]>
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 ( |
3bed6217 RA |
12 | compat_HTTPError, |
13 | compat_kwargs, | |
aad0d6d5 | 14 | compat_str, |
668de34c | 15 | compat_urlparse, |
1cc79574 PH |
16 | ) |
17 | from ..utils import ( | |
de7aade2 | 18 | error_to_compat_str, |
aad0d6d5 | 19 | ExtractorError, |
e09965d5 | 20 | float_or_none, |
548c3957 | 21 | HEADRequest, |
eb920777 | 22 | int_or_none, |
e09965d5 | 23 | KNOWN_EXTENSIONS, |
e09965d5 S |
24 | mimetype2ext, |
25 | str_or_none, | |
f516f440 S |
26 | try_get, |
27 | unified_timestamp, | |
d7c7100e | 28 | update_url_query, |
7c5307f4 | 29 | url_or_none, |
d7c7100e | 30 | ) |
aad0d6d5 PH |
31 | |
32 | ||
548c3957 | 33 | class SoundcloudEmbedIE(InfoExtractor): |
cf80ff18 RA |
34 | _VALID_URL = r'https?://(?:w|player|p)\.soundcloud\.com/player/?.*?\burl=(?P<id>.+)' |
35 | _TEST = { | |
36 | # from https://www.soundi.fi/uutiset/ennakkokuuntelussa-timo-kaukolammen-station-to-station-to-station-julkaisua-juhlitaan-tanaan-g-livelabissa/ | |
37 | 'url': 'https://w.soundcloud.com/player/?visual=true&url=https%3A%2F%2Fapi.soundcloud.com%2Fplaylists%2F922213810&show_artwork=true&maxwidth=640&maxheight=960&dnt=1&secret_token=s-ziYey', | |
38 | 'only_matching': True, | |
39 | } | |
548c3957 RA |
40 | |
41 | @staticmethod | |
42 | def _extract_urls(webpage): | |
43 | return [m.group('url') for m in re.finditer( | |
44 | r'<iframe[^>]+src=(["\'])(?P<url>(?:https?://)?(?:w\.)?soundcloud\.com/player.+?)\1', | |
45 | webpage)] | |
46 | ||
47 | def _real_extract(self, url): | |
cf80ff18 RA |
48 | query = compat_urlparse.parse_qs( |
49 | compat_urlparse.urlparse(url).query) | |
50 | api_url = query['url'][0] | |
51 | secret_token = query.get('secret_token') | |
52 | if secret_token: | |
53 | api_url = update_url_query(api_url, {'secret_token': secret_token[0]}) | |
54 | return self.url_result(api_url) | |
548c3957 RA |
55 | |
56 | ||
aad0d6d5 PH |
57 | class SoundcloudIE(InfoExtractor): |
58 | """Information extractor for soundcloud.com | |
59 | To access the media, the uid of the song and a stream token | |
60 | must be extracted from the page source and the script must make | |
61 | a request to media.soundcloud.com/crossdomain.xml. Then | |
62 | the media can be grabbed by requesting from an url composed | |
63 | of the stream token and uid | |
64 | """ | |
65 | ||
20991253 | 66 | _VALID_URL = r'''(?x)^(?:https?://)? |
71507a11 | 67 | (?:(?:(?:www\.|m\.)?soundcloud\.com/ |
836ef264 | 68 | (?!stations/track) |
4ff50ef8 | 69 | (?P<uploader>[\w\d-]+)/ |
3ef2da2d | 70 | (?!(?:tracks|albums|sets(?:/.+?)?|reposts|likes|spotlight)/?(?:$|[?#])) |
22a6f150 | 71 | (?P<title>[\w\d-]+)/? |
de2dd4c5 | 72 | (?P<token>[^?]+?)?(?:[?].*)?$) |
548c3957 | 73 | |(?:api(?:-v2)?\.soundcloud\.com/tracks/(?P<track_id>\d+) |
0403b069 | 74 | (?:/?\?secret_token=(?P<secret_token>[^&]+))?) |
eb6a41ba JMF |
75 | ) |
76 | ''' | |
fbcd7b5f | 77 | IE_NAME = 'soundcloud' |
12c167c8 JMF |
78 | _TESTS = [ |
79 | { | |
fbcd7b5f | 80 | 'url': 'http://soundcloud.com/ethmusic/lostin-powers-she-so-heavy', |
fbcd7b5f PH |
81 | 'md5': 'ebef0a451b909710ed1d7787dddbf0d7', |
82 | 'info_dict': { | |
0eb9fb9f JMF |
83 | 'id': '62986583', |
84 | 'ext': 'mp3', | |
f516f440 | 85 | 'title': 'Lostin Powers - She so Heavy (SneakPreview) Adrian Ackers Blueprint 1', |
0eb9fb9f JMF |
86 | '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', |
87 | 'uploader': 'E.T. ExTerrestrial Music', | |
548c3957 | 88 | 'uploader_id': '1571244', |
f516f440 S |
89 | 'timestamp': 1349920598, |
90 | 'upload_date': '20121011', | |
e09965d5 | 91 | 'duration': 143.216, |
4bfd294e | 92 | 'license': 'all-rights-reserved', |
f516f440 S |
93 | 'view_count': int, |
94 | 'like_count': int, | |
95 | 'comment_count': int, | |
96 | 'repost_count': int, | |
12c167c8 JMF |
97 | } |
98 | }, | |
e4e5fa6e | 99 | # not streamable song, preview |
12c167c8 | 100 | { |
fbcd7b5f PH |
101 | 'url': 'https://soundcloud.com/the-concept-band/goldrushed-mastered?in=the-concept-band/sets/the-royal-concept-ep', |
102 | 'info_dict': { | |
103 | 'id': '47127627', | |
104 | 'ext': 'mp3', | |
105 | 'title': 'Goldrushed', | |
