]>
Commit | Line | Data |
---|---|---|
dcdb292f | 1 | # coding: utf-8 |
fbcd7b5f PH |
2 | from __future__ import unicode_literals |
3 | ||
92790f4e | 4 | import itertools |
73602bcd | 5 | import re |
aad0d6d5 | 6 | |
2abf7cab | 7 | from .common import ( |
8 | InfoExtractor, | |
9 | SearchInfoExtractor | |
10 | ) | |
1cc79574 | 11 | from ..compat import ( |
aad0d6d5 | 12 | compat_str, |
668de34c | 13 | compat_urlparse, |
15707c7e | 14 | compat_urllib_parse_urlencode, |
1cc79574 PH |
15 | ) |
16 | from ..utils import ( | |
aad0d6d5 | 17 | ExtractorError, |
eb920777 | 18 | int_or_none, |
aad0d6d5 | 19 | unified_strdate, |
d7c7100e S |
20 | update_url_query, |
21 | ) | |
aad0d6d5 PH |
22 | |
23 | ||
24 | class SoundcloudIE(InfoExtractor): | |
25 | """Information extractor for soundcloud.com | |
26 | To access the media, the uid of the song and a stream token | |
27 | must be extracted from the page source and the script must make | |
28 | a request to media.soundcloud.com/crossdomain.xml. Then | |
29 | the media can be grabbed by requesting from an url composed | |
30 | of the stream token and uid | |
31 | """ | |
32 | ||
20991253 | 33 | _VALID_URL = r'''(?x)^(?:https?://)? |
71507a11 | 34 | (?:(?:(?:www\.|m\.)?soundcloud\.com/ |
836ef264 | 35 | (?!stations/track) |
4ff50ef8 | 36 | (?P<uploader>[\w\d-]+)/ |
3ef2da2d | 37 | (?!(?:tracks|albums|sets(?:/.+?)?|reposts|likes|spotlight)/?(?:$|[?#])) |
22a6f150 | 38 | (?P<title>[\w\d-]+)/? |
de2dd4c5 | 39 | (?P<token>[^?]+?)?(?:[?].*)?$) |
9296738f | 40 | |(?:api\.soundcloud\.com/tracks/(?P<track_id>\d+) |
0403b069 | 41 | (?:/?\?secret_token=(?P<secret_token>[^&]+))?) |
31c1cf5a | 42 | |(?P<player>(?:w|player|p.)\.soundcloud\.com/player/?.*?url=.*) |
eb6a41ba JMF |
43 | ) |
44 | ''' | |
fbcd7b5f | 45 | IE_NAME = 'soundcloud' |
12c167c8 JMF |
46 | _TESTS = [ |
47 | { | |
fbcd7b5f | 48 | 'url': 'http://soundcloud.com/ethmusic/lostin-powers-she-so-heavy', |
fbcd7b5f PH |
49 | 'md5': 'ebef0a451b909710ed1d7787dddbf0d7', |
50 | 'info_dict': { | |
0eb9fb9f JMF |
51 | 'id': '62986583', |
52 | 'ext': 'mp3', | |
53 | 'upload_date': '20121011', | |
54 | 'description': 'No Downloads untill we record the finished version this weekend, i was too pumped n i had to post it , earl is prolly gonna b hella p.o\'d', | |
55 | 'uploader': 'E.T. ExTerrestrial Music', | |
56 | 'title': 'Lostin Powers - She so Heavy (SneakPreview) Adrian Ackers Blueprint 1', | |
57 | 'duration': 143, | |
4bfd294e | 58 | 'license': 'all-rights-reserved', |
12c167c8 JMF |
59 | } |
60 | }, | |
61 | # not streamable song | |
62 | { | |
fbcd7b5f PH |
63 | 'url': 'https://soundcloud.com/the-concept-band/goldrushed-mastered?in=the-concept-band/sets/the-royal-concept-ep', |
64 | 'info_dict': { | |
65 | 'id': '47127627', | |
66 | 'ext': 'mp3', | |
67 | 'title': 'Goldrushed', | |
63ad0315 | 68 | 'description': 'From Stockholm Sweden\r\nPovel / Magnus / Filip / David\r\nwww.theroyalconcept.com', |
fbcd7b5f PH |
69 | 'uploader': 'The Royal Concept', |
70 | 'upload_date': '20120521', | |
eb920777 | 71 | 'duration': 227, |
4bfd294e | 72 | 'license': 'all-rights-reserved', |
12c167c8 | 73 | }, |
fbcd7b5f | 74 | 'params': { |
12c167c8 | 75 | # rtmp |
fbcd7b5f | 76 | 'skip_download': True, |
12c167c8 JMF |
77 | }, |
78 | }, | |
de2dd4c5 JMF |
79 | # private link |
80 | { | |
fbcd7b5f PH |
81 | 'url': 'https://soundcloud.com/jaimemf/youtube-dl-test-video-a-y-baw/s-8Pjrp', |
