smokephil/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2025-12-05 22:34:59 +01:00
Code Issues Projects Releases Packages Wiki Activity

[ie/web.archive:youtube] Fix extractor (#15234)

Browse source 
Closes #15233
Authored by: seproDev
This commit is contained in:
sepro 2025-12-04 18:15:09 +01:00 • committed by GitHub
parent f7acf3c1f4
commit 7ec6b9bc40
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 39 additions and 11 deletions
Download patch file Download diff file Expand all files Collapse all files

50
yt_dlp/extractor/archiveorg.py
View file

@ -704,6 +704,24 @@ class YoutubeWebArchiveIE(InfoExtractor):
'thumbnail': 'https://web.archive.org/web/20160108040020if_/https://i.ytimg.com/vi/SQCom7wjGDs/maxresdefault.jpg',
'upload_date': '20160107',
},
}, {
# dmuxed formats
'url': 'https://web.archive.org/web/20240922160632/https://www.youtube.com/watch?v=z7hzvTL3k1k',
'info_dict': {
'id': 'z7hzvTL3k1k',
'ext': 'webm',
'title': 'Praise the Lord and Pass the Ammunition (BARRXN REMIX)',
'description': 'md5:45dbf2c71c23b0734c8dfb82dd1e94b6',
'uploader': 'Barrxn',
'uploader_id': 'TheRockstar6086',
'uploader_url': 'https://www.youtube.com/user/TheRockstar6086',
'channel_id': 'UCjJPGUTtvR9uizmawn2ThqA',
'channel_url': 'https://www.youtube.com/channel/UCjJPGUTtvR9uizmawn2ThqA',
'duration': 125,
'thumbnail': r're:https?://.*\.(jpg|webp)',
'upload_date': '20201207',
},
'params': {'format': 'bv'},
}, {
'url': 'https://web.archive.org/web/http://www.youtube.com/watch?v=kH-G_aIBlFw',
'only_matching': True,
@ -1060,6 +1078,19 @@ class YoutubeWebArchiveIE(InfoExtractor):
capture_dates.extend([self._OLDEST_CAPTURE_DATE, self._NEWEST_CAPTURE_DATE])
return orderedSet(filter(None, capture_dates))
def _parse_fmt(self, fmt, extra_info=None):
format_id = traverse_obj(fmt, ('url', {parse_qs}, 'itag', 0))
return {
'format_id': format_id,
**self._FORMATS.get(format_id, {}),
**traverse_obj(fmt, {
'url': ('url', {lambda x: f'https://web.archive.org/web/2id_/{x}'}),
'ext': ('ext', {str}),
'filesize': ('url', {parse_qs}, 'clen', 0, {int_or_none}),
}),
**(extra_info or {}),
}
def _real_extract(self, url):
video_id, url_date, url_date_2 = self._match_valid_url(url).group('id', 'date', 'date2')
url_date = url_date or url_date_2
@ -1090,17 +1121,14 @@ class YoutubeWebArchiveIE(InfoExtractor):
info['thumbnails'] = self._extract_thumbnails(video_id)
formats = []
for fmt in traverse_obj(video_info, ('formats', lambda _, v: url_or_none(v['url']))):
format_id = traverse_obj(fmt, ('url', {parse_qs}, 'itag', 0))
formats.append({
'format_id': format_id,
**self._FORMATS.get(format_id, {}),
**traverse_obj(fmt, {
'url': ('url', {lambda x: f'https://web.archive.org/web/2id_/{x}'}),
'ext': ('ext', {str}),
'filesize': ('url', {parse_qs}, 'clen', 0, {int_or_none}),
}),
})
if video_info.get('dmux'):
for vf in traverse_obj(video_info, ('formats', 'video', lambda _, v: url_or_none(v['url']))):
formats.append(self._parse_fmt(vf, {'acodec': 'none'}))
for af in traverse_obj(video_info, ('formats', 'audio', lambda _, v: url_or_none(v['url']))):
formats.append(self._parse_fmt(af, {'vcodec': 'none'}))
else:
for fmt in traverse_obj(video_info, ('formats', lambda _, v: url_or_none(v['url']))):
formats.append(self._parse_fmt(fmt))
info['formats'] = formats
return info