]>
Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/bandcamp.py
1 from __future__
import unicode_literals
8 from .common
import InfoExtractor
25 class BandcampIE(InfoExtractor
):
26 _VALID_URL
= r
'https?://.*?\.bandcamp\.com/track/(?P<title>[^/?#&]+)'
28 'url': 'http://youtube-dl.bandcamp.com/track/youtube-dl-test-song',
29 'md5': 'c557841d5e50261777a6585648adf439',
33 'title': "youtube-dl \"'/\\\u00e4\u21ad - youtube-dl test song \"'/\\\u00e4\u21ad",
36 '_skip': 'There is a limit of 200 free downloads / month for the test song'
38 'url': 'http://benprunty.bandcamp.com/track/lanius-battle',
39 'md5': '0369ace6b939f0927e62c67a1a8d9fa7',
43 'title': 'Ben Prunty - Lanius (Battle)',
44 'uploader': 'Ben Prunty',
48 def _real_extract(self
, url
):
49 mobj
= re
.match(self
._VALID
_URL
, url
)
50 title
= mobj
.group('title')
51 webpage
= self
._download
_webpage
(url
, title
)
52 thumbnail
= self
._html
_search
_meta
('og:image', webpage
, default
=None)
53 m_download
= re
.search(r
'freeDownloadPage: "(.*?)"', webpage
)
55 m_trackinfo
= re
.search(r
'trackinfo: (.+),\s*?\n', webpage
)
57 json_code
= m_trackinfo
.group(1)
58 data
= json
.loads(json_code
)[0]
59 track_id
= compat_str(data
['id'])
61 if not data
.get('file'):
62 raise ExtractorError('Not streamable', video_id
=track_id
, expected
=True)
65 for format_id
, format_url
in data
['file'].items():
66 ext
, abr_str
= format_id
.split('-', 1)
68 'format_id': format_id
,
69 'url': self
._proto
_relative
_url
(format_url
, 'http:'),
73 'abr': int_or_none(abr_str
),
76 self
._sort
_formats
(formats
)
80 'title': data
['title'],
81 'thumbnail': thumbnail
,
83 'duration': float_or_none(data
.get('duration')),
86 raise ExtractorError('No free songs found')
88 download_link
= m_download
.group(1)
89 video_id
= self
._search
_regex
(
90 r
'(?ms)var TralbumData = .*?[{,]\s*id: (?P<id>\d+),?$',
93 download_webpage
= self
._download
_webpage
(
94 download_link
, video_id
, 'Downloading free downloads page')
96 blob
= self
._parse
_json
(
98 r
'data-blob=(["\'])(?P
<blob
>{.+?
})\
1', download_webpage,
99 'blob
', group='blob
'),
100 video_id, transform_source=unescapeHTML)
102 info = blob['digital_items
'][0]
104 downloads = info['downloads
']
105 track = info['title
']
107 artist = info.get('artist
')
108 title = '%s - %s' % (artist, track) if artist else track
110 download_formats = {}
111 for f in blob['download_formats
']:
112 name, ext = f.get('name
'), f.get('file_extension
')
113 if all(isinstance(x, compat_str) for x in (name, ext)):
114 download_formats[name] = ext.strip('.')
117 for format_id, f in downloads.items():
118 format_url = f.get('url
')
121 # Stat URL generation algorithm is reverse engineered from
122 # download_*_bundle_*.js
123 stat_url = update_url_query(
124 format_url.replace('/download
/', '/statdownload
/'), {
125 '.rand
': int(time.time() * 1000 * random.random()),
127 format_id = f.get('encoding_name
') or format_id
128 stat = self._download_json(
129 stat_url, video_id, 'Downloading
%s JSON
' % format_id,
130 transform_source=lambda s: s[s.index('{'):s.rindex('}') + 1],
134 retry_url = stat.get('retry_url
')
135 if not isinstance(retry_url, compat_str):
138 'url
': self._proto_relative_url(retry_url, 'http
:'),
139 'ext
': download_formats.get(format_id),
140 'format_id
': format_id,
141 'format_note
': f.get('description
'),
142 'filesize
': parse_filesize(f.get('size_mb
')),
145 self._sort_formats(formats)
150 'thumbnail
': info.get('thumb_url
') or thumbnail,
151 'uploader
': info.get('artist
'),
158 class BandcampAlbumIE(InfoExtractor):
159 IE_NAME = 'Bandcamp
:album
'
160 _VALID_URL = r'https?
://(?
:(?P
<subdomain
>[^
.]+)\
.)?bandcamp\
.com(?
:/album
/(?P
<album_id
>[^
/?
#&]+))?'
163 'url': 'http://blazo.bandcamp.com/album/jazz-format-mixtape-vol-1',
166 'md5': '39bc1eded3476e927c724321ddf116cf',
174 'md5': '1a2c32e2691474643e912cc6cd4bffaa',
178 'title': 'Kero One - Keep It Alive (Blazo remix)',
183 'title': 'Jazz Format Mixtape vol.1',
184 'id': 'jazz-format-mixtape-vol-1',
185 'uploader_id': 'blazo',
190 'skip': 'Bandcamp imposes download limits.'
