From 2c475e48b54b071a3e59441829b6dec7d5b3c0ac Mon Sep 17 00:00:00 2001 From: pukkandan Date: Fri, 2 Sep 2022 01:38:21 +0530 Subject: [PATCH] [extractor/bandcamp] Extract `uploader_url` Closes #4755 --- yt_dlp/extractor/bandcamp.py | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/yt_dlp/extractor/bandcamp.py b/yt_dlp/extractor/bandcamp.py index b34fcb1081..2dae49e770 100644 --- a/yt_dlp/extractor/bandcamp.py +++ b/yt_dlp/extractor/bandcamp.py @@ -21,7 +21,7 @@ class BandcampIE(InfoExtractor): - _VALID_URL = r'https?://[^/]+\.bandcamp\.com/track/(?P[^/?#&]+)' + _VALID_URL = r'https?://(?P[^/]+)\.bandcamp\.com/track/(?P[^/?#&]+)' _EMBED_REGEX = [r']*?content="(?P.*?bandcamp\.com.*?)"'] _TESTS = [{ 'url': 'http://youtube-dl.bandcamp.com/track/youtube-dl-test-song', @@ -85,7 +85,7 @@ def _extract_data_attr(self, webpage, video_id, attr='tralbum', fatal=True): attr + ' data', group=2), video_id, fatal=fatal) def _real_extract(self, url): - title = self._match_id(url) + title, uploader = self._match_valid_url(url).group('id', 'uploader') webpage = self._download_webpage(url, title) tralbum = self._extract_data_attr(webpage, title) thumbnail = self._og_search_thumbnail(webpage) @@ -197,6 +197,8 @@ def _real_extract(self, url): 'title': title, 'thumbnail': thumbnail, 'uploader': artist, + 'uploader_id': uploader, + 'uploader_url': f'https://{uploader}.bandcamp.com', 'timestamp': timestamp, 'release_timestamp': unified_timestamp(tralbum.get('album_release_date')), 'duration': duration,