]>
Commit | Line | Data |
---|---|---|
1 | # coding: utf-8 | |
2 | from __future__ import unicode_literals | |
3 | ||
4 | import collections | |
5 | import functools | |
6 | import re | |
7 | ||
8 | from .common import InfoExtractor | |
9 | from ..compat import compat_urlparse | |
10 | from ..utils import ( | |
11 | clean_html, | |
12 | ExtractorError, | |
13 | get_element_by_class, | |
14 | int_or_none, | |
15 | OnDemandPagedList, | |
16 | orderedSet, | |
17 | str_or_none, | |
18 | str_to_int, | |
19 | unescapeHTML, | |
20 | unified_timestamp, | |
21 | url_or_none, | |
22 | urlencode_postdata, | |
23 | ) | |
24 | from .dailymotion import DailymotionIE | |
25 | from .odnoklassniki import OdnoklassnikiIE | |
26 | from .pladform import PladformIE | |
27 | from .vimeo import VimeoIE | |
28 | from .youtube import YoutubeIE | |
29 | ||
30 | ||
31 | class VKBaseIE(InfoExtractor): | |
32 | _NETRC_MACHINE = 'vk' | |
33 | ||
34 | def _login(self): | |
35 | username, password = self._get_login_info() | |
36 | if username is None: | |
37 | return | |
38 | ||
39 | login_page, url_handle = self._download_webpage_handle( | |
40 | 'https://vk.com', None, 'Downloading login page') | |
41 | ||
42 | login_form = self._hidden_inputs(login_page) | |
43 | ||
44 | login_form.update({ | |
45 | 'email': username.encode('cp1251'), | |
46 | 'pass': password.encode('cp1251'), | |
47 | }) | |
48 | ||
49 | # vk serves two same remixlhk cookies in Set-Cookie header and expects | |
50 | # first one to be actually set | |
51 | self._apply_first_set_cookie_header(url_handle, 'remixlhk') | |
52 | ||
53 | login_page = self._download_webpage( | |
54 | 'https://login.vk.com/?act=login', None, | |
55 | note='Logging in', | |
56 | data=urlencode_postdata(login_form)) | |
57 | ||
58 | if re.search(r'onLoginFailed', login_page): | |
59 | raise ExtractorError( | |
60 | 'Unable to login, incorrect username and/or password', expected=True) | |
61 | ||
62 | def _real_initialize(self): | |
63 | self._login() | |
64 | ||
65 | def _download_payload(self, path, video_id, data, fatal=True): | |
66 | data['al'] = 1 | |
67 | code, payload = self._download_json( | |
68 | 'https://vk.com/%s.php' % path, video_id, | |
69 | data=urlencode_postdata(data), fatal=fatal, | |
70 | headers={'X-Requested-With': 'XMLHttpRequest'})['payload'] | |
71 | if code == '3': | |
72 | self.raise_login_required() | |
73 | elif code == '8': | |
74 | raise ExtractorError(clean_html(payload[0][1:-1]), expected=True) | |
75 | return payload | |
76 | ||
77 | ||
78 | class VKIE(VKBaseIE): | |
79 | IE_NAME = 'vk' | |
80 | IE_DESC = 'VK' | |
81 | _VALID_URL = r'''(?x) | |
82 | https?:// | |
83 | (?: | |
84 | (?: | |
85 | (?:(?:m|new)\.)?vk\.com/video_| | |
86 | (?:www\.)?daxab.com/ | |
87 | ) | |
88 | ext\.php\?(?P<embed_query>.*?\boid=(?P<oid>-?\d+).*?\bid=(?P<id>\d+).*)| | |
89 | (?: | |
90 | (?:(?:m|new)\.)?vk\.com/(?:.+?\?.*?z=)?video| | |
91 | (?:www\.)?daxab.com/embed/ | |
92 | ) | |
93 | (?P<videoid>-?\d+_\d+)(?:.*\blist=(?P<list_id>[\da-f]+))? | |
94 | ) | |
95 | ''' | |
96 | _TESTS = [ | |
97 | { | |