82 | 'md5': 'aa0dd32bfea9b0c5ef4f02aacd080604', | |
83 | 'info_dict': { | |
84 | 'id': '123998367', | |
85 | 'ext': 'mp3', | |
86 | 'title': 'Youtube - Dl Test Video \'\' Ä↭', | |
87 | 'uploader': 'jaimeMF', | |
88 | 'description': 'test chars: \"\'/\\ä↭', | |
89 | 'upload_date': '20131209', | |
eb920777 | 90 | 'duration': 9, |
4bfd294e | 91 | 'license': 'all-rights-reserved', |
de2dd4c5 JMF |
92 | }, |
93 | }, | |
9296738f | 94 | # private link (alt format) |
95 | { | |
96 | 'url': 'https://api.soundcloud.com/tracks/123998367?secret_token=s-8Pjrp', | |
97 | 'md5': 'aa0dd32bfea9b0c5ef4f02aacd080604', | |
98 | 'info_dict': { | |
99 | 'id': '123998367', | |
100 | 'ext': 'mp3', | |
101 | 'title': 'Youtube - Dl Test Video \'\' Ä↭', | |
102 | 'uploader': 'jaimeMF', | |
103 | 'description': 'test chars: \"\'/\\ä↭', | |
104 | 'upload_date': '20131209', | |
105 | 'duration': 9, | |
4bfd294e | 106 | 'license': 'all-rights-reserved', |
9296738f | 107 | }, |
108 | }, | |
f67ca84d JMF |
109 | # downloadable song |
110 | { | |
00a82ea8 | 111 | 'url': 'https://soundcloud.com/oddsamples/bus-brakes', |
eae12e3f | 112 | 'md5': '7624f2351f8a3b2e7cd51522496e7631', |
fbcd7b5f | 113 | 'info_dict': { |
00a82ea8 | 114 | 'id': '128590877', |
eae12e3f | 115 | 'ext': 'mp3', |
00a82ea8 | 116 | 'title': 'Bus Brakes', |
0eb9fb9f | 117 | 'description': 'md5:0053ca6396e8d2fd7b7e1595ef12ab66', |
00a82ea8 S |
118 | 'uploader': 'oddsamples', |
119 | 'upload_date': '20140109', | |
120 | 'duration': 17, | |
4bfd294e | 121 | 'license': 'cc-by-sa', |
f67ca84d JMF |
122 | }, |
123 | }, | |
d7c7100e S |
124 | # private link, downloadable format |
125 | { | |
126 | 'url': 'https://soundcloud.com/oriuplift/uponly-238-no-talking-wav/s-AyZUd', | |
127 | 'md5': '64a60b16e617d41d0bef032b7f55441e', | |
128 | 'info_dict': { | |
129 | 'id': '340344461', | |
130 | 'ext': 'wav', | |
131 | 'title': 'Uplifting Only 238 [No Talking] (incl. Alex Feed Guestmix) (Aug 31, 2017) [wav]', | |
132 | 'description': 'md5:fa20ee0fca76a3d6df8c7e57f3715366', | |
133 | 'uploader': 'Ori Uplift Music', | |
134 | 'upload_date': '20170831', | |
135 | 'duration': 7449, | |
136 | 'license': 'all-rights-reserved', | |
137 | }, | |
138 | }, | |
0b0870f9 PV |
139 | # no album art, use avatar pic for thumbnail |
140 | { | |
141 | 'url': 'https://soundcloud.com/garyvee/sideways-prod-mad-real', | |
142 | 'md5': '59c7872bc44e5d99b7211891664760c2', | |
143 | 'info_dict': { | |
144 | 'id': '309699954', | |
145 | 'ext': 'mp3', | |
146 | 'title': 'Sideways (Prod. Mad Real)', | |
147 | 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e', | |
148 | 'uploader': 'garyvee', | |
149 | 'upload_date': '20170226', | |
150 | 'duration': 207, | |
151 | 'thumbnail': r're:https?://.*\.jpg', | |
152 | 'license': 'all-rights-reserved', | |
153 | }, | |
154 | 'params': { | |
155 | 'skip_download': True, | |
156 | }, | |
157 | }, | |
12c167c8 | 158 | ] |
aad0d6d5 | 159 | |
3ef2da2d | 160 | _CLIENT_ID = 'NmW1FlPaiL94ueEu7oziOWjYEzZzQDcK' |
7d239269 | 161 | |
fbdf8d15 S |
162 | @staticmethod |
163 | def _extract_urls(webpage): | |
164 | return [m.group('url') for m in re.finditer( | |
165 | r'<iframe[^>]+src=(["\'])(?P<url>(?:https?://)?(?:w\.)?soundcloud\.com/player.+?)\1', | |
166 | webpage)] | |
167 | ||
aad0d6d5 PH |
168 | def report_resolve(self, video_id): |
169 | """Report information extraction.""" | |
