(self, video_id, ops, note, fatal=True):
|
||||
for op in ops:
|
||||
op['extensions'] = {
|
||||
'persistedQuery': {
|
||||
'version': 1,
|
||||
'sha256Hash': self._OPERATION_HASHES[op['operationName']],
|
||||
}
|
||||
}
|
||||
return self._download_json(
|
||||
'https://gql.twitch.tv/gql', video_id, note,
|
||||
data=json.dumps(ops).encode(),
|
||||
headers={
|
||||
'Content-Type': 'text/plain;charset=UTF-8',
|
||||
'Client-ID': self._CLIENT_ID,
|
||||
}, fatal=fatal)
|
||||
|
||||
|
||||
class TwitchCollectionIE(TwitchGraphQLBaseIE):
|
||||
_VALID_URL = r'https?://(?:(?:www|go|m)\.)?twitch\.tv/collections/(?P<id>[^/]+)'
|
||||
|
||||
_TESTS = [{
|
||||
@@ -421,9 +400,7 @@ class TwitchCollectionIE(TwitchBaseIE):
|
||||
entries, playlist_id=collection_id, playlist_title=title)
|
||||
|
||||
|
||||
class TwitchPlaylistBaseIE(TwitchBaseIE):
|
||||
_PAGE_LIMIT = 100
|
||||
|
||||
class TwitchPlaylistBaseIE(TwitchGraphQLBaseIE):
|
||||
def _entries(self, channel_name, *args):
|
||||
cursor = None
|
||||
variables_common = self._make_variables(channel_name, *args)
|
||||
@@ -463,6 +440,49 @@ class TwitchPlaylistBaseIE(TwitchBaseIE):
|
||||
if not cursor or not isinstance(cursor, compat_str):
|
||||
break
|
||||
|
||||
# Deprecated kraken v5 API
|
||||
def _entries_kraken(self, channel_name, broadcast_type, sort):
|
||||
access_token = self._download_access_token(channel_name)
|
||||
channel_id = self._extract_channel_id(access_token['token'], channel_name)
|
||||
offset = 0
|
||||
counter_override = None
|
||||
for counter in itertools.count(1):
|
||||
response = self._call_api(
|
||||
'kraken/channels/%s/videos/' % channel_id,
|
||||
channel_id,
|
||||
'Downloading video JSON page %s' % (counter_override or counter),
|
||||
query={
|
||||
'offset': offset,
|
||||
'limit': self._PAGE_LIMIT,
|
||||
'broadcast_type': broadcast_type,
|
||||
'sort': sort,
|
||||
})
|
||||
videos = response.get('videos')
|
||||
if not isinstance(videos, list):
|
||||
break
|
||||
for video in videos:
|
||||
if not isinstance(video, dict):
|
||||
continue
|
||||
video_url = url_or_none(video.get('url'))
|
||||
if not video_url:
|
||||
continue
|
||||
yield {
|
||||
'_type': 'url_transparent',
|
||||
'ie_key': TwitchVodIE.ie_key(),
|
||||
'id': video.get('_id'),
|
||||
'url': video_url,
|
||||
'title': video.get('title'),
|
||||
'description': video.get('description'),
|
||||
'timestamp': unified_timestamp(video.get('published_at')),
|
||||
'duration': float_or_none(video.get('length')),
|
||||
'view_count': int_or_none(video.get('views')),
|
||||
'language': video.get('language'),
|
||||
}
|
||||
offset += self._PAGE_LIMIT
|
||||
total = int_or_none(response.get('_total'))
|
||||
if total and offset >= total:
|
||||
break
|
||||
|
||||
|
||||
class TwitchVideosIE(TwitchPlaylistBaseIE):
|
||||
_VALID_URL = r'https?://(?:(?:www|go|m)\.)?twitch\.tv/(?P<id>[^/]+)/(?:videos|profile)'
|
||||
@@ -704,7 +724,7 @@ class TwitchVideosCollectionsIE(TwitchPlaylistBaseIE):
|
||||
playlist_title='%s - Collections' % channel_name)
|
||||
|
||||
|
||||
class TwitchStreamIE(TwitchBaseIE):
|
||||
class TwitchStreamIE(TwitchGraphQLBaseIE):
|
||||
IE_NAME = 'twitch:stream'
|
||||
_VALID_URL = r'''(?x)
|
||||
https?://
|
||||
@@ -794,9 +814,8 @@ class TwitchStreamIE(TwitchBaseIE):
|
||||
if not stream:
|
||||
raise ExtractorError('%s is offline' % channel_name, expected=True)
|
||||
|
||||
access_token = self._download_access_token(
|
||||
channel_name, 'stream', 'channelName')
|
||||
token = access_token['value']
|
||||
access_token = self._download_access_token(channel_name)
|
||||
token = access_token['token']
|
||||
|
||||
stream_id = stream.get('id') or channel_name
|
||||
query = {
|
||||
@@ -807,7 +826,7 @@ class TwitchStreamIE(TwitchBaseIE):
|
||||
'player': 'twitchweb',
|
||||
'playlist_include_framerate': 'true',
|
||||
'segment_preference': '4',
|
||||
'sig': access_token['signature'].encode('utf-8'),
|
||||
'sig': access_token['sig'].encode('utf-8'),
|
||||
'token': token.encode('utf-8'),
|
||||
}
|
||||
formats = self._extract_m3u8_formats(
|
||||
@@ -893,8 +912,8 @@ class TwitchClipsIE(TwitchBaseIE):
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
clip = self._download_base_gql(
|
||||
video_id, {
|
||||
clip = self._download_json(
|
||||
'https://gql.twitch.tv/gql', video_id, data=json.dumps({
|
||||
'query': '''{
|
||||
clip(slug: "%s") {
|
||||
broadcaster {
|
||||
@@ -918,7 +937,10 @@ class TwitchClipsIE(TwitchBaseIE):
|
||||
}
|
||||
viewCount
|
||||
}
|
||||
}''' % video_id}, 'Downloading clip GraphQL')['data']['clip']
|
||||
}''' % video_id,
|
||||
}).encode(), headers={
|
||||
'Client-ID': self._CLIENT_ID,
|
||||
})['data']['clip']
|
||||
|
||||
if not clip:
|
||||
raise ExtractorError(
|
||||
|
||||
@@ -251,10 +251,10 @@ class TwitterIE(TwitterBaseIE):
|
||||
'info_dict': {
|
||||
'id': '700207533655363584',
|
||||
'ext': 'mp4',
|
||||
'title': 'simon vertugo - BEAT PROD: @suhmeduh #Damndaniel',
|
||||
'title': 'simon vetugo - BEAT PROD: @suhmeduh #Damndaniel',
|
||||
'description': 'BEAT PROD: @suhmeduh https://t.co/HBrQ4AfpvZ #Damndaniel https://t.co/byBooq2ejZ',
|
||||
'thumbnail': r're:^https?://.*\.jpg',
|
||||
'uploader': 'simon vertugo',
|
||||
'uploader': 'simon vetugo',
|
||||
'uploader_id': 'simonvertugo',
|
||||
'duration': 30.0,
|
||||
