]>
Commit | Line | Data |
---|---|---|
e6da9240 | 1 | import itertools |
80cbb6dd PH |
2 | |
3 | from .common import InfoExtractor | |
c96eca42 | 4 | from ..compat import ( |
5d7d805c | 5 | compat_b64decode, |
dd91dfcd | 6 | compat_ord, |
095774e5 | 7 | compat_str, |
c96eca42 | 8 | compat_urllib_parse_unquote, |
c96eca42 | 9 | ) |
1cc79574 | 10 | from ..utils import ( |
9040e2d6 | 11 | ExtractorError, |
095774e5 | 12 | int_or_none, |
5d92b407 RA |
13 | parse_iso8601, |
14 | strip_or_none, | |
095774e5 | 15 | try_get, |
095774e5 | 16 | ) |
80cbb6dd PH |
17 | |
18 | ||
5d92b407 RA |
19 | class MixcloudBaseIE(InfoExtractor): |
20 | def _call_api(self, object_type, object_fields, display_id, username, slug=None): | |
21 | lookup_key = object_type + 'Lookup' | |
22 | return self._download_json( | |
23 | 'https://www.mixcloud.com/graphql', display_id, query={ | |
24 | 'query': '''{ | |
25 | %s(lookup: {username: "%s"%s}) { | |
26 | %s | |
27 | } | |
28 | }''' % (lookup_key, username, ', slug: "%s"' % slug if slug else '', object_fields) | |
29 | })['data'][lookup_key] | |
30 | ||
31 | ||
32 | class MixcloudIE(MixcloudBaseIE): | |
655cb545 | 33 | _VALID_URL = r'https?://(?:(?:www|beta|m)\.)?mixcloud\.com/([^/]+)/(?!stream|uploads|favorites|listens|playlists)([^/]+)' |
d0390a0c | 34 | IE_NAME = 'mixcloud' |
80cbb6dd | 35 | |
58ba6c01 | 36 | _TESTS = [{ |
d0390a0c | 37 | 'url': 'http://www.mixcloud.com/dholbach/cryptkeeper/', |
d0390a0c | 38 | 'info_dict': { |
5d92b407 | 39 | 'id': 'dholbach_cryptkeeper', |
f896e1cc | 40 | 'ext': 'm4a', |
d0390a0c PH |
41 | 'title': 'Cryptkeeper', |
42 | 'description': 'After quite a long silence from myself, finally another Drum\'n\'Bass mix with my favourite current dance floor bangers.', | |
43 | 'uploader': 'Daniel Holbach', | |
44 | 'uploader_id': 'dholbach', | |
ec85ded8 | 45 | 'thumbnail': r're:https?://.*\.jpg', |
57c7411f | 46 | 'view_count': int, |
5d92b407 RA |
47 | 'timestamp': 1321359578, |
48 | 'upload_date': '20111115', | |
19e1d359 | 49 | }, |
58ba6c01 S |
50 | }, { |
51 | 'url': 'http://www.mixcloud.com/gillespeterson/caribou-7-inch-vinyl-mix-chat/', | |
52 | 'info_dict': { | |
5d92b407 | 53 | 'id': 'gillespeterson_caribou-7-inch-vinyl-mix-chat', |
7a757b71 JMF |
54 | 'ext': 'mp3', |
55 | 'title': 'Caribou 7 inch Vinyl Mix & Chat', | |
58ba6c01 | 56 | 'description': 'md5:2b8aec6adce69f9d41724647c65875e8', |
7a757b71 | 57 | 'uploader': 'Gilles Peterson Worldwide', |
58ba6c01 | 58 | 'uploader_id': 'gillespeterson', |
dd91dfcd | 59 | 'thumbnail': 're:https?://.*', |
58ba6c01 | 60 | 'view_count': int, |
5d92b407 RA |
61 | 'timestamp': 1422987057, |
62 | 'upload_date': '20150203', | |
58ba6c01 | 63 | }, |
655cb545 S |
64 | }, { |
65 | 'url': 'https://beta.mixcloud.com/RedLightRadio/nosedrip-15-red-light-radio-01-18-2016/', | |
66 | 'only_matching': True, | |
58ba6c01 | 67 | }] |
5d92b407 | 68 | _DECRYPTION_KEY = 'IFYOUWANTTHEARTISTSTOGETPAIDDONOTDOWNLOADFROMMIXCLOUD' |
80cbb6dd | 69 | |
2384f5a6 TI |
70 | @staticmethod |
71 | def _decrypt_xor_cipher(key, ciphertext): | |
72 | """Encrypt/Decrypt XOR cipher. Both ways are possible because it's XOR.""" | |
73 | return ''.join([ | |
ac668111 | 74 | chr(compat_ord(ch) ^ compat_ord(k)) |
f9934b96 | 75 | for ch, k in zip(ciphertext, itertools.cycle(key))]) |
2384f5a6 | 76 | |
80cbb6dd | 77 | def _real_extract(self, url): |
5ad28e7f | 78 | username, slug = self._match_valid_url(url).groups() |
5d92b407 RA |
79 | username, slug = compat_urllib_parse_unquote(username), compat_urllib_parse_unquote(slug) |