63ad0315 | 106 | 'description': 'From Stockholm Sweden\r\nPovel / Magnus / Filip / David\r\nwww.theroyalconcept.com', |
fbcd7b5f | 107 | 'uploader': 'The Royal Concept', |
548c3957 | 108 | 'uploader_id': '9615865', |
f516f440 | 109 | 'timestamp': 1337635207, |
fbcd7b5f | 110 | 'upload_date': '20120521', |
f516f440 | 111 | 'duration': 30, |
4bfd294e | 112 | 'license': 'all-rights-reserved', |
f516f440 S |
113 | 'view_count': int, |
114 | 'like_count': int, | |
115 | 'comment_count': int, | |
116 | 'repost_count': int, | |
12c167c8 | 117 | }, |
fbcd7b5f | 118 | 'params': { |
12c167c8 | 119 | # rtmp |
fbcd7b5f | 120 | 'skip_download': True, |
12c167c8 JMF |
121 | }, |
122 | }, | |
de2dd4c5 JMF |
123 | # private link |
124 | { | |
fbcd7b5f PH |
125 | 'url': 'https://soundcloud.com/jaimemf/youtube-dl-test-video-a-y-baw/s-8Pjrp', |
126 | 'md5': 'aa0dd32bfea9b0c5ef4f02aacd080604', | |
127 | 'info_dict': { | |
128 | 'id': '123998367', | |
129 | 'ext': 'mp3', | |
130 | 'title': 'Youtube - Dl Test Video \'\' Ä↭', | |
fbcd7b5f | 131 | 'description': 'test chars: \"\'/\\ä↭', |
f516f440 | 132 | 'uploader': 'jaimeMF', |
548c3957 | 133 | 'uploader_id': '69767071', |
f516f440 | 134 | 'timestamp': 1386604920, |
fbcd7b5f | 135 | 'upload_date': '20131209', |
e09965d5 | 136 | 'duration': 9.927, |
4bfd294e | 137 | 'license': 'all-rights-reserved', |
f516f440 S |
138 | 'view_count': int, |
139 | 'like_count': int, | |
140 | 'comment_count': int, | |
141 | 'repost_count': int, | |
de2dd4c5 JMF |
142 | }, |
143 | }, | |
9296738f | 144 | # private link (alt format) |
145 | { | |
146 | 'url': 'https://api.soundcloud.com/tracks/123998367?secret_token=s-8Pjrp', | |
147 | 'md5': 'aa0dd32bfea9b0c5ef4f02aacd080604', | |
148 | 'info_dict': { | |
149 | 'id': '123998367', | |
150 | 'ext': 'mp3', | |
151 | 'title': 'Youtube - Dl Test Video \'\' Ä↭', | |
9296738f | 152 | 'description': 'test chars: \"\'/\\ä↭', |
f516f440 | 153 | 'uploader': 'jaimeMF', |
548c3957 | 154 | 'uploader_id': '69767071', |
f516f440 | 155 | 'timestamp': 1386604920, |
9296738f | 156 | 'upload_date': '20131209', |
e09965d5 | 157 | 'duration': 9.927, |
4bfd294e | 158 | 'license': 'all-rights-reserved', |
f516f440 S |
159 | 'view_count': int, |
160 | 'like_count': int, | |
161 | 'comment_count': int, | |
162 | 'repost_count': int, | |
9296738f | 163 | }, |
164 | }, | |
f67ca84d JMF |
165 | # downloadable song |
166 | { | |
00a82ea8 | 167 | 'url': 'https://soundcloud.com/oddsamples/bus-brakes', |
eae12e3f | 168 | 'md5': '7624f2351f8a3b2e7cd51522496e7631', |
fbcd7b5f | 169 | 'info_dict': { |
00a82ea8 | 170 | 'id': '128590877', |
eae12e3f | 171 | 'ext': 'mp3', |
00a82ea8 | 172 | 'title': 'Bus Brakes', |
0eb9fb9f | 173 | 'description': 'md5:0053ca6396e8d2fd7b7e1595ef12ab66', |
00a82ea8 | 174 | 'uploader': 'oddsamples', |
548c3957 | 175 | 'uploader_id': '73680509', |
f516f440 | 176 | 'timestamp': 1389232924, |
00a82ea8 | 177 | 'upload_date': '20140109', |
e09965d5 | 178 | 'duration': 17.346, |
4bfd294e | 179 | 'license': 'cc-by-sa', |
f516f440 S |
180 | 'view_count': int, |
181 | 'like_count': int, | |
182 | 'comment_count': int, | |
183 | 'repost_count': int, | |
f67ca84d JMF |
184 | }, |
185 | }, | |
d7c7100e S |
186 | # private link, downloadable format |
187 | { | |
188 | 'url': 'https://soundcloud.com/oriuplift/uponly-238-no-talking-wav/s-AyZUd', | |
189 | 'md5': '64a60b16e617d41d0bef032b7f55441e', | |
190 | 'info_dict': { | |
191 | 'id': '340344461', | |
192 | 'ext': 'wav', | |
193 | 'title': 'Uplifting Only 238 [No Talking] (incl. Alex Feed Guestmix) (Aug 31, 2017) [wav]', | |
194 | 'description': 'md5:fa20ee0fca76a3d6df8c7e57f3715366', | |
195 | 'uploader': 'Ori Uplift Music', | |
548c3957 | 196 | 'uploader_id': '12563093', |
f516f440 | 197 | 'timestamp': 1504206263, |
d7c7100e | 198 | 'upload_date': '20170831', |
e09965d5 | 199 | 'duration': 7449.096, |
d7c7100e | 200 | 'license': 'all-rights-reserved', |
f516f440 S |
201 | 'view_count': int, |
202 | 'like_count': int, | |
203 | 'comment_count': int, | |
204 | 'repost_count': int, | |
d7c7100e S |
205 | }, |
206 | }, | |
0b0870f9 PV |
207 | # no album art, use avatar pic for thumbnail |
208 | { | |
209 | 'url': 'https://soundcloud.com/garyvee/sideways-prod-mad-real', | |