'timestamp': 1455777459,
|
||||
@@ -312,7 +312,6 @@ class TwitterIE(TwitterBaseIE):
|
||||
'timestamp': 1492000653,
|
||||
'upload_date': '20170412',
|
||||
},
|
||||
'skip': 'Account suspended',
|
||||
}, {
|
||||
'url': 'https://twitter.com/i/web/status/910031516746514432',
|
||||
'info_dict': {
|
||||
@@ -373,24 +372,6 @@ class TwitterIE(TwitterBaseIE):
|
||||
'uploader_id': '1eVjYOLGkGrQL',
|
||||
},
|
||||
'add_ie': ['TwitterBroadcast'],
|
||||
}, {
|
||||
# unified card
|
||||
'url': 'https://twitter.com/BrooklynNets/status/1349794411333394432?s=20',
|
||||
'info_dict': {
|
||||
'id': '1349794411333394432',
|
||||
'ext': 'mp4',
|
||||
'title': 'md5:d1c4941658e4caaa6cb579260d85dcba',
|
||||
'thumbnail': r're:^https?://.*\.jpg',
|
||||
'description': 'md5:71ead15ec44cee55071547d6447c6a3e',
|
||||
'uploader': 'Brooklyn Nets',
|
||||
'uploader_id': 'BrooklynNets',
|
||||
'duration': 324.484,
|
||||
'timestamp': 1610651040,
|
||||
'upload_date': '20210114',
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
}, {
|
||||
# Twitch Clip Embed
|
||||
'url': 'https://twitter.com/GunB1g/status/1163218564784017422',
|
||||
@@ -399,30 +380,6 @@ class TwitterIE(TwitterBaseIE):
|
||||
# promo_video_website card
|
||||
'url': 'https://twitter.com/GunB1g/status/1163218564784017422',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# promo_video_convo card
|
||||
'url': 'https://twitter.com/poco_dandy/status/1047395834013384704',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# appplayer card
|
||||
'url': 'https://twitter.com/poco_dandy/status/1150646424461176832',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# video_direct_message card
|
||||
'url': 'https://twitter.com/qarev001/status/1348948114569269251',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# poll2choice_video card
|
||||
'url': 'https://twitter.com/CAF_Online/status/1349365911120195585',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# poll3choice_video card
|
||||
'url': 'https://twitter.com/SamsungMobileSA/status/1348609186725289984',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# poll4choice_video card
|
||||
'url': 'https://twitter.com/SouthamptonFC/status/1347577658079641604',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
@@ -467,7 +424,8 @@ class TwitterIE(TwitterBaseIE):
|
||||
'tags': tags,
|
||||
}
|
||||
|
||||
def extract_from_video_info(media):
|
||||
media = try_get(status, lambda x: x['extended_entities']['media'][0])
|
||||
if media and media.get('type') != 'photo':
|
||||
video_info = media.get('video_info') or {}
|
||||
|
||||
formats = []
|
||||
@@ -494,10 +452,6 @@ class TwitterIE(TwitterBaseIE):
|
||||
'thumbnails': thumbnails,
|
||||
'duration': float_or_none(video_info.get('duration_millis'), 1000),
|
||||
})
|
||||
|
||||
media = try_get(status, lambda x: x['extended_entities']['media'][0])
|
||||
if media and media.get('type') != 'photo':
|
||||
extract_from_video_info(media)
|
||||
else:
|
||||
card = status.get('card')
|
||||
if card:
|
||||
@@ -508,35 +462,7 @@ class TwitterIE(TwitterBaseIE):
|
||||
return try_get(o, lambda x: x[x['type'].lower() + '_value'])
|
||||
|
||||
card_name = card['name'].split(':')[-1]
|
||||
if card_name == 'player':
|
||||
info.update({
|
||||
'_type': 'url',
|
||||
'url': get_binding_value('player_url'),
|
||||
})
|
||||
elif card_name == 'periscope_broadcast':
|
||||
info.update({
|
||||
'_type': 'url',
|
||||
'url': get_binding_value('url') or get_binding_value('player_url'),
|
||||
'ie_key': PeriscopeIE.ie_key(),
|
||||
})
|
||||
elif card_name == 'broadcast':
|
||||
info.update({
|
||||
'_type': 'url',
|
||||
'url': get_binding_value('broadcast_url'),
|
||||
'ie_key': TwitterBroadcastIE.ie_key(),
|
||||
})
|
||||
elif card_name == 'summary':
|
||||
info.update({
|
||||
'_type': 'url',
|
||||
'url': get_binding_value('card_url'),
|
||||
})
|
||||
elif card_name == 'unified_card':
|
||||
media_entities = self._parse_json(get_binding_value('unified_card'), twid)['media_entities']
|
||||
extract_from_video_info(next(iter(media_entities.values())))
|
||||
# amplify, promo_video_website, promo_video_convo, appplayer,
|
||||
# video_direct_message, poll2choice_video, poll3choice_video,
|
||||
# poll4choice_video, ...
|
||||
else:
|
||||
if card_name in ('amplify', 'promo_video_website'):
|
||||
is_amplify = card_name == 'amplify'
|
||||
vmap_url = get_binding_value('amplify_url_vmap') if is_amplify else get_binding_value('player_stream_url')
|
||||
content_id = get_binding_value('%s_content_id' % (card_name if is_amplify else 'player'))
|
||||
@@ -562,6 +488,25 @@ class TwitterIE(TwitterBaseIE):
|
||||
'duration': int_or_none(get_binding_value(
|
||||
'content_duration_seconds')),
|
||||
})
|
||||
elif card_name == 'player':
|
||||
info.update({
|
||||
'_type': 'url',
|
||||
'url': get_binding_value('player_url'),
|
||||
})
|
||||
elif card_name == 'periscope_broadcast':
|
||||
info.update({
|
||||
'_type': 'url',
|
||||
'url': get_binding_value('url') or get_binding_value('player_url'),
|
||||
'ie_key': PeriscopeIE.ie_key(),
|
||||
})
|
||||
elif card_name == 'broadcast':
|
||||
info.update({
|
||||
'_type': 'url',
|
||||
'url': get_binding_value('broadcast_url'),
|
||||
'ie_key': TwitterBroadcastIE.ie_key(),
|
||||
})
|
||||
else:
|
||||
raise ExtractorError('Unsupported Twitter Card.')
