artem/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2026-04-02 15:12:45 +00:00
Code Issues Packages Projects Releases Wiki Activity

[ie/cbc] Fix extractors (#15631)

Browse Source 
Closes #15584
Authored by: subrat-lima
This commit is contained in:
Subrat Lima 2026-01-20 04:09:27 +05:30 committed by GitHub
parent 5382c6c81b
commit 457dd036af
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 19 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
yt_dlp/extractor/cbc.py
View File

@ -105,7 +105,7 @@ class CBCIE(InfoExtractor):
# multiple CBC.APP.Caffeine.initInstance(...) # multiple CBC.APP.Caffeine.initInstance(...)
'url': 'http://www.cbc.ca/news/canada/calgary/dog-indoor-exercise-winter-1.3928238', 'url': 'http://www.cbc.ca/news/canada/calgary/dog-indoor-exercise-winter-1.3928238',
'info_dict': { 'info_dict': {
'title': 'Keep Rover active during the deep freeze with doggie pushups and other fun indoor tasks', # FIXME: actual title includes " | CBC News" 'title': 'Keep Rover active during the deep freeze with doggie pushups and other fun indoor tasks',
'id': 'dog-indoor-exercise-winter-1.3928238', 'id': 'dog-indoor-exercise-winter-1.3928238',
'description': 'md5:c18552e41726ee95bd75210d1ca9194c', 'description': 'md5:c18552e41726ee95bd75210d1ca9194c',
}, },
@ -134,6 +134,13 @@ class CBCIE(InfoExtractor):
title = (self._og_search_title(webpage, default=None) title = (self._og_search_title(webpage, default=None)
or self._html_search_meta('twitter:title', webpage, 'title', default=None) or self._html_search_meta('twitter:title', webpage, 'title', default=None)
or self._html_extract_title(webpage)) or self._html_extract_title(webpage))
title = self._search_regex(
r'^(?P<title>.+?)(?:\s*[|–-]\s*CBC.*)?$',
title, 'cleaned title', group='title', default=title)
data = self._search_json(
r'window\.__INITIAL_STATE__\s*=', webpage,
'initial state', display_id, default={}, transform_source=js_to_json)
entries = [ entries = [
self._extract_player_init(player_init, display_id) self._extract_player_init(player_init, display_id)
for player_init in re.findall(r'CBC\.APP\.Caffeine\.initInstance\(({.+?})\);', webpage)] for player_init in re.findall(r'CBC\.APP\.Caffeine\.initInstance\(({.+?})\);', webpage)]
@ -143,6 +150,11 @@ class CBCIE(InfoExtractor):
r'<div[^>]+\bid=["\']player-(\d+)', r'<div[^>]+\bid=["\']player-(\d+)',
r'guid["\']\s*:\s*["\'](\d+)'): r'guid["\']\s*:\s*["\'](\d+)'):
media_ids.extend(re.findall(media_id_re, webpage)) media_ids.extend(re.findall(media_id_re, webpage))
media_ids.extend(traverse_obj(data, (
'detail', 'content', 'body', ..., 'content',
lambda _, v: v['type'] == 'polopoly_media', 'content', 'sourceId', {str})))
if content_id := traverse_obj(data, ('app', 'contentId', {str})):
media_ids.append(content_id)
entries.extend([ entries.extend([
self.url_result(f'cbcplayer:{media_id}', 'CBCPlayer', media_id) self.url_result(f'cbcplayer:{media_id}', 'CBCPlayer', media_id)
for media_id in orderedSet(media_ids)]) for media_id in orderedSet(media_ids)])
@ -268,7 +280,7 @@ class CBCPlayerIE(InfoExtractor):
'duration': 2692.833, 'duration': 2692.833,
'subtitles': { 'subtitles': {
'en-US': [{ 'en-US': [{
'name': 'English Captions', 'name': r're:English',
'url': 'https://cbchls.akamaized.net/delivery/news-shows/2024/06/17/NAT_JUN16-00-55-00/NAT_JUN16_cc.vtt', 'url': 'https://cbchls.akamaized.net/delivery/news-shows/2024/06/17/NAT_JUN16-00-55-00/NAT_JUN16_cc.vtt',
}], }],
}, },
@ -322,6 +334,7 @@ class CBCPlayerIE(InfoExtractor):
'categories': ['Olympics Summer Soccer', 'Summer Olympics Replays', 'Summer Olympics Soccer Replays'], 'categories': ['Olympics Summer Soccer', 'Summer Olympics Replays', 'Summer Olympics Soccer Replays'],
'location': 'Canada', 'location': 'Canada',
}, },
'skip': 'Video no longer available',
'params': {'skip_download': 'm3u8'}, 'params': {'skip_download': 'm3u8'},
}, { }, {
'url': 'https://www.cbc.ca/player/play/video/9.6459530', 'url': 'https://www.cbc.ca/player/play/video/9.6459530',
@ -380,7 +393,8 @@ class CBCPlayerIE(InfoExtractor):
video_id = self._match_id(url) video_id = self._match_id(url)
webpage = self._download_webpage(f'https://www.cbc.ca/player/play/{video_id}', video_id) webpage = self._download_webpage(f'https://www.cbc.ca/player/play/{video_id}', video_id)
data = self._search_json( data = self._search_json(
r'window\.__INITIAL_STATE__\s*=', webpage, 'initial state', video_id)['video']['currentClip'] r'window\.__INITIAL_STATE__\s*=', webpage,
'initial state', video_id, transform_source=js_to_json)['video']['currentClip']
assets = traverse_obj( assets = traverse_obj(
data, ('media', 'assets', lambda _, v: url_or_none(v['key']) and v['type'])) data, ('media', 'assets', lambda _, v: url_or_none(v['key']) and v['type']))
@ -492,12 +506,14 @@ class CBCPlayerPlaylistIE(InfoExtractor):
'info_dict': { 'info_dict': {
'id': 'news/tv shows/the national/latest broadcast', 'id': 'news/tv shows/the national/latest broadcast',
}, },
'skip': 'Playlist no longer available',
}, { }, {
'url': 'https://www.cbc.ca/player/news/Canada/North', 'url': 'https://www.cbc.ca/player/news/Canada/North',
'playlist_mincount': 25, 'playlist_mincount': 25,
'info_dict': { 'info_dict': {
'id': 'news/canada/north', 'id': 'news/canada/north',
}, },
'skip': 'Playlist no longer available',
}] }]
def _real_extract(self, url): def _real_extract(self, url):