2 from __future__ import unicode_literals
7 from .common import InfoExtractor
8 from ..compat import compat_str
19 from .vimeo import VimeoIE
20 from .pladform import PladformIE
23 class VKIE(InfoExtractor):
29 (?:m\.)?vk\.com/video_ext\.php\?.*?\boid=(?P<oid>-?\d+).*?\bid=(?P<id>\d+)|
31 (?:m\.)?vk\.com/(?:.+?\?.*?z=)?video|
32 (?:www\.)?biqle\.ru/watch/
34 (?P<videoid>[^s].*?)(?:\?(?:.*\blist=(?P<list_id>[\da-f]+))?|%2F|$)
41 'url': 'http://vk.com/videos-77521?z=video-77521_162222515%2Fclub77521',
42 'md5': '0deae91935c54e00003c2a00646315f0',
46 'title': 'ProtivoGunz - Хуёвая песня',
47 'uploader': 're:(?:Noize MC|Alexander Ilyashenko).*',
49 'upload_date': '20120212',
54 'url': 'http://vk.com/video205387401_165548505',
55 'md5': '6c0aeb2e90396ba97035b9cbde548700',
59 'uploader': 'Tom Cruise',
62 'upload_date': '20130721',
67 'note': 'Embedded video',
68 'url': 'http://vk.com/video_ext.php?oid=32194266&id=162925554&hash=7d8c2e0d5e05aeaa&hd=1',
69 'md5': 'c7ce8f1f87bec05b3de07fdeafe21a0a',
73 'uploader': 'Vladimir Gavrin',
76 'upload_date': '20120730',
82 # please update if you find a video whose URL follows the same pattern
83 'url': 'http://vk.com/video-8871596_164049491',
84 'md5': 'a590bcaf3d543576c9bd162812387666',
85 'note': 'Only available for registered users',
89 'uploader': 'Триллеры',
90 'title': '► Бойцовский клуб / Fight Club 1999 [HD 720]',
92 'upload_date': '20121218',
95 'skip': 'Requires vk account credentials',
98 'url': 'http://vk.com/hd_kino_mania?z=video-43215063_168067957%2F15c66b9b533119788d',
99 'md5': '4d7a5ef8cf114dfa09577e57b2993202',
103 'uploader': 'Киномания - лучшее из мира кино',
106 'upload_date': '20140328',
108 'skip': 'Requires vk account credentials',
111 'url': 'http://m.vk.com/video-43215063_169084319?list=125c627d1aa1cebb83&from=wall-43215063_2566540',
112 'md5': '0c45586baa71b7cb1d0784ee3f4e00a6',
113 'note': 'ivi.ru embed',
117 'title': 'Книга Илая',
119 'upload_date': '20140626',
122 'skip': 'Only works from Russia',
125 # video (removed?) only available with list id
126 'url': 'https://vk.com/video30481095_171201961?list=8764ae2d21f14088d4',
127 'md5': '091287af5402239a1051c37ec7b92913',
131 'title': 'ТюменцевВВ_09.07.2015',
132 'uploader': 'Anton Ivanov',
134 'upload_date': '20150709',
140 'url': 'https://vk.com/video276849682_170681728',
144 'title': "DSWD Awards 'Children's Joy Foundation, Inc.' Certificate of Registration and License to Operate",
145 'description': 'md5:bf9c26cfa4acdfb146362682edd3827a',
147 'upload_date': '20130116',
148 'uploader': "Children's Joy Foundation",
149 'uploader_id': 'thecjf',
154 # video key is extra_data not url\d+
155 'url': 'http://vk.com/video-110305615_171782105',
156 'md5': 'e13fcda136f99764872e739d13fac1d1',
160 'title': 'S-Dance, репетиции к The way show',
161 'uploader': 'THE WAY SHOW | 17 апреля',
162 'upload_date': '20160207',
167 # removed video, just testing that we match the pattern
168 'url': 'http://vk.com/feed?z=video-43215063_166094326%2Fbb50cacd3177146d7a',
169 'only_matching': True,
172 # age restricted video, requires vk account credentials
173 'url': 'https://vk.com/video205387401_164765225',
174 'only_matching': True,
178 'url': 'http://www.biqle.ru/watch/847655_160197695',
179 'only_matching': True,
183 'url': 'https://vk.com/video-76116461_171554880',
184 'only_matching': True,
189 (username, password) = self._get_login_info()
193 login_page = self._download_webpage(
194 'https://vk.com', None, 'Downloading login page')
196 login_form = self._hidden_inputs(login_page)
199 'email': username.encode('cp1251'),
200 'pass': password.encode('cp1251'),
203 request = sanitized_Request(
204 'https://login.vk.com/?act=login',
205 urlencode_postdata(login_form))
206 login_page = self._download_webpage(
207 request, None, note='Logging in as %s' % username)
209 if re.search(r'onLoginFailed', login_page):
210 raise ExtractorError(
211 'Unable to login, incorrect username and/or password', expected=True)
213 def _real_initialize(self):
216 def _real_extract(self, url):
217 mobj = re.match(self._VALID_URL, url)
218 video_id = mobj.group('videoid')
221 video_id = '%s_%s' % (mobj.group('oid'), mobj.group('id'))
223 info_url = 'https://vk.com/al_video.php?act=show&al=1&module=video&video=%s' % video_id