98 | 'url': 'http://vk.com/videos-77521?z=video-77521_162222515%2Fclub77521', | |
99 | 'md5': '7babad3b85ea2e91948005b1b8b0cb84', | |
100 | 'info_dict': { | |
101 | 'id': '-77521_162222515', | |
102 | 'ext': 'mp4', | |
103 | 'title': 'ProtivoGunz - Хуёвая песня', | |
104 | 'uploader': 're:(?:Noize MC|Alexander Ilyashenko).*', | |
105 | 'uploader_id': '-77521', | |
106 | 'duration': 195, | |
107 | 'timestamp': 1329049880, | |
108 | 'upload_date': '20120212', | |
109 | }, | |
110 | }, | |
111 | { | |
112 | 'url': 'http://vk.com/video205387401_165548505', | |
113 | 'info_dict': { | |
114 | 'id': '205387401_165548505', | |
115 | 'ext': 'mp4', | |
116 | 'title': 'No name', | |
117 | 'uploader': 'Tom Cruise', | |
118 | 'uploader_id': '205387401', | |
119 | 'duration': 9, | |
120 | 'timestamp': 1374364108, | |
121 | 'upload_date': '20130720', | |
122 | } | |
123 | }, | |
124 | { | |
125 | 'note': 'Embedded video', | |
126 | 'url': 'https://vk.com/video_ext.php?oid=-77521&id=162222515&hash=87b046504ccd8bfa', | |
127 | 'md5': '7babad3b85ea2e91948005b1b8b0cb84', | |
128 | 'info_dict': { | |
129 | 'id': '-77521_162222515', | |
130 | 'ext': 'mp4', | |
131 | 'uploader': 're:(?:Noize MC|Alexander Ilyashenko).*', | |
132 | 'title': 'ProtivoGunz - Хуёвая песня', | |
133 | 'duration': 195, | |
134 | 'upload_date': '20120212', | |
135 | 'timestamp': 1329049880, | |
136 | 'uploader_id': '-77521', | |
137 | }, | |
138 | }, | |
139 | { | |
140 | # VIDEO NOW REMOVED | |
141 | # please update if you find a video whose URL follows the same pattern | |
142 | 'url': 'http://vk.com/video-8871596_164049491', | |
143 | 'md5': 'a590bcaf3d543576c9bd162812387666', | |
144 | 'note': 'Only available for registered users', | |
145 | 'info_dict': { | |
146 | 'id': '-8871596_164049491', | |
147 | 'ext': 'mp4', | |
148 | 'uploader': 'Триллеры', | |
149 | 'title': '► Бойцовский клуб / Fight Club 1999 [HD 720]', | |
150 | 'duration': 8352, | |
151 | 'upload_date': '20121218', | |
152 | 'view_count': int, | |
153 | }, | |
154 | 'skip': 'Removed', | |
155 | }, | |
156 | { | |
157 | 'url': 'http://vk.com/hd_kino_mania?z=video-43215063_168067957%2F15c66b9b533119788d', | |
158 | 'info_dict': { | |
159 | 'id': '-43215063_168067957', | |
160 | 'ext': 'mp4', | |
161 | 'uploader': 'Bro Mazter', | |
162 | 'title': ' ', | |
163 | 'duration': 7291, | |
164 | 'upload_date': '20140328', | |
165 | 'uploader_id': '223413403', | |
166 | 'timestamp': 1396018030, | |
167 | }, | |
168 | 'skip': 'Requires vk account credentials', | |
169 | }, | |
170 | { | |
171 | 'url': 'http://m.vk.com/video-43215063_169084319?list=125c627d1aa1cebb83&from=wall-43215063_2566540', | |
172 | 'md5': '0c45586baa71b7cb1d0784ee3f4e00a6', | |
173 | 'note': 'ivi.ru embed', | |
174 | 'info_dict': { | |
175 | 'id': '-43215063_169084319', | |
176 | 'ext': 'mp4', | |
177 | 'title': 'Книга Илая', | |
178 | 'duration': 6771, | |
179 | 'upload_date': '20140626', | |
180 | 'view_count': int, | |
181 | }, | |
182 | 'skip': 'Removed', | |
183 | }, | |
184 | { | |
185 | # video (removed?) only available with list id | |
186 | 'url': 'https://vk.com/video30481095_171201961?list=8764ae2d21f14088d4', | |
