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

Compare commits

...

28 Commits

Author SHA1 Message Date
pukkandan
6fd35a1101 Release 2021.01.09 2021-01-09 18:14:11 +05:30
pukkandan
f5b1bca913 Kill child processes when yt-dlc is killed (https://github.com/ytdl-org/youtube-dl/pull/26592)
Authored by: Unrud
2021-01-09 18:08:07 +05:30
pukkandan
d9eebbc747 Fix incorrect ANSI sequence for restoring console-window title (https://github.com/ytdl-org/youtube-dl/pull/26637)
Authored by: glenn-slayden
2021-01-09 18:08:07 +05:30
pukkandan
c3e6ffba53 Stop immediately when reaching '--max-downloads' (https://github.com/ytdl-org/youtube-dl/pull/26638)
Authored by: glenn-slayden
2021-01-09 18:08:06 +05:30
pukkandan
8c04f0be96 batch-file enumeration improvements (https://github.com/ytdl-org/youtube-dl/pull/26813)
Co-authored by: glenn-slayden
Modified from c9a9ccf8a3

These improvements apply to reading the list of URLs from the file supplied via the `--batch-file` (`-a`) command line option.

1. Skip blank and empty lines in the file. Currently, lines with leading whitespace are only skipped when that whitespace is followed by a comment character (`#`, `;`, or `]`). This means that empty lines and lines consisting only of whitespace are returned as (trimmed) empty strings in the list of URLs to process.

2. [bug fix] Detect and remove the Unicode BOM when the file descriptor is already decoding Unicode.

With Python 3, the `batch_fd` enumerator returns the lines of the file as Unicode. For UTF-8, this means that the raw BOM bytes from the file `\xef \xbb \xbf` show up converted into a single `\ufeff` character prefixed to the first enumerated text line.

This fix solves several buggy interactions between the presence of BOM, the skipping of comments and/or blank lines, and ensuring the list of URLs is consistently trimmed. For example, if the first line of the file is blank, the BOM is incorrectly returned as a URL standing alone. If the first line contains a URL, it will be prefixed with this unwanted single character--but note that its being there will have inhibited the proper trimming of any leading whitespace. Currently, the `UnicodeBOMIE` helper attempts to recover from some of these error cases, but this fix prevents the error from happening in the first place (at least on Python3). In any case, the `UnicodeBOMIE` approach is flawed, because it is clearly illogical for a BOM to appear in the (non-batch) URL(s) specified directly on the command line (and for that matter, on URLs *after the first line* of a batch list, also)

3. Adds proper trimming of the " #" into the read_batch_urls processing so that the URLs it enumerates are cleaned and trimmed more consistently.
2021-01-09 18:08:03 +05:30
Alex Merkel
ab8e5e516f Add post_hooks option to YoutubeDL.py (https://github.com/ytdl-org/youtube-dl/pull/27573)
Authored by: alexmerkel
2021-01-09 16:00:49 +05:30
pukkandan
62d80ba17c [youtube] Fix bug (Closes https://github.com/pukkandan/yt-dlc/issues/10) 2021-01-08 23:27:00 +05:30
pukkandan
e8273c86a3 [version] update 2021-01-08 22:59:45 +05:30
pukkandan
e5bc03a6fa Release 2021.01.08 2021-01-08 22:54:34 +05:30
pukkandan
034b6215b4 Move changelog to seperate file 2021-01-08 22:50:49 +05:30
pukkandan
00dd0cd573 Update to ytdl-2021.01.08 2021-01-08 21:59:10 +05:30
pukkandan
0c0ff18f7d [CI] Created quick-test 2021-01-08 03:44:54 +05:30
pukkandan
a26c99ac13 Release 2021.01.07-1 2021-01-08 02:13:14 +05:30
pukkandan
1b77b347d4 Allow passing different arguments to different postprocessors
* Also deprecated --sponskrub-args

Closes: https://github.com/ytdl-org/youtube-dl/issues/27593
Eg: `--postprocessor-args "VideoConvertor:-c:v h264_nvenc -preset slow"`
Eg: `--postprocessor-args "SponsKrub:-include-selfpromo"`

For backward compatibility, `--postprocessor-args args` is equivalent to:
`--post-processor-args "sponskrub:" --post-processor-args "default:args"`
2021-01-08 01:41:08 +05:30
pukkandan
6c40e33c9e ffmpeg: ignore extra data streams #9 by jbruchon
closes #2, blackjack4494#291

Authored by jbruchon
2021-01-08 01:08:21 +05:30
Jody Bruchon
e0da59fe54 ffmpeg: ignore extra data streams with -dn (fixes #2)
Sometimes, video files will arrive with a timecode data stream
that causes `-map 0` to error out due to the stream not being
supported in the output container. These data streams generally do
not matter, so tell ffmpeg to ignore them rather than choking on
them.
2021-01-07 12:26:50 -05:00
pukkandan
c82fc65d03 Akamai fix #6 (blackjack4494#274) by nixxo
Authored by nixxo
2021-01-07 21:22:31 +05:30
nixxo
1c3a61baae Merge branch 'master' into akamai-fix 2021-01-07 16:49:07 +01:00
pukkandan
9d88274ca2 Tiktok fix #8 (blackjack4494#20)
Authored by GreyAlien502
2021-01-07 20:53:03 +05:30
pukkandan
7dbce2c532 [vlive] add support for playlists #7 (blackjack4494#223)
Authored by kyuyeunk
2021-01-07 20:53:03 +05:30
pukkandan
2c35345868 Make sure playerOffsetMs is positive in youtube_live_chat by siikamiika #5 (blackjack4494#262)
Authored by siikamiika
2021-01-07 20:53:03 +05:30
pukkandan
3ad6c46175 Release 2021.01.07 2021-01-07 20:10:10 +05:30
Kyu Yeun Kim
3d54ebd427 [vlive] add support for playlists 2020-12-04 23:24:23 +09:00
Remita Amine
727006d951 [extractor/commons] improve Akamai HTTP formats extraction 2020-12-03 13:11:21 +01:00
Remita Amine
0827033479 [extractor/common] improve Akamai HTTP format extraction
- Allow m3u8 manifest without an additional audio format
- Fix extraction for qualities starting with a number
Solution provided by @nixxo based on: https://stackoverflow.com/a/5984688
2020-12-03 13:10:24 +01:00
siikamiika
ae6e4e25aa make sure playerOffsetMs is positive 2020-11-28 02:19:38 +02:00
GreyAlien502
61e76c1e5f simplify second page fetch
Co-authored-by: Merval <merval@users.noreply.github.com>
2020-10-27 02:20:18 +00:00
GreyAlien502
7bbc0bbce0 fix tiktok download 2020-10-26 12:38:25 +00:00
57 changed files with 1274 additions and 617 deletions

View File

@@ -21,7 +21,7 @@ assignees: ''
<!--
Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dlc:
- First of, make sure you are using the latest version of youtube-dlc. Run `youtube-dlc --version` and ensure your version is 2021.01.05-2. If it's not, see https://github.com/pukkandan/yt-dlc 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 2021.01.08. 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-dlc.
- Search the bugtracker for similar issues: https://github.com/pukkandan/yt-dlc. DO NOT post duplicates.
@@ -29,7 +29,7 @@ Carefully read and work through this check list in order to prevent the most com
-->
- [ ] I'm reporting a broken site support
- [ ] I've verified that I'm running youtube-dlc version **2021.01.05-2**
- [ ] I've verified that I'm running youtube-dlc version **2021.01.08**
- [ ] 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] youtube-dlc version 2021.01.05-2
[debug] youtube-dlc version 2021.01.08
[debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
[debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
[debug] Proxy map: {}

View File

@@ -21,7 +21,7 @@ assignees: ''
<!--
Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dlc:
- First of, make sure you are using the latest version of youtube-dlc. Run `youtube-dlc --version` and ensure your version is 2021.01.05-2. If it's not, see https://github.com/pukkandan/yt-dlc 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 2021.01.08. 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-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.
@@ -29,7 +29,7 @@ Carefully read and work through this check list in order to prevent the most com
-->
- [ ] I'm reporting a new site support request
- [ ] I've verified that I'm running youtube-dlc version **2021.01.05-2**
- [ ] I've verified that I'm running youtube-dlc version **2021.01.08**
- [ ] I've checked that all provided URLs are alive and playable in a browser
- [ ] I've checked that none of provided URLs violate any copyrights
- [ ] I've searched the bugtracker for similar site support requests including closed ones

View File

@@ -21,13 +21,13 @@ assignees: ''
<!--
Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dlc:
- First of, make sure you are using the latest version of youtube-dlc. Run `youtube-dlc --version` and ensure your version is 2021.01.05-2. If it's not, see https://github.com/pukkandan/yt-dlc 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 2021.01.08. 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 youtube-dlc version **2021.01.05-2**
- [ ] I've verified that I'm running youtube-dlc version **2021.01.08**
- [ ] I've searched the bugtracker for similar site feature requests including closed ones

