PublicMirrors/you-get
1
0
Fork 0
mirror of https://github.com/soimort/you-get.git synced 2025-01-23 21:45:02 +03:00
Code Issues Actions Packages Projects Releases 1 Wiki Activity

[youtube] we should extract ytInitialPlayerResponse more reliably

Browse Source
This commit is contained in:
Mort Yao 2022-06-07 16:19:14 +02:00
parent 6ddc3fce89
commit c0151a9775
No known key found for this signature in database
GPG Key ID: 07DA00CB78203251
1 changed files with 8 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
src/you_get/extractors/youtube.py
View File

@ -237,7 +237,10 @@ class YouTube(VideoExtractor):
except: except:
# ytplayer_config = {args:{raw_player_response:ytInitialPlayerResponse}} # ytplayer_config = {args:{raw_player_response:ytInitialPlayerResponse}}
try: # FIXME: we should extract ytInitialPlayerResponse more reliably
ytInitialPlayerResponse = json.loads(re.search('ytInitialPlayerResponse\s*=\s*([^\n]+?});</script>', video_page).group(1)) ytInitialPlayerResponse = json.loads(re.search('ytInitialPlayerResponse\s*=\s*([^\n]+?});</script>', video_page).group(1))
except:
ytInitialPlayerResponse = json.loads(re.search('ytInitialPlayerResponse\s*=\s*([^\n]+?});', video_page).group(1))
stream_list = ytInitialPlayerResponse['streamingData']['formats'] stream_list = ytInitialPlayerResponse['streamingData']['formats']
#stream_list = ytInitialPlayerResponse['streamingData']['adaptiveFormats'] #stream_list = ytInitialPlayerResponse['streamingData']['adaptiveFormats']
@ -262,7 +265,10 @@ class YouTube(VideoExtractor):
# Parse video page instead # Parse video page instead
video_page = get_content('https://www.youtube.com/watch?v=%s' % self.vid) video_page = get_content('https://www.youtube.com/watch?v=%s' % self.vid)
try: # FIXME: we should extract ytInitialPlayerResponse more reliably
ytInitialPlayerResponse = json.loads(re.search('ytInitialPlayerResponse\s*=\s*([^\n]+?});</script>', video_page).group(1)) ytInitialPlayerResponse = json.loads(re.search('ytInitialPlayerResponse\s*=\s*([^\n]+?});</script>', video_page).group(1))
except:
ytInitialPlayerResponse = json.loads(re.search('ytInitialPlayerResponse\s*=\s*([^\n]+?});', video_page).group(1))
self.title = ytInitialPlayerResponse["videoDetails"]["title"] self.title = ytInitialPlayerResponse["videoDetails"]["title"]
if re.search('([^"]*/base\.js)"', video_page): if re.search('([^"]*/base\.js)"', video_page):