187 | 'md5': '091287af5402239a1051c37ec7b92913', | |
188 | 'info_dict': { | |
189 | 'id': '30481095_171201961', | |
190 | 'ext': 'mp4', | |
191 | 'title': 'ТюменцевВВ_09.07.2015', | |
192 | 'uploader': 'Anton Ivanov', | |
193 | 'duration': 109, | |
194 | 'upload_date': '20150709', | |
195 | 'view_count': int, | |
196 | }, | |
197 | 'skip': 'Removed', | |
198 | }, | |
199 | { | |
200 | # youtube embed | |
201 | 'url': 'https://vk.com/video276849682_170681728', | |
202 | 'info_dict': { | |
203 | 'id': 'V3K4mi0SYkc', | |
204 | 'ext': 'mp4', | |
205 | 'title': "DSWD Awards 'Children's Joy Foundation, Inc.' Certificate of Registration and License to Operate", | |
206 | 'description': 'md5:bf9c26cfa4acdfb146362682edd3827a', | |
207 | 'duration': 178, | |
208 | 'upload_date': '20130116', | |
209 | 'uploader': "Children's Joy Foundation Inc.", | |
210 | 'uploader_id': 'thecjf', | |
211 | 'view_count': int, | |
212 | }, | |
213 | }, | |
214 | { | |
215 | # dailymotion embed | |
216 | 'url': 'https://vk.com/video-37468416_456239855', | |
217 | 'info_dict': { | |
218 | 'id': 'k3lz2cmXyRuJQSjGHUv', | |
219 | 'ext': 'mp4', | |
220 | 'title': 'md5:d52606645c20b0ddbb21655adaa4f56f', | |
221 | 'description': 'md5:424b8e88cc873217f520e582ba28bb36', | |
222 | 'uploader': 'AniLibria.Tv', | |
223 | 'upload_date': '20160914', | |
224 | 'uploader_id': 'x1p5vl5', | |
225 | 'timestamp': 1473877246, | |
226 | }, | |
227 | 'params': { | |
228 | 'skip_download': True, | |
229 | }, | |
230 | }, | |
231 | { | |
232 | # video key is extra_data not url\d+ | |
233 | 'url': 'http://vk.com/video-110305615_171782105', | |
234 | 'md5': 'e13fcda136f99764872e739d13fac1d1', | |
235 | 'info_dict': { | |
236 | 'id': '-110305615_171782105', | |
237 | 'ext': 'mp4', | |
238 | 'title': 'S-Dance, репетиции к The way show', | |
239 | 'uploader': 'THE WAY SHOW | 17 апреля', | |
240 | 'uploader_id': '-110305615', | |
241 | 'timestamp': 1454859345, | |
242 | 'upload_date': '20160207', | |
243 | }, | |
244 | 'params': { | |
245 | 'skip_download': True, | |
246 | }, | |
247 | }, | |
248 | { | |
249 | # finished live stream, postlive_mp4 | |
250 | 'url': 'https://vk.com/videos-387766?z=video-387766_456242764%2Fpl_-387766_-2', | |
251 | 'info_dict': { | |
252 | 'id': '-387766_456242764', | |
253 | 'ext': 'mp4', | |
254 | 'title': 'ИгроМир 2016 День 1 — Игромания Утром', | |
255 | 'uploader': 'Игромания', | |
256 | 'duration': 5239, | |
257 | # TODO: use act=show to extract view_count | |
258 | # 'view_count': int, | |
259 | 'upload_date': '20160929', | |
260 | 'uploader_id': '-387766', | |
261 | 'timestamp': 1475137527, | |
262 | }, | |
263 | 'params': { | |
264 | 'skip_download': True, | |
265 | }, | |
266 | }, | |
267 | { | |
268 | # live stream, hls and rtmp links, most likely already finished live | |
269 | # stream by the time you are reading this comment | |
270 | 'url': 'https://vk.com/video-140332_456239111', | |
271 | 'only_matching': True, | |
272 | }, | |
273 | { | |
274 | # removed video, just testing that we match the pattern | |
275 | 'url': 'http://vk.com/feed?z=video-43215063_166094326%2Fbb50cacd3177146d7a', | |