210 | 'md5': '59c7872bc44e5d99b7211891664760c2', | |
211 | 'info_dict': { | |
212 | 'id': '309699954', | |
213 | 'ext': 'mp3', | |
214 | 'title': 'Sideways (Prod. Mad Real)', | |
215 | 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e', | |
216 | 'uploader': 'garyvee', | |
548c3957 | 217 | 'uploader_id': '2366352', |
f516f440 | 218 | 'timestamp': 1488152409, |
0b0870f9 | 219 | 'upload_date': '20170226', |
e09965d5 | 220 | 'duration': 207.012, |
0b0870f9 PV |
221 | 'thumbnail': r're:https?://.*\.jpg', |
222 | 'license': 'all-rights-reserved', | |
f516f440 S |
223 | 'view_count': int, |
224 | 'like_count': int, | |
225 | 'comment_count': int, | |
226 | 'repost_count': int, | |
0b0870f9 PV |
227 | }, |
228 | 'params': { | |
229 | 'skip_download': True, | |
230 | }, | |
231 | }, | |
843ad179 | 232 | # not available via api.soundcloud.com/i1/tracks/id/streams |
e09965d5 S |
233 | { |
234 | 'url': 'https://soundcloud.com/giovannisarani/mezzo-valzer', | |
235 | 'md5': 'e22aecd2bc88e0e4e432d7dcc0a1abf7', | |
236 | 'info_dict': { | |
237 | 'id': '583011102', | |
238 | 'ext': 'mp3', | |
239 | 'title': 'Mezzo Valzer', | |
240 | 'description': 'md5:4138d582f81866a530317bae316e8b61', | |
241 | 'uploader': 'Giovanni Sarani', | |
548c3957 | 242 | 'uploader_id': '3352531', |
e09965d5 S |
243 | 'timestamp': 1551394171, |
244 | 'upload_date': '20190228', | |
245 | 'duration': 180.157, | |
246 | 'thumbnail': r're:https?://.*\.jpg', | |
247 | 'license': 'all-rights-reserved', | |
248 | 'view_count': int, | |
249 | 'like_count': int, | |
250 | 'comment_count': int, | |
251 | 'repost_count': int, | |
252 | }, | |
253 | 'expected_warnings': ['Unable to download JSON metadata'], | |
254 | } | |
12c167c8 | 255 | ] |
aad0d6d5 | 256 | |
548c3957 RA |
257 | _API_BASE = 'https://api.soundcloud.com/' |
258 | _API_V2_BASE = 'https://api-v2.soundcloud.com/' | |
259 | _BASE_URL = 'https://soundcloud.com/' | |
548c3957 RA |
260 | _IMAGE_REPL_RE = r'-([0-9a-z]+)\.jpg' |
261 | ||
262 | _ARTWORK_MAP = { | |
263 | 'mini': 16, | |
264 | 'tiny': 20, | |
265 | 'small': 32, | |
266 | 'badge': 47, | |
267 | 't67x67': 67, | |
268 | 'large': 100, | |
269 | 't300x300': 300, | |
270 | 'crop': 400, | |
271 | 't500x500': 500, | |
272 | 'original': 0, | |
273 | } | |
fbdf8d15 | 274 | |
de7aade2 RA |
275 | def _store_client_id(self, client_id): |
276 | self._downloader.cache.store('soundcloud', 'client_id', client_id) | |
277 | ||
3bed6217 RA |
278 | def _update_client_id(self): |
279 | webpage = self._download_webpage('https://soundcloud.com/', None) | |
280 | for src in reversed(re.findall(r'<script[^>]+src="([^"]+)"', webpage)): | |
281 | script = self._download_webpage(src, None, fatal=False) | |
282 | if script: | |
283 | client_id = self._search_regex( | |
284 | r'client_id\s*:\s*"([0-9a-zA-Z]{32})"', | |
285 | script, 'client id', default=None) | |
286 | if client_id: | |
287 | self._CLIENT_ID = client_id | |
de7aade2 | 288 | self._store_client_id(client_id) |
3bed6217 RA |
289 | return |
290 | raise ExtractorError('Unable to extract client id') | |
291 | ||
292 | def _download_json(self, *args, **kwargs): | |
de7aade2 RA |
293 | non_fatal = kwargs.get('fatal') is False |
294 | if non_fatal: | |
295 | del kwargs['fatal'] | |
3bed6217 RA |
296 | query = kwargs.get('query', {}).copy() |
297 | for _ in range(2): | |
298 | query['client_id'] = self._CLIENT_ID | |
299 | kwargs['query'] = query | |
300 | try: | |
301 | return super(SoundcloudIE, self)._download_json(*args, **compat_kwargs(kwargs)) | |
302 | except ExtractorError as e: | |
303 | if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401: | |
de7aade2 | 304 | self._store_client_id(None) |
3bed6217 RA |
305 | self._update_client_id() |
306 | continue | |
de7aade2 RA |
307 | elif non_fatal: |
308 | self._downloader.report_warning(error_to_compat_str(e)) | |
309 | return False | |
3bed6217 RA |
310 | raise |
311 | ||
312 | def _real_initialize(self): | |
313 | self._CLIENT_ID = self._downloader.cache.load('soundcloud', 'client_id') or 'YUKXoArFcqrlQn9tfNHvvyfnDISj04zk' | |
314 | ||
7d239269 JMF |
315 | @classmethod |
316 | def _resolv_url(cls, url): | |
3bed6217 | 317 | return SoundcloudIE._API_V2_BASE + 'resolve?url=' + url |