83622b6d | 170 | self.to_screen('%s: Resolving id' % video_id) |
aad0d6d5 | 171 | |
7d239269 JMF |
172 | @classmethod |
173 | def _resolv_url(cls, url): | |
f1c05100 | 174 | return 'https://api.soundcloud.com/resolve.json?url=' + url + '&client_id=' + cls._CLIENT_ID |
7d239269 | 175 | |
de2dd4c5 | 176 | def _extract_info_dict(self, info, full_title=None, quiet=False, secret_token=None): |
12c167c8 JMF |
177 | track_id = compat_str(info['id']) |
178 | name = full_title or track_id | |
2a15e706 | 179 | if quiet: |
92790f4e | 180 | self.report_extraction(name) |
0b0870f9 | 181 | thumbnail = info.get('artwork_url') or info.get('user', {}).get('avatar_url') |
f62a77b9 | 182 | if isinstance(thumbnail, compat_str): |
7d239269 | 183 | thumbnail = thumbnail.replace('-large', '-t500x500') |
12c167c8 | 184 | result = { |
2a15e706 | 185 | 'id': track_id, |
f62a77b9 S |
186 | 'uploader': info.get('user', {}).get('username'), |
187 | 'upload_date': unified_strdate(info.get('created_at')), | |
2a15e706 | 188 | 'title': info['title'], |
f62a77b9 | 189 | 'description': info.get('description'), |
7d239269 | 190 | 'thumbnail': thumbnail, |
eb920777 | 191 | 'duration': int_or_none(info.get('duration'), 1000), |
579657ad | 192 | 'webpage_url': info.get('permalink_url'), |
f62a77b9 | 193 | 'license': info.get('license'), |
7d239269 | 194 | } |
5e114e4b | 195 | formats = [] |
73602bcd TI |
196 | query = {'client_id': self._CLIENT_ID} |
197 | if secret_token is not None: | |
198 | query['secret_token'] = secret_token | |
12c167c8 | 199 | if info.get('downloadable', False): |
64bb5187 | 200 | # We can build a direct link to the song |
73602bcd | 201 | format_url = update_url_query( |
d7c7100e | 202 | 'https://api.soundcloud.com/tracks/%s/download' % track_id, query) |
5e114e4b | 203 | formats.append({ |
2a15e706 | 204 | 'format_id': 'download', |
fbcd7b5f | 205 | 'ext': info.get('original_format', 'mp3'), |
2a15e706 | 206 | 'url': format_url, |
fb04e403 | 207 | 'vcodec': 'none', |
5e114e4b PH |
208 | 'preference': 10, |
209 | }) | |
210 | ||
211 | # We have to retrieve the url | |
20991253 | 212 | format_dict = self._download_json( |
f1c05100 | 213 | 'https://api.soundcloud.com/i1/tracks/%s/streams' % track_id, |
73602bcd | 214 | track_id, 'Downloading track url', query=query) |
5e114e4b | 215 | |
5e114e4b | 216 | for key, stream_url in format_dict.items(): |
c0fd20ab RA |
217 | ext, abr = 'mp3', None |
218 | mobj = re.search(r'_([^_]+)_(\d+)_url', key) | |
219 | if mobj: | |
220 | ext, abr = mobj.groups() | |
221 | abr = int(abr) | |
5e114e4b | 222 | if key.startswith('http'): |
3a194cb4 | 223 | stream_formats = [{ |
5e114e4b PH |
224 | 'format_id': key, |
225 | 'ext': ext, | |
226 | 'url': stream_url, | |
3a194cb4 | 227 | }] |
5e114e4b PH |
228 | elif key.startswith('rtmp'): |
229 | # The url doesn't have an rtmp app, we have to extract the playpath | |
230 | url, path = stream_url.split('mp3:', 1) | |
3a194cb4 | 231 | stream_formats = [{ |
5e114e4b PH |
232 | 'format_id': key, |
233 | 'url': url, | |
234 | 'play_path': 'mp3:' + path, | |
295df4ed | 235 | 'ext': 'flv', |
3a194cb4 | 236 | }] |
9b734718 | 237 | elif key.startswith('hls'): |
3a194cb4 | 238 | stream_formats = self._extract_m3u8_formats( |
c0fd20ab | 239 | stream_url, track_id, ext, entry_protocol='m3u8_native', |
9b734718 | 240 | m3u8_id=key, fatal=False) |
