github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-21 20:46:36 -05:00
Code Issues Projects Releases Packages Wiki Activity

[bandcamp] Add support for subdomains (Fixes #2850)

Browse source
This commit is contained in:
Philipp Hagemeister 2014-05-05 02:44:44 +02:00
parent 4f3e943080
commit b48f147d5a
1 changed files with 7 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

10
youtube_dl/extractor/bandcamp.py
View file

@ -12,7 +12,7 @@
class BandcampIE(InfoExtractor): class BandcampIE(InfoExtractor):
_VALID_URL = r'http://.*?\.bandcamp\.com/track/(?P<title>.*)' _VALID_URL = r'https?://.*?\.bandcamp\.com/track/(?P<title>.*)'
_TESTS = [{ _TESTS = [{
'url': 'http://youtube-dl.bandcamp.com/track/youtube-dl-test-song', 'url': 'http://youtube-dl.bandcamp.com/track/youtube-dl-test-song',
'file': '1812978515.mp3', 'file': '1812978515.mp3',
@ -100,7 +100,7 @@ def _real_extract(self, url):
class BandcampAlbumIE(InfoExtractor): class BandcampAlbumIE(InfoExtractor):
IE_NAME = 'Bandcamp:album' IE_NAME = 'Bandcamp:album'
_VALID_URL = r'http://.*?\.bandcamp\.com/album/(?P<title>.*)' _VALID_URL = r'https?://(?:(?P<subdomain>[^.]+)\.)?bandcamp\.com(?:/album/(?P<title>[^?#]+))?'
_TEST = { _TEST = {
'url': 'http://blazo.bandcamp.com/album/jazz-format-mixtape-vol-1', 'url': 'http://blazo.bandcamp.com/album/jazz-format-mixtape-vol-1',
@ -128,8 +128,10 @@ class BandcampAlbumIE(InfoExtractor):
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
playlist_id = mobj.group('subdomain')
title = mobj.group('title') title = mobj.group('title')
webpage = self._download_webpage(url, title) display_id = title or playlist_id
webpage = self._download_webpage(url, display_id)
tracks_paths = re.findall(r'<a href="(.*?)" itemprop="url">', webpage) tracks_paths = re.findall(r'<a href="(.*?)" itemprop="url">', webpage)
if not tracks_paths: if not tracks_paths:
raise ExtractorError('The page doesn\'t contain any tracks') raise ExtractorError('The page doesn\'t contain any tracks')
@ -139,6 +141,8 @@ def _real_extract(self, url):
title = self._search_regex(r'album_title : "(.*?)"', webpage, 'title') title = self._search_regex(r'album_title : "(.*?)"', webpage, 'title')
return { return {
'_type': 'playlist', '_type': 'playlist',
'id': playlist_id,
'display_id': display_id,
'title': title, 'title': title,
'entries': entries, 'entries': entries,
} }