|
||||
else:
|
||||
expanded_url = try_get(status, lambda x: x['entities']['urls'][0]['expanded_url'])
|
||||
if not expanded_url:
|
||||
|
||||
@@ -45,7 +45,6 @@ def aa_decode(aa_code):
|
||||
|
||||
class XFileShareIE(InfoExtractor):
|
||||
_SITES = (
|
||||
(r'aparat\.cam', 'Aparat'),
|
||||
(r'clipwatching\.com', 'ClipWatching'),
|
||||
(r'gounlimited\.to', 'GoUnlimited'),
|
||||
(r'govid\.me', 'GoVid'),
|
||||
@@ -79,9 +78,6 @@ class XFileShareIE(InfoExtractor):
|
||||
'title': 'sample',
|
||||
'thumbnail': r're:http://.*\.jpg',
|
||||
},
|
||||
}, {
|
||||
'url': 'https://aparat.cam/n4d6dh0wvlpr',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
@staticmethod
|
||||
|
||||
@@ -60,9 +60,6 @@ class YouPornIE(InfoExtractor):
|
||||
}, {
|
||||
'url': 'http://www.youporn.com/watch/505835',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.youporn.com/watch/13922959/femdom-principal/',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
@staticmethod
|
||||
@@ -91,7 +88,7 @@ class YouPornIE(InfoExtractor):
|
||||
# Main source
|
||||
definitions = self._parse_json(
|
||||
self._search_regex(
|
||||
r'mediaDefinition\s*[=:]\s*(\[.+?\])\s*[;,]', webpage,
|
||||
r'mediaDefinition\s*=\s*(\[.+?\]);', webpage,
|
||||
'media definitions', default='[]'),
|
||||
video_id, fatal=False)
|
||||
if definitions:
|
||||
@@ -103,7 +100,7 @@ class YouPornIE(InfoExtractor):
|
||||
links.append(video_url)
|
||||
|
||||
# Fallback #1, this also contains extra low quality 180p format
|
||||
for _, link in re.findall(r'<a[^>]+href=(["\'])(http(?:(?!\1).)+\.mp4(?:(?!\1).)*)\1[^>]+title=["\']Download [Vv]ideo', webpage):
|
||||
for _, link in re.findall(r'<a[^>]+href=(["\'])(http.+?)\1[^>]+title=["\']Download [Vv]ideo', webpage):
|
||||
links.append(link)
|
||||
|
||||
# Fallback #2 (unavailable as at 22.06.2017)
|
||||
@@ -131,9 +128,8 @@ class YouPornIE(InfoExtractor):
|
||||
# Video URL's path looks like this:
|
||||
# /201012/17/505835/720p_1500k_505835/YouPorn%20-%20Sex%20Ed%20Is%20It%20Safe%20To%20Masturbate%20Daily.mp4
|
||||
# /201012/17/505835/vl_240p_240k_505835/YouPorn%20-%20Sex%20Ed%20Is%20It%20Safe%20To%20Masturbate%20Daily.mp4
|
||||
# /videos/201703/11/109285532/1080P_4000K_109285532.mp4
|
||||
# We will benefit from it by extracting some metadata
|
||||
mobj = re.search(r'(?P<height>\d{3,4})[pP]_(?P<bitrate>\d+)[kK]_\d+', video_url)
|
||||
mobj = re.search(r'(?P<height>\d{3,4})[pP]_(?P<bitrate>\d+)[kK]_\d+/', video_url)
|
||||
if mobj:
|
||||
height = int(mobj.group('height'))
|
||||
bitrate = int(mobj.group('bitrate'))
|
||||
|
||||
@@ -332,36 +332,6 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
|
||||
r'ytcfg\.set\s*\(\s*({.+?})\s*\)\s*;', webpage, 'ytcfg',
|
||||
default='{}'), video_id, fatal=False)
|
||||
|
||||
def _extract_video(self, renderer):
|
||||
video_id = renderer.get('videoId')
|
||||
title = try_get(
|
||||
renderer,
|
||||
(lambda x: x['title']['runs'][0]['text'],
|
||||
lambda x: x['title']['simpleText']), compat_str)
|
||||
description = try_get(
|
||||
renderer, lambda x: x['descriptionSnippet']['runs'][0]['text'],
|
||||
compat_str)
|
||||
duration = parse_duration(try_get(
|
||||
renderer, lambda x: x['lengthText']['simpleText'], compat_str))
|
||||
view_count_text = try_get(
|
||||
renderer, lambda x: x['viewCountText']['simpleText'], compat_str) or ''
|
||||
view_count = str_to_int(self._search_regex(
|
||||
r'^([\d,]+)', re.sub(r'\s', '', view_count_text),
|
||||
'view count', default=None))
|
||||
uploader = try_get(
|
||||
renderer, lambda x: x['ownerText']['runs'][0]['text'], compat_str)
|
||||
return {
|
||||
'_type': 'url_transparent',
|
||||
'ie_key': YoutubeIE.ie_key(),
|
||||
'id': video_id,
|
||||
'url': video_id,
|
||||
'title': title,
|
||||
'description': description,
|
||||
'duration': duration,
|
||||
'view_count': view_count,
|
||||
'uploader': uploader,
|
||||
}
|
||||
|
||||
|
||||
class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||
IE_DESC = 'YouTube.com'
|
||||
@@ -1716,12 +1686,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||
if embedded_config:
|
||||
return embedded_config
|
||||
|
||||
video_info = {}
|
||||
player_response = {}
|
||||
ytplayer_config = None
|
||||
embed_webpage = None
|
||||
|
||||
# Get video info
|
||||
video_info = {}
|
||||
embed_webpage = None
|
||||
if (self._og_search_property('restrictions:age', video_webpage, default=None) == '18+'
|
||||
or re.search(r'player-age-gate-content">', video_webpage) is not None):
|
||||
cookie_keys = self._get_cookies('https://www.youtube.com').keys()
|
||||
@@ -1847,9 +1816,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||
if not isinstance(video_info, dict):
|
||||
video_info = {}
|
||||
|
||||
playable_in_embed = try_get(
|
||||
player_response, lambda x: x['playabilityStatus']['playableInEmbed'])
|
||||
|
||||
video_details = try_get(
|
||||
player_response, lambda x: x['videoDetails'], dict) or {}
|
||||
|
||||
@@ -2571,7 +2537,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||
'release_date': release_date,
|
||||
'release_year': release_year,
|
||||
'subscriber_count': subscriber_count,
|
||||
'playable_in_embed': playable_in_embed,
|
||||
}
|
||||
|
||||
|
||||
@@ -2901,6 +2866,36 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
|
||||
if renderer:
|
||||
return renderer
|
||||
|
||||
def _extract_video(self, renderer):
|
||||
video_id = renderer.get('videoId')
|
||||
title = try_get(
|
||||
renderer,
|
||||
(lambda x: x['title']['runs'][0]['text'],
|
||||
lambda x: x['title']['simpleText']), compat_str)
|
||||
description = try_get(
|
||||
renderer, lambda x: x['descriptionSnippet']['runs'][0]['text'],
|
||||
compat_str)
|
||||
duration = parse_duration(try_get(
|
||||
renderer, lambda x: x['lengthText']['simpleText'], compat_str))
|
||||
view_count_text = try_get(
|
||||
renderer, lambda x: x['viewCountText']['simpleText'], compat_str) or ''
|
||||
view_count = str_to_int(self._search_regex(
|
||||
r'^([\d,]+)', re.sub(r'\s', '', view_count_text),
|
||||
'view count', default=None))
|
||||
uploader = try_get(
|
||||
renderer, lambda x: x['ownerText']['runs'][0]['text'], compat_str)
|
||||
return {
|
||||
'_type': 'url_transparent',
|
||||
'ie_key': YoutubeIE.ie_key(),
|
||||
'id': video_id,
|
||||
'url': video_id,
|
||||
'title': title,
|
||||
'description': description,
|
||||
'duration': duration,
|
||||
'view_count': view_count,
|
||||
'uploader': uploader,
|
||||
}
|
||||
|
||||
def _grid_entries(self, grid_renderer):
|
||||
for item in grid_renderer['items']:
|
||||
if not isinstance(item, dict):
|
||||
@@ -3583,38 +3578,65 @@ class YoutubeSearchIE(SearchInfoExtractor, YoutubeBaseInfoExtractor):
|
||||
if not slr_contents:
|
||||
break
|
||||
|
||||
isr_contents = []
