2 from __future__ import unicode_literals
9 from .common import InfoExtractor
10 from ..compat import (
26 from .dailymotion import DailymotionIE
27 from .pladform import PladformIE
28 from .vimeo import VimeoIE
31 class VKBaseIE(InfoExtractor):
35 (username, password) = self._get_login_info()
39 login_page, url_handle = self._download_webpage_handle(
40 'https://vk.com', None, 'Downloading login page')
42 login_form = self._hidden_inputs(login_page)
45 'email': username.encode('cp1251'),
46 'pass': password.encode('cp1251'),
49 # https://new.vk.com/ serves two same remixlhk cookies in Set-Cookie header
50 # and expects the first one to be set rather than second (see
51 # https://github.com/rg3/youtube-dl/issues/9841#issuecomment-227871201).
52 # As of RFC6265 the newer one cookie should be set into cookie store
53 # what actually happens.
54 # We will workaround this VK issue by resetting the remixlhk cookie to
55 # the first one manually.
56 for header, cookies in url_handle.headers.items():
57 if header.lower() != 'set-cookie':
59 if sys.version_info[0] >= 3:
60 cookies = cookies.encode('iso-8859-1')
61 cookies = cookies.decode('utf-8')
62 remixlhk = re.search(r'remixlhk=(.+?);.*?\bdomain=(.+?)(?:[,;]|$)', cookies)
64 value, domain = remixlhk.groups()
65 self._set_cookie(domain, 'remixlhk', value)
68 login_page = self._download_webpage(
69 'https://login.vk.com/?act=login', None,
70 note='Logging in as %s' % username,
71 data=urlencode_postdata(login_form))
73 if re.search(r'onLoginFailed', login_page):
75 'Unable to login, incorrect username and/or password', expected=True)
77 def _real_initialize(self):
88 (?:(?:m|new)\.)?vk\.com/video_|
91 ext\.php\?(?P<embed_query>.*?\boid=(?P<oid>-?\d+).*?\bid=(?P<id>\d+).*)|
93 (?:(?:m|new)\.)?vk\.com/(?:.+?\?.*?z=)?video|
94 (?:www\.)?daxab.com/embed/
96 (?P<videoid>-?\d+_\d+)(?:.*\blist=(?P<list_id>[\da-f]+))?
101 'url': 'http://vk.com/videos-77521?z=video-77521_162222515%2Fclub77521',
102 'md5': '0deae91935c54e00003c2a00646315f0',
106 'title': 'ProtivoGunz - Хуёвая песня',
107 'uploader': 're:(?:Noize MC|Alexander Ilyashenko).*',
109 'upload_date': '20120212',
114 'url': 'http://vk.com/video205387401_165548505',
115 'md5': '6c0aeb2e90396ba97035b9cbde548700',
119 'uploader': 'Tom Cruise',
122 'upload_date': '20130721',
127 'note': 'Embedded video',
128 'url': 'http://vk.com/video_ext.php?oid=32194266&id=162925554&hash=7d8c2e0d5e05aeaa&hd=1',
129 'md5': 'c7ce8f1f87bec05b3de07fdeafe21a0a',
133 'uploader': 'Vladimir Gavrin',
136 'upload_date': '20120730',
139 'skip': 'This video has been removed from public access.',
143 # please update if you find a video whose URL follows the same pattern
144 'url': 'http://vk.com/video-8871596_164049491',
145 'md5': 'a590bcaf3d543576c9bd162812387666',
146 'note': 'Only available for registered users',
150 'uploader': 'Триллеры',
151 'title': '► Бойцовский клуб / Fight Club 1999 [HD 720]',
153 'upload_date': '20121218',
156 'skip': 'Requires vk account credentials',
159 'url': 'http://vk.com/hd_kino_mania?z=video-43215063_168067957%2F15c66b9b533119788d',
160 'md5': '4d7a5ef8cf114dfa09577e57b2993202',
164 'uploader': 'Киномания - лучшее из мира кино',
167 'upload_date': '20140328',
169 'skip': 'Requires vk account credentials',
172 'url': 'http://m.vk.com/video-43215063_169084319?list=125c627d1aa1cebb83&from=wall-43215063_2566540',
173 'md5': '0c45586baa71b7cb1d0784ee3f4e00a6',
174 'note': 'ivi.ru embed',
178 'title': 'Книга Илая',
180 'upload_date': '20140626',
183 'skip': 'Only works from Russia',