7d239269 | 318 | |
548c3957 | 319 | def _extract_info_dict(self, info, full_title=None, secret_token=None, version=2): |
12c167c8 | 320 | track_id = compat_str(info['id']) |
f516f440 | 321 | title = info['title'] |
548c3957 | 322 | track_base_url = self._API_BASE + 'tracks/%s' % track_id |
e09965d5 S |
323 | |
324 | format_urls = set() | |
5e114e4b | 325 | formats = [] |
73602bcd | 326 | query = {'client_id': self._CLIENT_ID} |
548c3957 | 327 | if secret_token: |
73602bcd | 328 | query['secret_token'] = secret_token |
548c3957 | 329 | |
2e9ad59a | 330 | if info.get('downloadable') and info.get('has_downloads_left'): |
73602bcd | 331 | format_url = update_url_query( |
548c3957 | 332 | info.get('download_url') or track_base_url + '/download', query) |
e09965d5 | 333 | format_urls.add(format_url) |
548c3957 RA |
334 | if version == 2: |
335 | v1_info = self._download_json( | |
336 | track_base_url, track_id, query=query, fatal=False) or {} | |
337 | else: | |
338 | v1_info = info | |
5e114e4b | 339 | formats.append({ |
2a15e706 | 340 | 'format_id': 'download', |
548c3957 RA |
341 | 'ext': v1_info.get('original_format') or 'mp3', |
342 | 'filesize': int_or_none(v1_info.get('original_content_size')), | |
2a15e706 | 343 | 'url': format_url, |
5e114e4b PH |
344 | 'preference': 10, |
345 | }) | |
346 | ||
548c3957 | 347 | def invalid_url(url): |
e4e5fa6e | 348 | return not url or url in format_urls |
e09965d5 | 349 | |
e4e5fa6e | 350 | def add_format(f, protocol, is_preview=False): |
548c3957 RA |
351 | mobj = re.search(r'\.(?P<abr>\d+)\.(?P<ext>[0-9a-z]{3,4})(?=[/?])', stream_url) |
352 | if mobj: | |
353 | for k, v in mobj.groupdict().items(): | |
354 | if not f.get(k): | |
355 | f[k] = v | |
356 | format_id_list = [] | |
357 | if protocol: | |
358 | format_id_list.append(protocol) | |
359 | for k in ('ext', 'abr'): | |
360 | v = f.get(k) | |
361 | if v: | |
362 | format_id_list.append(v) | |
e4e5fa6e S |
363 | preview = is_preview or re.search(r'/(?:preview|playlist)/0/30/', f['url']) |
364 | if preview: | |
365 | format_id_list.append('preview') | |
548c3957 RA |
366 | abr = f.get('abr') |
367 | if abr: | |
368 | f['abr'] = int(abr) | |
369 | f.update({ | |
370 | 'format_id': '_'.join(format_id_list), | |
371 | 'protocol': 'm3u8_native' if protocol == 'hls' else 'http', | |
e4e5fa6e | 372 | 'preference': -10 if preview else None, |
548c3957 RA |
373 | }) |
374 | formats.append(f) | |
e09965d5 S |
375 | |
376 | # New API | |
377 | transcodings = try_get( | |
378 | info, lambda x: x['media']['transcodings'], list) or [] | |
379 | for t in transcodings: | |
380 | if not isinstance(t, dict): | |
3a194cb4 | 381 | continue |
e09965d5 | 382 | format_url = url_or_none(t.get('url')) |
e4e5fa6e | 383 | if not format_url: |
e09965d5 S |
384 | continue |
385 | stream = self._download_json( | |
548c3957 | 386 | format_url, track_id, query=query, fatal=False) |
e09965d5 S |
387 | if not isinstance(stream, dict): |
388 | continue | |
389 | stream_url = url_or_none(stream.get('url')) | |
548c3957 | 390 | if invalid_url(stream_url): |
e09965d5 S |
391 | continue |
392 | format_urls.add(stream_url) | |
548c3957 RA |
393 | stream_format = t.get('format') or {} |
394 | protocol = stream_format.get('protocol') | |
e09965d5 S |
395 | if protocol != 'hls' and '/hls' in format_url: |
396 | protocol = 'hls' | |
397 | ext = None | |
398 | preset = str_or_none(t.get('preset')) | |
399 | if preset: | |
400 | ext = preset.split('_')[0] | |
548c3957 RA |
401 | if ext not in KNOWN_EXTENSIONS: |
402 | ext = mimetype2ext(stream_format.get('mime_type')) | |
403 | add_format({ | |
e09965d5 | 404 | 'url': stream_url, |
e09965d5 | 405 | 'ext': ext, |
e4e5fa6e S |
406 | }, 'http' if protocol == 'progressive' else protocol, |
407 | t.get('snipped') or '/preview/' in format_url) | |
548c3957 RA |
408 | |
409 | if not formats: | |
410 | # Old API, does not work for some tracks (e.g. | |
411 | # https://soundcloud.com/giovannisarani/mezzo-valzer) | |
412 | # and might serve preview URLs (e.g. | |
413 | # http://www.soundcloud.com/snbrn/ele) | |
414 | format_dict = self._download_json( | |
415 | track_base_url + '/streams', track_id, | |
