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

Update _real_extract in BandcampWeeklyIE class to handel the keyerror

Browse Source
This commit is contained in:
harsh1504660 2025-08-09 23:29:50 +05:30
parent e8d49b1c7f
commit 05285b7e0d
1 changed files with 66 additions and 22 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

86
yt_dlp/extractor/bandcamp.py
View File

@ -440,39 +440,83 @@ def _real_extract(self, url):
blob = self._extract_data_attr(webpage, show_id, 'blob')
show = blob['bcw_data'][show_id]
# Updated to correctly navigate the new data structure
# The data is now in a list under appData['shows']
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:
# Fallback to the original logic if the new path fails
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 This extractor is outdated.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 = []
for format_id, format_url in show['audio_stream'].items():
if not url_or_none(format_url):
continue
for known_ext in KNOWN_EXTENSIONS:
if known_ext in format_id:
ext = known_ext
break
else:
ext = None
formats.append({
'format_id': format_id,
'url': format_url,
'ext': ext,
'vcodec': 'none',
})
# The audio track ID is now in the 'audioTrackId' key
audio_track_id = str_or_none(show.get('audioTrackId'))
title = show.get('audio_title') or 'Bandcamp Weekly'
subtitle = show.get('subtitle')
# 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')
# The download links are on the new page, so we need a new way to parse
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',
})
# Fallback to the old logic if new parsing fails
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
for known_ext in KNOWN_EXTENSIONS:
if known_ext in format_id:
ext = known_ext
break
else:
ext = None
formats.append({
'format_id': format_id,
'url': format_url,
'ext': ext,
'vcodec': 'none',
})
# If no formats were found after all attempts, raise an error
if not formats:
raise ExtractorError('Could not find any audio formats for this episode.')
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,
}