Compare commits

...

6 Commits

Author SHA1 Message Date
Sergey M․
9360936f26
release 2020.11.18 2020-11-18 04:15:30 +07:00
Sergey M․
bb2b89e077
[ChangeLog] Actualize
[ci skip]
2020-11-18 04:11:58 +07:00
Sergey M․
2d7a29081c
[spiegel] Fix extraction (closes #24206, closes #24767)
Code picked from PR #24767 since original repo is not available due to takedown.
2020-11-18 04:09:02 +07:00
Sergey M․
2864179293
[youtube] Improve extraction
+ Add support for --no-playlist (closes #27009)
* Improve playlist and mix extraction (closes #26390, closes #26509, closes #26534, closes #27011)
+ Extract playlist uploader data
* Update tests
2020-11-18 03:34:08 +07:00
Remita Amine
284f8306df [youtube:tab] fix view_count extraction(closes #27051) 2020-11-17 20:32:50 +01:00
Remita Amine
aa613ef7e1 [malltv] fix extraction(closes #27035) 2020-11-17 19:13:38 +01:00
14 changed files with 248 additions and 279 deletions

View File

@ -18,7 +18,7 @@ title: ''
<!-- <!--
Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl: Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.11.17. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. - First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.11.18. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
- Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser. - Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser.
- Make sure that all URLs and arguments with special characters are properly quoted or escaped as explained in http://yt-dl.org/escape. - Make sure that all URLs and arguments with special characters are properly quoted or escaped as explained in http://yt-dl.org/escape.
- Search the bugtracker for similar issues: http://yt-dl.org/search-issues. DO NOT post duplicates. - Search the bugtracker for similar issues: http://yt-dl.org/search-issues. DO NOT post duplicates.
@ -26,7 +26,7 @@ Carefully read and work through this check list in order to prevent the most com
--> -->
- [ ] I'm reporting a broken site support - [ ] I'm reporting a broken site support
- [ ] I've verified that I'm running youtube-dl version **2020.11.17** - [ ] I've verified that I'm running youtube-dl version **2020.11.18**
- [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] I've checked that all provided URLs are alive and playable in a browser
- [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped - [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped
- [ ] I've searched the bugtracker for similar issues including closed ones - [ ] I've searched the bugtracker for similar issues including closed ones
@ -41,7 +41,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v <
[debug] User config: [] [debug] User config: []
[debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
[debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
[debug] youtube-dl version 2020.11.17 [debug] youtube-dl version 2020.11.18
[debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
[debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
[debug] Proxy map: {} [debug] Proxy map: {}

View File

@ -19,7 +19,7 @@ labels: 'site-support-request'
<!-- <!--
Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl: Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.11.17. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. - First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.11.18. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
- Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser. - Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser.
- Make sure that site you are requesting is not dedicated to copyright infringement, see https://yt-dl.org/copyright-infringement. youtube-dl does not support such sites. In order for site support request to be accepted all provided example URLs should not violate any copyrights. - Make sure that site you are requesting is not dedicated to copyright infringement, see https://yt-dl.org/copyright-infringement. youtube-dl 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: http://yt-dl.org/search-issues. DO NOT post duplicates. - Search the bugtracker for similar site support requests: http://yt-dl.org/search-issues. DO NOT post duplicates.
@ -27,7 +27,7 @@ Carefully read and work through this check list in order to prevent the most com
--> -->
- [ ] I'm reporting a new site support request - [ ] I'm reporting a new site support request
- [ ] I've verified that I'm running youtube-dl version **2020.11.17** - [ ] I've verified that I'm running youtube-dl version **2020.11.18**
- [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] I've checked that all provided URLs are alive and playable in a browser
- [ ] I've checked that none of provided URLs violate any copyrights - [ ] I've checked that none of provided URLs violate any copyrights
- [ ] I've searched the bugtracker for similar site support requests including closed ones - [ ] I've searched the bugtracker for similar site support requests including closed ones

View File

@ -18,13 +18,13 @@ title: ''
<!-- <!--
Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl: Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.11.17. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. - First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.11.18. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
- Search the bugtracker for similar site feature requests: http://yt-dl.org/search-issues. DO NOT post duplicates. - Search the bugtracker for similar site feature requests: http://yt-dl.org/search-issues. DO NOT post duplicates.
- Finally, put x into all relevant boxes (like this [x]) - Finally, put x into all relevant boxes (like this [x])
--> -->
- [ ] I'm reporting a site feature request - [ ] I'm reporting a site feature request
- [ ] I've verified that I'm running youtube-dl version **2020.11.17** - [ ] I've verified that I'm running youtube-dl version **2020.11.18**
- [ ] I've searched the bugtracker for similar site feature requests including closed ones - [ ] I've searched the bugtracker for similar site feature requests including closed ones

