2 from __future__ import unicode_literals
8 from .common import InfoExtractor
26 from .dailymotion import DailymotionIE
27 from .pladform import PladformIE
28 from .vimeo import VimeoIE
29 from .youtube import YoutubeIE
32 class VKBaseIE(InfoExtractor):
36 username, password = self._get_login_info()
40 login_page, url_handle = self._download_webpage_handle(
41 'https://vk.com', None, 'Downloading login page')
43 login_form = self._hidden_inputs(login_page)
46 'email': username.encode('cp1251'),
47 'pass': password.encode('cp1251'),
50 # https://new.vk.com/ serves two same remixlhk cookies in Set-Cookie header
51 # and expects the first one to be set rather than second (see
52 # https://github.com/rg3/youtube-dl/issues/9841#issuecomment-227871201).
53 # As of RFC6265 the newer one cookie should be set into cookie store
54 # what actually happens.
55 # We will workaround this VK issue by resetting the remixlhk cookie to
56 # the first one manually.
57 for header, cookies in url_handle.headers.items():
58 if header.lower() != 'set-cookie':
60 if sys.version_info[0] >= 3:
61 cookies = cookies.encode('iso-8859-1')
62 cookies = cookies.decode('utf-8')
63 remixlhk = re.search(r'remixlhk=(.+?);.*?\bdomain=(.+?)(?:[,;]|$)', cookies)
65 value, domain = remixlhk.groups()
66 self._set_cookie(domain, 'remixlhk', value)
69 login_page = self._download_webpage(
70 'https://login.vk.com/?act=login', None,
72 data=urlencode_postdata(login_form))
74 if re.search(r'onLoginFailed', login_page):
76 'Unable to login, incorrect username and/or password', expected=True)
78 def _real_initialize(self):
89 (?:(?:m|new)\.)?vk\.com/video_|
92 ext\.php\?(?P<embed_query>.*?\boid=(?P<oid>-?\d+).*?\bid=(?P<id>\d+).*)|
94 (?:(?:m|new)\.)?vk\.com/(?:.+?\?.*?z=)?video|
95 (?:www\.)?daxab.com/embed/
97 (?P<videoid>-?\d+_\d+)(?:.*\blist=(?P<list_id>[\da-f]+))?
102 'url': 'http://vk.com/videos-77521?z=video-77521_162222515%2Fclub77521',
103 'md5': '7babad3b85ea2e91948005b1b8b0cb84',
107 'title': 'ProtivoGunz - Хуёвая песня',
108 'uploader': 're:(?:Noize MC|Alexander Ilyashenko).*',
110 'timestamp': 1329060660,
111 'upload_date': '20120212',
116 'url': 'http://vk.com/video205387401_165548505',
117 'md5': '6c0aeb2e90396ba97035b9cbde548700',
121 'uploader': 'Tom Cruise',
124 'timestamp': 1374374880,
125 'upload_date': '20130721',
130 'note': 'Embedded video',
131 'url': 'http://vk.com/video_ext.php?oid=32194266&id=162925554&hash=7d8c2e0d5e05aeaa&hd=1',
132 'md5': 'c7ce8f1f87bec05b3de07fdeafe21a0a',
136 'uploader': 'Vladimir Gavrin',
139 'upload_date': '20120730',
142 'skip': 'This video has been removed from public access.',
146 # please update if you find a video whose URL follows the same pattern
147 'url': 'http://vk.com/video-8871596_164049491',
148 'md5': 'a590bcaf3d543576c9bd162812387666',
149 'note': 'Only available for registered users',
153 'uploader': 'Триллеры',
154 'title': '► Бойцовский клуб / Fight Club 1999 [HD 720]',
156 'upload_date': '20121218',
159 'skip': 'Requires vk account credentials',
162 'url': 'http://vk.com/hd_kino_mania?z=video-43215063_168067957%2F15c66b9b533119788d',
163 'md5': '4d7a5ef8cf114dfa09577e57b2993202',
167 'uploader': 'Киномания - лучшее из мира кино',
170 'upload_date': '20140328',
172 'skip': 'Requires vk account credentials',
175 'url': 'http://m.vk.com/video-43215063_169084319?list=125c627d1aa1cebb83&from=wall-43215063_2566540',
176 'md5': '0c45586baa71b7cb1d0784ee3f4e00a6',
177 'note': 'ivi.ru embed',
