]>
Commit | Line | Data |
---|---|---|
0aacd2de | 1 | import random |
45aef472 | 2 | import re |
0aacd2de | 3 | import time |
45aef472 PH |
4 | |
5 | from .common import InfoExtractor | |
8bdd16b4 | 6 | from ..compat import compat_str |
1cc79574 | 7 | from ..utils import ( |
45aef472 | 8 | ExtractorError, |
ba717dca S |
9 | float_or_none, |
10 | int_or_none, | |
6d923aab | 11 | KNOWN_EXTENSIONS, |
0aacd2de | 12 | parse_filesize, |
4991e16c S |
13 | str_or_none, |
14 | try_get, | |
0aacd2de | 15 | update_url_query, |
62bafabc | 16 | unified_strdate, |
4991e16c | 17 | unified_timestamp, |
3052a30d | 18 | url_or_none, |
8bdd16b4 | 19 | urljoin, |
45aef472 PH |
20 | ) |
21 | ||
22 | ||
8bdd16b4 | 23 | class BandcampIE(InfoExtractor): |
24 | _VALID_URL = r'https?://[^/]+\.bandcamp\.com/track/(?P<id>[^/?#&]+)' | |
bfd973ec | 25 | _EMBED_REGEX = [r'<meta property="og:url"[^>]*?content="(?P<url>.*?bandcamp\.com.*?)"'] |
cffa6aa1 | 26 | _TESTS = [{ |
3467b3e2 | 27 | 'url': 'http://youtube-dl.bandcamp.com/track/youtube-dl-test-song', |
3798eadc PH |
28 | 'md5': 'c557841d5e50261777a6585648adf439', |
29 | 'info_dict': { | |
d9bf4652 S |
30 | 'id': '1812978515', |
31 | 'ext': 'mp3', | |
8bdd16b4 | 32 | 'title': "youtube-dl \"'/\\ä↭ - youtube-dl \"'/\\ä↭ - youtube-dl test song \"'/\\ä↭", |
d9bf4652 | 33 | 'duration': 9.8485, |
8bdd16b4 | 34 | 'uploader': 'youtube-dl "\'/\\ä↭', |
3a379e5e | 35 | 'upload_date': '20121129', |
8bdd16b4 | 36 | 'timestamp': 1354224127, |
6f5ac90c | 37 | }, |
3798eadc | 38 | '_skip': 'There is a limit of 200 free downloads / month for the test song' |
d9bf4652 | 39 | }, { |
4991e16c | 40 | # free download |
d9bf4652 | 41 | 'url': 'http://benprunty.bandcamp.com/track/lanius-battle', |
d9bf4652 S |
42 | 'info_dict': { |
43 | 'id': '2650410135', | |
0f63dc24 TF |
44 | 'ext': 'aiff', |
45 | 'title': 'Ben Prunty - Lanius (Battle)', | |
4991e16c | 46 | 'thumbnail': r're:^https?://.*\.jpg$', |
0f63dc24 | 47 | 'uploader': 'Ben Prunty', |
4991e16c S |
48 | 'timestamp': 1396508491, |
49 | 'upload_date': '20140403', | |
10db0d2f | 50 | 'release_timestamp': 1396483200, |
4991e16c S |
51 | 'release_date': '20140403', |
52 | 'duration': 260.877, | |
53 | 'track': 'Lanius (Battle)', | |
54 | 'track_number': 1, | |
55 | 'track_id': '2650410135', | |
56 | 'artist': 'Ben Prunty', | |
57 | 'album': 'FTL: Advanced Edition Soundtrack', | |
d9bf4652 | 58 | }, |
14b7a24c | 59 | }, { |
4991e16c | 60 | # no free download, mp3 128 |
14b7a24c | 61 | 'url': 'https://relapsealumni.bandcamp.com/track/hail-to-fire', |
4991e16c | 62 | 'md5': 'fec12ff55e804bb7f7ebeb77a800c8b7', |
14b7a24c PV |
63 | 'info_dict': { |
64 | 'id': '2584466013', | |
65 | 'ext': 'mp3', | |
4991e16c S |
66 | 'title': 'Mastodon - Hail to Fire', |
67 | 'thumbnail': r're:^https?://.*\.jpg$', | |
68 | 'uploader': 'Mastodon', | |
69 | 'timestamp': 1322005399, | |
70 | 'upload_date': '20111122', | |
10db0d2f | 71 | 'release_timestamp': 1076112000, |
4991e16c S |
72 | 'release_date': '20040207', |
73 | 'duration': 120.79, | |
74 | 'track': 'Hail to Fire', | |
14b7a24c | 75 | 'track_number': 5, |
4991e16c S |
76 | 'track_id': '2584466013', |
77 | 'artist': 'Mastodon', | |
78 | 'album': 'Call of the Mastodon', | |