276 | 'only_matching': True, | |
277 | }, | |
278 | { | |
279 | # age restricted video, requires vk account credentials | |
280 | 'url': 'https://vk.com/video205387401_164765225', | |
281 | 'only_matching': True, | |
282 | }, | |
283 | { | |
284 | # pladform embed | |
285 | 'url': 'https://vk.com/video-76116461_171554880', | |
286 | 'only_matching': True, | |
287 | }, | |
288 | { | |
289 | 'url': 'http://new.vk.com/video205387401_165548505', | |
290 | 'only_matching': True, | |
291 | }, | |
292 | { | |
293 | # This video is no longer available, because its author has been blocked. | |
294 | 'url': 'https://vk.com/video-10639516_456240611', | |
295 | 'only_matching': True, | |
296 | }, | |
297 | { | |
298 | # The video is not available in your region. | |
299 | 'url': 'https://vk.com/video-51812607_171445436', | |
300 | 'only_matching': True, | |
301 | }] | |
302 | ||
303 | def _real_extract(self, url): | |
304 | mobj = re.match(self._VALID_URL, url) | |
305 | video_id = mobj.group('videoid') | |
306 | ||
307 | mv_data = {} | |
308 | if video_id: | |
309 | data = { | |
310 | 'act': 'show_inline', | |
311 | 'video': video_id, | |
312 | } | |
313 | # Some videos (removed?) can only be downloaded with list id specified | |
314 | list_id = mobj.group('list_id') | |
315 | if list_id: | |
316 | data['list'] = list_id | |
317 | ||
318 | payload = self._download_payload('al_video', video_id, data) | |
319 | info_page = payload[1] | |
320 | opts = payload[-1] | |
321 | mv_data = opts.get('mvData') or {} | |
322 | player = opts.get('player') or {} | |
323 | else: | |
324 | video_id = '%s_%s' % (mobj.group('oid'), mobj.group('id')) | |
325 | ||
326 | info_page = self._download_webpage( | |
327 | 'http://vk.com/video_ext.php?' + mobj.group('embed_query'), video_id) | |
328 | ||
329 | error_message = self._html_search_regex( | |
330 | [r'(?s)<!><div[^>]+class="video_layer_message"[^>]*>(.+?)</div>', | |
331 | r'(?s)<div[^>]+id="video_ext_msg"[^>]*>(.+?)</div>'], | |
332 | info_page, 'error message', default=None) | |
333 | if error_message: | |
334 | raise ExtractorError(error_message, expected=True) | |
335 | ||
336 | if re.search(r'<!>/login\.php\?.*\bact=security_check', info_page): | |
337 | raise ExtractorError( | |
338 | 'You are trying to log in from an unusual location. You should confirm ownership at vk.com to log in with this IP.', | |
339 | expected=True) | |
340 | ||
341 | ERROR_COPYRIGHT = 'Video %s has been removed from public access due to rightholder complaint.' | |
342 | ||
343 | ERRORS = { | |
344 | r'>Видеозапись .*? была изъята из публичного доступа в связи с обращением правообладателя.<': | |
345 | ERROR_COPYRIGHT, | |
346 | ||
347 | r'>The video .*? was removed from public access by request of the copyright holder.<': | |
348 | ERROR_COPYRIGHT, | |
349 | ||
350 | r'<!>Please log in or <': | |
351 | 'Video %s is only available for registered users, ' | |
352 | 'use --username and --password options to provide account credentials.', | |
353 | ||
354 | r'<!>Unknown error': | |
355 | 'Video %s does not exist.', | |
356 | ||
