2 from __future__ import unicode_literals
7 from .common import InfoExtractor
8 from ..compat import compat_urlparse
22 from .dailymotion import DailymotionIE
23 from .odnoklassniki import OdnoklassnikiIE
24 from .pladform import PladformIE
25 from .vimeo import VimeoIE
26 from .youtube import YoutubeIE
29 class VKBaseIE(InfoExtractor):
33 username, password = self._get_login_info()
37 login_page, url_handle = self._download_webpage_handle(
38 'https://vk.com', None, 'Downloading login page')
40 login_form = self._hidden_inputs(login_page)
43 'email': username.encode('cp1251'),
44 'pass': password.encode('cp1251'),
47 # vk serves two same remixlhk cookies in Set-Cookie header and expects
48 # first one to be actually set
49 self._apply_first_set_cookie_header(url_handle, 'remixlhk')
51 login_page = self._download_webpage(
52 'https://login.vk.com/?act=login', None,
54 data=urlencode_postdata(login_form))
56 if re.search(r'onLoginFailed', login_page):
58 'Unable to login, incorrect username and/or password', expected=True)
60 def _real_initialize(self):
63 def _download_payload(self, path, video_id, data, fatal=True):
65 code, payload = self._download_json(
66 'https://vk.com/%s.php' % path, video_id,
67 data=urlencode_postdata(data), fatal=fatal,
68 headers={'X-Requested-With': 'XMLHttpRequest'})['payload']
70 self.raise_login_required()
72 raise ExtractorError(clean_html(payload[0][1:-1]), expected=True)
83 (?:(?:m|new)\.)?vk\.com/video_|
86 ext\.php\?(?P<embed_query>.*?\boid=(?P<oid>-?\d+).*?\bid=(?P<id>\d+).*)|
88 (?:(?:m|new)\.)?vk\.com/(?:.+?\?.*?z=)?video|
89 (?:www\.)?daxab.com/embed/
91 (?P<videoid>-?\d+_\d+)(?:.*\blist=(?P<list_id>[\da-f]+))?
96 'url': 'http://vk.com/videos-77521?z=video-77521_162222515%2Fclub77521',
97 'md5': '7babad3b85ea2e91948005b1b8b0cb84',
99 'id': '-77521_162222515',
101 'title': 'ProtivoGunz - Хуёвая песня',
102 'uploader': 're:(?:Noize MC|Alexander Ilyashenko).*',
103 'uploader_id': '-77521',
105 'timestamp': 1329049880,
106 'upload_date': '20120212',
110 'url': 'http://vk.com/video205387401_165548505',
112 'id': '205387401_165548505',
115 'uploader': 'Tom Cruise',
116 'uploader_id': '205387401',
118 'timestamp': 1374364108,
119 'upload_date': '20130720',
123 'note': 'Embedded video',
124 'url': 'https://vk.com/video_ext.php?oid=-77521&id=162222515&hash=87b046504ccd8bfa',
125 'md5': '7babad3b85ea2e91948005b1b8b0cb84',
127 'id': '-77521_162222515',
129 'uploader': 're:(?:Noize MC|Alexander Ilyashenko).*',
130 'title': 'ProtivoGunz - Хуёвая песня',
132 'upload_date': '20120212',
133 'timestamp': 1329049880,
134 'uploader_id': '-77521',
139 # please update if you find a video whose URL follows the same pattern
140 'url': 'http://vk.com/video-8871596_164049491',
141 'md5': 'a590bcaf3d543576c9bd162812387666',
142 'note': 'Only available for registered users',
144 'id': '-8871596_164049491',
146 'uploader': 'Триллеры',
147 'title': '► Бойцовский клуб / Fight Club 1999 [HD 720]',
149 'upload_date': '20121218',
155 'url': 'http://vk.com/hd_kino_mania?z=video-43215063_168067957%2F15c66b9b533119788d',
157 'id': '-43215063_168067957',