|
||||
continuation_token = None
|
||||
# Youtube sometimes adds promoted content to searches,
|
||||
# changing the index location of videos and token.
|
||||
# So we search through all entries till we find them.
|
||||
continuation_token = None
|
||||
for slr_content in slr_contents:
|
||||
isr_contents = try_get(
|
||||
slr_content,
|
||||
lambda x: x['itemSectionRenderer']['contents'],
|
||||
list)
|
||||
for index, isr in enumerate(slr_contents):
|
||||
if not isr_contents:
|
||||
continue
|
||||
for content in isr_contents:
|
||||
if not isinstance(content, dict):
|
||||
continue
|
||||
video = content.get('videoRenderer')
|
||||
if not isinstance(video, dict):
|
||||
continue
|
||||
video_id = video.get('videoId')
|
||||
if not video_id:
|
||||
continue
|
||||
|
||||
yield self._extract_video(video)
|
||||
total += 1
|
||||
if total == n:
|
||||
return
|
||||
isr_contents = try_get(
|
||||
slr_contents,
|
||||
(lambda x: x[index]['itemSectionRenderer']['contents']),
|
||||
list)
|
||||
for content in isr_contents:
|
||||
if content.get('videoRenderer') is not None:
|
||||
break
|
||||
else:
|
||||
isr_contents = []
|
||||
|
||||
if continuation_token is None:
|
||||
continuation_token = try_get(
|
||||
slr_content,
|
||||
lambda x: x['continuationItemRenderer']['continuationEndpoint']['continuationCommand']['token'],
|
||||
slr_contents,
|
||||
lambda x: x[index]['continuationItemRenderer']['continuationEndpoint']['continuationCommand'][
|
||||
'token'],
|
||||
compat_str)
|
||||
if continuation_token is not None and isr_contents:
|
||||
break
|
||||
|
||||
if not isr_contents:
|
||||
break
|
||||
for content in isr_contents:
|
||||
if not isinstance(content, dict):
|
||||
continue
|
||||
video = content.get('videoRenderer')
|
||||
if not isinstance(video, dict):
|
||||
continue
|
||||
video_id = video.get('videoId')
|
||||
if not video_id:
|
||||
continue
|
||||
title = try_get(video, lambda x: x['title']['runs'][0]['text'], compat_str)
|
||||
description = try_get(video, lambda x: x['descriptionSnippet']['runs'][0]['text'], compat_str)
|
||||
duration = parse_duration(try_get(video, lambda x: x['lengthText']['simpleText'], compat_str))
|
||||
view_count_text = try_get(video, lambda x: x['viewCountText']['simpleText'], compat_str) or ''
|
||||
view_count = int_or_none(self._search_regex(
|
||||
r'^(\d+)', re.sub(r'\s', '', view_count_text),
|
||||
'view count', default=None))
|
||||
uploader = try_get(video, lambda x: x['ownerText']['runs'][0]['text'], compat_str)
|
||||
total += 1
|
||||
yield {
|
||||
'_type': 'url_transparent',
|
||||
'ie_key': YoutubeIE.ie_key(),
|
||||
'id': video_id,
|
||||
'url': video_id,
|
||||
'title': title,
|
||||
'description': description,
|
||||
'duration': duration,
|
||||
'view_count': view_count,
|
||||
'uploader': uploader,
|
||||
}
|
||||
if total == n:
|
||||
return
|
||||
if not continuation_token:
|
||||
break
|
||||
data['continuation'] = continuation_token
|
||||
|
||||
@@ -54,35 +54,42 @@ def parseOpts(overrideArguments=None):
|
||||
optionf.close()
|
||||
return res
|
||||
|
||||
def _readUserConf(package_name, default=[]):
|
||||
# .config
|
||||
xdg_config_home = compat_getenv('XDG_CONFIG_HOME') or compat_expanduser('~/.config')
|
||||
userConfFile = os.path.join(xdg_config_home, package_name, 'config')
|
||||
if not os.path.isfile(userConfFile):
|
||||
userConfFile = os.path.join(xdg_config_home, '%s.conf' % package_name)
|
||||
userConf = _readOptions(userConfFile, default=None)
|
||||
if userConf is not None:
|
||||
return userConf
|
||||
def _readUserConf():
|
||||
xdg_config_home = compat_getenv('XDG_CONFIG_HOME')
|
||||
if xdg_config_home:
|
||||
userConfFile = os.path.join(xdg_config_home, 'youtube-dlc', 'config')
|
||||
if not os.path.isfile(userConfFile):
|
||||
userConfFile = os.path.join(xdg_config_home, 'youtube-dlc.conf')
|
||||
else:
|
||||
userConfFile = os.path.join(compat_expanduser('~'), '.config', 'youtube-dlc', 'config')
|
||||
if not os.path.isfile(userConfFile):
|
||||
userConfFile = os.path.join(compat_expanduser('~'), '.config', 'youtube-dlc.conf')
|
||||
userConf = _readOptions(userConfFile, None)
|
||||
|
||||
# appdata
|
||||
appdata_dir = compat_getenv('appdata')
|
||||
if appdata_dir:
|
||||
userConfFile = os.path.join(appdata_dir, package_name, 'config')
|
||||
userConf = _readOptions(userConfFile, default=None)
|
||||
if userConf is None:
|
||||
userConf = _readOptions('%s.txt' % userConfFile, default=None)
|
||||
if userConf is not None:
|
||||
return userConf
|
||||
|
||||
# home
|
||||
userConfFile = os.path.join(compat_expanduser('~'), '%s.conf' % package_name)
|
||||
userConf = _readOptions(userConfFile, default=None)
|
||||
if userConf is None:
|
||||
userConf = _readOptions('%s.txt' % userConfFile, default=None)
|
||||
if userConf is not None:
|
||||
return userConf
|
||||
appdata_dir = compat_getenv('appdata')
|
||||
if appdata_dir:
|
||||
userConf = _readOptions(
|
||||
os.path.join(appdata_dir, 'youtube-dlc', 'config'),
|
||||
default=None)
|
||||
if userConf is None:
|
||||
userConf = _readOptions(
|
||||
os.path.join(appdata_dir, 'youtube-dlc', 'config.txt'),
|
||||
default=None)
|
||||
|
||||
return default
|
||||
if userConf is None:
|
||||
userConf = _readOptions(
|
||||
os.path.join(compat_expanduser('~'), 'youtube-dlc.conf'),
|
||||
default=None)
|
||||
if userConf is None:
|
||||
userConf = _readOptions(
|
||||
os.path.join(compat_expanduser('~'), 'youtube-dlc.conf.txt'),
|
||||
default=None)
|
||||
|
||||
if userConf is None:
|
||||
userConf = []
|
||||
|
||||
return userConf
|
||||
|
||||
def _format_option_string(option):
|
||||
''' ('-o', '--option') -> -o, --format METAVAR'''
|
||||
@@ -166,10 +173,10 @@ def parseOpts(overrideArguments=None):
|
||||
'--ignore-config', '--no-config',
|
||||
action='store_true',
|
||||
help=(
|
||||
'Disable loading any configuration files except the one provided by --config-location. '
|
||||
'When given inside a configuration file, no further configuration files are loaded. '
|
||||
'Additionally, (for backward compatibility) if this option is found inside the '
|
||||
'system configuration file, the user configuration is not loaded.'))