80 | track_id = '%s_%s' % (username, slug) | |
81 | ||
82 | cloudcast = self._call_api('cloudcast', '''audioLength | |
83 | comments(first: 100) { | |
84 | edges { | |
85 | node { | |
86 | comment | |
87 | created | |
88 | user { | |
89 | displayName | |
90 | username | |
91 | } | |
92 | } | |
93 | } | |
94 | totalCount | |
95 | } | |
96 | description | |
97 | favorites { | |
98 | totalCount | |
99 | } | |
100 | featuringArtistList | |
101 | isExclusive | |
102 | name | |
103 | owner { | |
104 | displayName | |
105 | url | |
106 | username | |
107 | } | |
108 | picture(width: 1024, height: 1024) { | |
109 | url | |
110 | } | |
111 | plays | |
112 | publishDate | |
113 | reposts { | |
114 | totalCount | |
115 | } | |
116 | streamInfo { | |
117 | dashUrl | |
118 | hlsUrl | |
119 | url | |
120 | } | |
121 | tags { | |
122 | tag { | |
123 | name | |
124 | } | |
9040e2d6 L |
125 | } |
126 | restrictedReason | |
127 | id''', track_id, username, slug) | |
128 | ||
129 | if not cloudcast: | |
130 | raise ExtractorError('Track not found', expected=True) | |
131 | ||
132 | reason = cloudcast.get('restrictedReason') | |
133 | if reason == 'tracklist': | |
134 | raise ExtractorError('Track unavailable in your country due to licensing restrictions', expected=True) | |
135 | elif reason == 'repeat_play': | |
136 | raise ExtractorError('You have reached your play limit for this track', expected=True) | |
137 | elif reason: | |
138 | raise ExtractorError('Track is restricted', expected=True) | |
dd2535c3 | 139 | |
5d92b407 | 140 | title = cloudcast['name'] |
19e1d359 | 141 | |
5d92b407 RA |
142 | stream_info = cloudcast['streamInfo'] |
143 | formats = [] | |
2384f5a6 | 144 | |
5d92b407 RA |
145 | for url_key in ('url', 'hlsUrl', 'dashUrl'): |
146 | format_url = stream_info.get(url_key) | |
147 | if not format_url: | |
148 | continue | |
149 | decrypted = self._decrypt_xor_cipher( | |
150 | self._DECRYPTION_KEY, compat_b64decode(format_url)) | |
151 | if url_key == 'hlsUrl': | |
152 | formats.extend(self._extract_m3u8_formats( | |
153 | decrypted, track_id, 'mp4', entry_protocol='m3u8_native', | |
154 | m3u8_id='hls', fatal=False)) | |
155 | elif url_key == 'dashUrl': | |
156 | formats.extend(self._extract_mpd_formats( | |
157 | decrypted, track_id, mpd_id='dash', fatal=False)) | |
2384f5a6 | 158 | else: |
5d92b407 RA |
159 | formats.append({ |
160 | 'format_id': 'http', | |
161 | 'url': decrypted, | |
162 | 'downloader_options': { | |
163 | # Mixcloud starts throttling at >~5M | |
164 | 'http_chunk_size': 5242880, | |
165 | }, | |
166 | }) | |
167 | ||
168 | if not formats and cloudcast.get('isExclusive'): | |
b7da73eb | 169 | self.raise_login_required(metadata_available=True) |
5d92b407 RA |
170 | |
171 | self._sort_formats(formats) | |
172 | ||
173 | comments = [] | |
174 | for edge in (try_get(cloudcast, lambda x: x['comments']['edges']) or []): | |
175 | node = edge.get('node') or {} | |
176 | text = strip_or_none(node.get('comment')) | |
177 | if not text: | |
2384f5a6 | 178 | continue |
5d92b407 RA |
179 | user = node.get('user') or {} |
180 | comments.append({ | |
181 | 'author': user.get('displayName'), | |
182 | 'author_id': user.get('username'), | |
183 | 'text': text, | |
184 | 'timestamp': parse_iso8601(node.get('created')), | |
185 | }) | |
2384f5a6 | 186 | |
5d92b407 RA |
187 | tags = [] |
188 | for t in cloudcast.get('tags'): | |
189 | tag = try_get(t, lambda x: x['tag']['name'], compat_str) | |
190 | if not tag: | |
191 | tags.append(tag) | |