View File

@ -18,7 +18,7 @@ title: ''
<!-- <!--
Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl: Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.11.17. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. - First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.11.18. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
- Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser. - Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser.
- Make sure that all URLs and arguments with special characters are properly quoted or escaped as explained in http://yt-dl.org/escape. - Make sure that all URLs and arguments with special characters are properly quoted or escaped as explained in http://yt-dl.org/escape.
- Search the bugtracker for similar issues: http://yt-dl.org/search-issues. DO NOT post duplicates. - Search the bugtracker for similar issues: http://yt-dl.org/search-issues. DO NOT post duplicates.
@ -27,7 +27,7 @@ Carefully read and work through this check list in order to prevent the most com
--> -->
- [ ] I'm reporting a broken site support issue - [ ] I'm reporting a broken site support issue
- [ ] I've verified that I'm running youtube-dl version **2020.11.17** - [ ] I've verified that I'm running youtube-dl version **2020.11.18**
- [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] I've checked that all provided URLs are alive and playable in a browser
- [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped - [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped
- [ ] I've searched the bugtracker for similar bug reports including closed ones - [ ] I've searched the bugtracker for similar bug reports including closed ones
@ -43,7 +43,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v <
[debug] User config: [] [debug] User config: []
[debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
[debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
[debug] youtube-dl version 2020.11.17 [debug] youtube-dl version 2020.11.18
[debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
[debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
[debug] Proxy map: {} [debug] Proxy map: {}

View File

@ -19,13 +19,13 @@ labels: 'request'
<!-- <!--
Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl: Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.11.17. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. - First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.11.18. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
- Search the bugtracker for similar feature requests: http://yt-dl.org/search-issues. DO NOT post duplicates. - Search the bugtracker for similar feature requests: http://yt-dl.org/search-issues. DO NOT post duplicates.
- Finally, put x into all relevant boxes (like this [x]) - Finally, put x into all relevant boxes (like this [x])
--> -->
- [ ] I'm reporting a feature request - [ ] I'm reporting a feature request
- [ ] I've verified that I'm running youtube-dl version **2020.11.17** - [ ] I've verified that I'm running youtube-dl version **2020.11.18**
- [ ] I've searched the bugtracker for similar feature requests including closed ones - [ ] I've searched the bugtracker for similar feature requests including closed ones

View File

@ -1,3 +1,19 @@
version 2020.11.18
Extractors
* [spiegel] Fix extraction (#24206, #24767)
* [youtube] Improve extraction
+ Add support for --no-playlist (#27009)
* Improve playlist and mix extraction (#26390, #26509, #26534, #27011)
+ Extract playlist uploader data
* [youtube:tab] Fix view count extraction (#27051)
* [malltv] Fix extraction (#27035)
+ [bandcamp] Extract playlist description (#22684)
* [urplay] Fix extraction (#26828)
* [youtube:tab] Fix playlist title extraction (#27015)
* [youtube] Fix chapters extraction (#26005)
version 2020.11.17 version 2020.11.17
Core Core

View File

@ -824,8 +824,6 @@
- **SpankBangPlaylist** - **SpankBangPlaylist**
- **Spankwire** - **Spankwire**
- **Spiegel** - **Spiegel**
- **Spiegel:Article**: Articles on spiegel.de
- **Spiegeltv**
- **sport.francetvinfo.fr** - **sport.francetvinfo.fr**
- **Sport5** - **Sport5**
- **SportBox** - **SportBox**

View File

@ -31,16 +31,17 @@ class TestAllURLsMatching(unittest.TestCase):
def test_youtube_playlist_matching(self): def test_youtube_playlist_matching(self):
assertPlaylist = lambda url: self.assertMatch(url, ['youtube:playlist']) assertPlaylist = lambda url: self.assertMatch(url, ['youtube:playlist'])
assertTab = lambda url: self.assertMatch(url, ['youtube:tab'])
assertPlaylist('ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8') assertPlaylist('ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8')
assertPlaylist('UUBABnxM4Ar9ten8Mdjj1j0Q') # 585 assertPlaylist('UUBABnxM4Ar9ten8Mdjj1j0Q') # 585
assertPlaylist('PL63F0C78739B09958') assertPlaylist('PL63F0C78739B09958')
# assertPlaylist('https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q') assertTab('https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q')
assertPlaylist('https://www.youtube.com/course?list=ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8') assertPlaylist('https://www.youtube.com/course?list=ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8')
# assertPlaylist('https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC') assertTab('https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC')
assertPlaylist('https://www.youtube.com/watch?v=AV6J6_AeFEQ&playnext=1&list=PL4023E734DA416012') # 668 assertTab('https://www.youtube.com/watch?v=AV6J6_AeFEQ&playnext=1&list=PL4023E734DA416012') # 668
self.assertFalse('youtube:playlist' in self.matching_ies('PLtS2H6bU1M')) self.assertFalse('youtube:playlist' in self.matching_ies('PLtS2H6bU1M'))
# Top tracks # Top tracks
# assertPlaylist('https://www.youtube.com/playlist?list=MCUS.20142101') assertTab('https://www.youtube.com/playlist?list=MCUS.20142101')
def test_youtube_matching(self): def test_youtube_matching(self):
self.assertTrue(YoutubeIE.suitable('PLtS2H6bU1M')) self.assertTrue(YoutubeIE.suitable('PLtS2H6bU1M'))

View File

@ -1054,8 +1054,7 @@ from .spankbang import (
SpankBangPlaylistIE, SpankBangPlaylistIE,
) )
from .spankwire import SpankwireIE from .spankwire import SpankwireIE
from .spiegel import SpiegelIE, SpiegelArticleIE from .spiegel import SpiegelIE
from .spiegeltv import SpiegeltvIE
from .spike import ( from .spike import (
BellatorIE, BellatorIE,
ParamountNetworkIE, ParamountNetworkIE,