3a194cb4 S |
241 | else: |
242 | continue | |
243 | ||
c0fd20ab RA |
244 | if abr: |
245 | for f in stream_formats: | |
246 | f['abr'] = abr | |
3a194cb4 S |
247 | |
248 | formats.extend(stream_formats) | |
249 | ||
250 | if not formats: | |
251 | # We fallback to the stream_url in the original info, this | |
252 | # cannot be always used, sometimes it can give an HTTP 404 error | |
253 | formats.append({ | |
254 | 'format_id': 'fallback', | |
73602bcd | 255 | 'url': update_url_query(info['stream_url'], query), |
c0fd20ab | 256 | 'ext': 'mp3', |
3a194cb4 S |
257 | }) |
258 | ||
259 | for f in formats: | |
260 | f['vcodec'] = 'none' | |
2a15e706 | 261 | |
562ceab1 S |
262 | self._check_formats(formats, track_id) |
263 | self._sort_formats(formats) | |
264 | result['formats'] = formats | |
64bb5187 | 265 | |
12c167c8 | 266 | return result |
7d239269 | 267 | |
aad0d6d5 | 268 | def _real_extract(self, url): |
eb6a41ba | 269 | mobj = re.match(self._VALID_URL, url, flags=re.VERBOSE) |
aad0d6d5 | 270 | if mobj is None: |
83622b6d | 271 | raise ExtractorError('Invalid URL: %s' % url) |
aad0d6d5 | 272 | |
eb6a41ba | 273 | track_id = mobj.group('track_id') |
4bfd294e | 274 | |
eb6a41ba | 275 | if track_id is not None: |
f1c05100 | 276 | info_json_url = 'https://api.soundcloud.com/tracks/' + track_id + '.json?client_id=' + self._CLIENT_ID |
eb6a41ba | 277 | full_title = track_id |
9296738f | 278 | token = mobj.group('secret_token') |
279 | if token: | |
611c1dd9 | 280 | info_json_url += '&secret_token=' + token |
31c1cf5a | 281 | elif mobj.group('player'): |
668de34c | 282 | query = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query) |
024ebb27 JMF |
283 | real_url = query['url'][0] |
284 | # If the token is in the query of the original url we have to | |
285 | # manually add it | |
286 | if 'secret_token' in query: | |
287 | real_url += '?secret_token=' + query['secret_token'][0] | |
288 | return self.url_result(real_url) | |
eb6a41ba JMF |
289 | else: |
290 | # extract uploader (which is in the url) | |
de2dd4c5 | 291 | uploader = mobj.group('uploader') |
eb6a41ba | 292 | # extract simple title (uploader + slug of song title) |
8bcc8756 | 293 | slug_title = mobj.group('title') |
de2dd4c5 JMF |
294 | token = mobj.group('token') |
295 | full_title = resolve_title = '%s/%s' % (uploader, slug_title) | |
296 | if token: | |
297 | resolve_title += '/%s' % token | |
5f6a1245 | 298 | |
eb6a41ba | 299 | self.report_resolve(full_title) |
5f6a1245 | 300 | |
f1c05100 | 301 | url = 'https://soundcloud.com/%s' % resolve_title |
eb6a41ba | 302 | info_json_url = self._resolv_url(url) |
20991253 | 303 | info = self._download_json(info_json_url, full_title, 'Downloading info JSON') |
aad0d6d5 | 304 | |
de2dd4c5 | 305 | return self._extract_info_dict(info, full_title, secret_token=token) |
aad0d6d5 | 306 | |
20991253 | 307 | |
7518a61d | 308 | class SoundcloudPlaylistBaseIE(SoundcloudIE): |
8e45e1cc S |
309 | @staticmethod |
310 | def _extract_id(e): | |
311 | return compat_str(e['id']) if e.get('id') else None | |
312 | ||
313 | def _extract_track_entries(self, tracks): | |
314 | return [ | |
315 | self.url_result( | |
316 | track['permalink_url'], SoundcloudIE.ie_key(), | |
317 | video_id=self._extract_id(track)) | |
318 | for track in tracks if track.get('permalink_url')] | |
319 | ||
320 | ||
7518a61d | 321 | class SoundcloudSetIE(SoundcloudPlaylistBaseIE): |