181 'title': 'Книга Илая',
183 'upload_date': '20140626',
186 'skip': 'Only works from Russia',
189 # video (removed?) only available with list id
190 'url': 'https://vk.com/video30481095_171201961?list=8764ae2d21f14088d4',
191 'md5': '091287af5402239a1051c37ec7b92913',
195 'title': 'ТюменцевВВ_09.07.2015',
196 'uploader': 'Anton Ivanov',
198 'upload_date': '20150709',
205 'url': 'https://vk.com/video276849682_170681728',
209 'title': "DSWD Awards 'Children's Joy Foundation, Inc.' Certificate of Registration and License to Operate",
210 'description': 'md5:d9903938abdc74c738af77f527ca0596',
212 'upload_date': '20130116',
213 'uploader': "Children's Joy Foundation",
214 'uploader_id': 'thecjf',
220 'url': 'https://vk.com/video-37468416_456239855',
222 'id': 'k3lz2cmXyRuJQSjGHUv',
224 'title': 'md5:d52606645c20b0ddbb21655adaa4f56f',
225 'description': 'md5:c651358f03c56f1150b555c26d90a0fd',
226 'uploader': 'AniLibria.Tv',
227 'upload_date': '20160914',
228 'uploader_id': 'x1p5vl5',
229 'timestamp': 1473877246,
232 'skip_download': True,
236 # video key is extra_data not url\d+
237 'url': 'http://vk.com/video-110305615_171782105',
238 'md5': 'e13fcda136f99764872e739d13fac1d1',
242 'title': 'S-Dance, репетиции к The way show',
243 'uploader': 'THE WAY SHOW | 17 апреля',
244 'timestamp': 1454870100,
245 'upload_date': '20160207',
250 # finished live stream, postlive_mp4
251 'url': 'https://vk.com/videos-387766?z=video-387766_456242764%2Fpl_-387766_-2',
252 'md5': '90d22d051fccbbe9becfccc615be6791',
256 'title': 'ИгроМир 2016 — день 1',
257 'uploader': 'Игромания',
263 # live stream, hls and rtmp links, most likely already finished live
264 # stream by the time you are reading this comment
265 'url': 'https://vk.com/video-140332_456239111',
266 'only_matching': True,
269 # removed video, just testing that we match the pattern
270 'url': 'http://vk.com/feed?z=video-43215063_166094326%2Fbb50cacd3177146d7a',
271 'only_matching': True,
274 # age restricted video, requires vk account credentials
275 'url': 'https://vk.com/video205387401_164765225',
276 'only_matching': True,
280 'url': 'https://vk.com/video-76116461_171554880',
281 'only_matching': True,
284 'url': 'http://new.vk.com/video205387401_165548505',
285 'only_matching': True,
288 # This video is no longer available, because its author has been blocked.
289 'url': 'https://vk.com/video-10639516_456240611',
290 'only_matching': True,
294 def _real_extract(self, url):
295 mobj = re.match(self._VALID_URL, url)
296 video_id = mobj.group('videoid')
299 info_url = 'https://vk.com/al_video.php?act=show&al=1&module=video&video=%s' % video_id
300 # Some videos (removed?) can only be downloaded with list id specified
301 list_id = mobj.group('list_id')
303 info_url += '&list=%s' % list_id
305 info_url = 'http://vk.com/video_ext.php?' + mobj.group('embed_query')
306 video_id = '%s_%s' % (mobj.group('oid'), mobj.group('id'))
308 info_page = self._download_webpage(info_url, video_id)
310 error_message = self._html_search_regex(
311 [r'(?s)<!><div[^>]+class="video_layer_message"[^>]*>(.+?)</div>',
312 r'(?s)<div[^>]+id="video_ext_msg"[^>]*>(.+?)</div>'],
313 info_page, 'error message', default=None)
315 raise ExtractorError(error_message, expected=True)
317 if re.search(r'<!>/login\.php\?.*\bact=security_check', info_page):
318 raise ExtractorError(
319 'You are trying to log in from an unusual location. You should confirm ownership at vk.com to log in with this IP.',