View File

@ -1,10 +1,16 @@
# coding: utf-8 # coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import merge_dicts from ..utils import (
clean_html,
dict_get,
float_or_none,
int_or_none,
merge_dicts,
parse_duration,
try_get,
)
class MallTVIE(InfoExtractor): class MallTVIE(InfoExtractor):
@ -17,7 +23,7 @@ class MallTVIE(InfoExtractor):
'display_id': '18-miliard-pro-neziskovky-opravdu-jsou-sportovci-nebo-clovek-v-tisni-pijavice', 'display_id': '18-miliard-pro-neziskovky-opravdu-jsou-sportovci-nebo-clovek-v-tisni-pijavice',
'ext': 'mp4', 'ext': 'mp4',
'title': '18 miliard pro neziskovky. Opravdu jsou sportovci nebo Člověk v tísni pijavice?', 'title': '18 miliard pro neziskovky. Opravdu jsou sportovci nebo Člověk v tísni pijavice?',
'description': 'md5:25fc0ec42a72ba602b602c683fa29deb', 'description': 'md5:db7d5744a4bd4043d9d98324aa72ab35',
'duration': 216, 'duration': 216,
'timestamp': 1538870400, 'timestamp': 1538870400,
'upload_date': '20181007', 'upload_date': '20181007',
@ -37,20 +43,46 @@ class MallTVIE(InfoExtractor):
webpage = self._download_webpage( webpage = self._download_webpage(
url, display_id, headers=self.geo_verification_headers()) url, display_id, headers=self.geo_verification_headers())
SOURCE_RE = r'(<source[^>]+\bsrc=(?:(["\'])(?:(?!\2).)+|[^\s]+)/(?P<id>[\da-z]+)/index)\b' video = self._parse_json(self._search_regex(
r'videoObject\s*=\s*JSON\.parse\(JSON\.stringify\(({.+?})\)\);',
webpage, 'video object'), display_id)
video_source = video['VideoSource']
video_id = self._search_regex( video_id = self._search_regex(
SOURCE_RE, webpage, 'video id', group='id') r'/([\da-z]+)/index\b', video_source, 'video id')
media = self._parse_html5_media_entries( formats = self._extract_m3u8_formats(
url, re.sub(SOURCE_RE, r'\1.m3u8', webpage), video_id, video_source + '.m3u8', video_id, 'mp4', 'm3u8_native')
m3u8_id='hls', m3u8_entry_protocol='m3u8_native')[0] self._sort_formats(formats)
subtitles = {}
for s in (video.get('Subtitles') or {}):
s_url = s.get('Url')
if not s_url:
continue
subtitles.setdefault(s.get('Language') or 'cz', []).append({
'url': s_url,
})
entity_counts = video.get('EntityCounts') or {}
def get_count(k):
v = entity_counts.get(k + 's') or {}
return int_or_none(dict_get(v, ('Count', 'StrCount')))
info = self._search_json_ld(webpage, video_id, default={}) info = self._search_json_ld(webpage, video_id, default={})
return merge_dicts(media, info, { return merge_dicts({
'id': video_id, 'id': video_id,
'display_id': display_id, 'display_id': display_id,
'title': self._og_search_title(webpage, default=None) or display_id, 'title': video.get('Title'),
'description': self._og_search_description(webpage, default=None), 'description': clean_html(video.get('Description')),
'thumbnail': self._og_search_thumbnail(webpage, default=None), 'thumbnail': video.get('ThumbnailUrl'),
}) 'formats': formats,
'subtitles': subtitles,
'duration': int_or_none(video.get('DurationSeconds')) or parse_duration(video.get('Duration')),
'view_count': get_count('View'),
'like_count': get_count('Like'),
'dislike_count': get_count('Dislike'),
'average_rating': float_or_none(try_get(video, lambda x: x['EntityRating']['AvarageRate'])),
'comment_count': get_count('Comment'),
}, info)

