]>
jfr.im git - yt-dlp.git/blob - youtube_dl/extractor/bandcamp.py
1 from __future__
import unicode_literals
8 from .common
import InfoExtractor
23 class BandcampIE(InfoExtractor
):
24 _VALID_URL
= r
'https?://.*?\.bandcamp\.com/track/(?P<title>.*)'
26 'url': 'http://youtube-dl.bandcamp.com/track/youtube-dl-test-song',
27 'md5': 'c557841d5e50261777a6585648adf439',
31 'title': "youtube-dl \"'/\\\u00e4\u21ad - youtube-dl test song \"'/\\\u00e4\u21ad",
34 '_skip': 'There is a limit of 200 free downloads / month for the test song'
36 'url': 'http://benprunty.bandcamp.com/track/lanius-battle',
37 'md5': '73d0b3171568232574e45652f8720b5c',
41 'title': 'Lanius (Battle)',
42 'uploader': 'Ben Prunty Music',
46 def _real_extract(self
, url
):
47 mobj
= re
.match(self
._VALID
_URL
, url
)
48 title
= mobj
.group('title')
49 webpage
= self
._download
_webpage
(url
, title
)
50 m_download
= re
.search(r
'freeDownloadPage: "(.*?)"', webpage
)
52 m_trackinfo
= re
.search(r
'trackinfo: (.+),\s*?\n', webpage
)
54 json_code
= m_trackinfo
.group(1)
55 data
= json
.loads(json_code
)[0]
56 track_id
= compat_str(data
['id'])
58 if not data
.get('file'):
59 raise ExtractorError('Not streamable', video_id
=track_id
, expected
=True)
62 for format_id
, format_url
in data
['file'].items():
63 ext
, abr_str
= format_id
.split('-', 1)
65 'format_id': format_id
,
66 'url': self
._proto
_relative
_url
(format_url
, 'http:'),
70 'abr': int_or_none(abr_str
),
73 self
._sort
_formats
(formats
)
77 'title': data
['title'],
79 'duration': float_or_none(data
.get('duration')),
82 raise ExtractorError('No free songs found')
84 download_link
= m_download
.group(1)
85 video_id
= self
._search
_regex
(
86 r
'(?ms)var TralbumData = .*?[{,]\s*id: (?P<id>\d+),?$',
89 download_webpage
= self
._download
_webpage
(
90 download_link
, video_id
, 'Downloading free downloads page')
92 blob
= self
._parse
_json
(
94 r
'data-blob=(["\'])(?P
<blob
>{.+?}
)\
1', download_webpage,
95 'blob
', group='blob
'),
96 video_id, transform_source=unescapeHTML)
98 info = blob['digital_items
'][0]
100 downloads = info['downloads
']
101 track = info['title
']
103 artist = info.get('artist
')
104 title = '%s - %s' % (artist, track) if artist else track
106 download_formats = {}
107 for f in blob['download_formats
']:
108 name, ext = f.get('name
'), f.get('file_extension
')
109 if all(isinstance(x, compat_str) for x in (name, ext)):
110 download_formats[name] = ext.strip('.')
113 for format_id, f in downloads.items():
114 format_url = f.get('url
')
117 # Stat URL generation algorithm is reverse engineered from
118 # download_*_bundle_*.js
119 stat_url = update_url_query(
120 format_url.replace('/download
/', '/statdownload
/'), {
121 '.rand
': int(time.time() * 1000 * random.random()),
123 format_id = f.get('encoding_name
') or format_id
124 stat = self._download_json(
125 stat_url, video_id, 'Downloading
%s JSON
' % format_id,
126 transform_source=lambda s: s[s.index('{'):s.rindex('}
') + 1],
130 retry_url = stat.get('retry_url
')
131 if not isinstance(retry_url, compat_str):
134 'url
': self._proto_relative_url(retry_url, 'http
:'),
135 'ext
': download_formats.get(format_id),
136 'format_id
': format_id,
137 'format_note
': f.get('description
'),
138 'filesize
': parse_filesize(f.get('size_mb
')),
141 self._sort_formats(formats)
146 'thumbnail
': info.get('thumb_url
'),
147 'uploader
': info.get('artist
'),
154 class BandcampAlbumIE(InfoExtractor):
155 IE_NAME = 'Bandcamp
:album
'
156 _VALID_URL = r'https?
://(?
:(?P
<subdomain
>[^
.]+)\
.)?bandcamp\
.com(?
:/album
/(?P
<album_id
>[^?
#]+)|/?(?:$|[?#]))'
159 'url': 'http://blazo.bandcamp.com/album/jazz-format-mixtape-vol-1',
162 'md5': '39bc1eded3476e927c724321ddf116cf',
170 'md5': '1a2c32e2691474643e912cc6cd4bffaa',
174 'title': 'Kero One - Keep It Alive (Blazo remix)',
179 'title': 'Jazz Format Mixtape vol.1',
180 'id': 'jazz-format-mixtape-vol-1',
181 'uploader_id': 'blazo',
186 'skip': 'Bandcamp imposes download limits.'
188 'url': 'http://nightbringer.bandcamp.com/album/hierophany-of-the-open-grave',
190 'title': 'Hierophany of the Open Grave',
191 'uploader_id': 'nightbringer',
192 'id': 'hierophany-of-the-open-grave',
194 'playlist_mincount': 9,
196 'url': 'http://dotscale.bandcamp.com',
200 'uploader_id': 'dotscale',
202 'playlist_mincount': 7,
204 # with escaped quote in title
205 'url': 'https://jstrecords.bandcamp.com/album/entropy-ep',
207 'title': '"Entropy" EP',
208 'uploader_id': 'jstrecords',
211 'playlist_mincount': 3,
214 def _real_extract(self
, url
):
215 mobj
= re
.match(self
._VALID
_URL
, url
)
216 uploader_id
= mobj
.group('subdomain')
217 album_id
= mobj
.group('album_id')
218 playlist_id
= album_id
or uploader_id
219 webpage
= self
._download
_webpage
(url
, playlist_id
)
220 tracks_paths
= re
.findall(r
'<a href="(.*?)" itemprop="url">', webpage
)
222 raise ExtractorError('The page doesn\'t contain any tracks')
224 self
.url_result(compat_urlparse
.urljoin(url
, t_path
), ie
=BandcampIE
.ie_key())
225 for t_path
in tracks_paths
]
226 title
= self
._html
_search
_regex
(
227 r
'album_title\s*:\s*"((?:\\.|[^"\\])+?)"',
228 webpage
, 'title', fatal
=False)
230 title
= title
.replace(r
'\"', '"')
233 'uploader_id': uploader_id
,