|
||||
'Do not read configuration files. '
|
||||
'When given in the global configuration file /etc/youtube-dl.conf: '
|
||||
'Do not read the user configuration in ~/.config/youtube-dl/config '
|
||||
'(%APPDATA%/youtube-dl/config.txt on Windows)'))
|
||||
general.add_option(
|
||||
'--config-location',
|
||||
dest='config_location', metavar='PATH',
|
||||
@@ -360,11 +367,7 @@ def parseOpts(overrideArguments=None):
|
||||
selection.add_option(
|
||||
'--break-on-existing',
|
||||
action='store_true', dest='break_on_existing', default=False,
|
||||
help="Stop the download process when encountering a file that's in the archive.")
|
||||
selection.add_option(
|
||||
'--break-on-reject',
|
||||
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 after attempting to download a file that's in the archive.")
|
||||
selection.add_option(
|
||||
'--no-download-archive',
|
||||
dest='download_archive', action="store_const", const=None,
|
||||
@@ -463,7 +466,7 @@ def parseOpts(overrideArguments=None):
|
||||
video_format.add_option(
|
||||
'--prefer-free-formats',
|
||||
action='store_true', dest='prefer_free_formats', default=False,
|
||||
help='Prefer free video formats over non-free formats of same quality')
|
||||
help='Prefer free video formats unless a specific one is requested')
|
||||
video_format.add_option(
|
||||
'-F', '--list-formats',
|
||||
action='store_true', dest='listformats',
|
||||
@@ -782,7 +785,7 @@ def parseOpts(overrideArguments=None):
|
||||
verbosity.add_option(
|
||||
'-C', '--call-home',
|
||||
dest='call_home', action='store_true', default=False,
|
||||
help='[Broken] Contact the youtube-dlc server for debugging')
|
||||
help='Contact the youtube-dlc server for debugging')
|
||||
verbosity.add_option(
|
||||
'--no-call-home',
|
||||
dest='call_home', action='store_false',
|
||||
@@ -831,16 +834,8 @@ def parseOpts(overrideArguments=None):
|
||||
help=optparse.SUPPRESS_HELP)
|
||||
filesystem.add_option(
|
||||
'-w', '--no-overwrites',
|
||||
action='store_false', dest='overwrites', default=None,
|
||||
help='Do not overwrite any files')
|
||||
filesystem.add_option(
|
||||
'--force-overwrites', '--yes-overwrites',
|
||||
action='store_true', dest='overwrites',
|
||||
help='Overwrite all video and metadata files. This option includes --no-continue')
|
||||
filesystem.add_option(
|
||||
'--no-force-overwrites',
|
||||
action='store_const', dest='overwrites', const=None,
|
||||
help='Do not overwrite the video, but overwrite related files (default)')
|
||||
action='store_true', dest='nooverwrites', default=False,
|
||||
help='Do not overwrite files')
|
||||
filesystem.add_option(
|
||||
'-c', '--continue',
|
||||
action='store_true', dest='continue_dl', default=True,
|
||||
@@ -981,9 +976,8 @@ def parseOpts(overrideArguments=None):
|
||||
'Give these arguments to the postprocessors. '
|
||||
"Specify the postprocessor name and the arguments separated by a colon ':' "
|
||||
'to give the argument to only the specified postprocessor. Supported names are '
|
||||
'ExtractAudio, VideoRemuxer, VideoConvertor, EmbedSubtitle, Metadata, Merger, FixupStretched, '
|
||||
'FixupM4a, FixupM3u8, SubtitlesConvertor, EmbedThumbnail, XAttrMetadata, SponSkrub and Default. '
|
||||
'You can use this option multiple times to give different arguments to different postprocessors'))
|
||||
'ExtractAudio, VideoRemuxer, VideoConvertor, EmbedSubtitle, Metadata, Merger, FixupStretched, FixupM4a, FixupM3u8, SubtitlesConvertor, SponSkrub and Default'
|
||||
'. You can use this option multiple times to give different arguments to different postprocessors'))
|
||||
postproc.add_option(
|
||||
'-k', '--keep-video',
|
||||
action='store_true', dest='keepvideo', default=False,
|
||||
@@ -1140,60 +1134,33 @@ def parseOpts(overrideArguments=None):
|
||||
return [a.decode(preferredencoding(), 'replace') for a in conf]
|
||||
return conf
|
||||
|
||||
configs = {
|
||||
'command_line': compat_conf(sys.argv[1:]),
|
||||
'custom': [], 'portable': [], 'user': [], 'system': []}
|
||||
opts, args = parser.parse_args(configs['command_line'])
|
||||
command_line_conf = compat_conf(sys.argv[1:])
|
||||
opts, args = parser.parse_args(command_line_conf)
|
||||
|
||||
def get_configs():
|
||||
if '--config-location' in configs['command_line']:
|
||||
location = compat_expanduser(opts.config_location)
|
||||
if os.path.isdir(location):
|
||||
location = os.path.join(location, 'youtube-dlc.conf')
|
||||
if not os.path.exists(location):
|
||||
parser.error('config-location %s does not exist.' % location)
|
||||
configs['custom'] = _readOptions(location)
|
||||
system_conf = user_conf = custom_conf = []
|
||||
|
||||
if '--ignore-config' in configs['command_line']:
|
||||
return
|
||||
if '--ignore-config' in configs['custom']:
|
||||
return
|
||||
if '--config-location' in command_line_conf:
|
||||
location = compat_expanduser(opts.config_location)
|
||||
if os.path.isdir(location):
|
||||
location = os.path.join(location, 'youtube-dlc.conf')
|
||||
if not os.path.exists(location):
|
||||
parser.error('config-location %s does not exist.' % location)
|
||||
custom_conf = _readOptions(location)
|
||||
elif '--ignore-config' in command_line_conf:
|
||||
pass
|
||||
else:
|
||||
system_conf = _readOptions('/etc/youtube-dlc.conf')
|
||||
if '--ignore-config' not in system_conf:
|
||||
user_conf = _readUserConf()
|
||||
|
||||
def get_portable_path():
|
||||
path = os.path.dirname(sys.argv[0])
|
||||
if os.path.abspath(sys.argv[0]) != os.path.abspath(sys.executable): # Not packaged
|
||||
path = os.path.join(path, '..')
