1 from __future__ import unicode_literals
6 from .common import InfoExtractor
18 class BandcampIE(InfoExtractor):
19 _VALID_URL = r'https?://.*?\.bandcamp\.com/track/(?P<title>.*)'
21 'url': 'http://youtube-dl.bandcamp.com/track/youtube-dl-test-song',
22 'md5': 'c557841d5e50261777a6585648adf439',
26 'title': "youtube-dl \"'/\\\u00e4\u21ad - youtube-dl test song \"'/\\\u00e4\u21ad",
29 '_skip': 'There is a limit of 200 free downloads / month for the test song'
31 'url': 'http://benprunty.bandcamp.com/track/lanius-battle',
32 'md5': '2b68e5851514c20efdff2afc5603b8b4',
36 'title': 'Lanius (Battle)',
37 'uploader': 'Ben Prunty Music',
41 def _real_extract(self, url):
42 mobj = re.match(self._VALID_URL, url)
43 title = mobj.group('title')
44 webpage = self._download_webpage(url, title)
45 m_download = re.search(r'freeDownloadPage: "(.*?)"', webpage)
47 m_trackinfo = re.search(r'trackinfo: (.+),\s*?\n', webpage)
49 json_code = m_trackinfo.group(1)
50 data = json.loads(json_code)[0]
53 for format_id, format_url in data['file'].items():
54 ext, abr_str = format_id.split('-', 1)
56 'format_id': format_id,
57 'url': self._proto_relative_url(format_url, 'http:'),
61 'abr': int_or_none(abr_str),
64 self._sort_formats(formats)
67 'id': compat_str(data['id']),
68 'title': data['title'],
70 'duration': float_or_none(data.get('duration')),
73 raise ExtractorError('No free songs found')
75 download_link = m_download.group(1)
76 video_id = self._search_regex(
77 r'(?ms)var TralbumData = .*?[{,]\s*id: (?P<id>\d+),?$',
80 download_webpage = self._download_webpage(download_link, video_id, 'Downloading free downloads page')
81 # We get the dictionary of the track from some javascript code
82 all_info = self._parse_json(self._search_regex(
83 r'(?sm)items: (.*?),$', download_webpage, 'items'), video_id)
85 # We pick mp3-320 for now, until format selection can be easily implemented.
86 mp3_info = info['downloads']['mp3-320']
87 # If we try to use this url it says the link has expired
88 initial_url = mp3_info['url']
90 r'(?P<server>http://(.*?)\.bandcamp\.com)/download/track\?enc=mp3-320&fsig=(?P<fsig>.*?)&id=(?P<id>.*?)&ts=(?P<ts>.*)$',
92 # We build the url we will use to get the final track url
93 # This url is build in Bandcamp in the script download_bunde_*.js
94 request_url = '%s/statdownload/track?enc=mp3-320&fsig=%s&id=%s&ts=%s&.rand=665028774616&.vrs=1' % (m_url.group('server'), m_url.group('fsig'), video_id, m_url.group('ts'))
95 final_url_webpage = self._download_webpage(request_url, video_id, 'Requesting download url')
96 # If we could correctly generate the .rand field the url would be
97 # in the "download_url" key
98 final_url = self._proto_relative_url(self._search_regex(
99 r'"retry_url":"(.+?)"', final_url_webpage, 'final video URL'), 'http:')
103 'title': info['title'],
107 'thumbnail': info.get('thumb_url'),
108 'uploader': info.get('artist'),
112 class BandcampAlbumIE(InfoExtractor):
113 IE_NAME = 'Bandcamp:album'
114 _VALID_URL = r'https?://(?:(?P<subdomain>[^.]+)\.)?bandcamp\.com(?:/album/(?P<album_id>[^?#]+)|/?(?:$|[?#]))'
117 'url': 'http://blazo.bandcamp.com/album/jazz-format-mixtape-vol-1',
120 'md5': '39bc1eded3476e927c724321ddf116cf',
128 'md5': '1a2c32e2691474643e912cc6cd4bffaa',
132 'title': 'Kero One - Keep It Alive (Blazo remix)',
137 'title': 'Jazz Format Mixtape vol.1',
138 'id': 'jazz-format-mixtape-vol-1',
139 'uploader_id': 'blazo',
144 'skip': 'Bandcamp imposes download limits.'
146 'url': 'http://nightbringer.bandcamp.com/album/hierophany-of-the-open-grave',
148 'title': 'Hierophany of the Open Grave',
149 'uploader_id': 'nightbringer',
150 'id': 'hierophany-of-the-open-grave',
152 'playlist_mincount': 9,
154 'url': 'http://dotscale.bandcamp.com',
158 'uploader_id': 'dotscale',
160 'playlist_mincount': 7,
163 def _real_extract(self, url):
164 mobj = re.match(self._VALID_URL, url)
165 uploader_id = mobj.group('subdomain')
166 album_id = mobj.group('album_id')
167 playlist_id = album_id or uploader_id
168 webpage = self._download_webpage(url, playlist_id)
169 tracks_paths = re.findall(r'<a href="(.*?)" itemprop="url">', webpage)
171 raise ExtractorError('The page doesn\'t contain any tracks')
173 self.url_result(compat_urlparse.urljoin(url, t_path), ie=BandcampIE.ie_key())
174 for t_path in tracks_paths]
175 title = self._search_regex(
176 r'album_title\s*:\s*"(.*?)"', webpage, 'title', fatal=False)
179 'uploader_id': uploader_id,