Cool_Tools/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-28 01:21:01 +01:00
Code Issues Packages Projects Releases Wiki Activity

[ie/ZenYandex] Fix extractor (#9813)

Browse Source 
Closes #9803
Authored by: src-tinkerer
This commit is contained in:
src-tinkerer 2024-05-08 21:27:30 +00:00 committed by GitHub
parent 2338827072
commit c4b87dd885
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 5 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
yt_dlp/extractor/yandexvideo.py
View File

@ -259,15 +259,15 @@ def _real_extract(self, url):
webpage = self._download_webpage(redirect, video_id, note='Redirecting') webpage = self._download_webpage(redirect, video_id, note='Redirecting')
data_json = self._search_json( data_json = self._search_json(
r'("data"\s*:|data\s*=)', webpage, 'metadata', video_id, contains_pattern=r'{["\']_*serverState_*video.+}') r'("data"\s*:|data\s*=)', webpage, 'metadata', video_id, contains_pattern=r'{["\']_*serverState_*video.+}')
serverstate = self._search_regex(r'(_+serverState_+video-site_[^_]+_+)', serverstate = self._search_regex(r'(_+serverState_+video-site_[^_]+_+)', webpage, 'server state')
webpage, 'server state').replace('State', 'Settings')
uploader = self._search_regex(r'(<a\s*class=["\']card-channel-link[^"\']+["\'][^>]+>)', uploader = self._search_regex(r'(<a\s*class=["\']card-channel-link[^"\']+["\'][^>]+>)',
webpage, 'uploader', default='<a>') webpage, 'uploader', default='<a>')
uploader_name = extract_attributes(uploader).get('aria-label') uploader_name = extract_attributes(uploader).get('aria-label')
video_json = try_get(data_json, lambda x: x[serverstate]['exportData']['video'], dict) item_id = traverse_obj(data_json, (serverstate, 'videoViewer', 'openedItemId', {str}))
stream_urls = try_get(video_json, lambda x: x['video']['streams']) video_json = traverse_obj(data_json, (serverstate, 'videoViewer', 'items', item_id, {dict})) or {}
formats, subtitles = [], {} formats, subtitles = [], {}
for s_url in stream_urls: for s_url in traverse_obj(video_json, ('video', 'streams', ..., {url_or_none})):
ext = determine_ext(s_url) ext = determine_ext(s_url)
if ext == 'mpd': if ext == 'mpd':
fmts, subs = self._extract_mpd_formats_and_subtitles(s_url, video_id, mpd_id='dash') fmts, subs = self._extract_mpd_formats_and_subtitles(s_url, video_id, mpd_id='dash')