mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2025-07-18 03:08:31 +00:00
Code Issues Projects Releases Wiki Activity

Merge ace97a88fa into c1ac543c81

Browse Source
This commit is contained in:
garret1317 2025-07-17 09:06:29 +08:00 committed by GitHub
commit aab8367ce0
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 25 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

32
yt_dlp/extractor/bandcamp.py
View File

@ -11,10 +11,12 @@
float_or_none, float_or_none,
int_or_none, int_or_none,
parse_filesize, parse_filesize,
smuggle_url,
str_or_none, str_or_none,
try_get, try_get,
unified_strdate, unified_strdate,
unified_timestamp, unified_timestamp,
unsmuggle_url,
update_url_query, update_url_query,
url_or_none, url_or_none,
urljoin, urljoin,
@ -127,6 +129,8 @@ def _extract_data_attr(self, webpage, video_id, attr='tralbum', fatal=True):
attr + ' data', group=2), video_id, fatal=fatal) attr + ' data', group=2), video_id, fatal=fatal)
def _real_extract(self, url): def _real_extract(self, url):
url, smuggled_track_info = unsmuggle_url(url, None)
title, uploader = self._match_valid_url(url).group('id', 'uploader') title, uploader = self._match_valid_url(url).group('id', 'uploader')
webpage = self._download_webpage(url, title) webpage = self._download_webpage(url, title)
tralbum = self._extract_data_attr(webpage, title) tralbum = self._extract_data_attr(webpage, title)
@ -138,7 +142,7 @@ def _real_extract(self, url):
duration = None duration = None
formats = [] formats = []
track_info = try_get(tralbum, lambda x: x['trackinfo'][0], dict) track_info = try_get(tralbum, lambda x: x['trackinfo'][0], dict) or smuggled_track_info
if track_info: if track_info:
file_ = track_info.get('file') file_ = track_info.get('file')
if isinstance(file_, dict): if isinstance(file_, dict):
@ -347,6 +351,15 @@ class BandcampAlbumIE(BandcampIE): # XXX: Do not subclass from concrete IE
'description': 'md5:b3cf845ee41b2b1141dc7bde9237255f', 'description': 'md5:b3cf845ee41b2b1141dc7bde9237255f',
}, },
'playlist_count': 2, 'playlist_count': 2,
}, {
# tracks need track_info smuggled because they don't have a usable one on the pages
'url': 'https://wetleg.bandcamp.com/album/wet-leg',
'info_dict': {
'id': 'wet-leg',
'title': 'Wet Leg',
'uploader_id': 'wetleg',
},
'playlist_count': 12,
}] }]
@classmethod @classmethod
@ -364,12 +377,17 @@ def _real_extract(self, url):
if not track_info: if not track_info:
raise ExtractorError('The page doesn\'t contain any tracks') raise ExtractorError('The page doesn\'t contain any tracks')
# Only tracks with duration info have songs # Only tracks with duration info have songs
entries = [ entries = []
self.url_result( for t in track_info:
urljoin(url, t['title_link']), BandcampIE.ie_key(), if t.get('duration'):
str_or_none(t.get('track_id') or t.get('id')), t.get('title')) url = urljoin(url, t['title_link'])
for t in track_info if t.get('track_license_id'):
if t.get('duration')] # tracks with this set don't have a usable tralbum on their pages
url = smuggle_url(url, t)
entries.append(self.url_result(
url, BandcampIE.ie_key(),
str_or_none(t.get('track_id') or t.get('id')), t.get('title'),
))
current = tralbum.get('current') or {} current = tralbum.get('current') or {}