c808ef81 | 322 | _VALID_URL = r'https?://(?:(?:www|m)\.)?soundcloud\.com/(?P<uploader>[\w\d-]+)/sets/(?P<slug_title>[\w\d-]+)(?:/(?P<token>[^?/]+))?' |
fbcd7b5f | 323 | IE_NAME = 'soundcloud:set' |
22a6f150 PH |
324 | _TESTS = [{ |
325 | 'url': 'https://soundcloud.com/the-concept-band/sets/the-royal-concept-ep', | |
326 | 'info_dict': { | |
a9551e90 | 327 | 'id': '2284613', |
22a6f150 PH |
328 | 'title': 'The Royal Concept EP', |
329 | }, | |
bf2dc9cc | 330 | 'playlist_mincount': 5, |
f7043ef3 S |
331 | }, { |
332 | 'url': 'https://soundcloud.com/the-concept-band/sets/the-royal-concept-ep/token', | |
333 | 'only_matching': True, | |
22a6f150 | 334 | }] |
aad0d6d5 | 335 | |
aad0d6d5 PH |
336 | def _real_extract(self, url): |
337 | mobj = re.match(self._VALID_URL, url) | |
aad0d6d5 PH |
338 | |
339 | # extract uploader (which is in the url) | |
2f834e93 | 340 | uploader = mobj.group('uploader') |
aad0d6d5 | 341 | # extract simple title (uploader + slug of song title) |
2f834e93 | 342 | slug_title = mobj.group('slug_title') |
aad0d6d5 | 343 | full_title = '%s/sets/%s' % (uploader, slug_title) |
f1c05100 | 344 | url = 'https://soundcloud.com/%s/sets/%s' % (uploader, slug_title) |
2f834e93 | 345 | |
346 | token = mobj.group('token') | |
347 | if token: | |
348 | full_title += '/' + token | |
349 | url += '/' + token | |
aad0d6d5 PH |
350 | |
351 | self.report_resolve(full_title) | |
352 | ||
7d239269 | 353 | resolv_url = self._resolv_url(url) |
20991253 | 354 | info = self._download_json(resolv_url, full_title) |
aad0d6d5 | 355 | |
aad0d6d5 | 356 | if 'errors' in info: |
214e74bf JMF |
357 | msgs = (compat_str(err['error_message']) for err in info['errors']) |
358 | raise ExtractorError('unable to download video webpage: %s' % ','.join(msgs)) | |
aad0d6d5 | 359 | |
8e45e1cc | 360 | entries = self._extract_track_entries(info['tracks']) |
b14fa8e6 | 361 | |
22a6f150 PH |
362 | return { |
363 | '_type': 'playlist', | |
b14fa8e6 | 364 | 'entries': entries, |
a9551e90 | 365 | 'id': '%s' % info['id'], |
22a6f150 PH |
366 | 'title': info['title'], |
367 | } | |
92790f4e JMF |
368 | |
369 | ||
836ef264 | 370 | class SoundcloudPagedPlaylistBaseIE(SoundcloudPlaylistBaseIE): |
836ef264 S |
371 | _API_V2_BASE = 'https://api-v2.soundcloud.com' |
372 | ||
373 | def _extract_playlist(self, base_url, playlist_id, playlist_title): | |
374 | COMMON_QUERY = { | |
375 | 'limit': 50, | |
376 | 'client_id': self._CLIENT_ID, | |
377 | 'linked_partitioning': '1', | |
378 | } | |
379 | ||
380 | query = COMMON_QUERY.copy() | |
381 | query['offset'] = 0 | |
382 | ||
383 | next_href = base_url + '?' + compat_urllib_parse_urlencode(query) | |
384 | ||
385 | entries = [] | |
386 | for i in itertools.count(): | |
387 | response = self._download_json( | |
388 | next_href, playlist_id, 'Downloading track page %s' % (i + 1)) | |
389 | ||
390 | collection = response['collection'] | |
3ef2da2d S |
391 | |
392 | if not isinstance(collection, list): | |
393 | collection = [] | |
394 | ||
395 | # Empty collection may be returned, in this case we proceed | |
396 | # straight to next_href | |
836ef264 | 397 | |
6cc6e0c3 CH |
398 | def append_url_result(entries, item): |
399 | for cand in (item, item.get('track'), item.get('playlist')): | |
836ef264 S |
400 | if isinstance(cand, dict): |
401 | permalink_url = cand.get('permalink_url') | |