322 ERROR_COPYRIGHT = 'Video %s has been removed from public access due to rightholder complaint.'
325 r'>Видеозапись .*? была изъята из публичного доступа в связи с обращением правообладателя.<':
328 r'>The video .*? was removed from public access by request of the copyright holder.<':
331 r'<!>Please log in or <':
332 'Video %s is only available for registered users, '
333 'use --username and --password options to provide account credentials.',
336 'Video %s does not exist.',
338 r'<!>Видео временно недоступно':
339 'Video %s is temporarily unavailable.',
342 'Access denied to video %s.',
344 r'<!>Видеозапись недоступна, так как её автор был заблокирован.':
345 'Video %s is no longer available, because its author has been blocked.',
347 r'<!>This video is no longer available, because its author has been blocked.':
348 'Video %s is no longer available, because its author has been blocked.',
351 for error_re, error_msg in ERRORS.items():
352 if re.search(error_re, info_page):
353 raise ExtractorError(error_msg % video_id, expected=True)
355 youtube_url = YoutubeIE._extract_url(info_page)
357 return self.url_result(youtube_url, ie=YoutubeIE.ie_key())
359 vimeo_url = VimeoIE._extract_url(url, info_page)
360 if vimeo_url is not None:
361 return self.url_result(vimeo_url)
363 pladform_url = PladformIE._extract_url(info_page)
365 return self.url_result(pladform_url)
367 m_rutube = re.search(
368 r'\ssrc="((?:https?:)?//rutube\.ru\\?/(?:video|play)\\?/embed(?:.*?))\\?"', info_page)
369 if m_rutube is not None:
370 rutube_url = self._proto_relative_url(
371 m_rutube.group(1).replace('\\', ''))
372 return self.url_result(rutube_url)
374 dailymotion_urls = DailymotionIE._extract_urls(info_page)
376 return self.url_result(dailymotion_urls[0], DailymotionIE.ie_key())
378 m_opts = re.search(r'(?s)var\s+opts\s*=\s*({.+?});', info_page)
380 m_opts_url = re.search(r"url\s*:\s*'((?!/\b)[^']+)", m_opts.group(1))
382 opts_url = m_opts_url.group(1)
383 if opts_url.startswith('//'):
384 opts_url = 'http:' + opts_url
385 return self.url_result(opts_url)
387 # vars does not look to be served anymore since 24.10.2016
388 data = self._parse_json(
390 r'var\s+vars\s*=\s*({.+?});', info_page, 'vars', default='{}'),
391 video_id, fatal=False)
393 # <!json> is served instead
395 data = self._parse_json(
397 r'<!json>\s*({.+?})\s*<!>', info_page, 'json', default='{}'),
400 data = data['player']['params'][0]
403 data = self._parse_json(
405 r'var\s+playerParams\s*=\s*({.+?})\s*;\s*\n', info_page,
407 video_id)['params'][0]
409 title = unescapeHTML(data['md_title'])
412 # 3 = post live (finished live)
413 is_live = data.get('live') == 2
415 title = self._live_title(title)
417 timestamp = unified_timestamp(self._html_search_regex(
418 r'class=["\']mv_info_date[^>]+>([^<]+)(?:<|from)', info_page,
419 'upload date', fatal=False))
421 view_count = str_to_int(self._search_regex(
422 r'class=["\']mv_views_count[^>]+>\s*([\d,.]+)',
423 info_page, 'view count', default=None))
426 for format_id, format_url in data.items():
427 format_url = url_or_none(format_url)
428 if not format_url or not format_url.startswith(('http', '//', 'rtmp')):
430 if (format_id.startswith(('url', 'cache')) or
431 format_id in ('extra_data', 'live_mp4', 'postlive_mp4')):
432 height = int_or_none(self._search_regex(
433 r'^(?:url|cache)(\d+)', format_id, 'height', default=None))
435 'format_id': format_id,
439 elif format_id == 'hls':
440 formats.extend(self._extract_m3u8_formats(
441 format_url, video_id, 'mp4', 'm3u8_native',
442 m3u8_id=format_id, fatal=False, live=is_live))
443 elif format_id == 'rtmp':
445 'format_id': format_id,
449 self._sort_formats(formats)
452 'id': compat_str(data.get('vid') or video_id),
455 'thumbnail': data.get('jpg'),
456 'uploader': data.get('md_author'),
457 'duration': data.get('duration'),
458 'timestamp': timestamp,
459 'view_count': view_count,
464 class VKUserVideosIE(VKBaseIE):
465 IE_NAME = 'vk:uservideos'
466 IE_DESC = "VK - User's Videos"
467 _VALID_URL = r'https?://(?:(?:m|new)\.)?vk\.com/videos(?P<id>-?[0-9]+)(?!\?.*\bz=video)(?:[/?#&]|$)'