14b7a24c | 79 | }, |
cffa6aa1 | 80 | }] |
45aef472 | 81 | |
8bdd16b4 | 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) | |
86 | ||
45aef472 | 87 | def _real_extract(self, url): |
8bdd16b4 | 88 | title = self._match_id(url) |
45aef472 | 89 | webpage = self._download_webpage(url, title) |
8bdd16b4 | 90 | tralbum = self._extract_data_attr(webpage, title) |
91 | thumbnail = self._og_search_thumbnail(webpage) | |
92 | ||
93 | track_id = None | |
94 | track = None | |
95 | track_number = None | |
96 | duration = None | |
97 | ||
98 | formats = [] | |
99 | track_info = try_get(tralbum, lambda x: x['trackinfo'][0], dict) | |
100 | if track_info: | |
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): | |
105 | continue | |
106 | ext, abr_str = format_id.split('-', 1) | |
107 | formats.append({ | |
108 | 'format_id': format_id, | |
109 | 'url': self._proto_relative_url(format_url, 'http:'), | |
110 | 'ext': ext, | |
111 | 'vcodec': 'none', | |
112 | 'acodec': ext, | |
113 | 'abr': int_or_none(abr_str), | |
114 | }) | |
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')) | |
120 | ||
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')) | |
126 | ||
127 | download_link = tralbum.get('freeDownloadPage') | |
4991e16c | 128 | if download_link: |
8bdd16b4 | 129 | track_id = compat_str(tralbum['id']) |
4991e16c S |
130 | |
131 | download_webpage = self._download_webpage( | |
132 | download_link, track_id, 'Downloading free downloads page') | |
133 | ||
8bdd16b4 | 134 | blob = self._extract_data_attr(download_webpage, track_id, 'blob') |
4991e16c S |
135 | |
136 | info = try_get( | |
137 | blob, (lambda x: x['digital_items'][0], | |
138 | lambda x: x['download_items'][0]), dict) | |
139 | if info: | |
140 | downloads = info.get('downloads') | |
141 | if isinstance(downloads, dict): | |
8bdd16b4 | 142 | if not track: |
143 | track = info.get('title') | |
4991e16c S |
144 | if not artist: |
145 | artist = info.get('artist') | |
146 | if not thumbnail: | |
147 | thumbnail = info.get('thumb_url') | |
148 | ||
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('.') | |
156 | ||
157 | for format_id, f in downloads.items(): | |
158 | format_url = f.get('url') | |
159 | if not format_url: | |
160 | continue | |
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()), | |
166 | }) | |
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], | |
171 | fatal=False) | |
172 | if not stat: | |
173 | continue | |
174 | retry_url = url_or_none(stat.get('retry_url')) | |
175 | if not retry_url: | |
176 | continue | |
8bdd16b4 | 177 | formats.append({ |
4991e16c S |
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')), | |
183 | 'vcodec': 'none', | |
933dbf5a | 184 | 'acodec': format_id.split('-')[0], |
4991e16c | 185 | }) |
5ecd3c6a | 186 | |
8bdd16b4 | 187 | self._sort_formats(formats) |
0aacd2de | 188 | |
8bdd16b4 | 189 | title = '%s - %s' % (artist, track) if artist else track |
190 | ||
191 | if not duration: | |
192 | duration = float_or_none(self._html_search_meta( | |
193 | 'duration', webpage, default=None)) | |
45aef472 | 194 | |
5ecd3c6a | 195 | return { |
8bdd16b4 | 196 | 'id': track_id, |
197 | 'title': title, | |
4991e16c | 198 | 'thumbnail': thumbnail, |