416 | 'Downloading track url', query=query, fatal=False) or {} | |
417 | ||
418 | for key, stream_url in format_dict.items(): | |
419 | if invalid_url(stream_url): | |
420 | continue | |
421 | format_urls.add(stream_url) | |
422 | mobj = re.search(r'(http|hls)_([^_]+)_(\d+)_url', key) | |
423 | if mobj: | |
424 | protocol, ext, abr = mobj.groups() | |
425 | add_format({ | |
426 | 'abr': abr, | |
427 | 'ext': ext, | |
428 | 'url': stream_url, | |
429 | }, protocol) | |
3a194cb4 S |
430 | |
431 | if not formats: | |
432 | # We fallback to the stream_url in the original info, this | |
433 | # cannot be always used, sometimes it can give an HTTP 404 error | |
548c3957 RA |
434 | urlh = self._request_webpage( |
435 | HEADRequest(info.get('stream_url') or track_base_url + '/stream'), | |
436 | track_id, query=query, fatal=False) | |
437 | if urlh: | |
438 | stream_url = urlh.geturl() | |
439 | if not invalid_url(stream_url): | |
440 | add_format({'url': stream_url}, 'http') | |
3a194cb4 S |
441 | |
442 | for f in formats: | |
443 | f['vcodec'] = 'none' | |
2a15e706 | 444 | |
562ceab1 | 445 | self._sort_formats(formats) |
64bb5187 | 446 | |
548c3957 RA |
447 | user = info.get('user') or {} |
448 | ||
449 | thumbnails = [] | |
450 | artwork_url = info.get('artwork_url') | |
451 | thumbnail = artwork_url or user.get('avatar_url') | |
452 | if isinstance(thumbnail, compat_str): | |
453 | if re.search(self._IMAGE_REPL_RE, thumbnail): | |
454 | for image_id, size in self._ARTWORK_MAP.items(): | |
455 | i = { | |
456 | 'id': image_id, | |
457 | 'url': re.sub(self._IMAGE_REPL_RE, '-%s.jpg' % image_id, thumbnail), | |
458 | } | |
459 | if image_id == 'tiny' and not artwork_url: | |
460 | size = 18 | |
461 | elif image_id == 'original': | |
462 | i['preference'] = 10 | |
463 | if size: | |
464 | i.update({ | |
465 | 'width': size, | |
466 | 'height': size, | |
467 | }) | |
468 | thumbnails.append(i) | |
469 | else: | |
470 | thumbnails = [{'url': thumbnail}] | |
471 | ||
472 | def extract_count(key): | |
473 | return int_or_none(info.get('%s_count' % key)) | |
474 | ||
475 | return { | |
476 | 'id': track_id, | |
477 | 'uploader': user.get('username'), | |
478 | 'uploader_id': str_or_none(user.get('id')) or user.get('permalink'), | |
479 | 'uploader_url': user.get('permalink_url'), | |
480 | 'timestamp': unified_timestamp(info.get('created_at')), | |
481 | 'title': title, | |
482 | 'description': info.get('description'), | |
483 | 'thumbnails': thumbnails, | |
484 | 'duration': float_or_none(info.get('duration'), 1000), | |
485 | 'webpage_url': info.get('permalink_url'), | |
486 | 'license': info.get('license'), | |
487 | 'view_count': extract_count('playback'), | |
488 | 'like_count': extract_count('favoritings') or extract_count('likes'), | |
489 | 'comment_count': extract_count('comment'), | |
490 | 'repost_count': extract_count('reposts'), | |
491 | 'genre': info.get('genre'), | |
492 | 'formats': formats | |
493 | } | |
7d239269 | 494 | |
aad0d6d5 | 495 | def _real_extract(self, url): |
548c3957 | 496 | mobj = re.match(self._VALID_URL, url) |
aad0d6d5 | 497 | |
eb6a41ba | 498 | track_id = mobj.group('track_id') |
4bfd294e | 499 | |
3bed6217 | 500 | query = {} |
548c3957 RA |
501 | if track_id: |
502 | info_json_url = self._API_V2_BASE + 'tracks/' + track_id | |
eb6a41ba | 503 | full_title = track_id |
9296738f | 504 | token = mobj.group('secret_token') |
505 | if token: | |
548c3957 | 506 | query['secret_token'] = token |
eb6a41ba | 507 | else: |
548c3957 | 508 | full_title = resolve_title = '%s/%s' % mobj.group('uploader', 'title') |
de2dd4c5 | 509 | token = mobj.group('token') |
de2dd4c5 JMF |
510 | if token: |
511 | resolve_title += '/%s' % token | |
548c3957 | 512 | info_json_url = self._resolv_url(self._BASE_URL + resolve_title) |
5f6a1245 | 513 | |
548c3957 | 514 | version = 2 |
e09965d5 | 515 | info = self._download_json( |
548c3957 RA |
516 | info_json_url, full_title, 'Downloading info JSON', query=query, fatal=False) |
517 | if not info: | |
518 | info = self._download_json( | |
519 | info_json_url.replace(self._API_V2_BASE, self._API_BASE), | |
520 | full_title, 'Downloading info JSON', query=query) | |
521 | version = 1 | |
e09965d5 | 522 | |
