mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2025-08-17 18:08:30 +00:00
Code Issues Projects Releases Wiki Activity

Merge 364ef4b90b into e8d49b1c7f

Browse Source
This commit is contained in:
Harsh Joshi 2025-08-09 18:36:33 +00:00 committed by GitHub
commit 499dd819d2
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 58 additions and 24 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

52
yt_dlp/extractor/bandcamp.py
View File

@ -71,7 +71,7 @@ class BandcampIE(InfoExtractor):
'album_artists': ['Ben Prunty'],
},
}, {
# no free download, mp3 128
# track from compilation album (artist/album_artist difference)
'url': 'https://relapsealumni.bandcamp.com/track/hail-to-fire',
'md5': 'fec12ff55e804bb7f7ebeb77a800c8b7',
'info_dict': {
@ -96,7 +96,7 @@ class BandcampIE(InfoExtractor):
'album_artists': ['Mastodon'],
},
}, {
# track from compilation album (artist/album_artist difference)
# FIXME: Embed detection
'url': 'https://diskotopia.bandcamp.com/track/safehouse',
'md5': '19c5337bca1428afa54129f86a2f6a69',
'info_dict': {
@ -440,9 +440,42 @@ def _real_extract(self, url):
blob = self._extract_data_attr(webpage, show_id, 'blob')
show = blob['bcw_data'][show_id]
shows_list = try_get(blob, lambda x: x['appData']['shows'], list)
show = None
if shows_list:
for s in shows_list:
if str(s.get('showId')) == show_id:
show = s
break
if not show:
show = try_get(blob, lambda x: x['bcw_data'][show_id], dict)
if not show:
raise ExtractorError('Bandcamp Weekly data not found. This extractor is outdated. Please report this issue.')
formats = []
audio_track_id = str_or_none(show.get('audioTrackId'))
# If audio track ID is found, download the audio page to get formats
if audio_track_id:
track_url = f'https://bandcamp.com/download?id={audio_track_id}'
audio_page = self._download_webpage(
track_url, show_id, 'Downloading audio download page')
audio_blob = self._extract_data_attr(audio_page, show_id, 'blob', fatal=False)
if audio_blob:
# The formats are now in the 'downloads' list within the audio_blob
downloads = try_get(audio_blob, lambda x: x['digital_items'][0]['downloads'], dict)
if downloads:
for format_id, f in downloads.items():
formats.append({
'url': f.get('url'),
'format_id': format_id,
'ext': f.get('encoding_name'),
'vcodec': 'none',
})
if not formats and show.get('audio_stream'):
for format_id, format_url in show['audio_stream'].items():
if not url_or_none(format_url):
continue
@ -458,21 +491,22 @@ def _real_extract(self, url):
'ext': ext,
'vcodec': 'none',
})
if not formats:
raise ExtractorError('Could not find any audio formats for this episode.')
title = show.get('audio_title') or 'Bandcamp Weekly'
subtitle = show.get('subtitle')
title = show.get('audio_title') or show.get('title') or 'Bandcamp Weekly'
subtitle = show.get('shortDesc')
if subtitle:
title += f' - {subtitle}'
return {
'id': show_id,
'title': title,
'description': show.get('desc') or show.get('short_desc'),
'description': show.get('desc') or show.get('shortDesc'),
'duration': float_or_none(show.get('audio_duration')),
'is_live': False,
'release_date': unified_strdate(show.get('published_date')),
'release_date': unified_strdate(show.get('date')),
'series': 'Bandcamp Weekly',
'episode': show.get('subtitle'),
'episode': show.get('shortDesc'),
'episode_id': show_id,
'formats': formats,
}