View File

@@ -21,7 +21,7 @@ assignees: ''
<!--
Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dlc:
- First of, make sure you are using the latest version of youtube-dlc. Run `youtube-dlc --version` and ensure your version is 2021.01.05-2. If it's not, see https://github.com/pukkandan/yt-dlc 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 2021.01.08. 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-dlc.
- Search the bugtracker for similar issues: https://github.com/pukkandan/yt-dlc. DO NOT post duplicates.
@@ -30,7 +30,7 @@ Carefully read and work through this check list in order to prevent the most com
-->
- [ ] I'm reporting a broken site support issue
- [ ] I've verified that I'm running youtube-dlc version **2021.01.05-2**
- [ ] I've verified that I'm running youtube-dlc version **2021.01.08**
- [ ] 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] youtube-dlc version 2021.01.05-2
[debug] youtube-dlc version 2021.01.08
[debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
[debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
[debug] Proxy map: {}

View File

@@ -21,13 +21,13 @@ assignees: ''
<!--
Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dlc:
- First of, make sure you are using the latest version of youtube-dlc. Run `youtube-dlc --version` and ensure your version is 2021.01.05-2. If it's not, see https://github.com/pukkandan/yt-dlc 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 2021.01.08. 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 youtube-dlc version **2021.01.05-2**
- [ ] I've verified that I'm running youtube-dlc version **2021.01.08**
- [ ] I've searched the bugtracker for similar feature requests including closed ones

View File

@@ -1,4 +1,4 @@
name: CI
name: Full Test
on: [push]
jobs:
tests:
@@ -60,16 +60,4 @@ jobs:
env:
YTDL_TEST_SET: ${{ matrix.ytdl-test-set }}
run: ./devscripts/run_tests.${{ matrix.run-tests-ext }}
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 .
# flake8 has been moved to quick-test

31
.github/workflows/quick-test.yml vendored Normal file
View File

@@ -0,0 +1,31 @@
name: Core Test
on: [push]
jobs:
tests:
name: Core Tests
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
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 .

View File

@@ -1,3 +1,8 @@
pukkandan
h-h-h-h
pauldubois98
pauldubois98
nixxo
GreyAlien502
kyuyeunk
siikamiika
jbruchon

53
Changelog.md Normal file
View File

@@ -0,0 +1,53 @@
# Changelog
### 2020.01.08
* **Merge youtube-dl:** Upto [2020.01.08](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 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
* 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

View File

@@ -1,5 +1,5 @@
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 clean
doc: README.md CONTRIBUTING.md issuetemplates supportedsites
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 CONTRIBUTING.md.tmp youtube-dlc youtube-dlc.exe
@@ -50,7 +50,8 @@ offlinetest: codetest
--exclude test_subtitles.py \
--exclude test_write_annotations.py \
--exclude test_youtube_lists.py \
--exclude test_youtube_signature.py
--exclude test_youtube_signature.py \
--exclude test_post_hooks.py
tar: youtube-dlc.tar.gz

View File

@@ -1,12 +1,13 @@
[![Build Status](https://github.com/pukkandan/yt-dlc/workflows/CI/badge.svg)](https://github.com/pukkandan/yt-dlc/actions?query=workflow%3ACI)
[![Release Version](https://img.shields.io/badge/Release-2021.01.07-brightgreen)](https://github.com/pukkandan/yt-dlc/releases/latest)
[![Release Version](https://img.shields.io/badge/Release-2021.01.09-brightgreen)](https://github.com/pukkandan/yt-dlc/releases/latest)
[![License: Unlicense](https://img.shields.io/badge/License-Unlicense-blue.svg)](https://github.com/pukkandan/yt-dlc/blob/master/LICENSE)
[![Core Status](https://github.com/pukkandan/yt-dlc/workflows/Core%20Test/badge.svg?branch=master)](https://github.com/pukkandan/yt-dlc/actions?query=workflow%3ACore)
[![CI Status](https://github.com/pukkandan/yt-dlc/workflows/Full%20Test/badge.svg?branch=master)](https://github.com/pukkandan/yt-dlc/actions?query=workflow%3AFull)
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)
* [CHANGES FROM YOUTUBE-DLC](#changes)
* [NEW FEATURES](#new-features)
* [INSTALLATION](#installation)
* [UPDATE](#update)
* [COMPILE](#compile)
@@ -27,7 +28,7 @@ This is a fork of [youtube-dlc](https://github.com/blackjack4494/yt-dlc) which i
* [Authentication Options](#authentication-options)
* [Adobe Pass Options](#adobe-pass-options)
* [Post-processing Options](#post-processing-options)
* [SponSkrub Options (SponsorBlock)](#sponskrub-options-sponsorblock)
* [SponSkrub Options (SponsorBlock)](#sponSkrub-options-sponsorblock)
* [Extractor Options](#extractor-options)
* [CONFIGURATION](#configuration)
* [Authentication with .netrc file](#authentication-with-netrc-file)
@@ -42,43 +43,19 @@ This is a fork of [youtube-dlc](https://github.com/blackjack4494/yt-dlc) which i
* [MORE](#more)
# CHANGES
See [commits](https://github.com/pukkandan/yt-dlc/commits) for more details
# NEW FEATURES
The major new features are:
### 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
* **[SponSkrub Integration](#sponSkrub-options-sponsorblock)** - You can use [SponSkrub](https://github.com/faissaloo/SponSkrub) to mark/remove sponsor sections in youtube videos by utilizing the [SponsorBlock](https://sponsor.ajay.app) API
### 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`
* **[Format Sorting](#sorting-format)** - The default format sorting options have been changed so that higher resolution and better codecs will be now prefered instead of simply using larger bitrate. Furthermore, you can now specify the sort order using `-S`. This allows for much easier format selection that what is possible by simply using `--format` ([examples](#format-selection-examples))
* Merged with youtube-dl **v2020.01.08** - You get the new 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)
* **New options** - `--list-formats-as-table`, `--write-link`, `--force-download-archive` etc
and many other features and patches. See [changelog](Changelog.md) or [commits](https://github.com/pukkandan/yt-dlc/commits) for the full list of changes
### 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
# INSTALLATION
@@ -470,8 +447,8 @@ 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 unless a specific
one is requested
--prefer-free-formats Prefer free video formats over non-free
formats of same quality
-F, --list-formats List all available formats of requested
videos
--list-formats-as-table Present the output of -F in a more tabular
@@ -550,7 +527,18 @@ Then simply type this
--recode-video FORMAT Re-encode the video into another format if
re-encoding is necessary (currently
supported: mp4|flv|ogg|webm|mkv|avi)
--postprocessor-args ARGS Give these arguments to the postprocessor
--postprocessor-args NAME:ARGS 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, 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
--no-keep-video Delete the intermediate video file after
@@ -613,7 +601,6 @@ 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
@@ -932,9 +919,17 @@ $ 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'
# Download the worst video available
# 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)
$ youtube-dlc -f 'wv*+wa/w'
# Download the best video available but with the smallest resolution
@@ -993,13 +988,6 @@ $ 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)'

View File

@@ -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"
set DOWNLOAD_TESTS="age_restriction^|download^|iqiyi_sdk_interpreter^|socks^|subtitles^|write_annotations^|youtube_lists^|youtube_signature^|post_hooks"
if "%YTDL_TEST_SET%" == "core" (
set test_set="-I test_("%DOWNLOAD_TESTS%")\.py"

View File

@@ -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|socks|subtitles|write_annotations|youtube_lists|youtube_signature"
DOWNLOAD_TESTS="age_restriction|download|iqiyi_sdk_interpreter|socks|subtitles|write_annotations|youtube_lists|youtube_signature|post_hooks"
test_set=""
multiprocess_args=""

View File

@@ -55,6 +55,7 @@
- **Aparat**
- **AppleConnect**
- **AppleDaily**: 臺灣蘋果日報
- **ApplePodcasts**
- **appletrailers**
- **appletrailers:section**
- **archive.org**: archive.org videos
@@ -99,6 +100,10 @@
- **BellMedia**
- **Bet**
- **bfi:player**
- **bfmtv**
- **bfmtv:article**
- **bfmtv:live**
- **BibelTV**
- **Bigflix**
- **Bild**: Bild.de
- **BiliBili**
@@ -346,6 +351,8 @@
- **Go**
- **GodTube**
- **Golem**
- **google:podcasts**
- **google:podcasts:feed**
- **GoogleDrive**
- **Goshgay**
- **GPUTechConf**
@@ -381,6 +388,8 @@
- **HungamaSong**
- **Hypem**
- **ign.com**
- **IHeartRadio**
- **iheartradio:podcast**
- **imdb**: Internet Movie Database trailers
- **imdb:list**: Internet Movie Database lists
- **Imgur**
@@ -706,7 +715,6 @@
- **Playwire**
- **pluralsight**
- **pluralsight:course**
- **plus.google**: Google Plus
- **podomatic**
- **Pokemon**
- **PokemonWatch**
@@ -1146,7 +1154,7 @@
- **WWE**
- **XBef**
- **XboxClips**
- **XFileShare**: XFileShare based sites: ClipWatching, GoUnlimited, GoVid, HolaVid, Streamty, TheVideoBee, Uqload, VidBom, vidlo, VidLocker, VidShare, VUp, XVideoSharing
- **XFileShare**: XFileShare based sites: Aparat, ClipWatching, GoUnlimited, GoVid, HolaVid, Streamty, TheVideoBee, Uqload, VidBom, vidlo, VidLocker, VidShare, VUp, XVideoSharing
- **XHamster**
- **XHamsterEmbed**
- **XHamsterUser**