357 | r'<!>Видео временно недоступно': | |
358 | 'Video %s is temporarily unavailable.', | |
359 | ||
360 | r'<!>Access denied': | |
361 | 'Access denied to video %s.', | |
362 | ||
363 | r'<!>Видеозапись недоступна, так как её автор был заблокирован.': | |
364 | 'Video %s is no longer available, because its author has been blocked.', | |
365 | ||
366 | r'<!>This video is no longer available, because its author has been blocked.': | |
367 | 'Video %s is no longer available, because its author has been blocked.', | |
368 | ||
369 | r'<!>This video is no longer available, because it has been deleted.': | |
370 | 'Video %s is no longer available, because it has been deleted.', | |
371 | ||
372 | r'<!>The video .+? is not available in your region.': | |
373 | 'Video %s is not available in your region.', | |
374 | } | |
375 | ||
376 | for error_re, error_msg in ERRORS.items(): | |
377 | if re.search(error_re, info_page): | |
378 | raise ExtractorError(error_msg % video_id, expected=True) | |
379 | ||
380 | player = self._parse_json(self._search_regex( | |
381 | r'var\s+playerParams\s*=\s*({.+?})\s*;\s*\n', | |
382 | info_page, 'player params'), video_id) | |
383 | ||
384 | youtube_url = YoutubeIE._extract_url(info_page) | |
385 | if youtube_url: | |
386 | return self.url_result(youtube_url, YoutubeIE.ie_key()) | |
387 | ||
388 | vimeo_url = VimeoIE._extract_url(url, info_page) | |
389 | if vimeo_url is not None: | |
390 | return self.url_result(vimeo_url, VimeoIE.ie_key()) | |
391 | ||
392 | pladform_url = PladformIE._extract_url(info_page) | |
393 | if pladform_url: | |
394 | return self.url_result(pladform_url, PladformIE.ie_key()) | |
395 | ||
396 | m_rutube = re.search( | |
397 | r'\ssrc="((?:https?:)?//rutube\.ru\\?/(?:video|play)\\?/embed(?:.*?))\\?"', info_page) | |
398 | if m_rutube is not None: | |
399 | rutube_url = self._proto_relative_url( | |
400 | m_rutube.group(1).replace('\\', '')) | |
401 | return self.url_result(rutube_url) | |
402 | ||
403 | dailymotion_urls = DailymotionIE._extract_urls(info_page) | |
404 | if dailymotion_urls: | |
405 | return self.url_result(dailymotion_urls[0], DailymotionIE.ie_key()) | |
406 | ||
407 | odnoklassniki_url = OdnoklassnikiIE._extract_url(info_page) | |
408 | if odnoklassniki_url: | |
409 | return self.url_result(odnoklassniki_url, OdnoklassnikiIE.ie_key()) | |
410 | ||
411 | m_opts = re.search(r'(?s)var\s+opts\s*=\s*({.+?});', info_page) | |
412 | if m_opts: | |
413 | m_opts_url = re.search(r"url\s*:\s*'((?!/\b)[^']+)", m_opts.group(1)) | |
414 | if m_opts_url: | |
415 | opts_url = m_opts_url.group(1) | |
416 | if opts_url.startswith('//'): | |
417 | opts_url = 'http:' + opts_url | |
418 | return self.url_result(opts_url) | |
419 | ||
420 | data = player['params'][0] | |
421 | title = unescapeHTML(data['md_title']) | |
422 | ||
423 | # 2 = live | |
424 | # 3 = post live (finished live) | |
425 | is_live = data.get('live') == 2 | |
426 | if is_live: | |
427 | title = self._live_title(title) | |
428 | ||
429 | timestamp = unified_timestamp(self._html_search_regex( | |
430 | r'class=["\']mv_info_date[^>]+>([^<]+)(?:<|from)', info_page, | |