186 # video (removed?) only available with list id
187 'url': 'https://vk.com/video30481095_171201961?list=8764ae2d21f14088d4',
188 'md5': '091287af5402239a1051c37ec7b92913',
192 'title': 'ТюменцевВВ_09.07.2015',
193 'uploader': 'Anton Ivanov',
195 'upload_date': '20150709',
201 'url': 'https://vk.com/video276849682_170681728',
205 'title': "DSWD Awards 'Children's Joy Foundation, Inc.' Certificate of Registration and License to Operate",
206 'description': 'md5:d9903938abdc74c738af77f527ca0596',
208 'upload_date': '20130116',
209 'uploader': "Children's Joy Foundation",
210 'uploader_id': 'thecjf',
216 'url': 'https://vk.com/video-37468416_456239855',
218 'id': 'k3lz2cmXyRuJQSjGHUv',
220 'title': 'md5:d52606645c20b0ddbb21655adaa4f56f',
221 'description': 'md5:c651358f03c56f1150b555c26d90a0fd',
222 'uploader': 'AniLibria.Tv',
223 'upload_date': '20160914',
224 'uploader_id': 'x1p5vl5',
225 'timestamp': 1473877246,
228 'skip_download': True,
232 # video key is extra_data not url\d+
233 'url': 'http://vk.com/video-110305615_171782105',
234 'md5': 'e13fcda136f99764872e739d13fac1d1',
238 'title': 'S-Dance, репетиции к The way show',
239 'uploader': 'THE WAY SHOW | 17 апреля',
240 'upload_date': '20160207',
245 # finished live stream, live_mp4
246 'url': 'https://vk.com/videos-387766?z=video-387766_456242764%2Fpl_-387766_-2',
247 'md5': '90d22d051fccbbe9becfccc615be6791',
251 'title': 'ИгроМир 2016 — день 1',
252 'uploader': 'Игромания',
257 # live stream, hls and rtmp links,most likely already finished live
258 # stream by the time you are reading this comment
259 'url': 'https://vk.com/video-140332_456239111',
260 'only_matching': True,
263 # removed video, just testing that we match the pattern
264 'url': 'http://vk.com/feed?z=video-43215063_166094326%2Fbb50cacd3177146d7a',
265 'only_matching': True,
268 # age restricted video, requires vk account credentials
269 'url': 'https://vk.com/video205387401_164765225',
270 'only_matching': True,
274 'url': 'https://vk.com/video-76116461_171554880',
275 'only_matching': True,
278 'url': 'http://new.vk.com/video205387401_165548505',
279 'only_matching': True,
283 def _real_extract(self, url):
284 mobj = re.match(self._VALID_URL, url)
285 video_id = mobj.group('videoid')
288 info_url = 'https://vk.com/al_video.php?act=show&al=1&module=video&video=%s' % video_id
289 # Some videos (removed?) can only be downloaded with list id specified
290 list_id = mobj.group('list_id')
292 info_url += '&list=%s' % list_id
294 info_url = 'http://vk.com/video_ext.php?' + mobj.group('embed_query')
295 video_id = '%s_%s' % (mobj.group('oid'), mobj.group('id'))
297 info_page = self._download_webpage(info_url, video_id)
299 error_message = self._html_search_regex(
300 [r'(?s)<!><div[^>]+class="video_layer_message"[^>]*>(.+?)</div>',
301 r'(?s)<div[^>]+id="video_ext_msg"[^>]*>(.+?)</div>'],
302 info_page, 'error message', default=None)
304 raise ExtractorError(error_message, expected=True)
306 if re.search(r'<!>/login\.php\?.*\bact=security_check', info_page):
307 raise ExtractorError(
308 'You are trying to log in from an unusual location. You should confirm ownership at vk.com to log in with this IP.',
312 r'>Видеозапись .*? была изъята из публичного доступа в связи с обращением правообладателя.<':
313 'Video %s has been removed from public access due to rightholder complaint.',
315 r'<!>Please log in or <':
316 'Video %s is only available for registered users, '
317 'use --username and --password options to provide account credentials.',
320 'Video %s does not exist.',
322 r'<!>Видео временно недоступно':