68
test/test_post_hooks.py Normal file
View File

@@ -0,0 +1,68 @@
#!/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()

View File

@@ -264,16 +264,24 @@ 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_allsubtitles(self):
def test_subtitles_key(self):
self.url = 'http://www.raiplay.it/video/2014/04/Report-del-07042014-cb27157f-9dd0-4aee-b788-b1f67643a391.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']), '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'

View File

@@ -21,6 +21,7 @@ from youtube_dlc.utils import (
encode_base_n,
caesar,
clean_html,
clean_podcast_url,
date_from_str,
DateRange,
detect_exe_version,
@@ -1497,6 +1498,10 @@ 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()

View File

@@ -99,6 +99,7 @@ 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
@@ -252,6 +253,9 @@ 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".
@@ -333,8 +337,9 @@ class YoutubeDL(object):
otherwise prefer ffmpeg.
ffmpeg_location: Location of the ffmpeg/avconv binary; either the path
to the binary or its containing directory.
postprocessor_args: A list of additional command-line arguments for the
postprocessor.
postprocessor_args: A dictionary of postprocessor names (in lower case) and a list
of additional command-line arguments for the postprocessor.
Use 'default' as the name for arguments to passed to all PP.
The following options are used by the Youtube extractor:
youtube_include_dash_manifest: If True (default), DASH manifests and related
@@ -368,6 +373,7 @@ class YoutubeDL(object):
self._ies = []
self._ies_instances = {}
self._pps = []
self._post_hooks = []
self._progress_hooks = []
self._download_retcode = 0
self._num_downloads = 0
@@ -471,6 +477,9 @@ 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)
@@ -523,6 +532,10 @@ 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)
@@ -577,7 +590,7 @@ 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):
@@ -2198,10 +2211,19 @@ 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."""
@@ -2500,7 +2522,7 @@ class YoutubeDL(object):
['git', 'rev-parse', '--short', 'HEAD'],
stdout=subprocess.PIPE, stderr=subprocess.PIPE,
cwd=os.path.dirname(os.path.abspath(__file__)))
out, err = sp.communicate()
out, err = process_communicate_or_kill(sp)
out = out.decode().strip()
if re.match('[0-9a-f]+', out):
self._write_string('[debug] Git HEAD: ' + out + '\n')

View File

@@ -331,9 +331,23 @@ def _real_main(argv=None):
external_downloader_args = None
if opts.external_downloader_args:
external_downloader_args = compat_shlex_split(opts.external_downloader_args)
postprocessor_args = None
if opts.postprocessor_args:
postprocessor_args = compat_shlex_split(opts.postprocessor_args)
postprocessor_args = {}
if opts.postprocessor_args is not None:
for string in opts.postprocessor_args:
mobj = re.match(r'(?P<pp>\w+):(?P<args>.*)$', string)
if mobj is None:
if 'sponskrub' not in postprocessor_args: # for backward compatibility
postprocessor_args['sponskrub'] = []
if opts.verbose:
write_string('[debug] Adding postprocessor args from command line option sponskrub:\n')
pp_name, pp_args = 'default', string
else:
pp_name, pp_args = mobj.group('pp').lower(), mobj.group('args')
if opts.verbose:
write_string('[debug] Adding postprocessor args from command line option %s:%s\n' % (pp_name, pp_args))
postprocessor_args[pp_name] = compat_shlex_split(pp_args)
match_filter = (
None if opts.match_filter is None
else match_filter_func(opts.match_filter))

View File

@@ -2896,6 +2896,7 @@ 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)
@@ -2912,7 +2913,7 @@ else:
sp = subprocess.Popen(
['stty', 'size'],
stdout=subprocess.PIPE, stderr=subprocess.PIPE)
out, err = sp.communicate()
out, err = process_communicate_or_kill(sp)
_lines, _columns = map(int, out.split())
except Exception:
_columns, _lines = _terminal_size(*fallback)

View File

@@ -22,6 +22,7 @@ from ..utils import (
handle_youtubedl_headers,
check_executable,
is_outdated_version,
process_communicate_or_kill,
)
@@ -104,7 +105,7 @@ class ExternalFD(FileDownloader):
p = subprocess.Popen(
cmd, stderr=subprocess.PIPE)
_, stderr = p.communicate()
_, stderr = process_communicate_or_kill(p)
if p.returncode != 0:
self.to_stderr(stderr.decode('utf-8', 'replace'))
return p.returncode
@@ -143,7 +144,7 @@ class CurlFD(ExternalFD):
# curl writes the progress to stderr so don't capture it.
p = subprocess.Popen(cmd)
p.communicate()
process_communicate_or_kill(p)
return p.returncode
@@ -343,14 +344,17 @@ class FFmpegFD(ExternalFD):
proc = subprocess.Popen(args, stdin=subprocess.PIPE, env=env)
try:
retval = proc.wait()
except KeyboardInterrupt:
except BaseException as e:
# 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 sys.platform != 'win32':
proc.communicate(b'q')
if isinstance(e, KeyboardInterrupt) and sys.platform != 'win32':
process_communicate_or_kill(proc, b'q')
else:
proc.kill()
proc.wait()
raise
return retval

View File

@@ -172,8 +172,12 @@ 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()
frag_content = AES.new(
decrypt_info['KEY'], AES.MODE_CBC, iv).decrypt(frag_content)
# 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)
self._append_fragment(ctx, frag_content)
# We only download the first fragment during the test
if test:

View File

@@ -89,11 +89,13 @@ class RtmpFD(FileDownloader):
self.to_screen('')
cursor_in_new_line = True
self.to_screen('[rtmpdump] ' + line)
finally:
if not cursor_in_new_line:
self.to_screen('')
return proc.wait()
except BaseException: # Including KeyboardInterrupt
proc.kill()
proc.wait()
if not cursor_in_new_line:
self.to_screen('')
return proc.returncode
raise
url = info_dict['url']
player_url = info_dict.get('player_url')

View File

@@ -61,7 +61,7 @@ class YoutubeLiveChatReplayFD(FragmentFD):
else:
url = ('https://www.youtube.com/live_chat_replay/get_live_chat_replay'
+ '?continuation={}'.format(continuation_id)
+ '&playerOffsetMs={}'.format(offset - 5000)
+ '&playerOffsetMs={}'.format(max(offset - 5000, 0))
+ '&hidden=false'
+ '&pbj=1')
success, raw_fragment = dl_fragment(url)

View File

@@ -6,6 +6,7 @@ import re
from .common import InfoExtractor
from ..utils import (
clean_html,
clean_podcast_url,
int_or_none,
parse_iso8601,
)
@@ -17,7 +18,7 @@ class ACastBaseIE(InfoExtractor):
info = {
'id': episode['id'],
'display_id': episode.get('episodeUrl'),
'url': episode['url'],
'url': clean_podcast_url(episode['url']),
'title': title,
'description': clean_html(episode.get('description') or episode.get('summary')),
'thumbnail': episode.get('image'),

View File

@@ -0,0 +1,61 @@
# 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,
}

View File

@@ -0,0 +1,103 @@
# 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 aujourdhui, 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))

View File

@@ -0,0 +1,30 @@
# 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')

View File

@@ -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,
)
@@ -37,6 +37,7 @@ 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',
@@ -47,29 +48,34 @@ class CanvasIE(InfoExtractor):
mobj = re.match(self._VALID_URL, url)
site_id, video_id = mobj.group('site_id'), mobj.group('id')
# 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)
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)
# 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={'Content-Type': 'application/json'})['vrtPlayerToken']
'Downloading token', data=b'', headers=headers)['vrtPlayerToken']
data = self._download_json(
'%s/videos/%s' % (self._REST_API_BASE, video_id),
video_id, 'Downloading video JSON', fatal=False, query={
video_id, 'Downloading video JSON', query={
'vrtPlayerToken': token,
'client': '%s@PROD' % site_id,
}, expected_status=400)
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)
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)
title = data['title']
description = data.get('description')
@@ -205,20 +211,24 @@ class CanvasEenIE(InfoExtractor):
class VrtNUIE(GigyaBaseIE):
IE_DESC = 'VrtNU.be'
_VALID_URL = r'https?://(?:www\.)?vrt\.be/(?P<site_id>vrtnu)/(?:[^/]+/)*(?P<id>[^/?#&]+)'
_VALID_URL = r'https?://(?:www\.)?vrt\.be/vrtnu/a-z/(?:[^/]+/){2}(?P<id>[^/?#&]+)'
_TESTS = [{
# Available via old API endpoint
'url': 'https://www.vrt.be/vrtnu/a-z/postbus-x/1/postbus-x-s1a1/',
'url': 'https://www.vrt.be/vrtnu/a-z/postbus-x/1989/postbus-x-s1989a1/',
'info_dict': {
'id': 'pbs-pub-2e2d8c27-df26-45c9-9dc6-90c78153044d$vid-90c932b1-e21d-4fb8-99b1-db7b49cf74de',
'id': 'pbs-pub-e8713dac-899e-41de-9313-81269f4c04ac$vid-90c932b1-e21d-4fb8-99b1-db7b49cf74de',
'ext': 'mp4',
'title': 'De zwarte weduwe',
'description': 'md5:db1227b0f318c849ba5eab1fef895ee4',
'title': 'Postbus X - Aflevering 1 (Seizoen 1989)',
'description': 'md5:b704f669eb9262da4c55b33d7c6ed4b7',
'duration': 1457.04,
'thumbnail': r're:^https?://.*\.jpg$',
'season': 'Season 1',
'season_number': 1,
'series': 'Postbus X',
'season': 'Seizoen 1989',
'season_number': 1989,
'episode': 'De zwarte weduwe',
'episode_number': 1,
'timestamp': 1595822400,
'upload_date': '20200727',
},
'skip': 'This video is only available for registered users',
'params': {
@@ -300,69 +310,25 @@ class VrtNUIE(GigyaBaseIE):
def _real_extract(self, url):
display_id = self._match_id(url)
webpage, urlh = self._download_webpage_handle(url, display_id)
webpage = self._download_webpage(url, display_id)
attrs = extract_attributes(self._search_regex(
r'(<nui-media[^>]+>)', webpage, 'media element'))
video_id = attrs['videoid']
publication_id = attrs.get('publicationid')
if publication_id:
video_id = publication_id + '$' + 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 {}
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,
'title': title,
'description': description,
'season': season,
'season_number': season_number,
'episode_number': episode_number,
'release_date': release_date,
'season_number': int_or_none(page.get('episode_season')),
})

