paradizelost/youtube-dl
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Merge 08202a62a7 into 4d05f84325

Browse Source
This commit is contained in:
dirkf 2024-06-27 06:36:00 +08:00 committed by GitHub
commit c2fc5a3e14
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
4 changed files with 134 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

125
youtube_dl/extractor/comedycentral.py
View File

@ -1,15 +1,22 @@
from __future__ import unicode_literals
import re
from ..compat import (
compat_str,
compat_urlparse,
)
from ..utils import urljoin
from .mtv import MTVServicesInfoExtractor
class ComedyCentralIE(MTVServicesInfoExtractor):
_VALID_URL = r'https?://(?:www\.)?cc\.com/(?:episodes|video(?:-clips)?)/(?P<id>[0-9a-z]{6})'
_VALID_URL = r'https?://(?:www\.)?cc\.com/(?:episodes|video(?:-clips)?|collection-playlist/[0-9a-z]+/[^/]+)/(?P<id>[0-9a-z]{6})'
_FEED_URL = 'http://comedycentral.com/feeds/mrss/'
_TESTS = [{
'url': 'http://www.cc.com/video-clips/5ke9v2/the-daily-show-with-trevor-noah-doc-rivers-and-steve-ballmer---the-nba-player-strike',
'md5': 'b8acb347177c680ff18a292aa2166f80',
'md5': '58e7caf5c7c0c865d9d79f7d151e5090',
'info_dict': {
'id': '89ccc86e-1b02-4f83-b0c9-1d9592ecd025',
'ext': 'mp4',
@ -18,13 +25,29 @@ class ComedyCentralIE(MTVServicesInfoExtractor):
'timestamp': 1598670000,
'upload_date': '20200829',
},
'params': {
'hls_prefer_native': False,
},
}, {
'url': 'http://www.cc.com/episodes/pnzzci/drawn-together--american-idol--parody-clip-show-season-3-ep-314',
'only_matching': True,
}, {
'url': 'https://www.cc.com/video/k3sdvm/the-daily-show-with-jon-stewart-exclusive-the-fourth-estate',
'only_matching': True,
}]
}, {
'url': 'https://www.cc.com/collection-playlist/8b7hw5/the-daily-shows-summer-exclusives/o2qny3',
'info_dict': {
'id': '2f56e756-91ec-4d68-8799-e3b710e360e4',
'ext': 'mp4',
'title': 'The Daily Show with Trevor Noah|August 4, 2021|26|NO-EPISODE#|Hottest Take - The Olympics',
'description': 'md5:104484314a4cba36d8c62b094523efc8',
'timestamp': 1628125200,
'upload_date': '20210805',
},
'params': {
'hls_prefer_native': False,
},
}, ]
class ComedyCentralTVIE(MTVServicesInfoExtractor):
@ -49,3 +72,99 @@ class ComedyCentralTVIE(MTVServicesInfoExtractor):
'imageEp': 'web.cc.tv',
'mgid': uri,
}
class ComedyCentralCollectionIE(ComedyCentralIE):
_VALID_URL = r'https?://(?:www\.)?cc\.com/collections/(?P<id>[0-9a-z]{6})(?:/[^/]*)?'
_TESTS = [{
'url': 'https://www.cc.com/collections/8b7hw5/the-daily-show-s-summer-exclusives',
'info_dict': {
'id': '8b7hw5',
'title': "The Daily Show's Summer Exclusives",
'description': 'md5:ae65028fcf8438e65f1c98099119fe6d',
},
'playlist_mincount': 11,
}, ]
_CLIP_IE = 'ComedyCentral'
# we need to know the redirected URL, so stash it in the extractor
# strange that this hasn't been a general requirement
def _request_webpage(self, url_or_request, video_id,
note=None, errnote=None, fatal=True, data=None,
headers={}, query={}, expected_status=None):
urlh = super(ComedyCentralCollectionIE, self)._request_webpage(
url_or_request, video_id, note, errnote, fatal,
data, headers, query, expected_status)
if urlh is not False:
self._url = urlh.geturl()
elif isinstance(url_or_request, compat_str):
self._url = url_or_request
else:
self._url = url_or_request.get_full_url()
return urlh
def _get_clip_id(self, url):
return None
def _real_extract(self, url):
playlist_id = self._match_id(url)
webpage = self._download_webpage(url, playlist_id)
url = self._url
clip_id = self._get_clip_id(url)
if clip_id:
url = url.rstrip(clip_id)
else:
url = url.replace('/collections/', '/collection-playlist/')
path = compat_urlparse.urlparse(url).path
if path.endswith('/'):
path = path[:-1]
clip_urls = re.finditer(
r'<a\s?[^>]*?href\s*=\s*"(?P<link>%s/(?P<id>[0-9a-z]{6}))"[^<]*>' % path,
webpage)
playlist_title = (self._html_search_meta('twitter:title', webpage, 'title')
or self._og_search_title(webpage, display_name='title')
or self._html_search_regex(r'<title\s?[^>]*>([^<]+)</',
webpage, 'title', default=None))
playlist_desc = (self._html_search_meta(('description', 'twitter:description'), webpage)
or self._og_search_description(webpage, display_name='description'))
pl = self.playlist_from_matches(clip_urls, playlist_id, playlist_title,
lambda m: urljoin(url, m.group('link')),
self._CLIP_IE)
if pl:
pl['description'] = playlist_desc
return pl
class ComedyCentralPlaylistIE(ComedyCentralCollectionIE):
_VALID_URL = r'https?://(?:www\.)?cc\.com/playlists/(?P<id>[0-9a-z]{6})(?:/(?:[^/]+(?:/(?P<clip_id>[0-9a-z]{6})?)?)?)?'
_TESTS = [{
'url': 'https://www.cc.com/playlists/mym6e5/corporate-working-nine-to-five',
'info_dict': {
'id': 'mym6e5',
'title': 'Coffee Break - Corporate | Comedy Central US',
'description': 'md5:89bc6e8e983ad34ded85af84108f6ea8',
},
'playlist_mincount': 5,
}, {
'url': 'https://www.cc.com/playlists/mym6e5/corporate-working-nine-to-five/dm8ekc',
'only_matching': True,
}, ]
def _get_clip_id(self, url):
mobj = re.match(self._VALID_URL, url)
return mobj.group('clip_id')
def _real_initialize(self):
self._CLIP_IE = self.IE_NAME
def _real_extract(self, url):
if self._get_clip_id(url):
return ComedyCentralIE._real_extract(self, url)
playlist_id = self._match_id(url)
if self._downloader.params.get('noplaylist', False):
_ = self._download_webpage(url, playlist_id)
if self._get_clip_id(self._url):
self.to_screen(
'Downloading just the "now playing" clip because of --no-playlist')
return self.url_result(self._url, self._CLIP_IE, playlist_id)
return super(ComedyCentralPlaylistIE, self)._real_extract(url)

