2 from __future__
import unicode_literals
8 from .common
import InfoExtractor
9 from ..compat
import compat_str
26 class BandcampIE(InfoExtractor
):
27 _VALID_URL
= r
'https?://[^/]+\.bandcamp\.com/track/(?P<id>[^/?#&]+)'
29 'url': 'http://youtube-dl.bandcamp.com/track/youtube-dl-test-song',
30 'md5': 'c557841d5e50261777a6585648adf439',
34 'title': "youtube-dl \"'/\\ä↭ - youtube-dl \"'/\\ä↭ - youtube-dl test song \"'/\\ä↭",
36 'uploader': 'youtube-dl "\'/\\ä↭',
37 'upload_date': '20121129',
38 'timestamp': 1354224127,
40 '_skip': 'There is a limit of 200 free downloads / month for the test song'
43 'url': 'http://benprunty.bandcamp.com/track/lanius-battle',
47 'title': 'Ben Prunty - Lanius (Battle)',
48 'thumbnail': r
're:^https?://.*\.jpg$',
49 'uploader': 'Ben Prunty',
50 'timestamp': 1396508491,
51 'upload_date': '20140403',
52 'release_date': '20140403',
54 'track': 'Lanius (Battle)',
56 'track_id': '2650410135',
57 'artist': 'Ben Prunty',
58 'album': 'FTL: Advanced Edition Soundtrack',
61 # no free download, mp3 128
62 'url': 'https://relapsealumni.bandcamp.com/track/hail-to-fire',
63 'md5': 'fec12ff55e804bb7f7ebeb77a800c8b7',
67 'title': 'Mastodon - Hail to Fire',
68 'thumbnail': r
're:^https?://.*\.jpg$',
69 'uploader': 'Mastodon',
70 'timestamp': 1322005399,
71 'upload_date': '20111122',
72 'release_date': '20040207',
74 'track': 'Hail to Fire',
76 'track_id': '2584466013',
78 'album': 'Call of the Mastodon',
82 def _extract_data_attr(self
, webpage
, video_id
, attr
='tralbum', fatal
=True):
83 return self
._parse
_json
(self
._html
_search
_regex
(
84 r
'data-%s=(["\'])({.+?}
)\
1' % attr, webpage,
85 attr + ' data
', group=2), video_id, fatal=fatal)
87 def _real_extract(self, url):
88 title = self._match_id(url)
89 webpage = self._download_webpage(url, title)
90 tralbum = self._extract_data_attr(webpage, title)
91 thumbnail = self._og_search_thumbnail(webpage)
99 track_info = try_get(tralbum, lambda x: x['trackinfo
'][0], dict)
101 file_ = track_info.get('file')
102 if isinstance(file_, dict):
103 for format_id, format_url in file_.items():
104 if not url_or_none(format_url):
106 ext, abr_str = format_id.split('-', 1)
108 'format_id
': format_id,
109 'url
': self._proto_relative_url(format_url, 'http
:'),
113 'abr
': int_or_none(abr_str),
115 track = track_info.get('title
')
116 track_id = str_or_none(
117 track_info.get('track_id
') or track_info.get('id'))
118 track_number = int_or_none(track_info.get('track_num
'))
119 duration = float_or_none(track_info.get('duration
'))
121 embed = self._extract_data_attr(webpage, title, 'embed
', False)
122 current = tralbum.get('current
') or {}
123 artist = embed.get('artist
') or current.get('artist
') or tralbum.get('artist
')
124 timestamp = unified_timestamp(
125 current.get('publish_date
') or tralbum.get('album_publish_date
'))
127 download_link = tralbum.get('freeDownloadPage
')
129 track_id = compat_str(tralbum['id'])
131 download_webpage = self._download_webpage(
132 download_link, track_id, 'Downloading free downloads page
')
134 blob = self._extract_data_attr(download_webpage, track_id, 'blob
')
137 blob, (lambda x: x['digital_items
'][0],
138 lambda x: x['download_items
'][0]), dict)
140 downloads = info.get('downloads
')
141 if isinstance(downloads, dict):
143 track = info.get('title
')
145 artist = info.get('artist
')
147 thumbnail = info.get('thumb_url
')
149 download_formats = {}
150 download_formats_list = blob.get('download_formats
')
151 if isinstance(download_formats_list, list):
152 for f in blob['download_formats
']:
153 name, ext = f.get('name
'), f.get('file_extension
')
154 if all(isinstance(x, compat_str) for x in (name, ext)):
155 download_formats[name] = ext.strip('.')
157 for format_id, f in downloads.items():
158 format_url = f.get('url
')
161 # Stat URL generation algorithm is reverse engineered from
162 # download_*_bundle_*.js
163 stat_url = update_url_query(
164 format_url.replace('/download
/', '/statdownload
/'), {
165 '.rand
': int(time.time() * 1000 * random.random()),
167 format_id = f.get('encoding_name
') or format_id
168 stat = self._download_json(
169 stat_url, track_id, 'Downloading
%s JSON
' % format_id,
170 transform_source=lambda s: s[s.index('{'):s.rindex('}
') + 1],
174 retry_url = url_or_none(stat.get('retry_url
'))
178 'url
': self._proto_relative_url(retry_url, 'http
:'),
179 'ext
': download_formats.get(format_id),
180 'format_id
': format_id,
181 'format_note
': f.get('description
'),
182 'filesize
': parse_filesize(f.get('size_mb
')),
186 self._sort_formats(formats)
188 title = '%s - %s' % (artist, track) if artist else track
191 duration = float_or_none(self._html_search_meta(
192 'duration
', webpage, default=None))
197 'thumbnail
': thumbnail,
199 'timestamp
': timestamp,
200 'release_date
': unified_strdate(tralbum.get('album_release_date
')),
201 'duration
': duration,
203 'track_number
': track_number,
204 'track_id
': track_id,
206 'album
': embed.get('album_title
'),
211 class BandcampAlbumIE(BandcampIE):
212 IE_NAME = 'Bandcamp
:album
'
213 _VALID_URL = r'https?