|
||||
return os.path.abspath(path)
|
||||
|
||||
run_path = get_portable_path()
|
||||
configs['portable'] = _readOptions(os.path.join(run_path, 'yt-dlp.conf'), default=None)
|
||||
if configs['portable'] is None:
|
||||
configs['portable'] = _readOptions(os.path.join(run_path, 'youtube-dlc.conf'))
|
||||
|
||||
if '--ignore-config' in configs['portable']:
|
||||
return
|
||||
configs['system'] = _readOptions('/etc/yt-dlp.conf', default=None)
|
||||
if configs['system'] is None:
|
||||
configs['system'] = _readOptions('/etc/youtube-dlc.conf')
|
||||
|
||||
if '--ignore-config' in configs['system']:
|
||||
return
|
||||
configs['user'] = _readUserConf('yt-dlp', default=None)
|
||||
if configs['user'] is None:
|
||||
configs['user'] = _readUserConf('youtube-dlc')
|
||||
if '--ignore-config' in configs['user']:
|
||||
configs['system'] = []
|
||||
|
||||
get_configs()
|
||||
argv = configs['system'] + configs['user'] + configs['portable'] + configs['custom'] + configs['command_line']
|
||||
argv = system_conf + user_conf + custom_conf + command_line_conf
|
||||
opts, args = parser.parse_args(argv)
|
||||
if opts.verbose:
|
||||
for conf_label, conf in (
|
||||
('System config', configs['system']),
|
||||
('User config', configs['user']),
|
||||
('Portable config', configs['portable']),
|
||||
('Custom config', configs['custom']),
|
||||
('Command-line args', configs['command_line'])):
|
||||
('System config', system_conf),
|
||||
('User config', user_conf),
|
||||
('Custom config', custom_conf),
|
||||
('Command-line args', command_line_conf)):
|
||||
write_string('[debug] %s: %s\n' % (conf_label, repr(_hide_login_info(conf))))
|
||||
|
||||
return parser, opts, args
|
||||
|
||||
@@ -37,25 +37,7 @@ class PostProcessor(object):
|
||||
self.PP_NAME = self.__class__.__name__[:-2]
|
||||
|
||||
def to_screen(self, text, *args, **kwargs):
|
||||
if self._downloader:
|
||||
return self._downloader.to_screen('[%s] %s' % (self.PP_NAME, text), *args, **kwargs)
|
||||
|
||||
def report_warning(self, text, *args, **kwargs):
|
||||
if self._downloader:
|
||||
return self._downloader.report_warning(text, *args, **kwargs)
|
||||
|
||||
def report_error(self, text, *args, **kwargs):
|
||||
if self._downloader:
|
||||
return self._downloader.report_error(text, *args, **kwargs)
|
||||
|
||||
def write_debug(self, text, *args, **kwargs):
|
||||
if self.get_param('verbose', False):
|
||||
return self._downloader.to_screen('[debug] %s' % text, *args, **kwargs)
|
||||
|
||||
def get_param(self, name, default=None, *args, **kwargs):
|
||||
if self._downloader:
|
||||
return self._downloader.params.get(name, default, *args, **kwargs)
|
||||
return default
|
||||
return self._downloader.to_screen('[%s] %s' % (self.PP_NAME, text), *args, **kwargs)
|
||||
|
||||
def set_downloader(self, downloader):
|
||||
"""Sets the downloader for this PP."""
|
||||
@@ -82,10 +64,10 @@ class PostProcessor(object):
|
||||
try:
|
||||
os.utime(encodeFilename(path), (atime, mtime))
|
||||
except Exception:
|
||||
self.report_warning(errnote)
|
||||
self._downloader.report_warning(errnote)
|
||||
|
||||
def _configuration_args(self, default=[]):
|
||||
args = self.get_param('postprocessor_args', {})
|
||||
args = self._downloader.params.get('postprocessor_args', {})
|
||||
if isinstance(args, list): # for backward compatibility
|
||||
args = {'default': args, 'sponskrub': []}
|
||||
return cli_configuration_args(args, self.PP_NAME.lower(), args.get('default', []))
|
||||
|
||||
@@ -14,8 +14,7 @@ from ..utils import (
|
||||
PostProcessingError,
|
||||
prepend_extension,
|
||||
replace_extension,
|
||||
shell_quote,
|
||||
process_communicate_or_kill,
|
||||
shell_quote
|
||||
)
|
||||
|
||||
|
||||
@@ -41,7 +40,8 @@ class EmbedThumbnailPP(FFmpegPostProcessor):
|
||||
thumbnail_filename = info['thumbnails'][-1]['filename']
|
||||
|
||||
if not os.path.exists(encodeFilename(thumbnail_filename)):
|
||||
self.report_warning('Skipping embedding the thumbnail because the file is missing.')
|
||||
self._downloader.report_warning(
|
||||
'Skipping embedding the thumbnail because the file is missing.')
|
||||
return [], info
|
||||
|
||||
def is_webp(path):
|
||||
@@ -124,10 +124,11 @@ class EmbedThumbnailPP(FFmpegPostProcessor):
|
||||
|
||||
self.to_screen('Adding thumbnail to "%s"' % filename)
|
||||
|
||||
self.write_debug('AtomicParsley command line: %s' % shell_quote(cmd))
|
||||
if self._downloader.params.get('verbose', False):
|
||||
self._downloader.to_screen('[debug] AtomicParsley command line: %s' % shell_quote(cmd))
|
||||
|
||||
p = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
|
||||
stdout, stderr = process_communicate_or_kill(p)
|
||||
stdout, stderr = p.communicate()
|
||||
|
||||
if p.returncode != 0:
|
||||
msg = stderr.decode('utf-8', 'replace').strip()
|
||||
@@ -138,7 +139,7 @@ class EmbedThumbnailPP(FFmpegPostProcessor):
|
||||
# for formats that don't support thumbnails (like 3gp) AtomicParsley
|
||||
# won't create to the temporary file
|
||||
if b'No changes' in stdout:
|
||||
self.report_warning('The file format doesn\'t support embedding a thumbnail')
|
||||
self._downloader.report_warning('The file format doesn\'t support embedding a thumbnail')
|
||||
else:
|
||||
os.remove(encodeFilename(filename))
|
||||
os.rename(encodeFilename(temp_filename), encodeFilename(filename))
|
||||
|
||||
@@ -21,7 +21,6 @@ from ..utils import (
|
||||
dfxp2srt,
|
||||
ISO639Utils,
|
||||
replace_extension,
|
||||
process_communicate_or_kill,
|
||||
)
|
||||
|
||||
|
||||
@@ -68,7 +67,8 @@ class FFmpegPostProcessor(PostProcessor):
|
||||
self._versions[self.basename], required_version):
|
||||
warning = 'Your copy of %s is outdated, update %s to version %s or newer if you encounter any errors.' % (
|
||||
self.basename, self.basename, required_version)
|
||||
self.report_warning(warning)
|
||||
if self._downloader:
|
||||
self._downloader.report_warning(warning)
|
||||
|
||||
@staticmethod
|
||||
def get_versions(downloader=None):
|
||||
@@ -98,11 +98,11 @@ class FFmpegPostProcessor(PostProcessor):
|
||||
self._paths = None
|
||||
self._versions = None
|
||||
if self._downloader:
|
||||
prefer_ffmpeg = self.get_param('prefer_ffmpeg', True)
|
||||
location = self.get_param('ffmpeg_location')
|
||||
prefer_ffmpeg = self._downloader.params.get('prefer_ffmpeg', True)
|
||||
location = self._downloader.params.get('ffmpeg_location')