View File

@@ -17,7 +17,12 @@ from ..utils import (
class DPlayIE(InfoExtractor):
_VALID_URL = r'''(?x)https?://
(?P<domain>
(?:www\.)?(?P<host>dplay\.(?P<country>dk|fi|jp|se|no))|
(?:www\.)?(?P<host>d
(?:
play\.(?P<country>dk|fi|jp|se|no)|
iscoveryplus\.(?P<plus_country>dk|es|fi|it|se|no)
)
)|
(?P<subdomain_country>es|it)\.dplay\.com
)/[^/]+/(?P<id>[^/]+/[^/?#]+)'''
@@ -126,6 +131,24 @@ 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):
@@ -241,7 +264,7 @@ 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')
host = 'disco-api.' + domain if domain.startswith('dplay.') else 'eu2-prod.disco-api.com'
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'
return self._get_disco_api_info(
url, display_id, host, 'dplay' + country, country)

View File

@@ -59,6 +59,7 @@ from .appletrailers import (
AppleTrailersIE,
AppleTrailersSectionIE,
)
from .applepodcasts import ApplePodcastsIE
from .archiveorg import ArchiveOrgIE
from .arcpublishing import ArcPublishingIE
from .arkena import ArkenaIE
@@ -104,6 +105,12 @@ 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 (
@@ -442,7 +449,10 @@ from .go import GoIE
from .godtube import GodTubeIE
from .golem import GolemIE
from .googledrive import GoogleDriveIE
from .googleplus import GooglePlusIE
from .googlepodcasts import (
GooglePodcastsIE,
GooglePodcastsFeedIE,
)
from .googlesearch import GoogleSearchIE
from .goshgay import GoshgayIE
from .gputechconf import GPUTechConfIE
@@ -484,6 +494,10 @@ from .ign import (
OneUPIE,
PCMagIE,
)
from .iheart import (
IHeartRadioIE,
IHeartRadioPodcastIE,
)
from .imdb import (
ImdbIE,
ImdbListIE

View File

@@ -1,73 +0,0 @@
# 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,
}

View File

@@ -0,0 +1,88 @@
# 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]))

View File

@@ -0,0 +1,97 @@
# 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'))

View File

@@ -2,92 +2,71 @@ 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/zomerse-filmpjes',
'md5': '6bdeb65998930251bbd1c510750edba9',
'url': 'https://www.ketnet.be/kijken/n/nachtwacht/3/nachtwacht-s3a1-de-greystook',
'md5': '37b2b7bb9b3dcaa05b67058dc3a714a9',
'info_dict': {
'id': 'zomerse-filmpjes',
'id': 'pbs-pub-aef8b526-115e-4006-aa24-e59ff6c6ef6f$vid-ddb815bf-c8e7-467b-8879-6bad7a32cebd',
'ext': 'mp4',
'title': 'Gluur mee op de filmset en op Pennenzakkenrock',
'description': 'Gluur mee met Ghost Rockers op de filmset',
'title': 'Nachtwacht - Reeks 3: Aflevering 1',
'description': 'De Nachtwacht krijgt te maken met een parasiet',
'thumbnail': r're:^https?://.*\.jpg$',
}
}, {
# 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,
'duration': 1468.02,
'timestamp': 1609225200,
'upload_date': '20201229',
'series': 'Nachtwacht',
'season': 'Reeks 3',
'episode': 'De Greystook',
'episode_number': 1,
},
'expected_warnings': ['is not a supported codec', 'Unknown MIME type'],
}, {
'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',
'url': 'https://www.ketnet.be/themas/karrewiet/jaaroverzicht-20200/karrewiet-het-jaar-van-black-mamba',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
display_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
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']
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)
mz_id = compat_urllib_parse_unquote(video['mediaReference'])
return {
'id': video_id,
'title': title,
'description': config.get('description'),
'thumbnail': config.get('image'),
'series': config.get('program'),
'episode': config.get('episode'),
'formats': formats,
'_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(),
}

View File

@@ -61,6 +61,23 @@ 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):
@@ -85,20 +102,28 @@ 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 = 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)
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')
comment_count = webpage.count('class="media-comment-contents"')
uploader_id = self._html_search_regex(

View File

@@ -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
if legal_age == 'A':
age_limit = 0
elif legal_age.isdigit():
age_limit = int_or_none(legal_age)
else:
age_limit = None
age_limit = None
if legal_age:
if legal_age == 'A':
age_limit = 0
elif legal_age.isdigit():
age_limit = int_or_none(legal_age)
is_series = try_get(data, lambda x: x['_links']['series']['name']) == 'series'
@@ -298,6 +298,14 @@ 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',

View File

@@ -17,6 +17,7 @@ from ..utils import (
get_exe_version,
is_outdated_version,
std_headers,
process_communicate_or_kill,
)
@@ -226,7 +227,7 @@ class PhantomJSwrapper(object):
self.exe, '--ssl-protocol=any',
self._TMP_FILES['script'].name
], stdout=subprocess.PIPE, stderr=subprocess.PIPE)
out, err = p.communicate()
out, err = process_communicate_or_kill(p)
if p.returncode != 0:
raise ExtractorError(
'Executing JS failed\n:' + encodeArgument(err))

View File

@@ -103,22 +103,28 @@ class RaiBaseIE(InfoExtractor):
}.items() if v is not None)
@staticmethod
def _extract_subtitles(url, subtitle_url):
def _extract_subtitles(url, video_data):
STL_EXT = 'stl'
SRT_EXT = 'srt'
subtitles = {}
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,
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 STL_EXT == sub_ext:
subtitles[sub_lang].append({
'ext': SRT_EXT,
'url': sub_url[:-len(STL_EXT)] + SRT_EXT,
})
return subtitles
@@ -138,6 +144,9 @@ class RaiPlayIE(RaiBaseIE):
'duration': 6160,
'series': 'Report',
'season': '2013/14',
'subtitles': {
'it': 'count:2',
},
},
'params': {
'skip_download': True,
@@ -145,6 +154,10 @@ 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):
@@ -171,7 +184,7 @@ class RaiPlayIE(RaiBaseIE):
if date_published and time_published:
date_published += ' ' + time_published
subtitles = self._extract_subtitles(url, video.get('subtitles'))
subtitles = self._extract_subtitles(url, video)
program_info = media.get('program_info') or {}
season = media.get('season')
@@ -325,6 +338,22 @@ 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',
@@ -365,7 +394,7 @@ class RaiIE(RaiBaseIE):
'url': compat_urlparse.urljoin(url, thumbnail_url),
})
subtitles = self._extract_subtitles(url, media.get('subtitlesUrl'))
subtitles = self._extract_subtitles(url, media)
info = {
'id': content_id,
@@ -402,7 +431,8 @@ class RaiIE(RaiBaseIE):
r'''(?x)
(?:
(?:initEdizione|drawMediaRaiTV)\(|
<(?:[^>]+\bdata-id|var\s+uniquename)=
<(?:[^>]+\bdata-id|var\s+uniquename)=|
<iframe[^>]+\bsrc=
)
(["\'])
(?:(?!\1).)*\bContentItem-(?P<id>%s)

View File

@@ -10,7 +10,7 @@ from ..utils import (
class SBSIE(InfoExtractor):
IE_DESC = 'sbs.com.au'
_VALID_URL = r'https?://(?:www\.)?sbs\.com\.au/(?:ondemand|news)/video/(?:single/)?(?P<id>[0-9]+)'
_VALID_URL = r'https?://(?:www\.)?sbs\.com\.au/(?:ondemand(?:/video/(?:single/)?|.*?\bplay=)|news/(?:embeds/)?video/)(?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': '320403011771',
'id': '_rFBPRPO4pMR',
'ext': 'mp4',
'title': 'Dingo Conservation (The Feed)',
'description': 'md5:f250a9856fca50d22dec0b5b8015f8a5',
@@ -34,6 +34,15 @@ 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):