View File

@ -1,159 +1,54 @@
# coding: utf-8 # coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
import re
from .common import InfoExtractor from .common import InfoExtractor
from .nexx import ( from .jwplatform import JWPlatformIE
NexxIE,
NexxEmbedIE,
)
from .spiegeltv import SpiegeltvIE
from ..compat import compat_urlparse
from ..utils import (
parse_duration,
strip_or_none,
unified_timestamp,
)
class SpiegelIE(InfoExtractor): class SpiegelIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?spiegel\.de/video/[^/]*-(?P<id>[0-9]+)(?:-embed|-iframe)?(?:\.html)?(?:#.*)?$' _UUID_RE = r'[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12}'
_VALID_URL = r'https?://(?:www\.)?(?:spiegel|manager-magazin)\.de(?:/[^/]+)+/[^/]*-(?P<id>[0-9]+|%s)(?:-embed|-iframe)?(?:\.html)?(?:#.*)?$' % _UUID_RE
_TESTS = [{ _TESTS = [{
'url': 'http://www.spiegel.de/video/vulkan-tungurahua-in-ecuador-ist-wieder-aktiv-video-1259285.html', 'url': 'http://www.spiegel.de/video/vulkan-tungurahua-in-ecuador-ist-wieder-aktiv-video-1259285.html',
'md5': 'b57399839d055fccfeb9a0455c439868', 'md5': '50c7948883ec85a3e431a0a44b7ad1d6',
'info_dict': { 'info_dict': {
'id': '563747', 'id': 'II0BUyxY',
'display_id': '1259285',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Vulkanausbruch in Ecuador: Der "Feuerschlund" ist wieder aktiv', 'title': 'Vulkan Tungurahua in Ecuador ist wieder aktiv - DER SPIEGEL - Wissenschaft',
'description': 'md5:8029d8310232196eb235d27575a8b9f4', 'description': 'md5:8029d8310232196eb235d27575a8b9f4',
'duration': 49, 'duration': 48.0,
'upload_date': '20130311', 'upload_date': '20130311',
'timestamp': 1362994320, 'timestamp': 1362997920,
}, },
}, { }, {
'url': 'http://www.spiegel.de/video/schach-wm-videoanalyse-des-fuenften-spiels-video-1309159.html', 'url': 'http://www.spiegel.de/video/schach-wm-videoanalyse-des-fuenften-spiels-video-1309159.html',
'md5': '5b6c2f4add9d62912ed5fc78a1faed80',
'info_dict': {
'id': '580988',
'ext': 'mp4',
'title': 'Schach-WM in der Videoanalyse: Carlsen nutzt die Fehlgriffe des Titelverteidigers',
'description': 'md5:c2322b65e58f385a820c10fa03b2d088',
'duration': 983,
'upload_date': '20131115',
'timestamp': 1384546642,
},
}, {
'url': 'http://www.spiegel.de/video/astronaut-alexander-gerst-von-der-iss-station-beantwortet-fragen-video-1519126-embed.html',
'md5': '97b91083a672d72976faa8433430afb9',
'info_dict': {
'id': '601883',
'ext': 'mp4',
'description': 'SPIEGEL ONLINE-Nutzer durften den deutschen Astronauten Alexander Gerst über sein Leben auf der ISS-Station befragen. Hier kommen seine Antworten auf die besten sechs Fragen.',
'title': 'Fragen an Astronaut Alexander Gerst: "Bekommen Sie die Tageszeiten mit?"',
'upload_date': '20140904',
'timestamp': 1409834160,
}
}, {
'url': 'http://www.spiegel.de/video/astronaut-alexander-gerst-von-der-iss-station-beantwortet-fragen-video-1519126-iframe.html',
'only_matching': True, 'only_matching': True,
}, { }, {
# nexx video 'url': 'https://www.spiegel.de/video/eifel-zoo-aufregung-um-ausgebrochene-raubtiere-video-99018031.html',
'only_matching': True,
}, {
'url': 'https://www.spiegel.de/panorama/urteile-im-goldmuenzenprozess-haftstrafen-fuer-clanmitglieder-a-aae8df48-43c1-4c61-867d-23f0a2d254b7',
'only_matching': True,
}, {
'url': 'http://www.spiegel.de/video/spiegel-tv-magazin-ueber-guellekrise-in-schleswig-holstein-video-99012776.html', 'url': 'http://www.spiegel.de/video/spiegel-tv-magazin-ueber-guellekrise-in-schleswig-holstein-video-99012776.html',
'only_matching': True, 'only_matching': True,
}] }, {
def _real_extract(self, url):
video_id = self._match_id(url)
metadata_url = 'http://www.spiegel.de/video/metadata/video-%s.json' % video_id
handle = self._request_webpage(metadata_url, video_id)
# 302 to spiegel.tv, like http://www.spiegel.de/video/der-film-zum-wochenende-die-wahrheit-ueber-maenner-video-99003272.html
if SpiegeltvIE.suitable(handle.geturl()):
return self.url_result(handle.geturl(), 'Spiegeltv')
video_data = self._parse_json(self._webpage_read_content(
handle, metadata_url, video_id), video_id)
title = video_data['title']
nexx_id = video_data['nexxOmniaId']
domain_id = video_data.get('nexxOmniaDomain') or '748'
return {
'_type': 'url_transparent',
'id': video_id,
'url': 'nexx:%s:%s' % (domain_id, nexx_id),
'title': title,
'description': strip_or_none(video_data.get('teaser')),
'duration': parse_duration(video_data.get('duration')),
'timestamp': unified_timestamp(video_data.get('datum')),
'ie_key': NexxIE.ie_key(),
}
class SpiegelArticleIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?spiegel\.de/(?!video/)[^?#]*?-(?P<id>[0-9]+)\.html'
IE_NAME = 'Spiegel:Article'
IE_DESC = 'Articles on spiegel.de'
_TESTS = [{
'url': 'http://www.spiegel.de/sport/sonst/badminton-wm-die-randsportart-soll-populaerer-werden-a-987092.html', 'url': 'http://www.spiegel.de/sport/sonst/badminton-wm-die-randsportart-soll-populaerer-werden-a-987092.html',
'info_dict': { 'only_matching': True,
'id': '1516455',
'ext': 'mp4',
'title': 'Faszination Badminton: Nennt es bloß nicht Federball',
'description': 're:^Patrick Kämnitz gehört.{100,}',
'upload_date': '20140825',
},
}, {
'url': 'http://www.spiegel.de/wissenschaft/weltall/astronaut-alexander-gerst-antwortet-spiegel-online-lesern-a-989876.html',
'info_dict': {
},
'playlist_count': 6,
}, {
# Nexx iFrame embed
'url': 'http://www.spiegel.de/sptv/spiegeltv/spiegel-tv-ueber-schnellste-katapult-achterbahn-der-welt-taron-a-1137884.html',
'info_dict': {
'id': '161464',
'ext': 'mp4',
'title': 'Nervenkitzel Achterbahn',
'alt_title': 'Karussellbauer in Deutschland',
'description': 'md5:ffe7b1cc59a01f585e0569949aef73cc',
'release_year': 2005,
'creator': 'SPIEGEL TV',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 2761,
'timestamp': 1394021479,
'upload_date': '20140305',
},
'params': {
'format': 'bestvideo',
'skip_download': True,
},
}] }]
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
media_id = self._html_search_regex(
# Single video on top of the page r'(&#34;|["\'])mediaId\1\s*:\s*(&#34;|["\'])(?P<id>(?:(?!\2).)+)\2',
video_link = self._search_regex( webpage, 'media id', group='id')
r'<a href="([^"]+)" onclick="return spOpenVideo\(this,', webpage, return {
'video page URL', default=None) '_type': 'url_transparent',
if video_link: 'id': video_id,
video_url = compat_urlparse.urljoin( 'display_id': video_id,
self.http_scheme() + '//spiegel.de/', video_link) 'url': 'jwplatform:%s' % media_id,
return self.url_result(video_url) 'title': self._og_search_title(webpage, default=None),
'ie_key': JWPlatformIE.ie_key(),
# Multiple embedded videos }
embeds = re.findall(
r'<div class="vid_holder[0-9]+.*?</div>\s*.*?url\s*=\s*"([^"]+)"',
webpage)
entries = [
self.url_result(compat_urlparse.urljoin(
self.http_scheme() + '//spiegel.de/', embed_path))
for embed_path in embeds]
if embeds:
return self.playlist_result(entries)
return self.playlist_from_matches(
NexxEmbedIE._extract_urls(webpage), ie=NexxEmbedIE.ie_key())