159 'uploader': 'Bro Mazter',
162 'upload_date': '20140328',
163 'uploader_id': '223413403',
164 'timestamp': 1396018030,
166 'skip': 'Requires vk account credentials',
169 'url': 'http://m.vk.com/video-43215063_169084319?list=125c627d1aa1cebb83&from=wall-43215063_2566540',
170 'md5': '0c45586baa71b7cb1d0784ee3f4e00a6',
171 'note': 'ivi.ru embed',
173 'id': '-43215063_169084319',
175 'title': 'Книга Илая',
177 'upload_date': '20140626',
183 # video (removed?) only available with list id
184 'url': 'https://vk.com/video30481095_171201961?list=8764ae2d21f14088d4',
185 'md5': '091287af5402239a1051c37ec7b92913',
187 'id': '30481095_171201961',
189 'title': 'ТюменцевВВ_09.07.2015',
190 'uploader': 'Anton Ivanov',
192 'upload_date': '20150709',
199 'url': 'https://vk.com/video276849682_170681728',
203 'title': "DSWD Awards 'Children's Joy Foundation, Inc.' Certificate of Registration and License to Operate",
204 'description': 'md5:bf9c26cfa4acdfb146362682edd3827a',
206 'upload_date': '20130116',
207 'uploader': "Children's Joy Foundation Inc.",
208 'uploader_id': 'thecjf',
214 'url': 'https://vk.com/video-37468416_456239855',
216 'id': 'k3lz2cmXyRuJQSjGHUv',
218 'title': 'md5:d52606645c20b0ddbb21655adaa4f56f',
219 'description': 'md5:424b8e88cc873217f520e582ba28bb36',
220 'uploader': 'AniLibria.Tv',
221 'upload_date': '20160914',
222 'uploader_id': 'x1p5vl5',
223 'timestamp': 1473877246,
226 'skip_download': True,
230 # video key is extra_data not url\d+
231 'url': 'http://vk.com/video-110305615_171782105',
232 'md5': 'e13fcda136f99764872e739d13fac1d1',
234 'id': '-110305615_171782105',
236 'title': 'S-Dance, репетиции к The way show',
237 'uploader': 'THE WAY SHOW | 17 апреля',
238 'uploader_id': '-110305615',
239 'timestamp': 1454859345,
240 'upload_date': '20160207',
243 'skip_download': True,
247 # finished live stream, postlive_mp4
248 'url': 'https://vk.com/videos-387766?z=video-387766_456242764%2Fpl_-387766_-2',
250 'id': '-387766_456242764',
252 'title': 'ИгроМир 2016 День 1 — Игромания Утром',
253 'uploader': 'Игромания',
255 # TODO: use act=show to extract view_count
257 'upload_date': '20160929',
258 'uploader_id': '-387766',
259 'timestamp': 1475137527,
262 'skip_download': True,
266 # live stream, hls and rtmp links, most likely already finished live
267 # stream by the time you are reading this comment
268 'url': 'https://vk.com/video-140332_456239111',
269 'only_matching': True,
272 # removed video, just testing that we match the pattern
273 'url': 'http://vk.com/feed?z=video-43215063_166094326%2Fbb50cacd3177146d7a',
274 'only_matching': True,
277 # age restricted video, requires vk account credentials
278 'url': 'https://vk.com/video205387401_164765225',
279 'only_matching': True,
283 'url': 'https://vk.com/video-76116461_171554880',
284 'only_matching': True,
287 'url': 'http://new.vk.com/video205387401_165548505',
288 'only_matching': True,
291 # This video is no longer available, because its author has been blocked.
292 'url': 'https://vk.com/video-10639516_456240611',
293 'only_matching': True,
296 # The video is not available in your region.