192 | ||
193 | get_count = lambda x: int_or_none(try_get(cloudcast, lambda y: y[x]['totalCount'])) | |
194 | ||
195 | owner = cloudcast.get('owner') or {} | |
19e1d359 JMF |
196 | |
197 | return { | |
198 | 'id': track_id, | |
57c7411f | 199 | 'title': title, |
2384f5a6 | 200 | 'formats': formats, |
5d92b407 RA |
201 | 'description': cloudcast.get('description'), |
202 | 'thumbnail': try_get(cloudcast, lambda x: x['picture']['url'], compat_str), | |
203 | 'uploader': owner.get('displayName'), | |
204 | 'timestamp': parse_iso8601(cloudcast.get('publishDate')), | |
205 | 'uploader_id': owner.get('username'), | |
206 | 'uploader_url': owner.get('url'), | |
207 | 'duration': int_or_none(cloudcast.get('audioLength')), | |
208 | 'view_count': int_or_none(cloudcast.get('plays')), | |
209 | 'like_count': get_count('favorites'), | |
210 | 'repost_count': get_count('reposts'), | |
211 | 'comment_count': get_count('comments'), | |
212 | 'comments': comments, | |
213 | 'tags': tags, | |
214 | 'artist': ', '.join(cloudcast.get('featuringArtistList') or []) or None, | |
19e1d359 | 215 | } |
c96eca42 PH |
216 | |
217 | ||
5d92b407 RA |
218 | class MixcloudPlaylistBaseIE(MixcloudBaseIE): |
219 | def _get_cloudcast(self, node): | |
220 | return node | |
c96eca42 | 221 | |
5d92b407 RA |
222 | def _get_playlist_title(self, title, slug): |
223 | return title | |
224 | ||
225 | def _real_extract(self, url): | |
5ad28e7f | 226 | username, slug = self._match_valid_url(url).groups() |
5d92b407 RA |
227 | username = compat_urllib_parse_unquote(username) |
228 | if not slug: | |
229 | slug = 'uploads' | |
230 | else: | |
231 | slug = compat_urllib_parse_unquote(slug) | |
232 | playlist_id = '%s_%s' % (username, slug) | |
e6da9240 | 233 | |
5d92b407 RA |
234 | is_playlist_type = self._ROOT_TYPE == 'playlist' |
235 | playlist_type = 'items' if is_playlist_type else slug | |
236 | list_filter = '' | |
9c250931 | 237 | |
5d92b407 RA |
238 | has_next_page = True |
239 | entries = [] | |
240 | while has_next_page: | |
241 | playlist = self._call_api( | |
242 | self._ROOT_TYPE, '''%s | |
243 | %s | |
244 | %s(first: 100%s) { | |
245 | edges { | |
246 | node { | |
247 | %s | |
248 | } | |
249 | } | |
250 | pageInfo { | |
251 | endCursor | |
252 | hasNextPage | |
253 | } | |
254 | }''' % (self._TITLE_KEY, self._DESCRIPTION_KEY, playlist_type, list_filter, self._NODE_TEMPLATE), | |
255 | playlist_id, username, slug if is_playlist_type else None) | |
256 | ||
257 | items = playlist.get(playlist_type) or {} | |
258 | for edge in items.get('edges', []): | |
259 | cloudcast = self._get_cloudcast(edge.get('node') or {}) | |
260 | cloudcast_url = cloudcast.get('url') | |
261 | if not cloudcast_url: | |
262 | continue | |
30a074c2 | 263 | slug = try_get(cloudcast, lambda x: x['slug'], compat_str) |
264 | owner_username = try_get(cloudcast, lambda x: x['owner']['username'], compat_str) | |
265 | video_id = '%s_%s' % (owner_username, slug) if slug and owner_username else None | |
5d92b407 | 266 | entries.append(self.url_result( |
30a074c2 | 267 | cloudcast_url, MixcloudIE.ie_key(), video_id)) |
e6da9240 | 268 | |
5d92b407 RA |
269 | page_info = items['pageInfo'] |
270 | has_next_page = page_info['hasNextPage'] | |
271 | list_filter = ', after: "%s"' % page_info['endCursor'] | |
9c250931 | 272 | |
5d92b407 RA |
273 | return self.playlist_result( |
274 | entries, playlist_id, | |
275 | self._get_playlist_title(playlist[self._TITLE_KEY], slug), | |
276 | playlist.get(self._DESCRIPTION_KEY)) | |