View File

@ -1,17 +0,0 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from .nexx import NexxIE
class SpiegeltvIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?spiegel\.tv/videos/(?P<id>\d+)'
_TEST = {
'url': 'http://www.spiegel.tv/videos/161681-flug-mh370/',
'only_matching': True,
}
def _real_extract(self, url):
return self.url_result(
'https://api.nexx.cloud/v3/748/videos/byid/%s'
% self._match_id(url), ie=NexxIE.ie_key())

View File

@ -45,6 +45,7 @@ from ..utils import (
unescapeHTML, unescapeHTML,
unified_strdate, unified_strdate,
unsmuggle_url, unsmuggle_url,
update_url_query,
uppercase_escape, uppercase_escape,
url_or_none, url_or_none,
urlencode_postdata, urlencode_postdata,
@ -65,7 +66,7 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
# If True it will raise an error if no login info is provided # If True it will raise an error if no login info is provided
_LOGIN_REQUIRED = False _LOGIN_REQUIRED = False
_PLAYLIST_ID_RE = r'(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}' _PLAYLIST_ID_RE = r'(?:(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}|RDMM)'
_YOUTUBE_CLIENT_HEADERS = { _YOUTUBE_CLIENT_HEADERS = {
'x-youtube-client-name': '1', 'x-youtube-client-name': '1',
@ -974,10 +975,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
'url': 'sJL6WA-aGkQ', 'url': 'sJL6WA-aGkQ',
'only_matching': True, 'only_matching': True,
}, },
{
'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
'only_matching': True,
},
{ {
'url': 'https://invidio.us/watch?v=BaW_jenozKc', 'url': 'https://invidio.us/watch?v=BaW_jenozKc',
'only_matching': True, 'only_matching': True,
@ -2351,7 +2348,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
class YoutubeTabIE(YoutubeBaseInfoExtractor): class YoutubeTabIE(YoutubeBaseInfoExtractor):
IE_DESC = 'YouTube.com tab' IE_DESC = 'YouTube.com tab'
_VALID_URL = r'https?://(?:\w+\.)?(?:youtube(?:kids)?\.com|invidio\.us)/(?:(?:channel|c|user)/|playlist\?.*?\blist=)(?P<id>[^/?#&]+)' _VALID_URL = r'https?://(?:\w+\.)?(?:youtube(?:kids)?\.com|invidio\.us)/(?:(?:channel|c|user)/|(?:playlist|watch)\?.*?\blist=)(?P<id>[^/?#&]+)'
IE_NAME = 'youtube:tab' IE_NAME = 'youtube:tab'
_TESTS = [{ _TESTS = [{
@ -2361,6 +2358,7 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
'info_dict': { 'info_dict': {
'id': 'UCqj7Cz7revf5maW9g5pgNcg', 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
'title': 'Игорь Клейнер - Playlists', 'title': 'Игорь Клейнер - Playlists',
'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
}, },
}, { }, {
# playlists, multipage, different order # playlists, multipage, different order
@ -2369,14 +2367,16 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
'info_dict': { 'info_dict': {
'id': 'UCqj7Cz7revf5maW9g5pgNcg', 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
'title': 'Игорь Клейнер - Playlists', 'title': 'Игорь Клейнер - Playlists',
'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
}, },
}, { }, {
# playlists, singlepage # playlists, singlepage
'url': 'https://www.youtube.com/user/ThirstForScience/playlists', 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
'playlist_mincount': 4, 'playlist_mincount': 4,
'info_dict': { 'info_dict': {
'id': 'ThirstForScience', 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
'title': 'ThirstForScience', 'title': 'ThirstForScience - Playlists',
'description': 'md5:609399d937ea957b0f53cbffb747a14c',
} }
}, { }, {
'url': 'https://www.youtube.com/c/ChristophLaimer/playlists', 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
@ -2407,6 +2407,7 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
'info_dict': { 'info_dict': {
'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
'title': 'lex will - Home', 'title': 'lex will - Home',
'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
}, },
'playlist_mincount': 2, 'playlist_mincount': 2,
}, { }, {
@ -2415,6 +2416,7 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
'info_dict': { 'info_dict': {
'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
'title': 'lex will - Videos', 'title': 'lex will - Videos',
'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
}, },
'playlist_mincount': 975, 'playlist_mincount': 975,
}, { }, {
@ -2423,6 +2425,7 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
'info_dict': { 'info_dict': {
'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
'title': 'lex will - Videos', 'title': 'lex will - Videos',
'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
}, },
'playlist_mincount': 199, 'playlist_mincount': 199,
}, { }, {
@ -2431,6 +2434,7 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
'info_dict': { 'info_dict': {
'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
'title': 'lex will - Playlists', 'title': 'lex will - Playlists',
'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
}, },
'playlist_mincount': 17, 'playlist_mincount': 17,
}, { }, {
@ -2439,6 +2443,7 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
'info_dict': { 'info_dict': {
'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
'title': 'lex will - Community', 'title': 'lex will - Community',