431 | 'upload date', default=None)) or int_or_none(data.get('date')) | |
432 | ||
433 | view_count = str_to_int(self._search_regex( | |
434 | r'class=["\']mv_views_count[^>]+>\s*([\d,.]+)', | |
435 | info_page, 'view count', default=None)) | |
436 | ||
437 | formats = [] | |
438 | for format_id, format_url in data.items(): | |
439 | format_url = url_or_none(format_url) | |
440 | if not format_url or not format_url.startswith(('http', '//', 'rtmp')): | |
441 | continue | |
442 | if (format_id.startswith(('url', 'cache')) | |
443 | or format_id in ('extra_data', 'live_mp4', 'postlive_mp4')): | |
444 | height = int_or_none(self._search_regex( | |
445 | r'^(?:url|cache)(\d+)', format_id, 'height', default=None)) | |
446 | formats.append({ | |
447 | 'format_id': format_id, | |
448 | 'url': format_url, | |
449 | 'height': height, | |
450 | }) | |
451 | elif format_id == 'hls': | |
452 | formats.extend(self._extract_m3u8_formats( | |
453 | format_url, video_id, 'mp4', 'm3u8_native', | |
454 | m3u8_id=format_id, fatal=False, live=is_live)) | |
455 | elif format_id == 'rtmp': | |
456 | formats.append({ | |
457 | 'format_id': format_id, | |
458 | 'url': format_url, | |
459 | 'ext': 'flv', | |
460 | }) | |
461 | self._sort_formats(formats) | |
462 | ||
463 | return { | |
464 | 'id': video_id, | |
465 | 'formats': formats, | |
466 | 'title': title, | |
467 | 'thumbnail': data.get('jpg'), | |
468 | 'uploader': data.get('md_author'), | |
469 | 'uploader_id': str_or_none(data.get('author_id') or mv_data.get('authorId')), | |
470 | 'duration': int_or_none(data.get('duration') or mv_data.get('duration')), | |
471 | 'timestamp': timestamp, | |
472 | 'view_count': view_count, | |
473 | 'like_count': int_or_none(mv_data.get('likes')), | |
474 | 'comment_count': int_or_none(mv_data.get('commcount')), | |
475 | 'is_live': is_live, | |
476 | } | |
477 | ||
478 | ||
479 | class VKUserVideosIE(VKBaseIE): | |
480 | IE_NAME = 'vk:uservideos' | |
481 | IE_DESC = "VK - User's Videos" | |
482 | _VALID_URL = r'https?://(?:(?:m|new)\.)?vk\.com/videos(?P<id>-?[0-9]+)(?!\?.*\bz=video)(?:[/?#&](?:.*?\bsection=(?P<section>\w+))?|$)' | |
483 | _TEMPLATE_URL = 'https://vk.com/videos' | |
484 | _TESTS = [{ | |
485 | 'url': 'https://vk.com/videos-767561', | |
486 | 'info_dict': { | |
487 | 'id': '-767561_all', | |
488 | }, | |
489 | 'playlist_mincount': 1150, | |
490 | }, { | |
491 | 'url': 'https://vk.com/videos-767561?section=uploaded', | |
492 | 'info_dict': { | |
493 | 'id': '-767561_uploaded', | |
494 | }, | |
495 | 'playlist_mincount': 425, | |
496 | }, { | |
497 | 'url': 'http://vk.com/videos205387401', | |
498 | 'only_matching': True, | |
499 | }, { | |
500 | 'url': 'http://vk.com/videos-77521', | |
501 | 'only_matching': True, | |
502 | }, { | |
503 | 'url': 'http://vk.com/videos-97664626?section=all', | |
504 | 'only_matching': True, | |
505 | }, { | |
506 | 'url': 'http://m.vk.com/videos205387401', | |
507 | 'only_matching': True, | |
508 | }, { | |
509 | 'url': 'http://new.vk.com/videos205387401', | |
510 | 'only_matching': True, | |
511 | }] | |
512 | _PAGE_SIZE = 1000 | |