548c3957 | 523 | return self._extract_info_dict(info, full_title, token, version) |
aad0d6d5 | 524 | |
20991253 | 525 | |
7518a61d | 526 | class SoundcloudPlaylistBaseIE(SoundcloudIE): |
548c3957 RA |
527 | def _extract_track_entries(self, tracks, token=None): |
528 | entries = [] | |
529 | for track in tracks: | |
530 | track_id = str_or_none(track.get('id')) | |
531 | url = track.get('permalink_url') | |
532 | if not url: | |
533 | if not track_id: | |
534 | continue | |
535 | url = self._API_V2_BASE + 'tracks/' + track_id | |
536 | if token: | |
537 | url += '?secret_token=' + token | |
538 | entries.append(self.url_result( | |
539 | url, SoundcloudIE.ie_key(), track_id)) | |
540 | return entries | |
8e45e1cc S |
541 | |
542 | ||
7518a61d | 543 | class SoundcloudSetIE(SoundcloudPlaylistBaseIE): |
c808ef81 | 544 | _VALID_URL = r'https?://(?:(?:www|m)\.)?soundcloud\.com/(?P<uploader>[\w\d-]+)/sets/(?P<slug_title>[\w\d-]+)(?:/(?P<token>[^?/]+))?' |
fbcd7b5f | 545 | IE_NAME = 'soundcloud:set' |
22a6f150 PH |
546 | _TESTS = [{ |
547 | 'url': 'https://soundcloud.com/the-concept-band/sets/the-royal-concept-ep', | |
548 | 'info_dict': { | |
a9551e90 | 549 | 'id': '2284613', |
22a6f150 PH |
550 | 'title': 'The Royal Concept EP', |
551 | }, | |
bf2dc9cc | 552 | 'playlist_mincount': 5, |
f7043ef3 S |
553 | }, { |
554 | 'url': 'https://soundcloud.com/the-concept-band/sets/the-royal-concept-ep/token', | |
555 | 'only_matching': True, | |
22a6f150 | 556 | }] |
aad0d6d5 | 557 | |
aad0d6d5 PH |
558 | def _real_extract(self, url): |
559 | mobj = re.match(self._VALID_URL, url) | |
aad0d6d5 | 560 | |
548c3957 | 561 | full_title = '%s/sets/%s' % mobj.group('uploader', 'slug_title') |
2f834e93 | 562 | token = mobj.group('token') |
563 | if token: | |
564 | full_title += '/' + token | |
aad0d6d5 | 565 | |
548c3957 RA |
566 | info = self._download_json(self._resolv_url( |
567 | self._BASE_URL + full_title), full_title) | |
aad0d6d5 | 568 | |
aad0d6d5 | 569 | if 'errors' in info: |
214e74bf JMF |
570 | msgs = (compat_str(err['error_message']) for err in info['errors']) |
571 | raise ExtractorError('unable to download video webpage: %s' % ','.join(msgs)) | |
aad0d6d5 | 572 | |
548c3957 | 573 | entries = self._extract_track_entries(info['tracks'], token) |
b14fa8e6 | 574 | |
548c3957 RA |
575 | return self.playlist_result( |
576 | entries, str_or_none(info.get('id')), info.get('title')) | |
92790f4e JMF |
577 | |
578 | ||
836ef264 | 579 | class SoundcloudPagedPlaylistBaseIE(SoundcloudPlaylistBaseIE): |
836ef264 S |
580 | def _extract_playlist(self, base_url, playlist_id, playlist_title): |
581 | COMMON_QUERY = { | |
548c3957 | 582 | 'limit': 2000000000, |
836ef264 S |
583 | 'linked_partitioning': '1', |
584 | } | |
585 | ||
586 | query = COMMON_QUERY.copy() | |
587 | query['offset'] = 0 | |
588 | ||
548c3957 | 589 | next_href = base_url |
836ef264 S |
590 | |
591 | entries = [] | |
592 | for i in itertools.count(): | |
593 | response = self._download_json( | |
548c3957 RA |
594 | next_href, playlist_id, |
595 | 'Downloading track page %s' % (i + 1), query=query) | |
836ef264 S |
596 | |
597 | collection = response['collection'] | |
3ef2da2d S |
598 | |
599 | if not isinstance(collection, list): | |
600 | collection = [] | |
601 | ||
602 | # Empty collection may be returned, in this case we proceed | |
603 | # straight to next_href | |
836ef264 | 604 | |
7c5307f4 S |
605 | def resolve_entry(candidates): |
606 | for cand in candidates: | |
607 | if not isinstance(cand, dict): | |
608 | continue | |
609 | permalink_url = url_or_none(cand.get('permalink_url')) | |
610 | if not permalink_url: | |
611 | continue | |
612 | return self.url_result( | |
613 | permalink_url, | |
548c3957 RA |
614 | SoundcloudIE.ie_key() if SoundcloudIE.suitable(permalink_url) else None, |
615 | str_or_none(cand.get('id')), cand.get('title')) | |
836ef264 S |
616 | |
617 | for e in collection: | |
7c5307f4 S |
618 | entry = resolve_entry((e, e.get('track'), e.get('playlist'))) |
619 | if entry: | |
620 | entries.append(entry) | |
836ef264 S |
621 | |
622 | next_href = response.get('next_href') | |
623 | if not next_href: | |
624 | break | |
625 | ||
548c3957 RA |