8bdd16b4 | 199 | 'uploader': artist, |
4991e16c | 200 | 'timestamp': timestamp, |
10db0d2f | 201 | 'release_timestamp': unified_timestamp(tralbum.get('album_release_date')), |
8bdd16b4 | 202 | 'duration': duration, |
203 | 'track': track, | |
204 | 'track_number': track_number, | |
205 | 'track_id': track_id, | |
206 | 'artist': artist, | |
207 | 'album': embed.get('album_title'), | |
208 | 'formats': formats, | |
5ecd3c6a | 209 | } |
09804265 JMF |
210 | |
211 | ||
8bdd16b4 | 212 | class BandcampAlbumIE(BandcampIE): |
3798eadc | 213 | IE_NAME = 'Bandcamp:album' |
85a0ad01 | 214 | _VALID_URL = r'https?://(?:(?P<subdomain>[^.]+)\.)?bandcamp\.com/album/(?P<id>[^/?#&]+)' |
09804265 | 215 | |
22a6f150 | 216 | _TESTS = [{ |
3798eadc PH |
217 | 'url': 'http://blazo.bandcamp.com/album/jazz-format-mixtape-vol-1', |
218 | 'playlist': [ | |
d35dc6d3 | 219 | { |
3798eadc PH |
220 | 'md5': '39bc1eded3476e927c724321ddf116cf', |
221 | 'info_dict': { | |
13ba3a64 PH |
222 | 'id': '1353101989', |
223 | 'ext': 'mp3', | |
8bdd16b4 | 224 | 'title': 'Blazo - Intro', |
225 | 'timestamp': 1311756226, | |
226 | 'upload_date': '20110727', | |
227 | 'uploader': 'Blazo', | |
d35dc6d3 JMF |
228 | } |
229 | }, | |
230 | { | |
3798eadc PH |
231 | 'md5': '1a2c32e2691474643e912cc6cd4bffaa', |
232 | 'info_dict': { | |
13ba3a64 PH |
233 | 'id': '38097443', |
234 | 'ext': 'mp3', | |
8bdd16b4 | 235 | 'title': 'Blazo - Kero One - Keep It Alive (Blazo remix)', |
236 | 'timestamp': 1311757238, | |
237 | 'upload_date': '20110727', | |
238 | 'uploader': 'Blazo', | |
d35dc6d3 JMF |
239 | } |
240 | }, | |
241 | ], | |
13ba3a64 PH |
242 | 'info_dict': { |
243 | 'title': 'Jazz Format Mixtape vol.1', | |
72c1f8de PH |
244 | 'id': 'jazz-format-mixtape-vol-1', |
245 | 'uploader_id': 'blazo', | |
13ba3a64 | 246 | }, |
3798eadc PH |
247 | 'params': { |
248 | 'playlistend': 2 | |
d35dc6d3 | 249 | }, |
72c1f8de | 250 | 'skip': 'Bandcamp imposes download limits.' |
22a6f150 PH |
251 | }, { |
252 | 'url': 'http://nightbringer.bandcamp.com/album/hierophany-of-the-open-grave', | |
253 | 'info_dict': { | |
254 | 'title': 'Hierophany of the Open Grave', | |
72c1f8de PH |
255 | 'uploader_id': 'nightbringer', |
256 | 'id': 'hierophany-of-the-open-grave', | |
22a6f150 PH |
257 | }, |
258 | 'playlist_mincount': 9, | |
64fc49ab S |
259 | }, { |
260 | # with escaped quote in title | |
261 | 'url': 'https://jstrecords.bandcamp.com/album/entropy-ep', | |
262 | 'info_dict': { | |
263 | 'title': '"Entropy" EP', | |
264 | 'uploader_id': 'jstrecords', | |
265 | 'id': 'entropy-ep', | |
8bdd16b4 | 266 | 'description': 'md5:0ff22959c943622972596062f2f366a5', |
64fc49ab S |
267 | }, |
268 | 'playlist_mincount': 3, | |
019f4c03 YCH |
269 | }, { |
270 | # not all tracks have songs | |
271 | 'url': 'https://insulters.bandcamp.com/album/we-are-the-plague', | |
272 | 'info_dict': { | |
273 | 'id': 'we-are-the-plague', | |
274 | 'title': 'WE ARE THE PLAGUE', | |
275 | 'uploader_id': 'insulters', | |
8bdd16b4 | 276 | 'description': 'md5:b3cf845ee41b2b1141dc7bde9237255f', |
019f4c03 YCH |
277 | }, |
278 | 'playlist_count': 2, | |
22a6f150 | 279 | }] |
d35dc6d3 | 280 | |
62bafabc AV |
281 | @classmethod |
282 | def suitable(cls, url): | |