513 | _VIDEO = collections.namedtuple('Video', ['owner_id', 'id']) | |
514 | ||
515 | def _fetch_page(self, page_id, section, page): | |
516 | l = self._download_payload('al_video', page_id, { | |
517 | 'act': 'load_videos_silent', | |
518 | 'offset': page * self._PAGE_SIZE, | |
519 | 'oid': page_id, | |
520 | 'section': section, | |
521 | })[0][section]['list'] | |
522 | ||
523 | for video in l: | |
524 | v = self._VIDEO._make(video[:2]) | |
525 | video_id = '%d_%d' % (v.owner_id, v.id) | |
526 | yield self.url_result( | |
527 | 'http://vk.com/video' + video_id, VKIE.ie_key(), video_id) | |
528 | ||
529 | def _real_extract(self, url): | |
530 | page_id, section = re.match(self._VALID_URL, url).groups() | |
531 | if not section: | |
532 | section = 'all' | |
533 | ||
534 | entries = OnDemandPagedList( | |
535 | functools.partial(self._fetch_page, page_id, section), | |
536 | self._PAGE_SIZE) | |
537 | ||
538 | return self.playlist_result(entries, '%s_%s' % (page_id, section)) | |
539 | ||
540 | ||
541 | class VKWallPostIE(VKBaseIE): | |
542 | IE_NAME = 'vk:wallpost' | |
543 | _VALID_URL = r'https?://(?:(?:(?:(?:m|new)\.)?vk\.com/(?:[^?]+\?.*\bw=)?wall(?P<id>-?\d+_\d+)))' | |
544 | _TESTS = [{ | |
545 | # public page URL, audio playlist | |
546 | 'url': 'https://vk.com/bs.official?w=wall-23538238_35', | |
547 | 'info_dict': { | |
548 | 'id': '-23538238_35', | |
549 | 'title': 'Black Shadow - Wall post -23538238_35', | |
550 | 'description': 'md5:3f84b9c4f9ef499731cf1ced9998cc0c', | |
551 | }, | |
552 | 'playlist': [{ | |
553 | 'md5': '5ba93864ec5b85f7ce19a9af4af080f6', | |
554 | 'info_dict': { | |
555 | 'id': '135220665_111806521', | |
556 | 'ext': 'mp4', | |
557 | 'title': 'Black Shadow - Слепое Верование', | |
558 | 'duration': 370, | |
559 | 'uploader': 'Black Shadow', | |
560 | 'artist': 'Black Shadow', | |
561 | 'track': 'Слепое Верование', | |
562 | }, | |
563 | }, { | |
564 | 'md5': '4cc7e804579122b17ea95af7834c9233', | |
565 | 'info_dict': { | |
566 | 'id': '135220665_111802303', | |
567 | 'ext': 'mp4', | |
568 | 'title': 'Black Shadow - Война - Негасимое Бездны Пламя!', | |
569 | 'duration': 423, | |
570 | 'uploader': 'Black Shadow', | |
571 | 'artist': 'Black Shadow', | |
572 | 'track': 'Война - Негасимое Бездны Пламя!', | |
573 | }, | |
574 | }], | |
575 | 'params': { | |
576 | 'skip_download': True, | |
577 | 'usenetrc': True, | |
578 | }, | |
579 | 'skip': 'Requires vk account credentials', | |
580 | }, { | |
581 | # single YouTube embed, no leading - | |
582 | 'url': 'https://vk.com/wall85155021_6319', | |
583 | 'info_dict': { | |
584 | 'id': '85155021_6319', | |
585 | 'title': 'Сергей Горбунов - Wall post 85155021_6319', | |
586 | }, | |
587 | 'playlist_count': 1, | |
588 | 'params': { | |
589 | 'usenetrc': True, | |
590 | }, | |
591 | 'skip': 'Requires vk account credentials', | |
592 | }, { | |
593 | # wall page URL | |
594 | 'url': 'https://vk.com/wall-23538238_35', | |
595 | 'only_matching': True, | |
596 | }, { | |
597 | # mobile wall page URL | |
598 | 'url': 'https://m.vk.com/wall-23538238_35', | |
599 | 'only_matching': True, | |
600 | }] | |
