X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;ds=inline;f=youtube_dl%2Fextractor%2Fbandcamp.py;h=c13446665d2fb0e202973a26f5c7499c325719d1;hb=baa708036c64e2dce419b5f0648ee6b84ce2132e;hp=886b0dfabb7537ebca8a13ce7e4d6d68b9966a4c;hpb=f8b5ab8cfa923edbefdd8cbfec82d6c1d4750913;p=youtube-dl
diff --git a/youtube_dl/extractor/bandcamp.py b/youtube_dl/extractor/bandcamp.py
index 886b0dfab..c13446665 100644
--- a/youtube_dl/extractor/bandcamp.py
+++ b/youtube_dl/extractor/bandcamp.py
@@ -12,66 +12,70 @@ from ..utils import (
class BandcampIE(InfoExtractor):
- _VALID_URL = r'http://.*?\.bandcamp\.com/track/(?P
.*)'
+ _VALID_URL = r'https?://.*?\.bandcamp\.com/track/(?P.*)'
_TESTS = [{
'url': 'http://youtube-dl.bandcamp.com/track/youtube-dl-test-song',
- 'file': '1812978515.mp3',
'md5': 'c557841d5e50261777a6585648adf439',
'info_dict': {
- "title": "youtube-dl \"'/\\\u00e4\u21ad - youtube-dl test song \"'/\\\u00e4\u21ad",
- "duration": 10,
+ 'id': '1812978515',
+ 'ext': 'mp3',
+ 'title': "youtube-dl \"'/\\\u00e4\u21ad - youtube-dl test song \"'/\\\u00e4\u21ad",
+ 'duration': 9.8485,
},
'_skip': 'There is a limit of 200 free downloads / month for the test song'
+ }, {
+ 'url': 'http://benprunty.bandcamp.com/track/lanius-battle',
+ 'md5': '2b68e5851514c20efdff2afc5603b8b4',
+ 'info_dict': {
+ 'id': '2650410135',
+ 'ext': 'mp3',
+ 'title': 'Lanius (Battle)',
+ 'uploader': 'Ben Prunty Music',
+ },
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
title = mobj.group('title')
webpage = self._download_webpage(url, title)
- # We get the link to the free download page
m_download = re.search(r'freeDownloadPage: "(.*?)"', webpage)
- if m_download is None:
+ if not m_download:
m_trackinfo = re.search(r'trackinfo: (.+),\s*?\n', webpage)
if m_trackinfo:
json_code = m_trackinfo.group(1)
- data = json.loads(json_code)
- d = data[0]
+ data = json.loads(json_code)[0]
- duration = int(round(d['duration']))
formats = []
- for format_id, format_url in d['file'].items():
- ext, _, abr_str = format_id.partition('-')
-
+ for format_id, format_url in data['file'].items():
+ ext, abr_str = format_id.split('-', 1)
formats.append({
'format_id': format_id,
'url': format_url,
- 'ext': format_id.partition('-')[0],
+ 'ext': ext,
'vcodec': 'none',
- 'acodec': format_id.partition('-')[0],
- 'abr': int(format_id.partition('-')[2]),
+ 'acodec': ext,
+ 'abr': int(abr_str),
})
self._sort_formats(formats)
return {
- 'id': compat_str(d['id']),
- 'title': d['title'],
+ 'id': compat_str(data['id']),
+ 'title': data['title'],
'formats': formats,
- 'duration': duration,
+ 'duration': float(data['duration']),
}
else:
raise ExtractorError('No free songs found')
download_link = m_download.group(1)
- video_id = re.search(
- r'var TralbumData = {(.*?)id: (?P\d*?)$',
- webpage, re.MULTILINE | re.DOTALL).group('id')
+ video_id = self._search_regex(
+ r'var TralbumData = {.*?id: (?P\d+),?$',
+ webpage, 'video id', flags=re.MULTILINE | re.DOTALL)
- download_webpage = self._download_webpage(download_link, video_id,
- 'Downloading free downloads page')
- # We get the dictionary of the track from some javascrip code
- info = re.search(r'items: (.*?),$',
- download_webpage, re.MULTILINE).group(1)
+ download_webpage = self._download_webpage(download_link, video_id, 'Downloading free downloads page')
+ # We get the dictionary of the track from some javascript code
+ info = re.search(r'items: (.*?),$', download_webpage, re.MULTILINE).group(1)
info = json.loads(info)[0]
# We pick mp3-320 for now, until format selection can be easily implemented.
mp3_info = info['downloads']['mp3-320']
@@ -100,9 +104,9 @@ class BandcampIE(InfoExtractor):
class BandcampAlbumIE(InfoExtractor):
IE_NAME = 'Bandcamp:album'
- _VALID_URL = r'http://.*?\.bandcamp\.com/album/(?P.*)'
+ _VALID_URL = r'https?://(?:(?P[^.]+)\.)?bandcamp\.com(?:/album/(?P[^?#]+))'
- _TEST = {
+ _TESTS = [{
'url': 'http://blazo.bandcamp.com/album/jazz-format-mixtape-vol-1',
'playlist': [
{
@@ -123,13 +127,21 @@ class BandcampAlbumIE(InfoExtractor):
'params': {
'playlistend': 2
},
- 'skip': 'Bancamp imposes download limits. See test_playlists:test_bandcamp_album for the playlist test'
- }
+ 'skip': 'Bandcamp imposes download limits. See test_playlists:test_bandcamp_album for the playlist test'
+ }, {
+ 'url': 'http://nightbringer.bandcamp.com/album/hierophany-of-the-open-grave',
+ 'info_dict': {
+ 'title': 'Hierophany of the Open Grave',
+ },
+ 'playlist_mincount': 9,
+ }]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
+ playlist_id = mobj.group('subdomain')
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'', webpage)
if not tracks_paths:
raise ExtractorError('The page doesn\'t contain any tracks')
@@ -139,6 +151,8 @@ class BandcampAlbumIE(InfoExtractor):
title = self._search_regex(r'album_title : "(.*?)"', webpage, 'title')
return {
'_type': 'playlist',
+ 'id': playlist_id,
+ 'display_id': display_id,
'title': title,
'entries': entries,
}