192 'url': 'http://nightbringer.bandcamp.com/album/hierophany-of-the-open-grave',
194 'title': 'Hierophany of the Open Grave',
195 'uploader_id': 'nightbringer',
196 'id': 'hierophany-of-the-open-grave',
198 'playlist_mincount': 9,
200 'url': 'http://dotscale.bandcamp.com',
204 'uploader_id': 'dotscale',
206 'playlist_mincount': 7,
208 # with escaped quote in title
209 'url': 'https://jstrecords.bandcamp.com/album/entropy-ep',
211 'title': '"Entropy" EP',
212 'uploader_id': 'jstrecords',
215 'playlist_mincount': 3,
217 # not all tracks have songs
218 'url': 'https://insulters.bandcamp.com/album/we-are-the-plague',
220 'id': 'we-are-the-plague',
221 'title': 'WE ARE THE PLAGUE',
222 'uploader_id': 'insulters',
228 def suitable(cls
, url
):
230 if BandcampWeeklyIE
.suitable(url
) or BandcampIE
.suitable(url
)
231 else super(BandcampAlbumIE
, cls
).suitable(url
))
233 def _real_extract(self
, url
):
234 mobj
= re
.match(self
._VALID
_URL
, url
)
235 uploader_id
= mobj
.group('subdomain')
236 album_id
= mobj
.group('album_id')
237 playlist_id
= album_id
or uploader_id
238 webpage
= self
._download
_webpage
(url
, playlist_id
)
239 track_elements
= re
.findall(
240 r
'(?s)<div[^>]*>(.*?<a[^>]+href="([^"]+?)"[^>]+itemprop="url"[^>]*>.*?)</div>', webpage
)
241 if not track_elements
:
242 raise ExtractorError('The page doesn\'t contain any tracks')
243 # Only tracks with duration info have songs
246 compat_urlparse
.urljoin(url
, t_path
),
247 ie
=BandcampIE
.ie_key(),
248 video_title
=self
._search
_regex
(
249 r
'<span\b[^>]+\bitemprop=["\']name
["\'][^>]*>([^<]+)',
250 elem_content, 'track title', fatal=False))
251 for elem_content, t_path in track_elements
252 if self._html_search_meta('duration', elem_content, default=None)]
254 title = self._html_search_regex(
255 r'album_title\s*:\s*"((?
:\\.|
[^
"\\])+?)"',
256 webpage, 'title
', fatal=False)
258 title = title.replace(r'\"', '"')
261 'uploader_id': uploader_id,
268 class BandcampWeeklyIE(InfoExtractor):
269 IE_NAME = 'Bandcamp:weekly'
270 _VALID_URL = r'https?://(?:www\.)?bandcamp\.com/?\?(?:.*?&)?show=(?P<id>\d+)'
272 'url': 'https://bandcamp.com/?show=224',
273 'md5': 'b00df799c733cf7e0c567ed187dea0fd',
277 'title': 'BC Weekly April 4th 2017 - Magic Moments',
278 'description': 'md5:5d48150916e8e02d030623a48512c874',
280 'release_date': '20170404',
281 'series': 'Bandcamp Weekly',
282 'episode': 'Magic Moments',
283 'episode_number': 208,
287 'url': 'https://bandcamp.com/?blah/blah@&show=228',
288 'only_matching': True
291 def _real_extract(self, url):
292 video_id = self._match_id(url)
293 webpage = self._download_webpage(url, video_id)
295 blob = self._parse_json(
297 r'data-blob=(["\'])(?P
<blob
>{.+?
})\
1', webpage,
298 'blob
', group='blob
'),
299 video_id, transform_source=unescapeHTML)
301 show = blob['bcw_show
']
303 # This is desired because any invalid show id redirects to `bandcamp.com`
304 # which happens to expose the latest Bandcamp Weekly episode.
305 show_id = int_or_none(show.get('show_id
')) or int_or_none(video_id)
308 for format_id, format_url in show['audio_stream
'].items():
309 if not isinstance(format_url, compat_str):
311 for known_ext in KNOWN_EXTENSIONS:
312 if known_ext in format_id:
318 'format_id
': format_id,
323 self._sort_formats(formats)
325 title = show.get('audio_title
') or 'Bandcamp Weekly
'
326 subtitle = show.get('subtitle
')
328 title += ' - %s' % subtitle
330 episode_number = None
331 seq = blob.get('bcw_seq
')
333 if seq and isinstance(seq, list):
335 episode_number = next(
336 int_or_none(e.get('episode_number
'))
338 if isinstance(e, dict) and int_or_none(e.get('id')) == show_id)
339 except StopIteration:
345 'description
': show.get('desc
') or show.get('short_desc
'),
346 'duration
': float_or_none(show.get('audio_duration
')),
348 'release_date
': unified_strdate(show.get('published_date
')),
349 'series
': 'Bandcamp Weekly
',
350 'episode
': show.get('subtitle
'),
351 'episode_number
': episode_number,
352 'episode_id
': compat_str(video_id),