297 'url': 'https://vk.com/video-51812607_171445436',
298 'only_matching': True,
301 def _real_extract(self, url):
302 mobj = re.match(self._VALID_URL, url)
303 video_id = mobj.group('videoid')
308 'act': 'show_inline',
311 # Some videos (removed?) can only be downloaded with list id specified
312 list_id = mobj.group('list_id')
314 data['list'] = list_id
316 payload = self._download_payload('al_video', video_id, data)
317 info_page = payload[1]
319 mv_data = opts.get('mvData') or {}
320 player = opts.get('player') or {}
322 video_id = '%s_%s' % (mobj.group('oid'), mobj.group('id'))
324 info_page = self._download_webpage(
325 'http://vk.com/video_ext.php?' + mobj.group('embed_query'), video_id)
327 error_message = self._html_search_regex(
328 [r'(?s)<!><div[^>]+class="video_layer_message"[^>]*>(.+?)</div>',
329 r'(?s)<div[^>]+id="video_ext_msg"[^>]*>(.+?)</div>'],
330 info_page, 'error message', default=None)
332 raise ExtractorError(error_message, expected=True)
334 if re.search(r'<!>/login\.php\?.*\bact=security_check', info_page):
335 raise ExtractorError(
336 'You are trying to log in from an unusual location. You should confirm ownership at vk.com to log in with this IP.',
339 ERROR_COPYRIGHT = 'Video %s has been removed from public access due to rightholder complaint.'
342 r'>Видеозапись .*? была изъята из публичного доступа в связи с обращением правообладателя.<':
345 r'>The video .*? was removed from public access by request of the copyright holder.<':
348 r'<!>Please log in or <':
349 'Video %s is only available for registered users, '
350 'use --username and --password options to provide account credentials.',
353 'Video %s does not exist.',
355 r'<!>Видео временно недоступно':
356 'Video %s is temporarily unavailable.',
359 'Access denied to video %s.',
361 r'<!>Видеозапись недоступна, так как её автор был заблокирован.':
362 'Video %s is no longer available, because its author has been blocked.',
364 r'<!>This video is no longer available, because its author has been blocked.':
365 'Video %s is no longer available, because its author has been blocked.',
367 r'<!>This video is no longer available, because it has been deleted.':
368 'Video %s is no longer available, because it has been deleted.',
370 r'<!>The video .+? is not available in your region.':
371 'Video %s is not available in your region.',
374 for error_re, error_msg in ERRORS.items():
375 if re.search(error_re, info_page):
376 raise ExtractorError(error_msg % video_id, expected=True)
378 player = self._parse_json(self._search_regex(
379 r'var\s+playerParams\s*=\s*({.+?})\s*;\s*\n',
380 info_page, 'player params'), video_id)
382 youtube_url = YoutubeIE._extract_url(info_page)
384 return self.url_result(youtube_url, YoutubeIE.ie_key())
386 vimeo_url = VimeoIE._extract_url(url, info_page)
387 if vimeo_url is not None:
388 return self.url_result(vimeo_url, VimeoIE.ie_key())
390 pladform_url = PladformIE._extract_url(info_page)
392 return self.url_result(pladform_url, PladformIE.ie_key())
394 m_rutube = re.search(
395 r'\ssrc="((?:https?:)?//rutube\.ru\\?/(?:video|play)\\?/embed(?:.*?))\\?"', info_page)
396 if m_rutube is not None:
397 rutube_url = self._proto_relative_url(
398 m_rutube.group(1).replace('\\', ''))
399 return self.url_result(rutube_url)
401 dailymotion_urls = DailymotionIE._extract_urls(info_page)
403 return self.url_result(dailymotion_urls[0], DailymotionIE.ie_key())
405 odnoklassniki_url = OdnoklassnikiIE._extract_url(info_page)