836ef264 | 402 | if permalink_url and permalink_url.startswith('http'): |
6cc6e0c3 CH |
403 | return entries.append( |
404 | self.url_result( | |
405 | permalink_url, | |
406 | ie=SoundcloudIE.ie_key() if SoundcloudIE.suitable(permalink_url) else None, | |
407 | video_id=self._extract_id(cand), | |
408 | video_title=cand.get('title'))) | |
836ef264 S |
409 | |
410 | for e in collection: | |
6cc6e0c3 | 411 | append_url_result(entries, e) |
836ef264 S |
412 | |
413 | next_href = response.get('next_href') | |
414 | if not next_href: | |
415 | break | |
416 | ||
417 | parsed_next_href = compat_urlparse.urlparse(response['next_href']) | |
418 | qs = compat_urlparse.parse_qs(parsed_next_href.query) | |
419 | qs.update(COMMON_QUERY) | |
420 | next_href = compat_urlparse.urlunparse( | |
421 | parsed_next_href._replace(query=compat_urllib_parse_urlencode(qs, True))) | |
422 | ||
423 | return { | |
424 | '_type': 'playlist', | |
425 | 'id': playlist_id, | |
426 | 'title': playlist_title, | |
427 | 'entries': entries, | |
428 | } | |
429 | ||
430 | ||
431 | class SoundcloudUserIE(SoundcloudPagedPlaylistBaseIE): | |
16a08978 S |
432 | _VALID_URL = r'''(?x) |
433 | https?:// | |
434 | (?:(?:www|m)\.)?soundcloud\.com/ | |
435 | (?P<user>[^/]+) | |
436 | (?:/ | |
3ef2da2d | 437 | (?P<rsrc>tracks|albums|sets|reposts|likes|spotlight) |
16a08978 S |
438 | )? |
439 | /?(?:[?#].*)?$ | |
440 | ''' | |
fbcd7b5f | 441 | IE_NAME = 'soundcloud:user' |
22a6f150 | 442 | _TESTS = [{ |
b6423e6c | 443 | 'url': 'https://soundcloud.com/soft-cell-official', |
22a6f150 | 444 | 'info_dict': { |
b6423e6c S |
445 | 'id': '207965082', |
446 | 'title': 'Soft Cell (All)', | |
22a6f150 | 447 | }, |
b6423e6c | 448 | 'playlist_mincount': 28, |
22a6f150 | 449 | }, { |
b6423e6c | 450 | 'url': 'https://soundcloud.com/soft-cell-official/tracks', |
22a6f150 | 451 | 'info_dict': { |
b6423e6c S |
452 | 'id': '207965082', |
453 | 'title': 'Soft Cell (Tracks)', | |
22a6f150 | 454 | }, |
b6423e6c | 455 | 'playlist_mincount': 27, |
03b9c944 | 456 | }, { |
b6423e6c S |
457 | 'url': 'https://soundcloud.com/soft-cell-official/albums', |
458 | 'info_dict': { | |
459 | 'id': '207965082', | |
460 | 'title': 'Soft Cell (Albums)', | |
461 | }, | |
462 | 'playlist_mincount': 1, | |
463 | }, { | |
464 | 'url': 'https://soundcloud.com/jcv246/sets', | |
80fb6d4a | 465 | 'info_dict': { |
b6423e6c S |
466 | 'id': '12982173', |
467 | 'title': 'Jordi / cv (Playlists)', | |
80fb6d4a | 468 | }, |
8e45e1cc | 469 | 'playlist_mincount': 2, |
80fb6d4a | 470 | }, { |
b6423e6c | 471 | 'url': 'https://soundcloud.com/jcv246/reposts', |
80fb6d4a | 472 | 'info_dict': { |
b6423e6c S |
473 | 'id': '12982173', |
474 | 'title': 'Jordi / cv (Reposts)', | |
80fb6d4a | 475 | }, |
b6423e6c | 476 | 'playlist_mincount': 6, |
80fb6d4a | 477 | }, { |
b6423e6c | 478 | 'url': 'https://soundcloud.com/clalberg/likes', |
80fb6d4a | 479 | 'info_dict': { |
b6423e6c S |
480 | 'id': '11817582', |
481 | 'title': 'clalberg (Likes)', | |
80fb6d4a | 482 | }, |
b6423e6c | 483 | 'playlist_mincount': 5, |
80fb6d4a S |
484 | }, { |
485 | 'url': 'https://soundcloud.com/grynpyret/spotlight', | |
486 | 'info_dict': { | |
487 | 'id': '7098329', | |
bf2dc9cc | 488 | 'title': 'Grynpyret (Spotlight)', |
80fb6d4a S |
489 | }, |
490 | 'playlist_mincount': 1, | |
22a6f150 | 491 | }] |
92790f4e | 492 | |
80fb6d4a | 493 | _BASE_URL_MAP = { |
3ef2da2d S |
