mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2025-08-14 08:28:29 +00:00
Code Issues Projects Releases Wiki Activity

fix: Correct SouthParkDeIE _real_extract method

Browse Source
This commit is contained in:
Randalix 2025-08-13 00:14:45 +02:00 committed by Randalix (aider)
parent 8207f3b824
commit d3de29389d
1 changed files with 9 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
yt_dlp/extractor/southpark.py
View File

@ -111,14 +111,10 @@ def _real_extract(self, url):
data = self._parse_json(self._search_regex( data = self._parse_json(self._search_regex(
r'window\.__DATA__\s*=\s*({.+?});', webpage, 'data'), display_id) r'window\.__DATA__\s*=\s*({.+?});', webpage, 'data'), display_id)
# Try multiple paths and, crucially, get only the FIRST match, not a list video_detail = traverse_obj(data, (
video_detail = traverse_obj(data, 'children', lambda _, v: v.get('type') == 'MainContainer',
# Path for regular episodes 'children', 0, 'children', 0, 'props', 'videoDetail'
('children', lambda _, v: v.get('type') == 'MainContainer', ), ('children', 0, 'videoDetail'), get_all=False)
'children', 0, 'children', 0, 'props', 'videoDetail'),
# Fallback path for special episodes
('children', 0, 'videoDetail'),
get_all=False)
if not video_detail: if not video_detail:
raise ExtractorError('Could not find video data in page') raise ExtractorError('Could not find video data in page')
@ -131,12 +127,11 @@ def _real_extract(self, url):
'clientPlatform': 'mobile', 'clientPlatform': 'mobile',
}) })
hls_url = traverse_obj(api_data, ('stitchedstream', 'source'), expected_type=str, get_all=False) hls_url = traverse_obj(api_data, ('stitchedstream', 'source'), expected_type=str)
return { info = {
'id': video_detail['id'], 'id': video_detail['id'],
'display_id': display_id, 'display_id': display_id,
'url': hls_url,
'title': video_detail.get('title'), 'title': video_detail.get('title'),
'description': video_detail.get('description'), 'description': video_detail.get('description'),
'duration': traverse_obj(video_detail, ('duration', 'milliseconds'), expected_type=int) / 1000, 'duration': traverse_obj(video_detail, ('duration', 'milliseconds'), expected_type=int) / 1000,
@ -145,6 +140,9 @@ def _real_extract(self, url):
'timestamp': traverse_obj(video_detail, ('publishDate', 'timestamp')), 'timestamp': traverse_obj(video_detail, ('publishDate', 'timestamp')),
'series': traverse_obj(video_detail, ('parentEntity', 'title')), 'series': traverse_obj(video_detail, ('parentEntity', 'title')),
} }
info['formats'] = self._extract_m3u8_formats(
hls_url, display_id, 'mp4', entry_protocol='m3u8_native', m3u8_id='hls')
return info
class SouthParkLatIE(SouthParkIE): # XXX: Do not subclass from concrete IE class SouthParkLatIE(SouthParkIE): # XXX: Do not subclass from concrete IE