225 # Some videos (removed?) can only be downloaded with list id specified
226 list_id = mobj.group('list_id')
228 info_url += '&list=%s' % list_id
230 info_page = self._download_webpage(info_url, video_id)
232 error_message = self._html_search_regex(
233 r'(?s)<!><div[^>]+class="video_layer_message"[^>]*>(.+?)</div>',
234 info_page, 'error message', default=None)
236 raise ExtractorError(error_message, expected=True)
238 if re.search(r'<!>/login\.php\?.*\bact=security_check', info_page):
239 raise ExtractorError(
240 'You are trying to log in from an unusual location. You should confirm ownership at vk.com to log in with this IP.',
244 r'>Видеозапись .*? была изъята из публичного доступа в связи с обращением правообладателя.<':
245 'Video %s has been removed from public access due to rightholder complaint.',
247 r'<!>Please log in or <':
248 'Video %s is only available for registered users, '
249 'use --username and --password options to provide account credentials.',
252 'Video %s does not exist.',
254 r'<!>Видео временно недоступно':
255 'Video %s is temporarily unavailable.',
258 'Access denied to video %s.',
261 for error_re, error_msg in ERRORS.items():
262 if re.search(error_re, info_page):
263 raise ExtractorError(error_msg % video_id, expected=True)
265 youtube_url = self._search_regex(
266 r'<iframe[^>]+src="((?:https?:)?//www.youtube.com/embed/[^"]+)"',
267 info_page, 'youtube iframe', default=None)
269 return self.url_result(youtube_url, 'Youtube')
271 vimeo_url = VimeoIE._extract_vimeo_url(url, info_page)
272 if vimeo_url is not None:
273 return self.url_result(vimeo_url)
275 pladform_url = PladformIE._extract_url(info_page)
277 return self.url_result(pladform_url)
279 m_rutube = re.search(
280 r'\ssrc="((?:https?:)?//rutube\.ru\\?/(?:video|play)\\?/embed(?:.*?))\\?"', info_page)
281 if m_rutube is not None:
282 rutube_url = self._proto_relative_url(
283 m_rutube.group(1).replace('\\', ''))
284 return self.url_result(rutube_url)
286 m_opts = re.search(r'(?s)var\s+opts\s*=\s*({.+?});', info_page)
288 m_opts_url = re.search(r"url\s*:\s*'((?!/\b)[^']+)", m_opts.group(1))
290 opts_url = m_opts_url.group(1)
291 if opts_url.startswith('//'):
292 opts_url = 'http:' + opts_url
293 return self.url_result(opts_url)
295 data_json = self._search_regex(r'var\s+vars\s*=\s*({.+?});', info_page, 'vars')
296 data = json.loads(data_json)
298 # Extract upload date
300 mobj = re.search(r'id="mv_date(?:_views)?_wrap"[^>]*>([a-zA-Z]+ [0-9]+), ([0-9]+) at', info_page)
302 mobj.group(1) + ' ' + mobj.group(2)
303 upload_date = unified_strdate(mobj.group(1) + ' ' + mobj.group(2))
306 views = self._html_search_regex(
307 r'"mv_views_count_number"[^>]*>(.+?\bviews?)<',
308 info_page, 'view count', fatal=False)
310 view_count = str_to_int(self._search_regex(
311 r'([\d,.]+)', views, 'view count', fatal=False))
314 for k, v in data.items():
315 if not k.startswith('url') and k != 'extra_data' or not v:
317 height = int_or_none(self._search_regex(
318 r'^url(\d+)', k, 'height', default=None))
324 self._sort_formats(formats)
327 'id': compat_str(data['vid']),
329 'title': unescapeHTML(data['md_title']),
330 'thumbnail': data.get('jpg'),
331 'uploader': data.get('md_author'),
332 'duration': data.get('duration'),
333 'upload_date': upload_date,
334 'view_count': view_count,
338 class VKUserVideosIE(InfoExtractor):
339 IE_NAME = 'vk:uservideos'
340 IE_DESC = "VK - User's Videos"
341 _VALID_URL = r'https?://vk\.com/videos(?P<id>-?[0-9]+)(?!\?.*\bz=video)(?:[/?#&]|$)'
342 _TEMPLATE_URL = 'https://vk.com/videos'
344 'url': 'http://vk.com/videos205387401',
347 'title': "Tom Cruise's Videos",
349 'playlist_mincount': 4,
351 'url': 'http://vk.com/videos-77521',
352 'only_matching': True,
354 'url': 'http://vk.com/videos-97664626?section=all',
355 'only_matching': True,
358 def _real_extract(self, url):
359 page_id = self._match_id(url)
361 webpage = self._download_webpage(url, page_id)
365 'http://vk.com/video' + video_id, 'VK', video_id=video_id)
366 for video_id in orderedSet(re.findall(r'href="/video(-?[0-9_]+)"', webpage))]
368 title = unescapeHTML(self._search_regex(
369 r'<title>\s*([^<]+?)\s+\|\s+\d+\s+videos',
370 webpage, 'title', default=page_id))
372 return self.playlist_result(entries, page_id, title)