|
||||
if location is not None:
|
||||
if not os.path.exists(location):
|
||||
self.report_warning(
|
||||
self._downloader.report_warning(
|
||||
'ffmpeg-location %s does not exist! '
|
||||
'Continuing without avconv/ffmpeg.' % (location))
|
||||
self._versions = {}
|
||||
@@ -110,7 +110,7 @@ class FFmpegPostProcessor(PostProcessor):
|
||||
elif not os.path.isdir(location):
|
||||
basename = os.path.splitext(os.path.basename(location))[0]
|
||||
if basename not in programs:
|
||||
self.report_warning(
|
||||
self._downloader.report_warning(
|
||||
'Cannot identify executable %s, its basename should be one of %s. '
|
||||
'Continuing without avconv/ffmpeg.' %
|
||||
(location, ', '.join(programs)))
|
||||
@@ -176,11 +176,13 @@ class FFmpegPostProcessor(PostProcessor):
|
||||
encodeFilename(self.executable, True),
|
||||
encodeArgument('-i')]
|
||||
cmd.append(encodeFilename(self._ffmpeg_filename_argument(path), True))
|
||||
self.write_debug('%s command line: %s' % (self.basename, shell_quote(cmd)))
|
||||
if self._downloader.params.get('verbose', False):
|
||||
self._downloader.to_screen(
|
||||
'[debug] %s command line: %s' % (self.basename, shell_quote(cmd)))
|
||||
handle = subprocess.Popen(
|
||||
cmd, stderr=subprocess.PIPE,
|
||||
stdout=subprocess.PIPE, stdin=subprocess.PIPE)
|
||||
stdout_data, stderr_data = process_communicate_or_kill(handle)
|
||||
stdout_data, stderr_data = handle.communicate()
|
||||
expected_ret = 0 if self.probe_available else 1
|
||||
if handle.wait() != expected_ret:
|
||||
return None
|
||||
@@ -225,9 +227,10 @@ class FFmpegPostProcessor(PostProcessor):
|
||||
+ [encodeArgument(o) for o in opts]
|
||||
+ [encodeFilename(self._ffmpeg_filename_argument(out_path), True)])
|
||||
|
||||
self.write_debug('ffmpeg command line: %s' % shell_quote(cmd))
|
||||
if self._downloader.params.get('verbose', False):
|
||||
self._downloader.to_screen('[debug] ffmpeg command line: %s' % shell_quote(cmd))
|
||||
p = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE, stdin=subprocess.PIPE)
|
||||
stdout, stderr = process_communicate_or_kill(p)
|
||||
stdout, stderr = p.communicate()
|
||||
if p.returncode != 0:
|
||||
stderr = stderr.decode('utf-8', 'replace')
|
||||
msg = stderr.strip().split('\n')[-1]
|
||||
@@ -562,7 +565,8 @@ class FFmpegMergerPP(FFmpegPostProcessor):
|
||||
'youtube-dlc will download single file media. '
|
||||
'Update %s to version %s or newer to fix this.') % (
|
||||
self.basename, self.basename, required_version)
|
||||
self.report_warning(warning)
|
||||
if self._downloader:
|
||||
self._downloader.report_warning(warning)
|
||||
return False
|
||||
return True
|
||||
|
||||
@@ -651,7 +655,7 @@ class FFmpegSubtitlesConvertorPP(FFmpegPostProcessor):
|
||||
new_file = subtitles_filename(filename, lang, new_ext, info.get('ext'))
|
||||
|
||||
if ext in ('dfxp', 'ttml', 'tt'):
|
||||
self.report_warning(
|
||||
self._downloader.report_warning(
|
||||
'You have requested to convert dfxp (TTML) subtitles into another format, '
|
||||
'which results in style information loss')
|
||||
|
||||
|
||||
@@ -46,16 +46,16 @@ class SponSkrubPP(PostProcessor):
|
||||
self.to_screen('Skipping sponskrub since it is not a YouTube video')
|
||||
return [], information
|
||||
if self.cutout and not self.force and not information.get('__real_download', False):
|
||||
self.report_warning(
|
||||
'Skipping sponskrub since the video was already downloaded. '
|
||||
self._downloader.to_screen(
|
||||
'[sponskrub] Skipping sponskrub since the video was already downloaded. '
|
||||
'Use --sponskrub-force to run sponskrub anyway')
|
||||
return [], information
|
||||
|
||||
self.to_screen('Trying to %s sponsor sections' % ('remove' if self.cutout else 'mark'))
|
||||
if self.cutout:
|
||||
self.report_warning('Cutting out sponsor segments will cause the subtitles to go out of sync.')
|
||||
self._downloader.to_screen('WARNING: Cutting out sponsor segments will cause the subtitles to go out of sync.')
|
||||
if not information.get('__real_download', False):
|
||||
self.report_warning('If sponskrub is run multiple times, unintended parts of the video could be cut out.')
|
||||
self._downloader.to_screen('WARNING: If sponskrub is run multiple times, unintended parts of the video could be cut out.')
|
||||
|
||||
filename = information['filepath']
|
||||
temp_filename = filename + '.' + self._temp_ext + os.path.splitext(filename)[1]
|
||||
@@ -68,7 +68,8 @@ class SponSkrubPP(PostProcessor):
|
||||
cmd += ['--', information['id'], filename, temp_filename]
|
||||
cmd = [encodeArgument(i) for i in cmd]
|
||||
|
||||
self.write_debug('sponskrub command line: %s' % shell_quote(cmd))
|
||||
if self._downloader.params.get('verbose', False):
|
||||
self._downloader.to_screen('[debug] sponskrub command line: %s' % shell_quote(cmd))
|
||||
p = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE, stdin=subprocess.PIPE)
|
||||
stdout, stderr = p.communicate()
|
||||
|
||||
@@ -80,8 +81,6 @@ class SponSkrubPP(PostProcessor):
|
||||
self.to_screen('No segments in the SponsorBlock database')
|
||||
else:
|
||||
stderr = stderr.decode('utf-8', 'replace')
|
||||
msg = stderr.strip()
|
||||
if not self.get_param('verbose', False):
|
||||
msg = msg.split('\n')[-1]
|
||||
msg = stderr.strip().split('\n')[-1]
|
||||
raise PostProcessingError(msg if msg else 'sponskrub failed with error code %s!' % p.returncode)
|
||||
return [], information
|
||||
|
||||
@@ -57,16 +57,16 @@ class XAttrMetadataPP(PostProcessor):
|
||||
return [], info
|
||||
|
||||
except XAttrUnavailableError as e:
|
||||
self.report_error(str(e))
|
||||
self._downloader.report_error(str(e))
|
||||
return [], info
|
||||
|
||||
except XAttrMetadataError as e:
|
||||
if e.reason == 'NO_SPACE':
|
||||
self.report_warning(
|
||||
self._downloader.report_warning(
|
||||
'There\'s no disk space left, disk quota exceeded or filesystem xattr limit exceeded. '
|
||||
+ (('Some ' if num_written else '') + 'extended attributes are not written.').capitalize())
|
||||
elif e.reason == 'VALUE_TOO_LONG':
|
||||
self.report_warning(
|
||||
self._downloader.report_warning(
|
||||
'Unable to write extended attributes due to too long values.')
|
||||
else:
|
||||
msg = 'This filesystem doesn\'t support extended attributes. '
|
||||
@@ -74,5 +74,5 @@ class XAttrMetadataPP(PostProcessor):
|
||||
msg += 'You need to use NTFS.'