468 _TEMPLATE_URL = 'https://vk.com/videos'
470 'url': 'http://vk.com/videos205387401',
473 'title': "Tom Cruise's Videos",
475 'playlist_mincount': 4,
477 'url': 'http://vk.com/videos-77521',
478 'only_matching': True,
480 'url': 'http://vk.com/videos-97664626?section=all',
481 'only_matching': True,
483 'url': 'http://m.vk.com/videos205387401',
484 'only_matching': True,
486 'url': 'http://new.vk.com/videos205387401',
487 'only_matching': True,
490 def _real_extract(self, url):
491 page_id = self._match_id(url)
493 webpage = self._download_webpage(url, page_id)
497 'http://vk.com/video' + video_id, 'VK', video_id=video_id)
498 for video_id in orderedSet(re.findall(r'href="/video(-?[0-9_]+)"', webpage))]
500 title = unescapeHTML(self._search_regex(
501 r'<title>\s*([^<]+?)\s+\|\s+\d+\s+videos',
502 webpage, 'title', default=page_id))
504 return self.playlist_result(entries, page_id, title)
507 class VKWallPostIE(VKBaseIE):
508 IE_NAME = 'vk:wallpost'
509 _VALID_URL = r'https?://(?:(?:(?:(?:m|new)\.)?vk\.com/(?:[^?]+\?.*\bw=)?wall(?P<id>-?\d+_\d+)))'
511 # public page URL, audio playlist
512 'url': 'https://vk.com/bs.official?w=wall-23538238_35',
515 'title': 'Black Shadow - Wall post 23538238_35',
516 'description': 'md5:3f84b9c4f9ef499731cf1ced9998cc0c',
519 'md5': '5ba93864ec5b85f7ce19a9af4af080f6',
521 'id': '135220665_111806521',
523 'title': 'Black Shadow - Слепое Верование',
525 'uploader': 'Black Shadow',
526 'artist': 'Black Shadow',
527 'track': 'Слепое Верование',
530 'md5': '4cc7e804579122b17ea95af7834c9233',
532 'id': '135220665_111802303',
534 'title': 'Black Shadow - Война - Негасимое Бездны Пламя!',
536 'uploader': 'Black Shadow',
537 'artist': 'Black Shadow',
538 'track': 'Война - Негасимое Бездны Пламя!',
541 'skip_download': True,
547 'skip': 'Requires vk account credentials',
549 # single YouTube embed, no leading -
550 'url': 'https://vk.com/wall85155021_6319',
552 'id': '85155021_6319',
553 'title': 'Sergey Gorbunov - Wall post 85155021_6319',
559 'skip': 'Requires vk account credentials',
562 'url': 'https://vk.com/wall-23538238_35',
563 'only_matching': True,
565 # mobile wall page URL
566 'url': 'https://m.vk.com/wall-23538238_35',
567 'only_matching': True,
570 def _real_extract(self, url):
571 post_id = self._match_id(url)
573 wall_url = 'https://vk.com/wall%s' % post_id
575 post_id = remove_start(post_id, '-')
577 webpage = self._download_webpage(wall_url, post_id)
579 error = self._html_search_regex(
580 r'>Error</div>\s*<div[^>]+class=["\']body["\'][^>]*>([^<]+)',
581 webpage, 'error', default=None)
583 raise ExtractorError('VK said: %s' % error, expected=True)
585 description = clean_html(get_element_by_class('wall_post_text', webpage))
586 uploader = clean_html(get_element_by_class('author', webpage))
587 thumbnail = self._og_search_thumbnail(webpage)
591 audio_ids = re.findall(r'data-full-id=["\'](\d+_\d+)', webpage)
593 al_audio = self._download_webpage(
594 'https://vk.com/al_audio.php', post_id,
595 note='Downloading audio info', fatal=False,
596 data=urlencode_postdata({
597 'act': 'reload_audio',
599 'ids': ','.join(audio_ids)
602 Audio = collections.namedtuple(
603 'Audio', ['id', 'user_id', 'url', 'track', 'artist', 'duration'])
604 audios = self._parse_json(
606 r'<!json>(.+?)<!>', al_audio, 'audios', default='[]'),
607 post_id, fatal=False, transform_source=unescapeHTML)
608 if isinstance(audios, list):
610 a = Audio._make(audio[:6])
612 'id': '%s_%s' % (a.user_id, a.id),
614 'title': '%s - %s' % (a.artist, a.track) if a.artist and a.track else a.id,
615 'thumbnail': thumbnail,
616 'duration': a.duration,
617 'uploader': uploader,
622 for video in re.finditer(
623 r'<a[^>]+href=(["\'])(?P<url>/video(?:-?[\d_]+).*?)\1', webpage):
624 entries.append(self.url_result(
625 compat_urlparse.urljoin(url, video.group('url')), VKIE.ie_key()))
627 title = 'Wall post %s' % post_id
629 return self.playlist_result(
630 orderedSet(entries), post_id,
631 '%s - %s' % (uploader, title) if uploader else title,