View File

@@ -8,13 +8,17 @@ 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})'
_TEST = {
_TESTS = [{
# shortform
'url': 'https://player.stv.tv/video/4gwd/emmerdale/60-seconds-on-set-with-laura-norton/',
'md5': '5adf9439c31d554f8be0707c7abe7e0a',
'info_dict': {
@@ -27,7 +31,11 @@ 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',
@@ -36,11 +44,31 @@ 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)
result = resp['results']
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']
video = result['video']
video_id = compat_str(video['id'])
@@ -57,7 +85,7 @@ class STVPlayerIE(InfoExtractor):
return {
'_type': 'url_transparent',
'id': video_id,
'url': self.BRIGHTCOVE_URL_TEMPLATE % video_id,
'url': smuggle_url(self.BRIGHTCOVE_URL_TEMPLATE % video_id, {'geo_countries': ['GB']}),
'description': result.get('summary'),
'duration': float_or_none(video.get('length'), 1000),
'subtitles': subtitles,

View File

@@ -133,6 +133,8 @@ class TikTokIE(TikTokBaseIE):
def _real_extract(self, url):
video_id = self._match_id(url)
# If we only call once, we get a 403 when downlaoding the video.
self._download_webpage(url, video_id)
webpage = self._download_webpage(url, video_id, note='Downloading video webpage')
json_string = self._search_regex(
r'id=\"__NEXT_DATA__\"\s+type=\"application\/json\"\s*[^>]+>\s*(?P<json_string_ld>[^<]+)',

View File

@@ -9,7 +9,6 @@ import re
from .common import InfoExtractor
from ..compat import (
compat_kwargs,
compat_parse_qs,
compat_str,
compat_urlparse,
@@ -42,30 +41,16 @@ class TwitchBaseIE(InfoExtractor):
_CLIENT_ID = 'kimne78kx3ncx6brgo4mv6wki5h1ko'
_NETRC_MACHINE = 'twitch'
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
_OPERATION_HASHES = {
'CollectionSideBar': '27111f1b382effad0b6def325caef1909c733fe6a4fbabf54f8d491ef2cf2f14',
'FilterableVideoTower_Videos': 'a937f1d22e269e39a03b509f65a7490f9fc247d7f83d6ac1421523e3b68042cb',
'ClipsCards__User': 'b73ad2bfaecfd30a9e6c28fada15bd97032c83ec77a0440766a56fe0bd632777',
'ChannelCollectionsContent': '07e3691a1bad77a36aba590c351180439a40baefc1c275356f40fc7082419a84',
'StreamMetadata': '1c719a40e481453e5c48d9bb585d971b8b372f8ebb105b17076722264dfa5b3e',
'ComscoreStreamingQuery': 'e1edae8122517d013405f237ffcc124515dc6ded82480a88daef69c83b53ac01',
'VideoPreviewOverlay': '3006e77e51b128d838fa4e835723ca4dc9a05c5efd4466c1085215c6e437e65c',
'VideoMetadata': '226edb3e692509f727fd56821f5653c05740242c82b0388883e0c0e75dcbf687',
}
def _real_initialize(self):
self._login()
@@ -151,13 +136,46 @@ class TwitchBaseIE(InfoExtractor):
})
self._sort_formats(formats)
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_base_gql(self, video_id, ops, note, fatal=True):
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)
def _extract_channel_id(self, token, channel_name):
return compat_str(self._parse_json(token, channel_name)['channel_id'])
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]
class TwitchVodIE(TwitchBaseIE):
@@ -170,8 +188,6 @@ class TwitchVodIE(TwitchBaseIE):
)
(?P<id>\d+)
'''
_ITEM_TYPE = 'vod'
_ITEM_SHORTCUT = 'v'
_TESTS = [{
'url': 'http://www.twitch.tv/riotgames/v/6528877?t=5m10s',
@@ -181,7 +197,7 @@ class TwitchVodIE(TwitchBaseIE):
'title': 'LCK Summer Split - Week 6 Day 1',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 17208,
'timestamp': 1435131709,
'timestamp': 1435131734,
'upload_date': '20150624',
'uploader': 'Riot Games',
'uploader_id': 'riotgames',
@@ -230,10 +246,20 @@ class TwitchVodIE(TwitchBaseIE):
}]
def _download_info(self, item_id):
return self._extract_info(
self._call_api(
'kraken/videos/%s' % item_id, item_id,
'Downloading video info JSON'))
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)
@staticmethod
def _extract_info(info):
@@ -272,13 +298,33 @@ 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._call_api(
'api/vods/%s/access_token' % vod_id, vod_id,
'Downloading %s access token' % self._ITEM_TYPE)
access_token = self._download_access_token(vod_id, 'video', 'id')
formats = self._extract_m3u8_formats(
'%s/vod/%s.m3u8?%s' % (
@@ -289,8 +335,8 @@ class TwitchVodIE(TwitchBaseIE):
'allow_spectre': 'true',
'player': 'twitchweb',
'playlist_include_framerate': 'true',
'nauth': access_token['token'],
'nauthsig': access_token['sig'],
'nauth': access_token['value'],
'nauthsig': access_token['signature'],
})),
vod_id, 'mp4', entry_protocol='m3u8_native')
@@ -333,37 +379,7 @@ def _make_video_result(node):
}
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):
class TwitchCollectionIE(TwitchBaseIE):
_VALID_URL = r'https?://(?:(?:www|go|m)\.)?twitch\.tv/collections/(?P<id>[^/]+)'
_TESTS = [{
@@ -400,7 +416,9 @@ class TwitchCollectionIE(TwitchGraphQLBaseIE):
entries, playlist_id=collection_id, playlist_title=title)
class TwitchPlaylistBaseIE(TwitchGraphQLBaseIE):
class TwitchPlaylistBaseIE(TwitchBaseIE):
_PAGE_LIMIT = 100
def _entries(self, channel_name, *args):
cursor = None
variables_common = self._make_variables(channel_name, *args)
@@ -440,49 +458,6 @@ class TwitchPlaylistBaseIE(TwitchGraphQLBaseIE):
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)'
@@ -724,7 +699,7 @@ class TwitchVideosCollectionsIE(TwitchPlaylistBaseIE):
playlist_title='%s - Collections' % channel_name)
class TwitchStreamIE(TwitchGraphQLBaseIE):
class TwitchStreamIE(TwitchBaseIE):
IE_NAME = 'twitch:stream'
_VALID_URL = r'''(?x)
https?://
@@ -814,8 +789,9 @@ class TwitchStreamIE(TwitchGraphQLBaseIE):
if not stream:
raise ExtractorError('%s is offline' % channel_name, expected=True)
access_token = self._download_access_token(channel_name)
token = access_token['token']
access_token = self._download_access_token(
channel_name, 'stream', 'channelName')
token = access_token['value']
stream_id = stream.get('id') or channel_name
query = {
@@ -826,7 +802,7 @@ class TwitchStreamIE(TwitchGraphQLBaseIE):
'player': 'twitchweb',
'playlist_include_framerate': 'true',
'segment_preference': '4',
'sig': access_token['sig'].encode('utf-8'),
'sig': access_token['signature'].encode('utf-8'),
'token': token.encode('utf-8'),
}
formats = self._extract_m3u8_formats(
@@ -912,8 +888,8 @@ class TwitchClipsIE(TwitchBaseIE):
def _real_extract(self, url):
video_id = self._match_id(url)
clip = self._download_json(
'https://gql.twitch.tv/gql', video_id, data=json.dumps({
clip = self._download_base_gql(
video_id, {
'query': '''{
clip(slug: "%s") {
broadcaster {
@@ -937,10 +913,7 @@ class TwitchClipsIE(TwitchBaseIE):
}
viewCount
}
}''' % video_id,
}).encode(), headers={
'Client-ID': self._CLIENT_ID,
})['data']['clip']
}''' % video_id}, 'Downloading clip GraphQL')['data']['clip']
if not clip:
raise ExtractorError(

View File

@@ -251,10 +251,10 @@ class TwitterIE(TwitterBaseIE):
'info_dict': {
'id': '700207533655363584',
'ext': 'mp4',
'title': 'simon vetugo - BEAT PROD: @suhmeduh #Damndaniel',
'title': 'simon vertugo - BEAT PROD: @suhmeduh #Damndaniel',
'description': 'BEAT PROD: @suhmeduh https://t.co/HBrQ4AfpvZ #Damndaniel https://t.co/byBooq2ejZ',
'thumbnail': r're:^https?://.*\.jpg',
'uploader': 'simon vetugo',
'uploader': 'simon vertugo',
'uploader_id': 'simonvertugo',
'duration': 30.0,
'timestamp': 1455777459,
@@ -312,6 +312,7 @@ class TwitterIE(TwitterBaseIE):
'timestamp': 1492000653,
'upload_date': '20170412',
},
'skip': 'Account suspended',
}, {
'url': 'https://twitter.com/i/web/status/910031516746514432',
'info_dict': {
@@ -380,6 +381,14 @@ 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,
}]
def _real_extract(self, url):
@@ -462,7 +471,30 @@ class TwitterIE(TwitterBaseIE):
return try_get(o, lambda x: x[x['type'].lower() + '_value'])
card_name = card['name'].split(':')[-1]
if card_name in ('amplify', 'promo_video_website'):
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'),
})
# amplify, promo_video_website, promo_video_convo, appplayer, ...
else:
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'))
@@ -488,25 +520,6 @@ 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:

View File

@@ -72,6 +72,13 @@ class VLiveIE(VLiveBaseIE):
# works only with gcc=KR
'url': 'https://www.vlive.tv/video/225019',
'only_matching': True,
}, {
'url': 'https://www.vlive.tv/video/223906',
'info_dict': {
'id': '58',
'title': 'RUN BTS!'
},
'playlist_mincount': 120
}]
def _real_initialize(self):
@@ -105,10 +112,12 @@ class VLiveIE(VLiveBaseIE):
if not is_logged_in():
raise ExtractorError('Unable to log in', expected=True)
def _call_api(self, path_template, video_id, fields=None):
def _call_api(self, path_template, video_id, fields=None, limit=None):
query = {'appId': self._APP_ID, 'gcc': 'KR'}
if fields:
query['fields'] = fields
if limit:
query['limit'] = limit
try:
return self._download_json(
'https://www.vlive.tv/globalv-web/vam-web/' + path_template % video_id, video_id,
@@ -124,10 +133,34 @@ class VLiveIE(VLiveBaseIE):
post = self._call_api(
'post/v1.0/officialVideoPost-%s', video_id,
'author{nickname},channel{channelCode,channelName},officialVideo{commentCount,exposeStatus,likeCount,playCount,playTime,status,title,type,vodId}')
'author{nickname},channel{channelCode,channelName},officialVideo{commentCount,exposeStatus,likeCount,playCount,playTime,status,title,type,vodId},playlist{playlistSeq,totalCount,name}')
video = post['officialVideo']
playlist = post.get('playlist')
if not playlist or self._downloader.params.get('noplaylist'):
if playlist:
self.to_screen(
'Downloading just video %s because of --no-playlist'
% video_id)
video = post['officialVideo']
return self._get_vlive_info(post, video, video_id)
else:
playlist_name = playlist.get('name')
playlist_id = str_or_none(playlist.get('playlistSeq'))
playlist_count = str_or_none(playlist.get('totalCount'))
playlist = self._call_api(
'playlist/v1.0/playlist-%s/posts', playlist_id, 'data', limit=playlist_count)
entries = []
for video_data in playlist['data']:
video = video_data.get('officialVideo')
video_id = str_or_none(video.get('videoSeq'))
entries.append(self._get_vlive_info(video_data, video, video_id))
return self.playlist_result(entries, playlist_id, playlist_name)
def _get_vlive_info(self, post, video, video_id):
def get_common_fields():
channel = post.get('channel') or {}
return {
@@ -323,22 +356,17 @@ class VLiveChannelIE(VLiveBaseIE):
video_id = compat_str(video_id)
if video_type in ('PLAYLIST'):
playlist_videos = try_get(
first_video_id = try_get(
video,
lambda x: x['videoPlaylist']['videoList'], list)
if not playlist_videos:
lambda x: x['videoPlaylist']['videoList'][0]['videoSeq'], int)
if not first_video_id:
continue
for playlist_video in playlist_videos:
playlist_video_id = playlist_video.get('videoSeq')
if not playlist_video_id:
continue
playlist_video_id = compat_str(playlist_video_id)
entries.append(
self.url_result(
'http://www.vlive.tv/video/%s' % playlist_video_id,
ie=VLiveIE.ie_key(), video_id=playlist_video_id))
entries.append(
self.url_result(
'http://www.vlive.tv/video/%s' % first_video_id,
ie=VLiveIE.ie_key(), video_id=first_video_id))
else:
entries.append(
self.url_result(

View File

@@ -45,6 +45,7 @@ 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'),
@@ -78,6 +79,9 @@ class XFileShareIE(InfoExtractor):
'title': 'sample',
'thumbnail': r're:http://.*\.jpg',
},
}, {
'url': 'https://aparat.cam/n4d6dh0wvlpr',
'only_matching': True,
}]
@staticmethod

View File

@@ -1686,11 +1686,12 @@ 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()

View File

@@ -466,7 +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 unless a specific one is requested')
help='Prefer free video formats over non-free formats of same quality')
video_format.add_option(
'-F', '--list-formats',
action='store_true', dest='listformats',
@@ -970,9 +970,14 @@ def parseOpts(overrideArguments=None):
metavar='FORMAT', dest='recodevideo', default=None,
help='Re-encode the video into another format if re-encoding is necessary (currently supported: mp4|flv|ogg|webm|mkv|avi)')
postproc.add_option(
'--postprocessor-args',
dest='postprocessor_args', metavar='ARGS',
help='Give these arguments to the postprocessor')
'--postprocessor-args', metavar='NAME:ARGS',
dest='postprocessor_args', action='append',
help=(
'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, 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,
@@ -1089,7 +1094,7 @@ def parseOpts(overrideArguments=None):
help='Location of the sponskrub binary; either the path to the binary or its containing directory.')
sponskrub.add_option(
'--sponskrub-args', dest='sponskrub_args', metavar='ARGS',
help='Give these arguments to sponskrub')
help=optparse.SUPPRESS_HELP)
extractor = optparse.OptionGroup(parser, 'Extractor Options')
extractor.add_option(

View File

@@ -33,6 +33,11 @@ class PostProcessor(object):
def __init__(self, downloader=None):
self._downloader = downloader
if not hasattr(self, 'PP_NAME'):
self.PP_NAME = self.__class__.__name__[:-2]
def to_screen(self, text, *args, **kwargs):
return self._downloader.to_screen('[%s] %s' % (self.PP_NAME, text), *args, **kwargs)
def set_downloader(self, downloader):
"""Sets the downloader for this PP."""
@@ -62,7 +67,10 @@ class PostProcessor(object):
self._downloader.report_warning(errnote)
def _configuration_args(self, default=[]):
return cli_configuration_args(self._downloader.params, 'postprocessor_args', default)
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', []))
class AudioConversionError(PostProcessingError):

View File

@@ -14,7 +14,8 @@ from ..utils import (
PostProcessingError,
prepend_extension,
replace_extension,
shell_quote
shell_quote,
process_communicate_or_kill,
)
@@ -23,6 +24,8 @@ class EmbedThumbnailPPError(PostProcessingError):
class EmbedThumbnailPP(FFmpegPostProcessor):
PP_NAME = 'EmbedThumbnail'
def __init__(self, downloader=None, already_have_thumbnail=False):
super(EmbedThumbnailPP, self).__init__(downloader)
self._already_have_thumbnail = already_have_thumbnail
@@ -32,7 +35,7 @@ class EmbedThumbnailPP(FFmpegPostProcessor):
temp_filename = prepend_extension(filename, 'temp')
if not info.get('thumbnails'):
self._downloader.to_screen('[embedthumbnail] There aren\'t any thumbnails to embed')
self.to_screen('There aren\'t any thumbnails to embed')
return [], info
thumbnail_filename = info['thumbnails'][-1]['filename']
@@ -52,8 +55,7 @@ class EmbedThumbnailPP(FFmpegPostProcessor):
if thumbnail_ext:
thumbnail_ext = thumbnail_ext[1:].lower()
if thumbnail_ext != 'webp' and is_webp(thumbnail_filename):
self._downloader.to_screen(
'[ffmpeg] Correcting extension to webp and escaping path for thumbnail "%s"' % thumbnail_filename)
self.to_screen('Correcting extension to webp and escaping path for thumbnail "%s"' % thumbnail_filename)
thumbnail_webp_filename = replace_extension(thumbnail_filename, 'webp')
os.rename(encodeFilename(thumbnail_filename), encodeFilename(thumbnail_webp_filename))
thumbnail_filename = thumbnail_webp_filename
@@ -66,7 +68,7 @@ class EmbedThumbnailPP(FFmpegPostProcessor):
escaped_thumbnail_filename = thumbnail_filename.replace('%', '#')
os.rename(encodeFilename(thumbnail_filename), encodeFilename(escaped_thumbnail_filename))
escaped_thumbnail_jpg_filename = replace_extension(escaped_thumbnail_filename, 'jpg')
self._downloader.to_screen('[ffmpeg] Converting thumbnail "%s" to JPEG' % escaped_thumbnail_filename)
self.to_screen('Converting thumbnail "%s" to JPEG' % escaped_thumbnail_filename)
self.run_ffmpeg(escaped_thumbnail_filename, escaped_thumbnail_jpg_filename, ['-bsf:v', 'mjpeg2jpeg'])
os.remove(encodeFilename(escaped_thumbnail_filename))
thumbnail_jpg_filename = replace_extension(thumbnail_filename, 'jpg')
@@ -79,7 +81,7 @@ class EmbedThumbnailPP(FFmpegPostProcessor):
'-c', 'copy', '-map', '0:0', '-map', '1:0', '-id3v2_version', '3',
'-metadata:s:v', 'title="Album cover"', '-metadata:s:v', 'comment="Cover (front)"']
self._downloader.to_screen('[ffmpeg] Adding thumbnail to "%s"' % filename)
self.to_screen('Adding thumbnail to "%s"' % filename)
self.run_ffmpeg_multiple_files([filename, thumbnail_filename], temp_filename, options)
@@ -96,10 +98,10 @@ class EmbedThumbnailPP(FFmpegPostProcessor):
os.rename(encodeFilename(old_thumbnail_filename), encodeFilename(thumbnail_filename))
options = [
'-c', 'copy', '-map', '0',
'-c', 'copy', '-map', '0', '-dn',
'-attach', thumbnail_filename, '-metadata:s:t', 'mimetype=image/jpeg']
self._downloader.to_screen('[ffmpeg] Adding thumbnail to "%s"' % filename)
self.to_screen('Adding thumbnail to "%s"' % filename)
self.run_ffmpeg_multiple_files([filename], temp_filename, options)
@@ -121,13 +123,13 @@ class EmbedThumbnailPP(FFmpegPostProcessor):
encodeArgument('-o'),
encodeFilename(temp_filename, True)]
self._downloader.to_screen('[atomicparsley] Adding thumbnail to "%s"' % filename)
self.to_screen('Adding thumbnail to "%s"' % filename)
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 = p.communicate()
stdout, stderr = process_communicate_or_kill(p)
if p.returncode != 0:
msg = stderr.decode('utf-8', 'replace').strip()