601 | _BASE64_CHARS = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMN0PQRSTUVWXYZO123456789+/=' | |
602 | _AUDIO = collections.namedtuple('Audio', ['id', 'owner_id', 'url', 'title', 'performer', 'duration', 'album_id', 'unk', 'author_link', 'lyrics', 'flags', 'context', 'extra', 'hashes', 'cover_url', 'ads']) | |
603 | ||
604 | def _decode(self, enc): | |
605 | dec = '' | |
606 | e = n = 0 | |
607 | for c in enc: | |
608 | r = self._BASE64_CHARS.index(c) | |
609 | cond = n % 4 | |
610 | e = 64 * e + r if cond else r | |
611 | n += 1 | |
612 | if cond: | |
613 | dec += chr(255 & e >> (-2 * n & 6)) | |
614 | return dec | |
615 | ||
616 | def _unmask_url(self, mask_url, vk_id): | |
617 | if 'audio_api_unavailable' in mask_url: | |
618 | extra = mask_url.split('?extra=')[1].split('#') | |
619 | func, base = self._decode(extra[1]).split(chr(11)) | |
620 | mask_url = list(self._decode(extra[0])) | |
621 | url_len = len(mask_url) | |
622 | indexes = [None] * url_len | |
623 | index = int(base) ^ vk_id | |
624 | for n in range(url_len - 1, -1, -1): | |
625 | index = (url_len * (n + 1) ^ index + n) % url_len | |
626 | indexes[n] = index | |
627 | for n in range(1, url_len): | |
628 | c = mask_url[n] | |
629 | index = indexes[url_len - 1 - n] | |
630 | mask_url[n] = mask_url[index] | |
631 | mask_url[index] = c | |
632 | mask_url = ''.join(mask_url) | |
633 | return mask_url | |
634 | ||
635 | def _real_extract(self, url): | |
636 | post_id = self._match_id(url) | |
637 | ||
638 | webpage = self._download_payload('wkview', post_id, { | |
639 | 'act': 'show', | |
640 | 'w': 'wall' + post_id, | |
641 | })[1] | |
642 | ||
643 | description = clean_html(get_element_by_class('wall_post_text', webpage)) | |
644 | uploader = clean_html(get_element_by_class('author', webpage)) | |
645 | ||
646 | entries = [] | |
647 | ||
648 | for audio in re.findall(r'data-audio="([^"]+)', webpage): | |
649 | audio = self._parse_json(unescapeHTML(audio), post_id) | |
650 | a = self._AUDIO._make(audio[:16]) | |
651 | if not a.url: | |
652 | continue | |
653 | title = unescapeHTML(a.title) | |
654 | performer = unescapeHTML(a.performer) | |
655 | entries.append({ | |
656 | 'id': '%s_%s' % (a.owner_id, a.id), | |
657 | 'url': self._unmask_url(a.url, a.ads['vk_id']), | |
658 | 'title': '%s - %s' % (performer, title) if performer else title, | |
659 | 'thumbnails': [{'url': c_url} for c_url in a.cover_url.split(',')] if a.cover_url else None, | |
660 | 'duration': int_or_none(a.duration), | |
661 | 'uploader': uploader, | |
662 | 'artist': performer, | |
663 | 'track': title, | |
664 | 'ext': 'mp4', | |
665 | 'protocol': 'm3u8', | |
666 | }) | |
667 | ||
668 | for video in re.finditer( | |
669 | r'<a[^>]+href=(["\'])(?P<url>/video(?:-?[\d_]+).*?)\1', webpage): | |
670 | entries.append(self.url_result( | |
671 | compat_urlparse.urljoin(url, video.group('url')), VKIE.ie_key())) | |
672 | ||
673 | title = 'Wall post %s' % post_id | |
674 | ||
675 | return self.playlist_result( | |
676 | orderedSet(entries), post_id, | |
677 | '%s - %s' % (uploader, title) if uploader else title, | |
678 | description) |