://(?
:(?P
<subdomain
>[^
.]+)\
.)?bandcamp\
.com(?
:/album
/(?P
<id>[^
/?
#&]+))?'
216 'url': 'http://blazo.bandcamp.com/album/jazz-format-mixtape-vol-1',
219 'md5': '39bc1eded3476e927c724321ddf116cf',
223 'title': 'Blazo - Intro',
224 'timestamp': 1311756226,
225 'upload_date': '20110727',
230 'md5': '1a2c32e2691474643e912cc6cd4bffaa',
234 'title': 'Blazo - Kero One - Keep It Alive (Blazo remix)',
235 'timestamp': 1311757238,
236 'upload_date': '20110727',
242 'title': 'Jazz Format Mixtape vol.1',
243 'id': 'jazz-format-mixtape-vol-1',
244 'uploader_id': 'blazo',
249 'skip': 'Bandcamp imposes download limits.'
251 'url': 'http://nightbringer.bandcamp.com/album/hierophany-of-the-open-grave',
253 'title': 'Hierophany of the Open Grave',
254 'uploader_id': 'nightbringer',
255 'id': 'hierophany-of-the-open-grave',
257 'playlist_mincount': 9,
259 'url': 'http://dotscale.bandcamp.com',
263 'uploader_id': 'dotscale',
265 'playlist_mincount': 7,
267 # with escaped quote in title
268 'url': 'https://jstrecords.bandcamp.com/album/entropy-ep',
270 'title': '"Entropy" EP',
271 'uploader_id': 'jstrecords',
273 'description': 'md5:0ff22959c943622972596062f2f366a5',
275 'playlist_mincount': 3,
277 # not all tracks have songs
278 'url': 'https://insulters.bandcamp.com/album/we-are-the-plague',
280 'id': 'we-are-the-plague',
281 'title': 'WE ARE THE PLAGUE',
282 'uploader_id': 'insulters',
283 'description': 'md5:b3cf845ee41b2b1141dc7bde9237255f',
289 def suitable(cls
, url
):
291 if BandcampWeeklyIE
.suitable(url
) or BandcampIE
.suitable(url
)
292 else super(BandcampAlbumIE
, cls
).suitable(url
))
294 def _real_extract(self
, url
):
295 uploader_id
, album_id
= re
.match(self
._VALID
_URL
, url
).groups()
296 playlist_id
= album_id
or uploader_id
297 webpage
= self
._download
_webpage
(url
, playlist_id
)
298 tralbum
= self
._extract
_data
_attr
(webpage
, playlist_id
)
299 track_info
= tralbum
.get('trackinfo')
301 raise ExtractorError('The page doesn\'t contain any tracks')
302 # Only tracks with duration info have songs
305 urljoin(url
, t
['title_link']), BandcampIE
.ie_key(),
306 str_or_none(t
.get('track_id') or t
.get('id')), t
.get('title'))
308 if t
.get('duration')]
310 current
= tralbum
.get('current') or {}
314 'uploader_id': uploader_id
,
316 'title': current
.get('title'),
317 'description': current
.get('about'),
322 class BandcampWeeklyIE(BandcampIE
):
323 IE_NAME
= 'Bandcamp:weekly'
324 _VALID_URL
= r
'https?://(?:www\.)?bandcamp\.com/?\?(?:.*?&)?show=(?P<id>\d+)'
326 'url': 'https://bandcamp.com/?show=224',
327 'md5': 'b00df799c733cf7e0c567ed187dea0fd',
331 'title': 'BC Weekly April 4th 2017 - Magic Moments',
332 'description': 'md5:5d48150916e8e02d030623a48512c874',
334 'release_date': '20170404',
335 'series': 'Bandcamp Weekly',
336 'episode': 'Magic Moments',
343 'url': 'https://bandcamp.com/?blah/blah@&show=228',
344 'only_matching': True
347 def _real_extract(self
, url
):
348 show_id
= self
._match
_id
(url
)
349 webpage
= self
._download
_webpage
(url
, show_id
)
351 blob
= self
._extract
_data
_attr
(webpage
, show_id
, 'blob')
353 show
= blob
['bcw_data'][show_id
]
356 for format_id
, format_url
in show
['audio_stream'].items():
357 if not url_or_none(format_url
):
359 for known_ext
in KNOWN_EXTENSIONS
:
360 if known_ext
in format_id
:
366 'format_id': format_id
,
371 self
._sort
_formats
(formats
)
373 title
= show
.get('audio_title') or 'Bandcamp Weekly'
374 subtitle
= show
.get('subtitle')
376 title
+= ' - %s' % subtitle
381 'description': show
.get('desc') or show
.get('short_desc'),
382 'duration': float_or_none(show
.get('audio_duration')),
384 'release_date': unified_strdate(show
.get('published_date')),
385 'series': 'Bandcamp Weekly',
386 'episode': show
.get('subtitle'),
387 'episode_id': show_id
,