2 from __future__ import unicode_literals
7 from .common import InfoExtractor
21 from .vimeo import VimeoIE
22 from .pladform import PladformIE
25 class VKIE(InfoExtractor):
31 (?:m\.)?vk\.com/video_ext\.php\?.*?\boid=(?P<oid>-?\d+).*?\bid=(?P<id>\d+)|
33 (?:m\.)?vk\.com/(?:.+?\?.*?z=)?video|
34 (?:www\.)?biqle\.ru/watch/
36 (?P<videoid>[^s].*?)(?:\?(?:.*\blist=(?P<list_id>[\da-f]+))?|%2F|$)
43 'url': 'http://vk.com/videos-77521?z=video-77521_162222515%2Fclub77521',
44 'md5': '0deae91935c54e00003c2a00646315f0',
48 'title': 'ProtivoGunz - Хуёвая песня',
49 'uploader': 're:(?:Noize MC|Alexander Ilyashenko).*',
51 'upload_date': '20120212',
56 'url': 'http://vk.com/video205387401_165548505',
57 'md5': '6c0aeb2e90396ba97035b9cbde548700',
61 'uploader': 'Tom Cruise',
64 'upload_date': '20130721',
69 'note': 'Embedded video',
70 'url': 'http://vk.com/video_ext.php?oid=32194266&id=162925554&hash=7d8c2e0d5e05aeaa&hd=1',
71 'md5': 'c7ce8f1f87bec05b3de07fdeafe21a0a',
75 'uploader': 'Vladimir Gavrin',
78 'upload_date': '20120730',
84 # please update if you find a video whose URL follows the same pattern
85 'url': 'http://vk.com/video-8871596_164049491',
86 'md5': 'a590bcaf3d543576c9bd162812387666',
87 'note': 'Only available for registered users',
91 'uploader': 'Триллеры',
92 'title': '► Бойцовский клуб / Fight Club 1999 [HD 720]',
94 'upload_date': '20121218',
97 'skip': 'Requires vk account credentials',
100 'url': 'http://vk.com/hd_kino_mania?z=video-43215063_168067957%2F15c66b9b533119788d',
101 'md5': '4d7a5ef8cf114dfa09577e57b2993202',
105 'uploader': 'Киномания - лучшее из мира кино',
108 'upload_date': '20140328',
110 'skip': 'Requires vk account credentials',
113 'url': 'http://m.vk.com/video-43215063_169084319?list=125c627d1aa1cebb83&from=wall-43215063_2566540',
114 'md5': '0c45586baa71b7cb1d0784ee3f4e00a6',
115 'note': 'ivi.ru embed',
119 'title': 'Книга Илая',
121 'upload_date': '20140626',
124 'skip': 'Only works from Russia',
127 # video (removed?) only available with list id
128 'url': 'https://vk.com/video30481095_171201961?list=8764ae2d21f14088d4',
129 'md5': '091287af5402239a1051c37ec7b92913',
133 'title': 'ТюменцевВВ_09.07.2015',
134 'uploader': 'Anton Ivanov',
136 'upload_date': '20150709',
142 'url': 'https://vk.com/video276849682_170681728',
146 'title': "DSWD Awards 'Children's Joy Foundation, Inc.' Certificate of Registration and License to Operate",
147 'description': 'md5:bf9c26cfa4acdfb146362682edd3827a',
149 'upload_date': '20130116',
150 'uploader': "Children's Joy Foundation",
151 'uploader_id': 'thecjf',
156 # video key is extra_data not url\d+
157 'url': 'http://vk.com/video-110305615_171782105',
158 'md5': 'e13fcda136f99764872e739d13fac1d1',
162 'title': 'S-Dance, репетиции к The way show',
163 'uploader': 'THE WAY SHOW | 17 апреля',
164 'upload_date': '20160207',
169 # removed video, just testing that we match the pattern
170 'url': 'http://vk.com/feed?z=video-43215063_166094326%2Fbb50cacd3177146d7a',
171 'only_matching': True,
174 # age restricted video, requires vk account credentials
175 'url': 'https://vk.com/video205387401_164765225',
176 'only_matching': True,
180 'url': 'http://www.biqle.ru/watch/847655_160197695',
181 'only_matching': True,
185 'url': 'https://vk.com/video-76116461_171554880',
186 'only_matching': True,
191 (username, password) = self._get_login_info()
195 login_page = self._download_webpage(
196 'https://vk.com', None, 'Downloading login page')
198 login_form = self._hidden_inputs(login_page)
201 'email': username.encode('cp1251'),
202 'pass': password.encode('cp1251'),
205 request = sanitized_Request(
206 'https://login.vk.com/?act=login',
207 compat_urllib_parse.urlencode(login_form).encode('utf-8'))
208 login_page = self._download_webpage(
209 request, None, note='Logging in as %s' % username)
211 if re.search(r'onLoginFailed', login_page):
212 raise ExtractorError(
213 'Unable to login, incorrect username and/or password', expected=True)
215 def _real_initialize(self):
218 def _real_extract(self, url):
219 mobj = re.match(self._VALID_URL, url)
220 video_id = mobj.group('videoid')
223 video_id = '%s_%s' % (mobj.group('oid'), mobj.group('id'))
225 info_url = 'https://vk.com/al_video.php?act=show&al=1&module=video&video=%s' % video_id