406 if odnoklassniki_url:
407 return self.url_result(odnoklassniki_url, OdnoklassnikiIE.ie_key())
409 m_opts = re.search(r'(?s)var\s+opts\s*=\s*({.+?});', info_page)
411 m_opts_url = re.search(r"url\s*:\s*'((?!/\b)[^']+)", m_opts.group(1))
413 opts_url = m_opts_url.group(1)
414 if opts_url.startswith('//'):
415 opts_url = 'http:' + opts_url
416 return self.url_result(opts_url)
418 data = player['params'][0]
419 title = unescapeHTML(data['md_title'])
422 # 3 = post live (finished live)
423 is_live = data.get('live') == 2
425 title = self._live_title(title)
427 timestamp = unified_timestamp(self._html_search_regex(
428 r'class=["\']mv_info_date[^>]+>([^<]+)(?:<|from)', info_page,
429 'upload date', default=None)) or int_or_none(data.get('date'))
431 view_count = str_to_int(self._search_regex(
432 r'class=["\']mv_views_count[^>]+>\s*([\d,.]+)',
433 info_page, 'view count', default=None))
436 for format_id, format_url in data.items():
437 format_url = url_or_none(format_url)
438 if not format_url or not format_url.startswith(('http', '//', 'rtmp')):
440 if (format_id.startswith(('url', 'cache'))
441 or format_id in ('extra_data', 'live_mp4', 'postlive_mp4')):
442 height = int_or_none(self._search_regex(
443 r'^(?:url|cache)(\d+)', format_id, 'height', default=None))
445 'format_id': format_id,
449 elif format_id == 'hls':
450 formats.extend(self._extract_m3u8_formats(
451 format_url, video_id, 'mp4', 'm3u8_native',
452 m3u8_id=format_id, fatal=False, live=is_live))
453 elif format_id == 'rtmp':
455 'format_id': format_id,
459 self._sort_formats(formats)
465 'thumbnail': data.get('jpg'),
466 'uploader': data.get('md_author'),
467 'uploader_id': str_or_none(data.get('author_id') or mv_data.get('authorId')),
468 'duration': int_or_none(data.get('duration') or mv_data.get('duration')),
469 'timestamp': timestamp,
470 'view_count': view_count,
471 'like_count': int_or_none(mv_data.get('likes')),
472 'comment_count': int_or_none(mv_data.get('commcount')),
477 class VKUserVideosIE(VKBaseIE):
478 IE_NAME = 'vk:uservideos'
479 IE_DESC = "VK - User's Videos"
480 _VALID_URL = r'https?://(?:(?:m|new)\.)?vk\.com/videos(?P<id>-?[0-9]+)(?!\?.*\bz=video)(?:[/?#&]|$)'
481 _TEMPLATE_URL = 'https://vk.com/videos'
483 'url': 'http://vk.com/videos205387401',
487 'playlist_mincount': 4,
489 'url': 'http://vk.com/videos-77521',
490 'only_matching': True,
492 'url': 'http://vk.com/videos-97664626?section=all',
493 'only_matching': True,
495 'url': 'http://m.vk.com/videos205387401',
496 'only_matching': True,
498 'url': 'http://new.vk.com/videos205387401',
499 'only_matching': True,
501 _VIDEO = collections.namedtuple(
502 'Video', ['owner_id', 'id', 'thumb', 'title', 'flags', 'duration', 'hash', 'moder_acts', 'owner', 'date', 'views', 'platform', 'blocked', 'music_video_meta'])
504 def _real_extract(self, url):
505 page_id = self._match_id(url)
507 l = self._download_payload('al_video', page_id, {
508 'act': 'load_videos_silent',
514 v = self._VIDEO._make(video)
515 video_id = '%d_%d' % (v.owner_id, v.id)
516 entries.append(self.url_result(
517 'http://vk.com/video' + video_id, 'VK', video_id=video_id))
519 return self.playlist_result(entries, page_id)
522 class VKWallPostIE(VKBaseIE):
523 IE_NAME = 'vk:wallpost'
524 _VALID_URL = r'https?://(?:(?:(?:(?:m|new)\.)?vk\.com/(?:[^?]+\?.*\bw=)?wall(?P<id>-?\d+_\d+)))'
526 # public page URL, audio playlist
527 'url': 'https://vk.com/bs.official?w=wall-23538238_35',