2
youtube_dl/extractor/extractors.py
View File

@ -251,6 +251,8 @@ from .coub import CoubIE
from .comedycentral import (
ComedyCentralIE,
ComedyCentralTVIE,
ComedyCentralCollectionIE,
ComedyCentralPlaylistIE,
)
from .commonmistakes import CommonMistakesIE, UnicodeBOMIE
from .commonprotocols import (

3
youtube_dl/extractor/generic.py
View File

@ -903,6 +903,9 @@ class GenericIE(InfoExtractor):
'timestamp': 1349922600,
'upload_date': '20121011',
},
'params': {
'hls-prefer-native': False,
},
},
# YouTube embed via <data-embed-url="">
{

8
youtube_dl/extractor/mtv.py
View File

@ -229,6 +229,8 @@ class MTVServicesInfoExtractor(InfoExtractor):
if info:
entries.append(info)
if len(entries) == 1:
return entries[0]
return self.playlist_result(
entries, playlist_title=title, playlist_description=description)
@ -290,7 +292,7 @@ class MTVServicesInfoExtractor(InfoExtractor):
main_container = self._extract_child_with_type(data, 'MainContainer')
ab_testing = self._extract_child_with_type(main_container, 'ABTesting')
video_player = self._extract_child_with_type(ab_testing or main_container, 'VideoPlayer')
mgid = video_player['props']['media']['video']['config']['uri']
mgid = try_get(video_player, lambda x: x['props']['media']['video']['config']['uri'])
return mgid
@ -298,7 +300,11 @@ class MTVServicesInfoExtractor(InfoExtractor):
title = url_basename(url)
webpage = self._download_webpage(url, title)
mgid = self._extract_mgid(webpage)
if not mgid:
raise ExtractorError('Unable to determine MTVServices ID (mgid)', expected=True)
videos_info = self._get_videos_info(mgid)
if videos_info and videos_info.get('_type') != 'playlist':
videos_info['display_id'] = title
return videos_info