6d923aab S |
283 | return (False |
284 | if BandcampWeeklyIE.suitable(url) or BandcampIE.suitable(url) | |
285 | else super(BandcampAlbumIE, cls).suitable(url)) | |
62bafabc | 286 | |
09804265 | 287 | def _real_extract(self, url): |
5ad28e7f | 288 | uploader_id, album_id = self._match_valid_url(url).groups() |
72c1f8de PH |
289 | playlist_id = album_id or uploader_id |
290 | webpage = self._download_webpage(url, playlist_id) | |
8bdd16b4 | 291 | tralbum = self._extract_data_attr(webpage, playlist_id) |
292 | track_info = tralbum.get('trackinfo') | |
293 | if not track_info: | |
294 | raise ExtractorError('The page doesn\'t contain any tracks') | |
019f4c03 | 295 | # Only tracks with duration info have songs |
09804265 | 296 | entries = [ |
8239c679 | 297 | self.url_result( |
8bdd16b4 | 298 | urljoin(url, t['title_link']), BandcampIE.ie_key(), |
299 | str_or_none(t.get('track_id') or t.get('id')), t.get('title')) | |
300 | for t in track_info | |
301 | if t.get('duration')] | |
302 | ||
303 | current = tralbum.get('current') or {} | |
3a379e5e | 304 | |
09804265 JMF |
305 | return { |
306 | '_type': 'playlist', | |
72c1f8de | 307 | 'uploader_id': uploader_id, |
b48f147d | 308 | 'id': playlist_id, |
8bdd16b4 | 309 | 'title': current.get('title'), |
310 | 'description': current.get('about'), | |
311 | 'entries': entries, | |
09804265 | 312 | } |
62bafabc AV |
313 | |
314 | ||
8bdd16b4 | 315 | class BandcampWeeklyIE(BandcampIE): |
6d923aab S |
316 | IE_NAME = 'Bandcamp:weekly' |
317 | _VALID_URL = r'https?://(?:www\.)?bandcamp\.com/?\?(?:.*?&)?show=(?P<id>\d+)' | |
62bafabc AV |
318 | _TESTS = [{ |
319 | 'url': 'https://bandcamp.com/?show=224', | |
320 | 'md5': 'b00df799c733cf7e0c567ed187dea0fd', | |
321 | 'info_dict': { | |
322 | 'id': '224', | |
323 | 'ext': 'opus', | |
6d923aab S |
324 | 'title': 'BC Weekly April 4th 2017 - Magic Moments', |
325 | 'description': 'md5:5d48150916e8e02d030623a48512c874', | |
326 | 'duration': 5829.77, | |
327 | 'release_date': '20170404', | |
328 | 'series': 'Bandcamp Weekly', | |
329 | 'episode': 'Magic Moments', | |
6d923aab | 330 | 'episode_id': '224', |
8bdd16b4 | 331 | }, |
332 | 'params': { | |
333 | 'format': 'opus-lo', | |
334 | }, | |
62bafabc AV |
335 | }, { |
336 | 'url': 'https://bandcamp.com/?blah/blah@&show=228', | |
337 | 'only_matching': True | |
338 | }] | |
339 | ||
340 | def _real_extract(self, url): | |
8bdd16b4 | 341 | show_id = self._match_id(url) |
342 | webpage = self._download_webpage(url, show_id) | |
62bafabc | 343 | |
8bdd16b4 | 344 | blob = self._extract_data_attr(webpage, show_id, 'blob') |
62bafabc | 345 | |
8bdd16b4 | 346 | show = blob['bcw_data'][show_id] |
62bafabc | 347 | |
6d923aab S |
348 | formats = [] |
349 | for format_id, format_url in show['audio_stream'].items(): | |
3052a30d | 350 | if not url_or_none(format_url): |
6d923aab S |
351 | continue |
352 | for known_ext in KNOWN_EXTENSIONS: | |
353 | if known_ext in format_id: | |
354 | ext = known_ext | |
355 | break | |
356 | else: | |
357 | ext = None | |
358 | formats.append({ | |
359 | 'format_id': format_id, | |
360 | 'url': format_url, | |
361 | 'ext': ext, | |
362 | 'vcodec': 'none', | |
363 | }) | |
364 | self._sort_formats(formats) | |