9c250931 YCH |
277 | |
278 | ||
279 | class MixcloudUserIE(MixcloudPlaylistBaseIE): | |
5d92b407 | 280 | _VALID_URL = r'https?://(?:www\.)?mixcloud\.com/(?P<id>[^/]+)/(?P<type>uploads|favorites|listens|stream)?/?$' |
c96eca42 PH |
281 | IE_NAME = 'mixcloud:user' |
282 | ||
283 | _TESTS = [{ | |
284 | 'url': 'http://www.mixcloud.com/dholbach/', | |
285 | 'info_dict': { | |
9c250931 | 286 | 'id': 'dholbach_uploads', |
c96eca42 | 287 | 'title': 'Daniel Holbach (uploads)', |
5d92b407 | 288 | 'description': 'md5:b60d776f0bab534c5dabe0a34e47a789', |
c96eca42 | 289 | }, |
5d92b407 | 290 | 'playlist_mincount': 36, |
c96eca42 PH |
291 | }, { |
292 | 'url': 'http://www.mixcloud.com/dholbach/uploads/', | |
293 | 'info_dict': { | |
9c250931 | 294 | 'id': 'dholbach_uploads', |
c96eca42 | 295 | 'title': 'Daniel Holbach (uploads)', |
5d92b407 | 296 | 'description': 'md5:b60d776f0bab534c5dabe0a34e47a789', |
c96eca42 | 297 | }, |
5d92b407 | 298 | 'playlist_mincount': 36, |
c96eca42 PH |
299 | }, { |
300 | 'url': 'http://www.mixcloud.com/dholbach/favorites/', | |
301 | 'info_dict': { | |
9c250931 | 302 | 'id': 'dholbach_favorites', |
c96eca42 | 303 | 'title': 'Daniel Holbach (favorites)', |
5d92b407 | 304 | 'description': 'md5:b60d776f0bab534c5dabe0a34e47a789', |
9c250931 | 305 | }, |
5d92b407 RA |
306 | # 'params': { |
307 | # 'playlist_items': '1-100', | |
308 | # }, | |
309 | 'playlist_mincount': 396, | |
c96eca42 PH |
310 | }, { |
311 | 'url': 'http://www.mixcloud.com/dholbach/listens/', | |
312 | 'info_dict': { | |
9c250931 | 313 | 'id': 'dholbach_listens', |
c96eca42 | 314 | 'title': 'Daniel Holbach (listens)', |
5d92b407 | 315 | 'description': 'md5:b60d776f0bab534c5dabe0a34e47a789', |
c96eca42 | 316 | }, |
5d92b407 RA |
317 | # 'params': { |
318 | # 'playlist_items': '1-100', | |
319 | # }, | |
320 | 'playlist_mincount': 1623, | |
321 | 'skip': 'Large list', | |
322 | }, { | |
323 | 'url': 'https://www.mixcloud.com/FirstEar/stream/', | |
324 | 'info_dict': { | |
325 | 'id': 'FirstEar_stream', | |
326 | 'title': 'First Ear (stream)', | |
327 | 'description': 'Curators of good music\r\n\r\nfirstearmusic.com', | |
9c250931 | 328 | }, |
5d92b407 | 329 | 'playlist_mincount': 271, |
c96eca42 PH |
330 | }] |
331 | ||
5d92b407 RA |
332 | _TITLE_KEY = 'displayName' |
333 | _DESCRIPTION_KEY = 'biog' | |
334 | _ROOT_TYPE = 'user' | |
335 | _NODE_TEMPLATE = '''slug | |
30a074c2 | 336 | url |
337 | owner { username }''' | |
c96eca42 | 338 | |
5d92b407 RA |
339 | def _get_playlist_title(self, title, slug): |
340 | return '%s (%s)' % (title, slug) | |
c96eca42 | 341 | |
c96eca42 | 342 | |
9c250931 | 343 | class MixcloudPlaylistIE(MixcloudPlaylistBaseIE): |
29c67266 | 344 | _VALID_URL = r'https?://(?:www\.)?mixcloud\.com/(?P<user>[^/]+)/playlists/(?P<playlist>[^/]+)/?$' |
c96eca42 PH |
345 | IE_NAME = 'mixcloud:playlist' |
346 | ||
347 | _TESTS = [{ | |
c96eca42 | 348 | 'url': 'https://www.mixcloud.com/maxvibes/playlists/jazzcat-on-ness-radio/', |
e6da9240 | 349 | 'info_dict': { |
5d92b407 RA |
350 | 'id': 'maxvibes_jazzcat-on-ness-radio', |
351 | 'title': 'Ness Radio sessions', | |
e6da9240 | 352 | }, |
5d92b407 RA |
353 | 'playlist_mincount': 59, |
354 | }] | |
355 | _TITLE_KEY = 'name' | |
356 | _DESCRIPTION_KEY = 'description' | |
357 | _ROOT_TYPE = 'playlist' | |
358 | _NODE_TEMPLATE = '''cloudcast { | |
359 | slug | |
360 | url | |
30a074c2 | 361 | owner { username } |
5d92b407 RA |
362 | }''' |
363 | ||
364 | def _get_cloudcast(self, node): | |
365 | return node.get('cloudcast') or {} |