|
||||
else:
|
||||
msg += '(You may have to enable them in your /etc/fstab)'
|
||||
self.report_error(msg)
|
||||
self._downloader.report_error(msg)
|
||||
return [], info
|
||||
|
||||
@@ -32,7 +32,7 @@ def rsa_verify(message, signature, key):
|
||||
def update_self(to_screen, verbose, opener):
|
||||
"""Update the program file with the latest version from the repository"""
|
||||
|
||||
return to_screen('Update is currently broken.\nVisit https://github.com/pukkandan/yt-dlp/releases/latest to get the latest version')
|
||||
return to_screen('Update is currently broken.\nVisit https://github.com/pukkandan/yt-dlc/releases/latest to get the latest version')
|
||||
|
||||
UPDATE_URL = 'https://blackjack4494.github.io//update/'
|
||||
VERSION_URL = UPDATE_URL + 'LATEST_VERSION'
|
||||
|
||||
@@ -2215,15 +2215,6 @@ def unescapeHTML(s):
|
||||
r'&([^&;]+;)', lambda m: _htmlentity_transform(m.group(1)), s)
|
||||
|
||||
|
||||
def process_communicate_or_kill(p, *args, **kwargs):
|
||||
try:
|
||||
return p.communicate(*args, **kwargs)
|
||||
except BaseException: # Including KeyboardInterrupt
|
||||
p.kill()
|
||||
p.wait()
|
||||
raise
|
||||
|
||||
|
||||
def get_subprocess_encoding():
|
||||
if sys.platform == 'win32' and sys.getwindowsversion()[0] >= 5:
|
||||
# For subprocess calls, encode with locale encoding
|
||||
@@ -2332,8 +2323,8 @@ def bug_reports_message():
|
||||
if ytdl_is_updateable():
|
||||
update_cmd = 'type youtube-dlc -U to update'
|
||||
else:
|
||||
update_cmd = 'see https://github.com/pukkandan/yt-dlp on how to update'
|
||||
msg = '; please report this issue on https://github.com/pukkandan/yt-dlp .'
|
||||
update_cmd = 'see https://github.com/pukkandan/yt-dlc on how to update'
|
||||
msg = '; please report this issue on https://github.com/pukkandan/yt-dlc .'
|
||||
msg += ' Make sure you are using the latest version; %s.' % update_cmd
|
||||
msg += ' Be sure to call youtube-dlc with the --verbose flag and include its complete output.'
|
||||
return msg
|
||||
@@ -2433,16 +2424,6 @@ class PostProcessingError(YoutubeDLError):
|
||||
self.msg = msg
|
||||
|
||||
|
||||
class ExistingVideoReached(YoutubeDLError):
|
||||
""" --max-downloads limit has been reached. """
|
||||
pass
|
||||
|
||||
|
||||
class RejectedVideoReached(YoutubeDLError):
|
||||
""" --max-downloads limit has been reached. """
|
||||
pass
|
||||
|
||||
|
||||
class MaxDownloadsReached(YoutubeDLError):
|
||||
""" --max-downloads limit has been reached. """
|
||||
pass
|
||||
@@ -3749,8 +3730,7 @@ def check_executable(exe, args=[]):
|
||||
""" Checks if the given binary is installed somewhere in PATH, and returns its name.
|
||||
args can be a list of arguments for a short output (like -version) """
|
||||
try:
|
||||
process_communicate_or_kill(subprocess.Popen(
|
||||
[exe] + args, stdout=subprocess.PIPE, stderr=subprocess.PIPE))
|
||||
subprocess.Popen([exe] + args, stdout=subprocess.PIPE, stderr=subprocess.PIPE).communicate()
|
||||
except OSError:
|
||||
return False
|
||||
return exe
|
||||
@@ -3764,10 +3744,10 @@ def get_exe_version(exe, args=['--version'],
|
||||
# STDIN should be redirected too. On UNIX-like systems, ffmpeg triggers
|
||||
# SIGTTOU if youtube-dlc is run in the background.
|
||||
# See https://github.com/ytdl-org/youtube-dl/issues/955#issuecomment-209789656
|
||||
out, _ = process_communicate_or_kill(subprocess.Popen(
|
||||
out, _ = subprocess.Popen(
|
||||
[encodeArgument(exe)] + args,
|
||||
stdin=subprocess.PIPE,
|
||||
stdout=subprocess.PIPE, stderr=subprocess.STDOUT))
|
||||
stdout=subprocess.PIPE, stderr=subprocess.STDOUT).communicate()
|
||||
except OSError:
|
||||
return False
|
||||
if isinstance(out, bytes): # Python 2.x
|
||||
@@ -3912,16 +3892,13 @@ def read_batch_urls(batch_fd):
|
||||
def fixup(url):
|
||||
if not isinstance(url, compat_str):
|
||||
url = url.decode('utf-8', 'replace')
|
||||
BOM_UTF8 = ('\xef\xbb\xbf', '\ufeff')
|
||||
for bom in BOM_UTF8:
|
||||
if url.startswith(bom):
|
||||
url = url[len(bom):]
|
||||
url = url.lstrip()
|
||||
if not url or url.startswith(('#', ';', ']')):
|
||||
BOM_UTF8 = '\xef\xbb\xbf'
|
||||
if url.startswith(BOM_UTF8):
|
||||
url = url[len(BOM_UTF8):]
|
||||
url = url.strip()
|
||||
if url.startswith(('#', ';', ']')):
|
||||
return False
|
||||
# "#" cannot be stripped out since it is part of the URI
|
||||
# However, it can be safely stipped out if follwing a whitespace
|
||||
return re.split(r'\s#', url, 1)[0].rstrip()
|
||||
return url
|
||||
|
||||
with contextlib.closing(batch_fd) as fd:
|
||||
return [url for url in map(fixup, fd) if url]
|
||||
@@ -5726,7 +5703,7 @@ def write_xattr(path, key, value):
|
||||
cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE, stdin=subprocess.PIPE)
|
||||
except EnvironmentError as e:
|
||||
raise XAttrMetadataError(e.errno, e.strerror)
|
||||
stdout, stderr = process_communicate_or_kill(p)
|
||||
stdout, stderr = p.communicate()
|
||||
stderr = stderr.decode('utf-8', 'replace')
|
||||
if p.returncode != 0:
|
||||
raise XAttrMetadataError(p.returncode, stderr)
|
||||
@@ -5842,20 +5819,3 @@ def format_field(obj, field, template='%s', ignore=(None, ''), default='', func=
|
||||
if func and val not in ignore:
|
||||
val = func(val)
|
||||
return template % val if val not in ignore else default
|
||||
|
||||
|
||||
def clean_podcast_url(url):
|
||||
return re.sub(r'''(?x)
|
||||
(?:
|
||||
(?:
|
||||
chtbl\.com/track|
|
||||
media\.blubrry\.com| # https://create.blubrry.com/resources/podcast-media-download-statistics/getting-started/
|
||||
play\.podtrac\.com
|
||||
)/[^/]+|
|
||||
(?:dts|www)\.podtrac\.com/(?:pts/)?redirect\.[0-9a-z]{3,4}| # http://analytics.podtrac.com/how-to-measure
|
||||
flex\.acast\.com|
|
||||
pd(?:
|
||||
cn\.co| # https://podcorn.com/analytics-prefix/
|
||||
st\.fm # https://podsights.com/docs/
|
||||
)/e
|
||||
)/''', '', url)
|
||||
|
||||
@@ -1,3 +1,3 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
__version__ = '2021.01.14'
|
||||
__version__ = '2021.01.07'
|
||||
|
||||
Reference in New Issue
Block a user