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': '73d0b3171568232574e45652f8720b5c',
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]
51 track_id = compat_str(data['id'])
53 if not data.get('file'):
54 raise ExtractorError('Not streamable', video_id=track_id, expected=True)
57 for format_id, format_url in data['file'].items():
58 ext, abr_str = format_id.split('-', 1)
60 'format_id': format_id,
61 'url': self._proto_relative_url(format_url, 'http:'),
65 'abr': int_or_none(abr_str),
68 self._sort_formats(formats)
72 'title': data['title'],
74 'duration': float_or_none(data.get('duration')),
77 raise ExtractorError('No free songs found')
79 download_link = m_download.group(1)
80 video_id = self._search_regex(
81 r'(?ms)var TralbumData = .*?[{,]\s*id: (?P<id>\d+),?$',
84 download_webpage = self._download_webpage(download_link, video_id, 'Downloading free downloads page')
85 # We get the dictionary of the track from some javascript code
86 all_info = self._parse_json(self._search_regex(
87 r'(?sm)items: (.*?),$', download_webpage, 'items'), video_id)
89 # We pick mp3-320 for now, until format selection can be easily implemented.
90 mp3_info = info['downloads']['mp3-320']
91 # If we try to use this url it says the link has expired
92 initial_url = mp3_info['url']
94 r'(?P<server>http://(.*?)\.bandcamp\.com)/download/track\?enc=mp3-320&fsig=(?P<fsig>.*?)&id=(?P<id>.*?)&ts=(?P<ts>.*)$',
96 # We build the url we will use to get the final track url
97 # This url is build in Bandcamp in the script download_bunde_*.js
98 request_url = '%s/statdownload/track?enc=mp3-320&fsig=%s&id=%s&ts=%s&.rand=665028774616&.vrs=1' % (m_url.group('server'), m_url.group('fsig'), video_id, m_url.group('ts'))
99 final_url_webpage = self._download_webpage(request_url, video_id, 'Requesting download url')
100 # If we could correctly generate the .rand field the url would be
101 # in the "download_url" key
102 final_url = self._proto_relative_url(self._search_regex(
103 r'"retry_url":"(.+?)"', final_url_webpage, 'final video URL'), 'http:')
107 'title': info['title'],
111 'thumbnail': info.get('thumb_url'),
112 'uploader': info.get('artist'),
116 class BandcampAlbumIE(InfoExtractor):
117 IE_NAME = 'Bandcamp:album'
118 _VALID_URL = r'https?://(?:(?P<subdomain>[^.]+)\.)?bandcamp\.com(?:/album/(?P<album_id>[^?#]+)|/?(?:$|[?#]))'
121 'url': 'http://blazo.bandcamp.com/album/jazz-format-mixtape-vol-1',
124 'md5': '39bc1eded3476e927c724321ddf116cf',
132 'md5': '1a2c32e2691474643e912cc6cd4bffaa',
136 'title': 'Kero One - Keep It Alive (Blazo remix)',
141 'title': 'Jazz Format Mixtape vol.1',
142 'id': 'jazz-format-mixtape-vol-1',
143 'uploader_id': 'blazo',
148 'skip': 'Bandcamp imposes download limits.'
150 'url': 'http://nightbringer.bandcamp.com/album/hierophany-of-the-open-grave',
152 'title': 'Hierophany of the Open Grave',
153 'uploader_id': 'nightbringer',
154 'id': 'hierophany-of-the-open-grave',
156 'playlist_mincount': 9,
158 'url': 'http://dotscale.bandcamp.com',
162 'uploader_id': 'dotscale',
164 'playlist_mincount': 7,
166 # with escaped quote in title
167 'url': 'https://jstrecords.bandcamp.com/album/entropy-ep',
169 'title': '"Entropy" EP',
170 'uploader_id': 'jstrecords',
173 'playlist_mincount': 3,
176 def _real_extract(self, url):
177 mobj = re.match(self._VALID_URL, url)
178 uploader_id = mobj.group('subdomain')
179 album_id = mobj.group('album_id')
180 playlist_id = album_id or uploader_id
181 webpage = self._download_webpage(url, playlist_id)
182 tracks_paths = re.findall(r'<a href="(.*?)" itemprop="url">', webpage)
184 raise ExtractorError('The page doesn\'t contain any tracks')
186 self.url_result(compat_urlparse.urljoin(url, t_path), ie=BandcampIE.ie_key())
187 for t_path in tracks_paths]
188 title = self._html_search_regex(
189 r'album_title\s*:\s*"((?:\\.|[^"\\])+?)"',
190 webpage, 'title', fatal=False)
192 title = title.replace(r'\"', '"')
195 'uploader_id': uploader_id,