View File

@@ -11,6 +11,8 @@ from ..utils import (
class ExecAfterDownloadPP(PostProcessor):
PP_NAME = 'Exec'
def __init__(self, downloader, exec_cmd):
super(ExecAfterDownloadPP, self).__init__(downloader)
self.exec_cmd = exec_cmd
@@ -22,7 +24,7 @@ class ExecAfterDownloadPP(PostProcessor):
cmd = cmd.replace('{}', compat_shlex_quote(information['filepath']))
self._downloader.to_screen('[exec] Executing command: %s' % cmd)
self.to_screen('Executing command: %s' % cmd)
retCode = subprocess.call(encodeArgument(cmd), shell=True)
if retCode != 0:
raise PostProcessingError(

View File

@@ -21,6 +21,7 @@ from ..utils import (
dfxp2srt,
ISO639Utils,
replace_extension,
process_communicate_or_kill,
)
@@ -53,6 +54,8 @@ class FFmpegPostProcessorError(PostProcessingError):
class FFmpegPostProcessor(PostProcessor):
def __init__(self, downloader=None):
if not hasattr(self, 'PP_NAME'):
self.PP_NAME = self.__class__.__name__[6:-2] # Remove ffmpeg from the front
PostProcessor.__init__(self, downloader)
self._determine_executables()
@@ -180,7 +183,7 @@ class FFmpegPostProcessor(PostProcessor):
handle = subprocess.Popen(
cmd, stderr=subprocess.PIPE,
stdout=subprocess.PIPE, stdin=subprocess.PIPE)
stdout_data, stderr_data = handle.communicate()
stdout_data, stderr_data = process_communicate_or_kill(handle)
expected_ret = 0 if self.probe_available else 1
if handle.wait() != expected_ret:
return None
@@ -228,7 +231,7 @@ class FFmpegPostProcessor(PostProcessor):
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 = p.communicate()
stdout, stderr = process_communicate_or_kill(p)
if p.returncode != 0:
stderr = stderr.decode('utf-8', 'replace')
msg = stderr.strip().split('\n')[-1]
@@ -328,11 +331,11 @@ class FFmpegExtractAudioPP(FFmpegPostProcessor):
# If we download foo.mp3 and convert it to... foo.mp3, then don't delete foo.mp3, silly.
if (new_path == path
or (self._nopostoverwrites and os.path.exists(encodeFilename(new_path)))):
self._downloader.to_screen('[ffmpeg] Post-process file %s exists, skipping' % new_path)
self.to_screen('Post-process file %s exists, skipping' % new_path)
return [], information
try:
self._downloader.to_screen('[ffmpeg] Destination: ' + new_path)
self.to_screen('Destination: ' + new_path)
self.run_ffmpeg(path, new_path, acodec, more_opts)
except AudioConversionError as e:
raise PostProcessingError(
@@ -357,12 +360,12 @@ class FFmpegVideoRemuxerPP(FFmpegPostProcessor):
def run(self, information):
path = information['filepath']
if information['ext'] == self._preferedformat:
self._downloader.to_screen('[ffmpeg] Not remuxing video file %s - already is in target format %s' % (path, self._preferedformat))
self.to_screen('Not remuxing video file %s - already is in target format %s' % (path, self._preferedformat))
return [], information
options = ['-c', 'copy', '-map', '0']
options = ['-c', 'copy', '-map', '0', '-dn']
prefix, sep, ext = path.rpartition('.')
outpath = prefix + sep + self._preferedformat
self._downloader.to_screen('[' + 'ffmpeg' + '] Remuxing video from %s to %s, Destination: ' % (information['ext'], self._preferedformat) + outpath)
self.to_screen('Remuxing video from %s to %s, Destination: ' % (information['ext'], self._preferedformat) + outpath)
self.run_ffmpeg(path, outpath, options)
information['filepath'] = outpath
information['format'] = self._preferedformat
@@ -378,14 +381,14 @@ class FFmpegVideoConvertorPP(FFmpegPostProcessor):
def run(self, information):
path = information['filepath']
if information['ext'] == self._preferedformat:
self._downloader.to_screen('[ffmpeg] Not converting video file %s - already is in target format %s' % (path, self._preferedformat))
self.to_screen('Not converting video file %s - already is in target format %s' % (path, self._preferedformat))
return [], information
options = []
if self._preferedformat == 'avi':
options.extend(['-c:v', 'libxvid', '-vtag', 'XVID'])
prefix, sep, ext = path.rpartition('.')
outpath = prefix + sep + self._preferedformat
self._downloader.to_screen('[' + 'ffmpeg' + '] Converting video from %s to %s, Destination: ' % (information['ext'], self._preferedformat) + outpath)
self.to_screen('Converting video from %s to %s, Destination: ' % (information['ext'], self._preferedformat) + outpath)
self.run_ffmpeg(path, outpath, options)
information['filepath'] = outpath
information['format'] = self._preferedformat
@@ -396,11 +399,11 @@ class FFmpegVideoConvertorPP(FFmpegPostProcessor):
class FFmpegEmbedSubtitlePP(FFmpegPostProcessor):
def run(self, information):
if information['ext'] not in ('mp4', 'webm', 'mkv'):
self._downloader.to_screen('[ffmpeg] Subtitles can only be embedded in mp4, webm or mkv files')
self.to_screen('Subtitles can only be embedded in mp4, webm or mkv files')
return [], information
subtitles = information.get('requested_subtitles')
if not subtitles:
self._downloader.to_screen('[ffmpeg] There aren\'t any subtitles to embed')
self.to_screen('There aren\'t any subtitles to embed')
return [], information
filename = information['filepath']
@@ -413,14 +416,14 @@ class FFmpegEmbedSubtitlePP(FFmpegPostProcessor):
for lang, sub_info in subtitles.items():
sub_ext = sub_info['ext']
if sub_ext == 'json':
self._downloader.to_screen('[ffmpeg] JSON subtitles cannot be embedded')
self.to_screen('JSON subtitles cannot be embedded')
elif ext != 'webm' or ext == 'webm' and sub_ext == 'vtt':
sub_langs.append(lang)
sub_filenames.append(subtitles_filename(filename, lang, sub_ext, ext))
else:
if not webm_vtt_warn and ext == 'webm' and sub_ext != 'vtt':
webm_vtt_warn = True
self._downloader.to_screen('[ffmpeg] Only WebVTT subtitles can be embedded in webm files')
self.to_screen('Only WebVTT subtitles can be embedded in webm files')
if not sub_langs:
return [], information
@@ -428,7 +431,7 @@ class FFmpegEmbedSubtitlePP(FFmpegPostProcessor):
input_files = [filename] + sub_filenames
opts = [
'-c', 'copy', '-map', '0',
'-c', 'copy', '-map', '0', '-dn',
# Don't copy the existing subtitles, we may be running the
# postprocessor a second time
'-map', '-0:s',
@@ -444,7 +447,7 @@ class FFmpegEmbedSubtitlePP(FFmpegPostProcessor):
opts.extend(['-metadata:s:s:%d' % i, 'language=%s' % lang_code])
temp_filename = prepend_extension(filename, 'temp')
self._downloader.to_screen('[ffmpeg] Embedding subtitles in \'%s\'' % filename)
self.to_screen('Embedding subtitles in \'%s\'' % filename)
self.run_ffmpeg_multiple_files(input_files, temp_filename, opts)
os.remove(encodeFilename(filename))
os.rename(encodeFilename(temp_filename), encodeFilename(filename))
@@ -492,13 +495,13 @@ class FFmpegMetadataPP(FFmpegPostProcessor):
add('episode_sort', 'episode_number')
if not metadata:
self._downloader.to_screen('[ffmpeg] There isn\'t any metadata to add')
self.to_screen('There isn\'t any metadata to add')
return [], info
filename = info['filepath']
temp_filename = prepend_extension(filename, 'temp')
in_filenames = [filename]
options = ['-map', '0']
options = ['-map', '0', '-dn']
if info['ext'] == 'm4a':
options.extend(['-vn', '-acodec', 'copy'])
@@ -527,7 +530,7 @@ class FFmpegMetadataPP(FFmpegPostProcessor):
in_filenames.append(metadata_filename)
options.extend(['-map_metadata', '1'])
self._downloader.to_screen('[ffmpeg] Adding metadata to \'%s\'' % filename)
self.to_screen('Adding metadata to \'%s\'' % filename)
self.run_ffmpeg_multiple_files(in_filenames, temp_filename, options)
if chapters:
os.remove(metadata_filename)
@@ -546,7 +549,7 @@ class FFmpegMergerPP(FFmpegPostProcessor):
args.extend(['-map', '%u:a:0' % (i)])
if fmt.get('vcodec') != 'none':
args.extend(['-map', '%u:v:0' % (i)])
self._downloader.to_screen('[ffmpeg] Merging formats into "%s"' % filename)
self.to_screen('Merging formats into "%s"' % filename)
self.run_ffmpeg_multiple_files(info['__files_to_merge'], temp_filename, args)
os.rename(encodeFilename(temp_filename), encodeFilename(filename))
return info['__files_to_merge'], info
@@ -578,8 +581,8 @@ class FFmpegFixupStretchedPP(FFmpegPostProcessor):
filename = info['filepath']
temp_filename = prepend_extension(filename, 'temp')
options = ['-c', 'copy', '-map', '0', '-aspect', '%f' % stretched_ratio]
self._downloader.to_screen('[ffmpeg] Fixing aspect ratio in "%s"' % filename)
options = ['-c', 'copy', '-map', '0', '-dn', '-aspect', '%f' % stretched_ratio]
self.to_screen('Fixing aspect ratio in "%s"' % filename)
self.run_ffmpeg(filename, temp_filename, options)
os.remove(encodeFilename(filename))
@@ -596,8 +599,8 @@ class FFmpegFixupM4aPP(FFmpegPostProcessor):
filename = info['filepath']
temp_filename = prepend_extension(filename, 'temp')
options = ['-c', 'copy', '-map', '0', '-f', 'mp4']
self._downloader.to_screen('[ffmpeg] Correcting container in "%s"' % filename)
options = ['-c', 'copy', '-map', '0', '-dn', '-f', 'mp4']
self.to_screen('Correcting container in "%s"' % filename)
self.run_ffmpeg(filename, temp_filename, options)
os.remove(encodeFilename(filename))
@@ -612,8 +615,8 @@ class FFmpegFixupM3u8PP(FFmpegPostProcessor):
if self.get_audio_codec(filename) == 'aac':
temp_filename = prepend_extension(filename, 'temp')
options = ['-c', 'copy', '-map', '0', '-f', 'mp4', '-bsf:a', 'aac_adtstoasc']
self._downloader.to_screen('[ffmpeg] Fixing malformed AAC bitstream in "%s"' % filename)
options = ['-c', 'copy', '-map', '0', '-dn', '-f', 'mp4', '-bsf:a', 'aac_adtstoasc']
self.to_screen('Fixing malformed AAC bitstream in "%s"' % filename)
self.run_ffmpeg(filename, temp_filename, options)
os.remove(encodeFilename(filename))
@@ -634,19 +637,18 @@ class FFmpegSubtitlesConvertorPP(FFmpegPostProcessor):
if new_format == 'vtt':
new_format = 'webvtt'
if subs is None:
self._downloader.to_screen('[ffmpeg] There aren\'t any subtitles to convert')
self.to_screen('There aren\'t any subtitles to convert')
return [], info
self._downloader.to_screen('[ffmpeg] Converting subtitles')
self.to_screen('Converting subtitles')
sub_filenames = []
for lang, sub in subs.items():
ext = sub['ext']
if ext == new_ext:
self._downloader.to_screen(
'[ffmpeg] Subtitle file for %s is already in the requested format' % new_ext)
self.to_screen('Subtitle file for %s is already in the requested format' % new_ext)
continue
elif ext == 'json':
self._downloader.to_screen(
'[ffmpeg] You have requested to convert json subtitles into another format, '
self.to_screen(
'You have requested to convert json subtitles into another format, '
'which is currently not possible')
continue
old_file = subtitles_filename(filename, lang, ext, info.get('ext'))
@@ -655,7 +657,7 @@ class FFmpegSubtitlesConvertorPP(FFmpegPostProcessor):
if ext in ('dfxp', 'ttml', 'tt'):
self._downloader.report_warning(
'[ffmpeg] You have requested to convert dfxp (TTML) subtitles into another format, '
'You have requested to convert dfxp (TTML) subtitles into another format, '
'which results in style information loss')
dfxp_file = old_file