'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
}, },
'playlist_mincount': 18, 'playlist_mincount': 18,
}, { }, {
@ -2447,6 +2452,7 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
'info_dict': { 'info_dict': {
'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
'title': 'lex will - Channels', 'title': 'lex will - Channels',
'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
}, },
'playlist_mincount': 138, 'playlist_mincount': 138,
}, { }, {
@ -2465,7 +2471,7 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
'title': '29C3: Not my department', 'title': '29C3: Not my department',
'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC', 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
'uploader': 'Christiaan008', 'uploader': 'Christiaan008',
'uploader_id': 'ChRiStIaAn008', 'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
}, },
'playlist_count': 96, 'playlist_count': 96,
}, { }, {
@ -2475,7 +2481,7 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
'title': 'Uploads from Cauchemar', 'title': 'Uploads from Cauchemar',
'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q', 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
'uploader': 'Cauchemar', 'uploader': 'Cauchemar',
'uploader_id': 'Cauchemar89', 'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
}, },
'playlist_mincount': 1123, 'playlist_mincount': 1123,
}, { }, {
@ -2489,7 +2495,7 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
'title': 'Uploads from Interstellar Movie', 'title': 'Uploads from Interstellar Movie',
'id': 'UUXw-G3eDE9trcvY2sBMM_aA', 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
'uploader': 'Interstellar Movie', 'uploader': 'Interstellar Movie',
'uploader_id': 'InterstellarMovie1', 'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
}, },
'playlist_mincount': 21, 'playlist_mincount': 21,
}, { }, {
@ -2498,13 +2504,43 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
'info_dict': { 'info_dict': {
'title': 'Data Analysis with Dr Mike Pound', 'title': 'Data Analysis with Dr Mike Pound',
'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba', 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
'uploader_id': 'Computerphile', 'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA',
'uploader': 'Computerphile', 'uploader': 'Computerphile',
}, },
'playlist_mincount': 11, 'playlist_mincount': 11,
}, { }, {
'url': 'https://invidio.us/playlist?list=PLDIoUOhQQPlXr63I_vwF9GD8sAKh77dWU', 'url': 'https://invidio.us/playlist?list=PLDIoUOhQQPlXr63I_vwF9GD8sAKh77dWU',
'only_matching': True, 'only_matching': True,
}, {
# Playlist URL that does not actually serve a playlist
'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
'info_dict': {
'id': 'FqZTN594JQw',
'ext': 'webm',
'title': "Smiley's People 01 detective, Adventure Series, Action",
'uploader': 'STREEM',
'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
'upload_date': '20150526',
'license': 'Standard YouTube License',
'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
'categories': ['People & Blogs'],
'tags': list,
'view_count': int,
'like_count': int,
'dislike_count': int,
},
'params': {
'skip_download': True,
},
'skip': 'This video is not available.',
'add_ie': [YoutubeIE.ie_key()],
}, {
'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
'only_matching': True,
}, {
'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
'only_matching': True,
}] }]
@classmethod @classmethod
@ -2535,7 +2571,9 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
def _extract_video(self, renderer): def _extract_video(self, renderer):
video_id = renderer.get('videoId') video_id = renderer.get('videoId')
title = try_get( title = try_get(
renderer, lambda x: x['title']['runs'][0]['text'], compat_str) renderer,
(lambda x: x['title']['runs'][0]['text'],
lambda x: x['title']['simpleText']), compat_str)
description = try_get( description = try_get(
renderer, lambda x: x['descriptionSnippet']['runs'][0]['text'], renderer, lambda x: x['descriptionSnippet']['runs'][0]['text'],
compat_str) compat_str)
@ -2543,8 +2581,8 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
renderer, lambda x: x['lengthText']['simpleText'], compat_str)) renderer, lambda x: x['lengthText']['simpleText'], compat_str))
view_count_text = try_get( view_count_text = try_get(
renderer, lambda x: x['viewCountText']['simpleText'], compat_str) or '' renderer, lambda x: x['viewCountText']['simpleText'], compat_str) or ''
view_count = int_or_none(self._search_regex( view_count = str_to_int(self._search_regex(
r'^(\d+)', re.sub(r'\s', '', view_count_text), r'^([\d,]+)', re.sub(r'\s', '', view_count_text),
'view count', default=None)) 'view count', default=None))
uploader = try_get( uploader = try_get(
renderer, lambda x: x['ownerText']['runs'][0]['text'], compat_str) renderer, lambda x: x['ownerText']['runs'][0]['text'], compat_str)
@ -2615,7 +2653,7 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
for content in video_list_renderer['contents']: for content in video_list_renderer['contents']:
if not isinstance(content, dict): if not isinstance(content, dict):
continue continue
renderer = content.get('playlistVideoRenderer') renderer = content.get('playlistVideoRenderer') or content.get('playlistPanelVideoRenderer')
if not isinstance(renderer, dict): if not isinstance(renderer, dict):
continue continue
video_id = renderer.get('videoId') video_id = renderer.get('videoId')
@ -2715,7 +2753,7 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
def _entries(self, tab, identity_token): def _entries(self, tab, identity_token):
continuation = None continuation = None
slr_contents = tab['sectionListRenderer']['contents'] slr_contents = try_get(tab, lambda x: x['sectionListRenderer']['contents'], list) or []
for slr_content in slr_contents: for slr_content in slr_contents:
if not isinstance(slr_content, dict): if not isinstance(slr_content, dict):
continue continue
@ -2824,13 +2862,30 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
else: else:
raise ExtractorError('Unable to find selected tab') raise ExtractorError('Unable to find selected tab')
def _real_extract(self, url): @staticmethod
item_id = self._match_id(url) def _extract_uploader(data):
url = compat_urlparse.urlunparse( uploader = {}
compat_urlparse.urlparse(url)._replace(netloc='www.youtube.com')) sidebar_renderer = try_get(
webpage = self._download_webpage(url, item_id) data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list)
data = self._extract_yt_initial_data(item_id, webpage) if sidebar_renderer:
tabs = data['contents']['twoColumnBrowseResultsRenderer']['tabs'] for item in sidebar_renderer:
if not isinstance(item, dict):
continue
renderer = item.get('playlistSidebarSecondaryInfoRenderer')
if not isinstance(renderer, dict):
continue
owner = try_get(
renderer, lambda x: x['videoOwner']['videoOwnerRenderer']['title']['runs'][0], dict)
if owner:
uploader['uploader'] = owner.get('text')
uploader['uploader_id'] = try_get(
owner, lambda x: x['navigationEndpoint']['browseEndpoint']['browseId'], compat_str)
uploader['uploader_url'] = urljoin(
'https://www.youtube.com/',
try_get(owner, lambda x: x['navigationEndpoint']['browseEndpoint']['canonicalBaseUrl'], compat_str))
return uploader
def _extract_from_tabs(self, item_id, webpage, data, tabs, identity_token):
selected_tab = self._extract_selected_tab(tabs) selected_tab = self._extract_selected_tab(tabs)
renderer = try_get( renderer = try_get(
data, lambda x: x['metadata']['channelMetadataRenderer'], dict) data, lambda x: x['metadata']['channelMetadataRenderer'], dict)
@ -2848,42 +2903,69 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
title = renderer.get('title') title = renderer.get('title')
description = None description = None
playlist_id = item_id playlist_id = item_id
identity_token = self._search_regex( playlist = self.playlist_result(
r'\bID_TOKEN["\']\s*:\s*["\'](.+?)["\']', webpage,
'identity token', default=None)
return self.playlist_result(
self._entries(selected_tab['content'], identity_token), self._entries(selected_tab['content'], identity_token),
playlist_id=playlist_id, playlist_title=title, playlist_id=playlist_id, playlist_title=title,
playlist_description=description) playlist_description=description)
playlist.update(self._extract_uploader(data))
return playlist
def _extract_from_playlist(self, item_id, data, playlist):
title = playlist.get('title') or try_get(
data, lambda x: x['titleText']['simpleText'], compat_str)
playlist_id = playlist.get('playlistId') or item_id
return self.playlist_result(
self._playlist_entries(playlist), playlist_id=playlist_id,
playlist_title=title)
def _real_extract(self, url):
item_id = self._match_id(url)
url = compat_urlparse.urlunparse(
compat_urlparse.urlparse(url)._replace(netloc='www.youtube.com'))
# Handle both video/playlist URLs
qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
video_id = qs.get('v', [None])[0]
playlist_id = qs.get('list', [None])[0]
if video_id and playlist_id:
if self._downloader.params.get('noplaylist'):
self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
return self.url_result(video_id, ie=YoutubeIE.ie_key(), video_id=video_id)
self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id))
webpage = self._download_webpage(url, item_id)
identity_token = self._search_regex(
r'\bID_TOKEN["\']\s*:\s*["\'](.+?)["\']', webpage,
'identity token', default=None)
data = self._extract_yt_initial_data(item_id, webpage)
tabs = try_get(
data, lambda x: x['contents']['twoColumnBrowseResultsRenderer']['tabs'], list)
if tabs:
return self._extract_from_tabs(item_id, webpage, data, tabs, identity_token)
playlist = try_get(
data, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
if playlist:
return self._extract_from_playlist(item_id, data, playlist)
# Fallback to video extraction if no playlist alike page is recognized
if video_id:
return self.url_result(video_id, ie=YoutubeIE.ie_key(), video_id=video_id)
# Failed to recognize
raise ExtractorError('Unable to recognize tab page')
class YoutubePlaylistIE(InfoExtractor): class YoutubePlaylistIE(InfoExtractor):