323 'Video %s is temporarily unavailable.',
326 'Access denied to video %s.',
329 for error_re, error_msg in ERRORS.items():
330 if re.search(error_re, info_page):
331 raise ExtractorError(error_msg % video_id, expected=True)
333 youtube_url = self._search_regex(
334 r'<iframe[^>]+src="((?:https?:)?//www.youtube.com/embed/[^"]+)"',
335 info_page, 'youtube iframe', default=None)
337 return self.url_result(youtube_url, 'Youtube')
339 vimeo_url = VimeoIE._extract_vimeo_url(url, info_page)
340 if vimeo_url is not None:
341 return self.url_result(vimeo_url)
343 pladform_url = PladformIE._extract_url(info_page)
345 return self.url_result(pladform_url)
347 m_rutube = re.search(
348 r'\ssrc="((?:https?:)?//rutube\.ru\\?/(?:video|play)\\?/embed(?:.*?))\\?"', info_page)
349 if m_rutube is not None:
350 rutube_url = self._proto_relative_url(
351 m_rutube.group(1).replace('\\', ''))
352 return self.url_result(rutube_url)
354 dailymotion_urls = DailymotionIE._extract_urls(info_page)
356 return self.url_result(dailymotion_urls[0], DailymotionIE.ie_key())
358 m_opts = re.search(r'(?s)var\s+opts\s*=\s*({.+?});', info_page)
360 m_opts_url = re.search(r"url\s*:\s*'((?!/\b)[^']+)", m_opts.group(1))
362 opts_url = m_opts_url.group(1)
363 if opts_url.startswith('//'):
364 opts_url = 'http:' + opts_url
365 return self.url_result(opts_url)
367 data_json = self._search_regex(r'var\s+vars\s*=\s*({.+?});', info_page, 'vars')
368 data = json.loads(data_json)
370 title = unescapeHTML(data['md_title'])
372 if data.get('live') == 2:
373 title = self._live_title(title)
375 # Extract upload date
377 mobj = re.search(r'id="mv_date(?:_views)?_wrap"[^>]*>([a-zA-Z]+ [0-9]+), ([0-9]+) at', info_page)
379 mobj.group(1) + ' ' + mobj.group(2)
380 upload_date = unified_strdate(mobj.group(1) + ' ' + mobj.group(2))
383 views = self._html_search_regex(
384 r'"mv_views_count_number"[^>]*>(.+?\bviews?)<',
385 info_page, 'view count', default=None)
387 view_count = str_to_int(self._search_regex(
388 r'([\d,.]+)', views, 'view count', fatal=False))
391 for format_id, format_url in data.items():
392 if not isinstance(format_url, compat_str) or not format_url.startswith(('http', '//', 'rtmp')):
394 if format_id.startswith(('url', 'cache')) or format_id in ('extra_data', 'live_mp4'):
395 height = int_or_none(self._search_regex(
396 r'^(?:url|cache)(\d+)', format_id, 'height', default=None))
398 'format_id': format_id,
402 elif format_id == 'hls':
403 formats.extend(self._extract_m3u8_formats(
404 format_url, video_id, 'mp4', m3u8_id=format_id,
405 fatal=False, live=True))
406 elif format_id == 'rtmp':
408 'format_id': format_id,
412 self._sort_formats(formats)
415 'id': compat_str(data.get('vid') or video_id),
418 'thumbnail': data.get('jpg'),
419 'uploader': data.get('md_author'),
420 'duration': data.get('duration'),
421 'upload_date': upload_date,
422 'view_count': view_count,
426 class VKUserVideosIE(VKBaseIE):
427 IE_NAME = 'vk:uservideos'
428 IE_DESC = "VK - User's Videos"
429 _VALID_URL = r'https?://(?:(?:m|new)\.)?vk\.com/videos(?P<id>-?[0-9]+)(?!\?.*\bz=video)(?:[/?#&]|$)'
430 _TEMPLATE_URL = 'https://vk.com/videos'
432 'url': 'http://vk.com/videos205387401',
435 'title': "Tom Cruise's Videos",
437 'playlist_mincount': 4,
439 'url': 'http://vk.com/videos-77521',
440 'only_matching': True,
442 'url': 'http://vk.com/videos-97664626?section=all',
443 'only_matching': True,
445 'url': 'http://m.vk.com/videos205387401',
446 'only_matching': True,
448 'url': 'http://new.vk.com/videos205387401',
449 'only_matching': True,