529 'id': '-23538238_35',
530 'title': 'Black Shadow - Wall post -23538238_35',
531 'description': 'md5:3f84b9c4f9ef499731cf1ced9998cc0c',
534 'md5': '5ba93864ec5b85f7ce19a9af4af080f6',
536 'id': '135220665_111806521',
538 'title': 'Black Shadow - Слепое Верование',
540 'uploader': 'Black Shadow',
541 'artist': 'Black Shadow',
542 'track': 'Слепое Верование',
545 'md5': '4cc7e804579122b17ea95af7834c9233',
547 'id': '135220665_111802303',
549 'title': 'Black Shadow - Война - Негасимое Бездны Пламя!',
551 'uploader': 'Black Shadow',
552 'artist': 'Black Shadow',
553 'track': 'Война - Негасимое Бездны Пламя!',
557 'skip_download': True,
560 'skip': 'Requires vk account credentials',
562 # single YouTube embed, no leading -
563 'url': 'https://vk.com/wall85155021_6319',
565 'id': '85155021_6319',
566 'title': 'Сергей Горбунов - Wall post 85155021_6319',
572 'skip': 'Requires vk account credentials',
575 'url': 'https://vk.com/wall-23538238_35',
576 'only_matching': True,
578 # mobile wall page URL
579 'url': 'https://m.vk.com/wall-23538238_35',
580 'only_matching': True,
582 _BASE64_CHARS = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMN0PQRSTUVWXYZO123456789+/='
583 _AUDIO = collections.namedtuple(
584 'Audio', ['id', 'owner_id', 'url', 'title', 'performer', 'duration', 'album_id', 'unk', 'author_link', 'lyrics', 'flags', 'context', 'extra', 'hashes', 'cover_url', 'ads', 'subtitle', 'main_artists', 'feat_artists', 'album', 'track_code', 'restriction', 'album_part', 'new_stats', 'access_key'])
586 def _decode(self, enc):
590 r = self._BASE64_CHARS.index(c)
592 e = 64 * e + r if cond else r
595 dec += chr(255 & e >> (-2 * n & 6))
598 def _unmask_url(self, mask_url, vk_id):
599 if 'audio_api_unavailable' in mask_url:
600 extra = mask_url.split('?extra=')[1].split('#')
601 func, base = self._decode(extra[1]).split(chr(11))
602 mask_url = list(self._decode(extra[0]))
603 url_len = len(mask_url)
604 indexes = [None] * url_len
605 index = int(base) ^ vk_id
606 for n in range(url_len - 1, -1, -1):
607 index = (url_len * (n + 1) ^ index + n) % url_len
609 for n in range(1, url_len):
611 index = indexes[url_len - 1 - n]
612 mask_url[n] = mask_url[index]
614 mask_url = ''.join(mask_url)
617 def _real_extract(self, url):
618 post_id = self._match_id(url)
620 webpage = self._download_payload('wkview', post_id, {
622 'w': 'wall' + post_id,
625 description = clean_html(get_element_by_class('wall_post_text', webpage))
626 uploader = clean_html(get_element_by_class('author', webpage))
630 for audio in re.findall(r'data-audio="([^"]+)', webpage):
631 audio = self._parse_json(unescapeHTML(audio), post_id)
632 a = self._AUDIO._make(audio)
635 title = unescapeHTML(a.title)
636 performer = unescapeHTML(a.performer)
638 'id': '%s_%s' % (a.owner_id, a.id),
639 'url': self._unmask_url(a.url, a.ads['vk_id']),
640 'title': '%s - %s' % (performer, title) if performer else title,
641 'thumbnails': [{'url': c_url} for c_url in a.cover_url.split(',')] if a.cover_url else None,
642 'duration': int_or_none(a.duration),
643 'uploader': uploader,
650 for video in re.finditer(
651 r'<a[^>]+href=(["\'])(?P<url>/video(?:-?[\d_]+).*?)\1', webpage):
652 entries.append(self.url_result(
653 compat_urlparse.urljoin(url, video.group('url')), VKIE.ie_key()))
655 title = 'Wall post %s' % post_id
657 return self.playlist_result(
658 orderedSet(entries), post_id,
659 '%s - %s' % (uploader, title) if uploader else title,