227 # Some videos (removed?) can only be downloaded with list id specified
228 list_id = mobj.group('list_id')
230 info_url += '&list=%s' % list_id
232 info_page = self._download_webpage(info_url, video_id)
234 error_message = self._html_search_regex(
235 r'(?s)<!><div[^>]+class="video_layer_message"[^>]*>(.+?)</div>',
236 info_page, 'error message', default=None)
238 raise ExtractorError(error_message, expected=True)
240 if re.search(r'<!>/login\.php\?.*\bact=security_check', info_page):
241 raise ExtractorError(
242 'You are trying to log in from an unusual location. You should confirm ownership at vk.com to log in with this IP.',
246 r'>Видеозапись .*? была изъята из публичного доступа в связи с обращением правообладателя.<':
247 'Video %s has been removed from public access due to rightholder complaint.',
249 r'<!>Please log in or <':
250 'Video %s is only available for registered users, '
251 'use --username and --password options to provide account credentials.',
254 'Video %s does not exist.',
256 r'<!>Видео временно недоступно':
257 'Video %s is temporarily unavailable.',
260 'Access denied to video %s.',
263 for error_re, error_msg in ERRORS.items():
264 if re.search(error_re, info_page):
265 raise ExtractorError(error_msg % video_id, expected=True)
267 youtube_url = self._search_regex(
268 r'<iframe[^>]+src="((?:https?:)?//www.youtube.com/embed/[^"]+)"',
269 info_page, 'youtube iframe', default=None)
271 return self.url_result(youtube_url, 'Youtube')
273 vimeo_url = VimeoIE._extract_vimeo_url(url, info_page)
274 if vimeo_url is not None:
275 return self.url_result(vimeo_url)
277 pladform_url = PladformIE._extract_url(info_page)
279 return self.url_result(pladform_url)
281 m_rutube = re.search(
282 r'\ssrc="((?:https?:)?//rutube\.ru\\?/(?:video|play)\\?/embed(?:.*?))\\?"', info_page)
283 if m_rutube is not None:
284 rutube_url = self._proto_relative_url(
285 m_rutube.group(1).replace('\\', ''))
286 return self.url_result(rutube_url)
288 m_opts = re.search(r'(?s)var\s+opts\s*=\s*({.+?});', info_page)
290 m_opts_url = re.search(r"url\s*:\s*'((?!/\b)[^']+)", m_opts.group(1))
292 opts_url = m_opts_url.group(1)
293 if opts_url.startswith('//'):
294 opts_url = 'http:' + opts_url
295 return self.url_result(opts_url)
297 data_json = self._search_regex(r'var\s+vars\s*=\s*({.+?});', info_page, 'vars')
298 data = json.loads(data_json)
300 # Extract upload date
302 mobj = re.search(r'id="mv_date(?:_views)?_wrap"[^>]*>([a-zA-Z]+ [0-9]+), ([0-9]+) at', info_page)
304 mobj.group(1) + ' ' + mobj.group(2)
305 upload_date = unified_strdate(mobj.group(1) + ' ' + mobj.group(2))
308 views = self._html_search_regex(
309 r'"mv_views_count_number"[^>]*>(.+?\bviews?)<',
310 info_page, 'view count', fatal=False)
312 view_count = str_to_int(self._search_regex(
313 r'([\d,.]+)', views, 'view count', fatal=False))
316 for k, v in data.items():
317 if not k.startswith('url') and k != 'extra_data' or not v:
319 height = int_or_none(self._search_regex(
320 r'^url(\d+)', k, 'height', default=None))
326 self._sort_formats(formats)
329 'id': compat_str(data['vid']),
331 'title': unescapeHTML(data['md_title']),
332 'thumbnail': data.get('jpg'),
333 'uploader': data.get('md_author'),
334 'duration': data.get('duration'),
335 'upload_date': upload_date,
336 'view_count': view_count,
340 class VKUserVideosIE(InfoExtractor):
341 IE_NAME = 'vk:uservideos'
342 IE_DESC = "VK - User's Videos"
343 _VALID_URL = r'https?://vk\.com/videos(?P<id>-?[0-9]+)(?!\?.*\bz=video)(?:[/?#&]|$)'
344 _TEMPLATE_URL = 'https://vk.com/videos'
346 'url': 'http://vk.com/videos205387401',
349 'title': "Tom Cruise's Videos",
351 'playlist_mincount': 4,
353 'url': 'http://vk.com/videos-77521',
354 'only_matching': True,
356 'url': 'http://vk.com/videos-97664626?section=all',
357 'only_matching': True,
360 def _real_extract(self, url):
361 page_id = self._match_id(url)
363 webpage = self._download_webpage(url, page_id)
367 'http://vk.com/video' + video_id, 'VK', video_id=video_id)
368 for video_id in orderedSet(re.findall(r'href="/video(-?[0-9_]+)"', webpage))]
370 title = unescapeHTML(self._search_regex(
371 r'<title>\s*([^<]+?)\s+\|\s+\d+\s+videos',
372 webpage, 'title', default=page_id))
374 return self.playlist_result(entries, page_id, title)