xZero707/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-23 11:31:29 +01:00
Code Issues Packages Projects Releases Wiki Activity

[bandcamp:album] Fix extractor results and associated test

Browse Source
This commit is contained in:
Philipp Hagemeister 2015-02-18 00:48:52 +01:00
parent 6e99868e4c
commit 72c1f8de06
1 changed files with 13 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
youtube_dl/extractor/bandcamp.py
View File

@ -109,7 +109,7 @@ def _real_extract(self, url):
class BandcampAlbumIE(InfoExtractor):
IE_NAME = 'Bandcamp:album'
_VALID_URL = r'https?://(?:(?P<subdomain>[^.]+)\.)?bandcamp\.com(?:/album/(?P<title>[^?#]+)|/?(?:$|[?#]))'
_VALID_URL = r'https?://(?:(?P<subdomain>[^.]+)\.)?bandcamp\.com(?:/album/(?P<album_id>[^?#]+)|/?(?:$|[?#]))'
_TESTS = [{
'url': 'http://blazo.bandcamp.com/album/jazz-format-mixtape-vol-1',
@ -133,31 +133,37 @@ class BandcampAlbumIE(InfoExtractor):
],
'info_dict': {
'title': 'Jazz Format Mixtape vol.1',
'id': 'jazz-format-mixtape-vol-1',
'uploader_id': 'blazo',
},
'params': {
'playlistend': 2
},
'skip': 'Bandcamp imposes download limits. See test_playlists:test_bandcamp_album for the playlist test'
'skip': 'Bandcamp imposes download limits.'
}, {
'url': 'http://nightbringer.bandcamp.com/album/hierophany-of-the-open-grave',
'info_dict': {
'title': 'Hierophany of the Open Grave',
'uploader_id': 'nightbringer',
'id': 'hierophany-of-the-open-grave',
},
'playlist_mincount': 9,
}, {
'url': 'http://dotscale.bandcamp.com',
'info_dict': {
'title': 'Loom',
'id': 'dotscale',
'uploader_id': 'dotscale',
},
'playlist_mincount': 7,
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
playlist_id = mobj.group('subdomain')
title = mobj.group('title')
display_id = title or playlist_id
webpage = self._download_webpage(url, display_id)
uploader_id = mobj.group('subdomain')
album_id = mobj.group('album_id')
playlist_id = album_id or uploader_id
webpage = self._download_webpage(url, playlist_id)
tracks_paths = re.findall(r'<a href="(.*?)" itemprop="url">', webpage)
if not tracks_paths:
raise ExtractorError('The page doesn\'t contain any tracks')
@ -168,8 +174,8 @@ def _real_extract(self, url):
r'album_title\s*:\s*"(.*?)"', webpage, 'title', fatal=False)
return {
'_type': 'playlist',
'uploader_id': uploader_id,
'id': playlist_id,
'display_id': display_id,
'title': title,
'entries': entries,
}