IE_DESC = 'YouTube.com playlists' IE_DESC = 'YouTube.com playlists'
_VALID_URL = r"""(?x)(?: _VALID_URL = r'''(?x)(?:
(?:https?://)? (?:https?://)?
(?:\w+\.)? (?:\w+\.)?
(?: (?:
(?: (?:
youtube(?:kids)?\.com| youtube(?:kids)?\.com|
invidio\.us invidio\.us|
youtu\.be
) )
/ /.*?\?.*?\blist=
(?: )?
(?:course|view_play_list|my_playlists|artist|playlist|watch|embed/(?:videoseries|[0-9A-Za-z_-]{11})) (?P<id>%(playlist_id)s)
\? (?:.*?[&;])*? (?:p|a|list)= )''' % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE}
| p/
)|
youtu\.be/[0-9A-Za-z_-]{11}\?.*?\blist=
)
(
(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)?[0-9A-Za-z-_]{10,}
# Top tracks, they can also include dots
|(?:MC)[\w\.]*
)
.*
|
(%(playlist_id)s)
)""" % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE}
IE_NAME = 'youtube:playlist' IE_NAME = 'youtube:playlist'
_TESTS = [{ _TESTS = [{
'note': 'issue #673', 'note': 'issue #673',
@ -2892,7 +2974,7 @@ class YoutubePlaylistIE(InfoExtractor):
'title': '[OLD]Team Fortress 2 (Class-based LP)', 'title': '[OLD]Team Fortress 2 (Class-based LP)',
'id': 'PLBB231211A4F62143', 'id': 'PLBB231211A4F62143',
'uploader': 'Wickydoo', 'uploader': 'Wickydoo',
'uploader_id': 'Wickydoo', 'uploader_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
}, },
'playlist_mincount': 29, 'playlist_mincount': 29,
}, { }, {
@ -2920,41 +3002,8 @@ class YoutubePlaylistIE(InfoExtractor):
'title': '2018 Chinese New Singles (11/6 updated)', 'title': '2018 Chinese New Singles (11/6 updated)',
'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl', 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
'uploader': 'LBK', 'uploader': 'LBK',
'uploader_id': 'sdragonfang', 'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA',
} }
}, {
'note': 'Embedded SWF player',
'url': 'https://www.youtube.com/p/YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ?hl=en_US&fs=1&rel=0',
'playlist_count': 4,
'info_dict': {
'title': 'JODA7',
'id': 'YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ',
},
'skip': 'This playlist does not exist',
}, {
# Playlist URL that does not actually serve a playlist
'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
'info_dict': {
'id': 'FqZTN594JQw',
'ext': 'webm',
'title': "Smiley's People 01 detective, Adventure Series, Action",
'uploader': 'STREEM',
'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
'upload_date': '20150526',
'license': 'Standard YouTube License',
'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
'categories': ['People & Blogs'],
'tags': list,
'view_count': int,
'like_count': int,
'dislike_count': int,
},
'params': {
'skip_download': True,
},
'skip': 'This video is not available.',
'add_ie': [YoutubeIE.ie_key()],
}, { }, {
'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5', 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
'info_dict': { 'info_dict': {
@ -2985,9 +3034,6 @@ class YoutubePlaylistIE(InfoExtractor):
# music album playlist # music album playlist
'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM', 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
'only_matching': True, 'only_matching': True,
}, {
'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
'only_matching': True,
}] }]
@classmethod @classmethod
@ -2996,13 +3042,12 @@ class YoutubePlaylistIE(InfoExtractor):
YoutubePlaylistIE, cls).suitable(url) YoutubePlaylistIE, cls).suitable(url)
def _real_extract(self, url): def _real_extract(self, url):
# Extract playlist id playlist_id = self._match_id(url)
mobj = re.match(self._VALID_URL, url) qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
if mobj is None: if not qs:
raise ExtractorError('Invalid URL: %s' % url) qs = {'list': playlist_id}
playlist_id = mobj.group(1) or mobj.group(2)
return self.url_result( return self.url_result(
'https://www.youtube.com/playlist?list=%s' % playlist_id, update_url_query('https://www.youtube.com/playlist', qs),
ie=YoutubeTabIE.ie_key(), video_id=playlist_id) ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
@ -3250,13 +3295,13 @@ class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor):
class YoutubeWatchLaterIE(InfoExtractor): class YoutubeWatchLaterIE(InfoExtractor):
IE_NAME = 'youtube:watchlater' IE_NAME = 'youtube:watchlater'
IE_DESC = 'Youtube watch later list, ":ytwatchlater" for short (requires authentication)' IE_DESC = 'Youtube watch later list, ":ytwatchlater" for short (requires authentication)'
_VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:feed/watch_later|(?:playlist|watch)\?(?:.+&)?list=WL)|:ytwatchlater' _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/watch_later|:ytwatchlater'
_TESTS = [{ _TESTS = [{
'url': 'https://www.youtube.com/watch?v=bCNU9TrbiRk&index=1&list=WL', 'url': 'https://www.youtube.com/feed/watch_later',
'only_matching': True, 'only_matching': True,
}, { }, {
'url': 'https://www.youtube.com/feed/watch_later', 'url': ':ytwatchlater',
'only_matching': True, 'only_matching': True,
}] }]

View File

@ -1,3 +1,3 @@
from __future__ import unicode_literals from __future__ import unicode_literals
__version__ = '2020.11.17' __version__ = '2020.11.18'