494 | 'all': '%s/stream/users/%%s' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE, |
495 | 'tracks': '%s/users/%%s/tracks' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE, | |
496 | 'albums': '%s/users/%%s/albums' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE, | |
836ef264 | 497 | 'sets': '%s/users/%%s/playlists' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE, |
3ef2da2d | 498 | 'reposts': '%s/stream/users/%%s/reposts' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE, |
836ef264 S |
499 | 'likes': '%s/users/%%s/likes' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE, |
500 | 'spotlight': '%s/users/%%s/spotlight' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE, | |
80fb6d4a S |
501 | } |
502 | ||
503 | _TITLE_MAP = { | |
504 | 'all': 'All', | |
505 | 'tracks': 'Tracks', | |
3ef2da2d | 506 | 'albums': 'Albums', |
80fb6d4a S |
507 | 'sets': 'Playlists', |
508 | 'reposts': 'Reposts', | |
509 | 'likes': 'Likes', | |
510 | 'spotlight': 'Spotlight', | |
511 | } | |
512 | ||
92790f4e JMF |
513 | def _real_extract(self, url): |
514 | mobj = re.match(self._VALID_URL, url) | |
515 | uploader = mobj.group('user') | |
516 | ||
f1c05100 | 517 | url = 'https://soundcloud.com/%s/' % uploader |
92790f4e | 518 | resolv_url = self._resolv_url(url) |
20991253 PH |
519 | user = self._download_json( |
520 | resolv_url, uploader, 'Downloading user info') | |
80fb6d4a S |
521 | |
522 | resource = mobj.group('rsrc') or 'all' | |
80fb6d4a | 523 | |
836ef264 S |
524 | return self._extract_playlist( |
525 | self._BASE_URL_MAP[resource] % user['id'], compat_str(user['id']), | |
526 | '%s (%s)' % (user['username'], self._TITLE_MAP[resource])) | |
97afd99a | 527 | |
92790f4e | 528 | |
836ef264 S |
529 | class SoundcloudTrackStationIE(SoundcloudPagedPlaylistBaseIE): |
530 | _VALID_URL = r'https?://(?:(?:www|m)\.)?soundcloud\.com/stations/track/[^/]+/(?P<id>[^/?#&]+)' | |
531 | IE_NAME = 'soundcloud:trackstation' | |
532 | _TESTS = [{ | |
533 | 'url': 'https://soundcloud.com/stations/track/officialsundial/your-text', | |
534 | 'info_dict': { | |
535 | 'id': '286017854', | |
536 | 'title': 'Track station: your-text', | |
537 | }, | |
538 | 'playlist_mincount': 47, | |
539 | }] | |
80fb6d4a | 540 | |
836ef264 S |
541 | def _real_extract(self, url): |
542 | track_name = self._match_id(url) | |
80fb6d4a | 543 | |
836ef264 | 544 | webpage = self._download_webpage(url, track_name) |
97afd99a | 545 | |
836ef264 S |
546 | track_id = self._search_regex( |
547 | r'soundcloud:track-stations:(\d+)', webpage, 'track id') | |
92790f4e | 548 | |
836ef264 S |
549 | return self._extract_playlist( |
550 | '%s/stations/soundcloud:track-stations:%s/tracks' | |
551 | % (self._API_V2_BASE, track_id), | |
552 | track_id, 'Track station: %s' % track_name) | |
20991253 PH |
553 | |
554 | ||
7518a61d | 555 | class SoundcloudPlaylistIE(SoundcloudPlaylistBaseIE): |
46f74bcf | 556 | _VALID_URL = r'https?://api\.soundcloud\.com/playlists/(?P<id>[0-9]+)(?:/?\?secret_token=(?P<token>[^&]+?))?$' |
20991253 | 557 | IE_NAME = 'soundcloud:playlist' |
46f74bcf | 558 | _TESTS = [{ |
f1c05100 | 559 | 'url': 'https://api.soundcloud.com/playlists/4110309', |
46f74bcf PH |
560 | 'info_dict': { |
561 | 'id': '4110309', | |
562 | 'title': 'TILT Brass - Bowery Poetry Club, August \'03 [Non-Site SCR 02]', | |
563 | 'description': 're:.*?TILT Brass - Bowery Poetry Club', | |