View File

@@ -35,14 +35,10 @@ class MetadataFromTitlePP(PostProcessor):
title = info['title']
match = re.match(self._titleregex, title)
if match is None:
self._downloader.to_screen(
'[fromtitle] Could not interpret title of video as "%s"'
% self._titleformat)
self.to_screen('Could not interpret title of video as "%s"' % self._titleformat)
return [], info
for attribute, value in match.groupdict().items():
info[attribute] = value
self._downloader.to_screen(
'[fromtitle] parsed %s: %s'
% (attribute, value if value is not None else 'NA'))
self.to_screen('parsed %s: %s' % (attribute, value if value is not None else 'NA'))
return [], info

View File

@@ -22,7 +22,7 @@ class SponSkrubPP(PostProcessor):
self.force = force
self.cutout = cut
self.args = ['-chapter'] if not cut else []
self.args += self._def_args if args is None else compat_shlex_split(args)
self.args += self._configuration_args(self._def_args) if args is None else compat_shlex_split(args)
self.path = self.get_exe(path)
if not ignoreerror and self.path is None:
@@ -43,7 +43,7 @@ class SponSkrubPP(PostProcessor):
return [], information
if information['extractor_key'].lower() != 'youtube':
self._downloader.to_screen('[sponskrub] Skipping sponskrub since it is not a YouTube video')
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._downloader.to_screen(
@@ -51,7 +51,7 @@ class SponSkrubPP(PostProcessor):
'Use --sponskrub-force to run sponskrub anyway')
return [], information
self._downloader.to_screen('[sponskrub] Trying to %s sponsor sections' % ('remove' if self.cutout else 'mark'))
self.to_screen('Trying to %s sponsor sections' % ('remove' if self.cutout else 'mark'))
if self.cutout:
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):
@@ -76,11 +76,11 @@ class SponSkrubPP(PostProcessor):
if p.returncode == 0:
os.remove(filename)
os.rename(temp_filename, filename)
self._downloader.to_screen('[sponskrub] Sponsor sections have been %s' % ('removed' if self.cutout else 'marked'))
elif p.returncode != 3: # error code 3 means there was no info about the video
self.to_screen('Sponsor sections have been %s' % ('removed' if self.cutout else 'marked'))
elif p.returncode == 3:
self.to_screen('No segments in the SponsorBlock database')
else:
stderr = stderr.decode('utf-8', 'replace')
msg = stderr.strip().split('\n')[-1]
raise PostProcessingError(msg if msg else 'sponskrub failed with error code %s!' % p.returncode)
else:
self._downloader.to_screen('[sponskrub] No segments in the SponsorBlock database')
return [], information

View File

@@ -11,7 +11,6 @@ from ..utils import (
class XAttrMetadataPP(PostProcessor):
#
# More info about extended attributes for media:
# http://freedesktop.org/wiki/CommonExtendedAttributes/
@@ -27,7 +26,7 @@ class XAttrMetadataPP(PostProcessor):
""" Set extended attributes on downloaded file (if xattr support is found). """
# Write the metadata to the file's xattrs
self._downloader.to_screen('[metadata] Writing metadata to file\'s xattrs')
self.to_screen('Writing metadata to file\'s xattrs')
filename = info['filepath']

View File

@@ -2215,6 +2215,15 @@ 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
@@ -3730,7 +3739,8 @@ 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:
subprocess.Popen([exe] + args, stdout=subprocess.PIPE, stderr=subprocess.PIPE).communicate()
process_communicate_or_kill(subprocess.Popen(
[exe] + args, stdout=subprocess.PIPE, stderr=subprocess.PIPE))
except OSError:
return False
return exe
@@ -3744,10 +3754,10 @@ 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, _ = subprocess.Popen(
out, _ = process_communicate_or_kill(subprocess.Popen(
[encodeArgument(exe)] + args,
stdin=subprocess.PIPE,
stdout=subprocess.PIPE, stderr=subprocess.STDOUT).communicate()
stdout=subprocess.PIPE, stderr=subprocess.STDOUT))
except OSError:
return False
if isinstance(out, bytes): # Python 2.x
@@ -3892,13 +3902,16 @@ 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'
if url.startswith(BOM_UTF8):
url = url[len(BOM_UTF8):]
url = url.strip()
if url.startswith(('#', ';', ']')):
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(('#', ';', ']')):
return False
return url
# "#" 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()
with contextlib.closing(batch_fd) as fd:
return [url for url in map(fixup, fd) if url]
@@ -5703,7 +5716,7 @@ 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 = p.communicate()
stdout, stderr = process_communicate_or_kill(p)
stderr = stderr.decode('utf-8', 'replace')
if p.returncode != 0:
raise XAttrMetadataError(p.returncode, stderr)
@@ -5819,3 +5832,20 @@ 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)

View File

@@ -1,3 +1,3 @@
from __future__ import unicode_literals
__version__ = '2021.01.05-2'
__version__ = '2021.01.08'