mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2025-08-13 16:08:29 +00:00
Code Issues Projects Releases Wiki Activity

fixes to extractor regex, artist splitting, and half·alive test

Browse Source
This commit is contained in:
theqwertycoder 2025-08-03 20:18:32 -04:00
parent 13e6a52074
commit 223b3b75ef
1 changed files with 29 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

34
yt_dlp/extractor/youtube/_video.py
View File

@ -1671,12 +1671,37 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
'url': 'https://music.youtube.com/watch?v=DbCvuSGfR3Y',
'info_dict': {
'id': 'DbCvuSGfR3Y',
'ext': 'mp4',
'title': 'Back Around',
'artists': ['half·alive'],
'track': 'Back Around',
'album': 'Conditions Of A Punk',
'release_date': '20221202',
'release_year': 2021,
'alt_title': 'Back Around',
'description': 'md5:bfc0e2b3cc903a608d8a85a13cb50f95',
'media_type': 'video',
'uploader': 'half•alive',
'channel': 'half•alive',
'channel_id': 'UCYQrYophdVI3nVDPOnXyIng',
'channel_url': 'https://www.youtube.com/channel/UCYQrYophdVI3nVDPOnXyIng',
'channel_is_verified': True,
'channel_follower_count': int,
'comment_count': int,
'view_count': int,
'like_count': int,
'age_limit': 0,
'duration': 223,
'thumbnail': 'https://i.ytimg.com/vi_webp/DbCvuSGfR3Y/maxresdefault.webp',
'heatmap': 'count:100',
'categories': ['Music'],
'tags': ['half·alive', 'Conditions Of A Punk', 'Back Around'],
'creators': ['half·alive'],
'timestamp': 1669889281,
'upload_date': '20221201',
'playable_in_embed': True,
'availability': 'public',
'live_status': 'not_live',
},
'params': {
'skip_download': True,
@ -4207,15 +4232,14 @@ def process_language(container, base_url, lang_code, sub_name, client_name, quer
# Youtube Music Auto-generated description
if (video_description or '').strip().endswith('\nAuto-generated by YouTube.'):
# Before you change this, learn how regexes work. The last guy didn't.
mobj = re.search(
r'''(?xs)
(?:\n|^)(?P<track>[^\n·]+)\ ·\ (?P<artist>[^\n]+)\n+
(?P<album>[^\n]+)\n+
(?:℗\s*(?P<release_year>\d{4})[^\n]+\n+)?
(?:Released\ on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))?
(?:℗\s*(?P<release_year>\d{4}))?
(?:.+?\nReleased\ on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))?
(?:.+?\nArtist\s*:\s*(?P<clean_artist>[^\n]+)\n)?
.+Auto-generated\ by\ YouTube\.\s*$
.+\nAuto-generated\ by\ YouTube\.\s*$
''', video_description)
if mobj:
release_year = mobj.group('release_year')
@ -4227,7 +4251,7 @@ def process_language(container, base_url, lang_code, sub_name, client_name, quer
info.update({
'album': mobj.group('album'.strip()),
'artists': ([a] if (a := mobj.group('clean_artist'))
else [a.strip() for a in mobj.group('artist').split('·')]),
else [a.strip() for a in mobj.group('artist').split(' · ')]),
'track': mobj.group('track').strip(),
'release_date': release_date,
'release_year': int_or_none(release_year),