564 | }, | |
565 | 'playlist_count': 6, | |
566 | }] | |
20991253 PH |
567 | |
568 | def _real_extract(self, url): | |
569 | mobj = re.match(self._VALID_URL, url) | |
570 | playlist_id = mobj.group('id') | |
571 | base_url = '%s//api.soundcloud.com/playlists/%s.json?' % (self.http_scheme(), playlist_id) | |
572 | ||
2f834e93 | 573 | data_dict = { |
20991253 | 574 | 'client_id': self._CLIENT_ID, |
2f834e93 | 575 | } |
576 | token = mobj.group('token') | |
577 | ||
578 | if token: | |
579 | data_dict['secret_token'] = token | |
580 | ||
15707c7e | 581 | data = compat_urllib_parse_urlencode(data_dict) |
20991253 PH |
582 | data = self._download_json( |
583 | base_url + data, playlist_id, 'Downloading playlist') | |
584 | ||
8e45e1cc | 585 | entries = self._extract_track_entries(data['tracks']) |
20991253 PH |
586 | |
587 | return { | |
588 | '_type': 'playlist', | |
589 | 'id': playlist_id, | |
590 | 'title': data.get('title'), | |
591 | 'description': data.get('description'), | |
592 | 'entries': entries, | |
92790f4e | 593 | } |
2abf7cab | 594 | |
595 | ||
596 | class SoundcloudSearchIE(SearchInfoExtractor, SoundcloudIE): | |
597 | IE_NAME = 'soundcloud:search' | |
598 | IE_DESC = 'Soundcloud search' | |
328a22e1 | 599 | _MAX_RESULTS = float('inf') |
2abf7cab | 600 | _TESTS = [{ |
601 | 'url': 'scsearch15:post-avant jazzcore', | |
602 | 'info_dict': { | |
603 | 'title': 'post-avant jazzcore', | |
604 | }, | |
605 | 'playlist_count': 15, | |
606 | }] | |
607 | ||
608 | _SEARCH_KEY = 'scsearch' | |
328a22e1 | 609 | _MAX_RESULTS_PER_PAGE = 200 |
610 | _DEFAULT_RESULTS_PER_PAGE = 50 | |
c30943b1 | 611 | _API_V2_BASE = 'https://api-v2.soundcloud.com' |
2abf7cab | 612 | |
613 | def _get_collection(self, endpoint, collection_id, **query): | |
a3372437 | 614 | limit = min( |
328a22e1 | 615 | query.get('limit', self._DEFAULT_RESULTS_PER_PAGE), |
616 | self._MAX_RESULTS_PER_PAGE) | |
f6c903e7 | 617 | query['limit'] = limit |
2abf7cab | 618 | query['client_id'] = self._CLIENT_ID |
619 | query['linked_partitioning'] = '1' | |
f6c903e7 | 620 | query['offset'] = 0 |
15707c7e | 621 | data = compat_urllib_parse_urlencode(query) |
f6c903e7 | 622 | next_url = '{0}{1}?{2}'.format(self._API_V2_BASE, endpoint, data) |
2abf7cab | 623 | |
2abf7cab | 624 | collected_results = 0 |
625 | ||
f6c903e7 | 626 | for i in itertools.count(1): |
7e347275 | 627 | response = self._download_json( |
f6c903e7 | 628 | next_url, collection_id, 'Downloading page {0}'.format(i), |
7e347275 | 629 | 'Unable to download API page') |
2abf7cab | 630 | |
f6c903e7 S |
631 | collection = response.get('collection', []) |
632 | if not collection: | |
633 | break | |
2abf7cab | 634 | |
f6c903e7 | 635 | collection = list(filter(bool, collection)) |
2abf7cab | 636 | collected_results += len(collection) |
637 | ||
f6c903e7 S |
638 | for item in collection: |
639 | yield self.url_result(item['uri'], SoundcloudIE.ie_key()) | |
2abf7cab | 640 | |
f6c903e7 | 641 | if not collection or collected_results >= limit: |
2abf7cab | 642 | break |
643 | ||
7e347275 | 644 | next_url = response.get('next_href') |
f6c903e7 S |
645 | if not next_url: |
646 | break | |
2abf7cab | 647 | |
648 | def _get_n_results(self, query, n): | |
f6c903e7 S |
649 | tracks = self._get_collection('/search/tracks', query, limit=n, q=query) |
650 | return self.playlist_result(tracks, playlist_title=query) |