452 def _real_extract(self, url):
453 page_id = self._match_id(url)
455 webpage = self._download_webpage(url, page_id)
459 'http://vk.com/video' + video_id, 'VK', video_id=video_id)
460 for video_id in orderedSet(re.findall(r'href="/video(-?[0-9_]+)"', webpage))]
462 title = unescapeHTML(self._search_regex(
463 r'<title>\s*([^<]+?)\s+\|\s+\d+\s+videos',
464 webpage, 'title', default=page_id))
466 return self.playlist_result(entries, page_id, title)
469 class VKWallPostIE(VKBaseIE):
470 IE_NAME = 'vk:wallpost'
471 _VALID_URL = r'https?://(?:(?:(?:(?:m|new)\.)?vk\.com/(?:[^?]+\?.*\bw=)?wall(?P<id>-?\d+_\d+)))'
473 # public page URL, audio playlist
474 'url': 'https://vk.com/bs.official?w=wall-23538238_35',
477 'title': 'Black Shadow - Wall post 23538238_35',
478 'description': 'md5:3f84b9c4f9ef499731cf1ced9998cc0c',
481 'md5': '5ba93864ec5b85f7ce19a9af4af080f6',
483 'id': '135220665_111806521',
485 'title': 'Black Shadow - Слепое Верование',
487 'uploader': 'Black Shadow',
488 'artist': 'Black Shadow',
489 'track': 'Слепое Верование',
492 'md5': '4cc7e804579122b17ea95af7834c9233',
494 'id': '135220665_111802303',
496 'title': 'Black Shadow - Война - Негасимое Бездны Пламя!',
498 'uploader': 'Black Shadow',
499 'artist': 'Black Shadow',
500 'track': 'Война - Негасимое Бездны Пламя!',
503 'skip_download': True,
509 'skip': 'Requires vk account credentials',
511 # single YouTube embed, no leading -
512 'url': 'https://vk.com/wall85155021_6319',
514 'id': '85155021_6319',
515 'title': 'Sergey Gorbunov - Wall post 85155021_6319',
521 'skip': 'Requires vk account credentials',
524 'url': 'https://vk.com/wall-23538238_35',
525 'only_matching': True,
527 # mobile wall page URL
528 'url': 'https://m.vk.com/wall-23538238_35',
529 'only_matching': True,
532 def _real_extract(self, url):
533 post_id = self._match_id(url)
535 wall_url = 'https://vk.com/wall%s' % post_id
537 post_id = remove_start(post_id, '-')
539 webpage = self._download_webpage(wall_url, post_id)
541 error = self._html_search_regex(
542 r'>Error</div>\s*<div[^>]+class=["\']body["\'][^>]*>([^<]+)',
543 webpage, 'error', default=None)
545 raise ExtractorError('VK said: %s' % error, expected=True)
547 description = clean_html(get_element_by_class('wall_post_text', webpage))
548 uploader = clean_html(get_element_by_class('author', webpage))
549 thumbnail = self._og_search_thumbnail(webpage)
553 audio_ids = re.findall(r'data-full-id=["\'](\d+_\d+)', webpage)
555 al_audio = self._download_webpage(
556 'https://vk.com/al_audio.php', post_id,
557 note='Downloading audio info', fatal=False,
558 data=urlencode_postdata({
559 'act': 'reload_audio',
561 'ids': ','.join(audio_ids)
564 Audio = collections.namedtuple(
565 'Audio', ['id', 'user_id', 'url', 'track', 'artist', 'duration'])
566 audios = self._parse_json(
568 r'<!json>(.+?)<!>', al_audio, 'audios', default='[]'),
569 post_id, fatal=False, transform_source=unescapeHTML)
570 if isinstance(audios, list):
572 a = Audio._make(audio[:6])
574 'id': '%s_%s' % (a.user_id, a.id),
576 'title': '%s - %s' % (a.artist, a.track) if a.artist and a.track else a.id,
577 'thumbnail': thumbnail,
578 'duration': a.duration,
579 'uploader': uploader,
584 for video in re.finditer(
585 r'<a[^>]+href=(["\'])(?P<url>/video(?:-?[\d_]+).*?)\1', webpage):
586 entries.append(self.url_result(
587 compat_urlparse.urljoin(url, video.group('url')), VKIE.ie_key()))
589 title = 'Wall post %s' % post_id
591 return self.playlist_result(
592 orderedSet(entries), post_id,
593 '%s - %s' % (uploader, title) if uploader else title,