626 | next_href = response['next_href'] |
627 | parsed_next_href = compat_urlparse.urlparse(next_href) | |
628 | query = compat_urlparse.parse_qs(parsed_next_href.query) | |
629 | query.update(COMMON_QUERY) | |
836ef264 S |
630 | |
631 | return { | |
632 | '_type': 'playlist', | |
633 | 'id': playlist_id, | |
634 | 'title': playlist_title, | |
635 | 'entries': entries, | |
636 | } | |
637 | ||
638 | ||
639 | class SoundcloudUserIE(SoundcloudPagedPlaylistBaseIE): | |
16a08978 S |
640 | _VALID_URL = r'''(?x) |
641 | https?:// | |
642 | (?:(?:www|m)\.)?soundcloud\.com/ | |
643 | (?P<user>[^/]+) | |
644 | (?:/ | |
3ef2da2d | 645 | (?P<rsrc>tracks|albums|sets|reposts|likes|spotlight) |
16a08978 S |
646 | )? |
647 | /?(?:[?#].*)?$ | |
648 | ''' | |
fbcd7b5f | 649 | IE_NAME = 'soundcloud:user' |
22a6f150 | 650 | _TESTS = [{ |
b6423e6c | 651 | 'url': 'https://soundcloud.com/soft-cell-official', |
22a6f150 | 652 | 'info_dict': { |
b6423e6c S |
653 | 'id': '207965082', |
654 | 'title': 'Soft Cell (All)', | |
22a6f150 | 655 | }, |
b6423e6c | 656 | 'playlist_mincount': 28, |
22a6f150 | 657 | }, { |
b6423e6c | 658 | 'url': 'https://soundcloud.com/soft-cell-official/tracks', |
22a6f150 | 659 | 'info_dict': { |
b6423e6c S |
660 | 'id': '207965082', |
661 | 'title': 'Soft Cell (Tracks)', | |
22a6f150 | 662 | }, |
b6423e6c | 663 | 'playlist_mincount': 27, |
03b9c944 | 664 | }, { |
b6423e6c S |
665 | 'url': 'https://soundcloud.com/soft-cell-official/albums', |
666 | 'info_dict': { | |
667 | 'id': '207965082', | |
668 | 'title': 'Soft Cell (Albums)', | |
669 | }, | |
670 | 'playlist_mincount': 1, | |
671 | }, { | |
672 | 'url': 'https://soundcloud.com/jcv246/sets', | |
80fb6d4a | 673 | 'info_dict': { |
b6423e6c | 674 | 'id': '12982173', |
548c3957 | 675 | 'title': 'Jordi / cv (Sets)', |
80fb6d4a | 676 | }, |
8e45e1cc | 677 | 'playlist_mincount': 2, |
80fb6d4a | 678 | }, { |
b6423e6c | 679 | 'url': 'https://soundcloud.com/jcv246/reposts', |
80fb6d4a | 680 | 'info_dict': { |
b6423e6c S |
681 | 'id': '12982173', |
682 | 'title': 'Jordi / cv (Reposts)', | |
80fb6d4a | 683 | }, |
b6423e6c | 684 | 'playlist_mincount': 6, |
80fb6d4a | 685 | }, { |
b6423e6c | 686 | 'url': 'https://soundcloud.com/clalberg/likes', |
80fb6d4a | 687 | 'info_dict': { |
b6423e6c S |
688 | 'id': '11817582', |
689 | 'title': 'clalberg (Likes)', | |
80fb6d4a | 690 | }, |
b6423e6c | 691 | 'playlist_mincount': 5, |
80fb6d4a S |
692 | }, { |
693 | 'url': 'https://soundcloud.com/grynpyret/spotlight', | |
694 | 'info_dict': { | |
695 | 'id': '7098329', | |
bf2dc9cc | 696 | 'title': 'Grynpyret (Spotlight)', |
80fb6d4a S |
697 | }, |
698 | 'playlist_mincount': 1, | |
22a6f150 | 699 | }] |
92790f4e | 700 | |
80fb6d4a | 701 | _BASE_URL_MAP = { |
548c3957 RA |
702 | 'all': 'stream/users/%s', |
703 | 'tracks': 'users/%s/tracks', | |
704 | 'albums': 'users/%s/albums', | |
705 | 'sets': 'users/%s/playlists', | |
706 | 'reposts': 'stream/users/%s/reposts', | |
707 | 'likes': 'users/%s/likes', | |
708 | 'spotlight': 'users/%s/spotlight', | |
80fb6d4a S |
709 | } |
710 | ||
92790f4e JMF |
711 | def _real_extract(self, url): |
712 | mobj = re.match(self._VALID_URL, url) | |
713 | uploader = mobj.group('user') | |
714 | ||
20991253 | 715 | user = self._download_json( |
548c3957 RA |
716 | self._resolv_url(self._BASE_URL + uploader), |
717 | uploader, 'Downloading user info') | |
80fb6d4a S |
718 | |
719 | resource = mobj.group('rsrc') or 'all' | |
80fb6d4a | 720 | |
836ef264 | 721 | return self._extract_playlist( |
548c3957 RA |
722 | self._API_V2_BASE + self._BASE_URL_MAP[resource] % user['id'], |
723 | str_or_none(user.get('id')), | |
724 | '%s (%s)' % (user['username'], resource.capitalize())) | |
97afd99a | 725 | |
92790f4e | 726 | |
836ef264 S |
727 | class SoundcloudTrackStationIE(SoundcloudPagedPlaylistBaseIE): |
728 | _VALID_URL = r'https?://(?:(?:www|m)\.)?soundcloud\.com/stations/track/[^/]+/(?P<id>[^/?#&]+)' | |
729 | IE_NAME = 'soundcloud:trackstation' | |
730 | _TESTS = [{ | |
731 | 'url': 'https://soundcloud.com/stations/track/officialsundial/your-text', | |
732 | 'info_dict': { | |
733 | 'id': '286017854', | |
548c3957 | 734 | 'title': 'Track station: your text', |
836ef264 S |
735 | }, |
