mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2025-05-07 14:30:09 +00:00
Code Issues Projects Releases Wiki Activity

[ie/GetCourseRu] Fix extractors (#12943)

Browse Source 
Closes #12941
Authored by: troex
This commit is contained in:
Sergey B (Troex Nevelin) 2025-04-23 02:14:42 +02:00 committed by GitHub
parent 34a061a295
commit 741fd809bc
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 12 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
yt_dlp/extractor/getcourseru.py
View File

@ -8,7 +8,7 @@ from ..utils.traversal import traverse_obj
class GetCourseRuPlayerIE(InfoExtractor):
_VALID_URL = r'https?://player02\.getcourse\.ru/sign-player/?\?(?:[^#]+&)?json=[^#&]+'
_VALID_URL = r'https?://(?:player02\.getcourse\.ru|cf-api-2\.vhcdn\.com)/sign-player/?\?(?:[^#]+&)?json=[^#&]+'
_EMBED_REGEX = [rf'<iframe[^>]+\bsrc=[\'"](?P<url>{_VALID_URL}[^\'"]*)']
_TESTS = [{
'url': 'http://player02.getcourse.ru/sign-player/?json=eyJ2aWRlb19oYXNoIjoiMTkwYmRmOTNmMWIyOTczNTMwOTg1M2E3YTE5ZTI0YjMiLCJ1c2VyX2lkIjozNTk1MjUxODMsInN1Yl9sb2dpbl91c2VyX2lkIjpudWxsLCJsZXNzb25faWQiOm51bGwsImlwIjoiNDYuMTQyLjE4Mi4yNDciLCJnY19ob3N0IjoiYWNhZGVteW1lbC5vbmxpbmUiLCJ0aW1lIjoxNzA1NDQ5NjQyLCJwYXlsb2FkIjoidV8zNTk1MjUxODMiLCJ1aV9sYW5ndWFnZSI6InJ1IiwiaXNfaGF2ZV9jdXN0b21fc3R5bGUiOnRydWV9&s=354ad2c993d95d5ac629e3133d6cefea&vh-static-feature=zigzag',
@ -20,6 +20,16 @@ class GetCourseRuPlayerIE(InfoExtractor):
'duration': 1693,
},
'skip': 'JWT expired',
}, {
'url': 'https://cf-api-2.vhcdn.com/sign-player/?json=example',
'info_dict': {
'id': '435735291',
'title': '8afd7c489952108e00f019590f3711f3',
'ext': 'mp4',
'thumbnail': 'https://preview-htz.vhcdn.com/preview/8afd7c489952108e00f019590f3711f3/preview.jpg?version=1682170973&host=vh-72',
'duration': 777,
},
'skip': 'JWT expired',
}]
def _real_extract(self, url):
@ -168,7 +178,7 @@ class GetCourseRuIE(InfoExtractor):
playlist_id = self._search_regex(
r'window\.(?:lessonId|gcsObjectId)\s*=\s*(\d+)', webpage, 'playlist id', default=display_id)
title = self._og_search_title(webpage) or self._html_extract_title(webpage)
title = self._og_search_title(webpage, default=None) or self._html_extract_title(webpage)
return self.playlist_from_matches(
re.findall(GetCourseRuPlayerIE._EMBED_REGEX[0], webpage),