62bafabc | 365 | |
6d923aab S |
366 | title = show.get('audio_title') or 'Bandcamp Weekly' |
367 | subtitle = show.get('subtitle') | |
368 | if subtitle: | |
369 | title += ' - %s' % subtitle | |
62bafabc | 370 | |
62bafabc | 371 | return { |
8bdd16b4 | 372 | 'id': show_id, |
6d923aab S |
373 | 'title': title, |
374 | 'description': show.get('desc') or show.get('short_desc'), | |
62bafabc | 375 | 'duration': float_or_none(show.get('audio_duration')), |
62bafabc AV |
376 | 'is_live': False, |
377 | 'release_date': unified_strdate(show.get('published_date')), | |
378 | 'series': 'Bandcamp Weekly', | |
6d923aab | 379 | 'episode': show.get('subtitle'), |
8bdd16b4 | 380 | 'episode_id': show_id, |
62bafabc AV |
381 | 'formats': formats |
382 | } | |
bc874548 A |
383 | |
384 | ||
85a0ad01 | 385 | class BandcampUserIE(InfoExtractor): |
386 | IE_NAME = 'Bandcamp:user' | |
387 | _VALID_URL = r'https?://(?!www\.)(?P<id>[^.]+)\.bandcamp\.com(?:/music)?/?(?:[#?]|$)' | |
388 | ||
bc874548 | 389 | _TESTS = [{ |
85a0ad01 | 390 | # Type 1 Bandcamp user page. |
391 | 'url': 'https://adrianvonziegler.bandcamp.com', | |
392 | 'info_dict': { | |
393 | 'id': 'adrianvonziegler', | |
394 | 'title': 'Discography of adrianvonziegler', | |
395 | }, | |
396 | 'playlist_mincount': 23, | |
397 | }, { | |
398 | # Bandcamp user page with only one album | |
399 | 'url': 'http://dotscale.bandcamp.com', | |
400 | 'info_dict': { | |
401 | 'id': 'dotscale', | |
402 | 'title': 'Discography of dotscale' | |
403 | }, | |
404 | 'playlist_count': 1, | |
405 | }, { | |
406 | # Type 2 Bandcamp user page. | |
407 | 'url': 'https://nightcallofficial.bandcamp.com', | |
408 | 'info_dict': { | |
409 | 'id': 'nightcallofficial', | |
410 | 'title': 'Discography of nightcallofficial', | |
411 | }, | |
412 | 'playlist_count': 4, | |
413 | }, { | |
bc874548 A |
414 | 'url': 'https://steviasphere.bandcamp.com/music', |
415 | 'playlist_mincount': 47, | |
416 | 'info_dict': { | |
417 | 'id': 'steviasphere', | |
85a0ad01 | 418 | 'title': 'Discography of steviasphere', |
bc874548 A |
419 | }, |
420 | }, { | |
421 | 'url': 'https://coldworldofficial.bandcamp.com/music', | |
422 | 'playlist_mincount': 10, | |
423 | 'info_dict': { | |
424 | 'id': 'coldworldofficial', | |
85a0ad01 | 425 | 'title': 'Discography of coldworldofficial', |
bc874548 A |
426 | }, |
427 | }, { | |
428 | 'url': 'https://nuclearwarnowproductions.bandcamp.com/music', | |
429 | 'playlist_mincount': 399, | |
430 | 'info_dict': { | |
431 | 'id': 'nuclearwarnowproductions', | |
85a0ad01 | 432 | 'title': 'Discography of nuclearwarnowproductions', |
bc874548 | 433 | }, |
85a0ad01 | 434 | }] |
bc874548 A |
435 | |
436 | def _real_extract(self, url): | |
85a0ad01 | 437 | uploader = self._match_id(url) |
438 | webpage = self._download_webpage(url, uploader) | |
439 | ||
96b49af0 | 440 | discography_data = (re.findall(r'<li data-item-id=["\'][^>]+>\s*<a href=["\'](?![^"\'/]*?/merch)([^"\']+)', webpage) |
85a0ad01 | 441 | or re.findall(r'<div[^>]+trackTitle["\'][^"\']+["\']([^"\']+)', webpage)) |
442 | ||
443 | return self.playlist_from_matches( | |
444 | discography_data, uploader, f'Discography of {uploader}', getter=lambda x: urljoin(url, x)) |