736 | 'playlist_mincount': 47, | |
737 | }] | |
80fb6d4a | 738 | |
836ef264 S |
739 | def _real_extract(self, url): |
740 | track_name = self._match_id(url) | |
80fb6d4a | 741 | |
548c3957 | 742 | track = self._download_json(self._resolv_url(url), track_name) |
836ef264 | 743 | track_id = self._search_regex( |
548c3957 | 744 | r'soundcloud:track-stations:(\d+)', track['id'], 'track id') |
92790f4e | 745 | |
836ef264 | 746 | return self._extract_playlist( |
548c3957 RA |
747 | self._API_V2_BASE + 'stations/%s/tracks' % track['id'], |
748 | track_id, 'Track station: %s' % track['title']) | |
20991253 PH |
749 | |
750 | ||
7518a61d | 751 | class SoundcloudPlaylistIE(SoundcloudPlaylistBaseIE): |
548c3957 | 752 | _VALID_URL = r'https?://api(?:-v2)?\.soundcloud\.com/playlists/(?P<id>[0-9]+)(?:/?\?secret_token=(?P<token>[^&]+?))?$' |
20991253 | 753 | IE_NAME = 'soundcloud:playlist' |
46f74bcf | 754 | _TESTS = [{ |
f1c05100 | 755 | 'url': 'https://api.soundcloud.com/playlists/4110309', |
46f74bcf PH |
756 | 'info_dict': { |
757 | 'id': '4110309', | |
758 | 'title': 'TILT Brass - Bowery Poetry Club, August \'03 [Non-Site SCR 02]', | |
759 | 'description': 're:.*?TILT Brass - Bowery Poetry Club', | |
760 | }, | |
761 | 'playlist_count': 6, | |
762 | }] | |
20991253 PH |
763 | |
764 | def _real_extract(self, url): | |
765 | mobj = re.match(self._VALID_URL, url) | |
766 | playlist_id = mobj.group('id') | |
20991253 | 767 | |
3bed6217 | 768 | query = {} |
2f834e93 | 769 | token = mobj.group('token') |
2f834e93 | 770 | if token: |
548c3957 | 771 | query['secret_token'] = token |
2f834e93 | 772 | |
20991253 | 773 | data = self._download_json( |
548c3957 RA |
774 | self._API_V2_BASE + 'playlists/' + playlist_id, |
775 | playlist_id, 'Downloading playlist', query=query) | |
20991253 | 776 | |
548c3957 | 777 | entries = self._extract_track_entries(data['tracks'], token) |
20991253 | 778 | |
548c3957 RA |
779 | return self.playlist_result( |
780 | entries, playlist_id, data.get('title'), data.get('description')) | |
2abf7cab | 781 | |
782 | ||
783 | class SoundcloudSearchIE(SearchInfoExtractor, SoundcloudIE): | |
784 | IE_NAME = 'soundcloud:search' | |
785 | IE_DESC = 'Soundcloud search' | |
328a22e1 | 786 | _MAX_RESULTS = float('inf') |
2abf7cab | 787 | _TESTS = [{ |
788 | 'url': 'scsearch15:post-avant jazzcore', | |
789 | 'info_dict': { | |
790 | 'title': 'post-avant jazzcore', | |
791 | }, | |
792 | 'playlist_count': 15, | |
793 | }] | |
794 | ||
795 | _SEARCH_KEY = 'scsearch' | |
328a22e1 | 796 | _MAX_RESULTS_PER_PAGE = 200 |
797 | _DEFAULT_RESULTS_PER_PAGE = 50 | |
2abf7cab | 798 | |
799 | def _get_collection(self, endpoint, collection_id, **query): | |
a3372437 | 800 | limit = min( |
328a22e1 | 801 | query.get('limit', self._DEFAULT_RESULTS_PER_PAGE), |
802 | self._MAX_RESULTS_PER_PAGE) | |
548c3957 RA |
803 | query.update({ |
804 | 'limit': limit, | |
548c3957 RA |
805 | 'linked_partitioning': 1, |
806 | 'offset': 0, | |
807 | }) | |
808 | next_url = update_url_query(self._API_V2_BASE + endpoint, query) | |
2abf7cab | 809 | |
2abf7cab | 810 | collected_results = 0 |
811 | ||
f6c903e7 | 812 | for i in itertools.count(1): |
7e347275 | 813 | response = self._download_json( |
f6c903e7 | 814 | next_url, collection_id, 'Downloading page {0}'.format(i), |
7e347275 | 815 | 'Unable to download API page') |
2abf7cab | 816 | |
f6c903e7 S |
817 | collection = response.get('collection', []) |
818 | if not collection: | |
819 | break | |
2abf7cab | 820 | |
f6c903e7 | 821 | collection = list(filter(bool, collection)) |
2abf7cab | 822 | collected_results += len(collection) |
823 | ||
f6c903e7 S |
824 | for item in collection: |
825 | yield self.url_result(item['uri'], SoundcloudIE.ie_key()) | |
2abf7cab | 826 | |
f6c903e7 | 827 | if not collection or collected_results >= limit: |
2abf7cab | 828 | break |
829 | ||
7e347275 | 830 | next_url = response.get('next_href') |
f6c903e7 S |
831 | if not next_url: |
832 | break | |
2abf7cab | 833 | |
834 | def _get_n_results(self, query, n): | |
548c3957 | 835 | tracks = self._get_collection('search/tracks', query, limit=n, q=query) |
f6c903e7 | 836 | return self.playlist_result(tracks, playlist_title=query) |