2 from __future__ import unicode_literals
7 from .common import InfoExtractor
10 compat_urllib_request,
17 class VKIE(InfoExtractor):
19 _VALID_URL = r'https?://(?:m\.)?vk\.com/(?:video_ext\.php\?.*?\boid=(?P<oid>-?\d+).*?\bid=(?P<id>\d+)|(?:.+?\?.*?z=)?video(?P<videoid>[^s].*?)(?:\?|%2F|$))'
24 'url': 'http://vk.com/videos-77521?z=video-77521_162222515%2Fclub77521',
25 'md5': '0deae91935c54e00003c2a00646315f0',
29 'title': 'ProtivoGunz - Хуёвая песня',
30 'uploader': 're:Noize MC.*',
32 'upload_date': '20120212',
36 'url': 'http://vk.com/video4643923_163339118',
37 'md5': 'f79bccb5cd182b1f43502ca5685b2b36',
41 'uploader': 'Elya Iskhakova',
42 'title': 'Dream Theater - Hollow Years Live at Budokan 720*',
47 'note': 'Embedded video',
48 'url': 'http://vk.com/video_ext.php?oid=32194266&id=162925554&hash=7d8c2e0d5e05aeaa&hd=1',
49 'md5': 'c7ce8f1f87bec05b3de07fdeafe21a0a',
53 'uploader': 'Vladimir Gavrin',
56 'upload_date': '20120730',
60 'url': 'http://vk.com/video-8871596_164049491',
61 'md5': 'a590bcaf3d543576c9bd162812387666',
62 'note': 'Only available for registered users',
66 'uploader': 'Триллеры',
67 'title': '► Бойцовский клуб / Fight Club 1999 [HD 720]',
70 'skip': 'Requires vk account credentials',
73 'url': 'http://vk.com/feed?z=video-43215063_166094326%2Fbb50cacd3177146d7a',
74 'md5': 'd82c22e449f036282d1d3f7f4d276869',
78 'uploader': 'Киномания - лучшее из мира кино',
79 'title': 'Запах женщины (1992)',
82 'skip': 'Requires vk account credentials',
85 'url': 'http://vk.com/hd_kino_mania?z=video-43215063_168067957%2F15c66b9b533119788d',
86 'md5': '4d7a5ef8cf114dfa09577e57b2993202',
90 'uploader': 'Киномания - лучшее из мира кино',
93 'upload_date': '20140328',
95 'skip': 'Requires vk account credentials',
98 'url': 'http://m.vk.com/video-43215063_169084319?list=125c627d1aa1cebb83&from=wall-43215063_2566540',
99 'md5': '0c45586baa71b7cb1d0784ee3f4e00a6',
100 'note': 'ivi.ru embed',
104 'title': 'Книга Илая',
106 'upload_date': '20140626',
108 'skip': 'Only works from Russia',
113 (username, password) = self._get_login_info()
125 request = compat_urllib_request.Request('https://login.vk.com/?act=login',
126 compat_urllib_parse.urlencode(login_form).encode('utf-8'))
127 login_page = self._download_webpage(request, None, note='Logging in as %s' % username)
129 if re.search(r'onLoginFailed', login_page):
130 raise ExtractorError('Unable to login, incorrect username and/or password', expected=True)
132 def _real_initialize(self):
135 def _real_extract(self, url):
136 mobj = re.match(self._VALID_URL, url)
137 video_id = mobj.group('videoid')
140 video_id = '%s_%s' % (mobj.group('oid'), mobj.group('id'))
142 info_url = 'http://vk.com/al_video.php?act=show&al=1&video=%s' % video_id
143 info_page = self._download_webpage(info_url, video_id)
146 r'>Видеозапись .*? была изъята из публичного доступа в связи с обращением правообладателя.<':
147 'Video %s has been removed from public access due to rightholder complaint.',
148 r'<!>Please log in or <':
149 'Video %s is only available for registered users, '
150 'use --username and --password options to provide account credentials.',
152 'Video %s does not exist.'
155 for error_re, error_msg in ERRORS.items():
156 if re.search(error_re, info_page):
157 raise ExtractorError(error_msg % video_id, expected=True)
159 m_yt = re.search(r'src="(http://www.youtube.com/.*?)"', info_page)
161 self.to_screen('Youtube video detected')
162 return self.url_result(m_yt.group(1), 'Youtube')
164 m_opts = re.search(r'(?s)var\s+opts\s*=\s*({.*?});', info_page)
166 m_opts_url = re.search(r"url\s*:\s*'([^']+)", m_opts.group(1))
168 opts_url = m_opts_url.group(1)
169 if opts_url.startswith('//'):
170 opts_url = 'http:' + opts_url
171 return self.url_result(opts_url)
173 data_json = self._search_regex(r'var vars = ({.*?});', info_page, 'vars')
174 data = json.loads(data_json)
176 # Extract upload date
178 mobj = re.search(r'id="mv_date_wrap".*?Added ([a-zA-Z]+ [0-9]+), ([0-9]+) at', info_page)
180 upload_date = unified_strdate(mobj.group(1) + ' ' + mobj.group(2))
185 'width': int(k[len('url'):]),
186 } for k, v in data.items()
187 if k.startswith('url')]
188 self._sort_formats(formats)
191 'id': compat_str(data['vid']),
193 'title': unescapeHTML(data['md_title']),
194 'thumbnail': data.get('jpg'),
195 'uploader': data.get('md_author'),
196 'duration': data.get('duration'),
197 'upload_date': upload_date,
201 class VKUserVideosIE(InfoExtractor):
202 IE_NAME = 'vk.com:user-videos'
203 IE_DESC = 'All of a user\'s videos'
204 _VALID_URL = r'https?://(?:m\.)?vk\.com/videos([0-9]+)(?:m\?.*)?'
205 _TEMPLATE_URL = 'https://vk.com/videos'
207 'url': 'http://vk.com/videos205387401',
208 'playlist_mincount': 4,
211 def extract_videos_from_page(self, page):
213 for mobj in re.finditer(r'href="/video([0-9_]+)"', page):
214 if mobj.group(1) not in ids_in_page:
215 ids_in_page.append(mobj.group(1))
218 def _real_extract(self, url):
220 mobj = re.match(self._VALID_URL, url)
222 raise ExtractorError('Invalid URL: %s' % url)
224 # Download page and get video ids
225 page_id = mobj.group(1)
226 page = self._download_webpage(url, page_id)
227 video_ids = self.extract_videos_from_page(page)
229 self._downloader.to_screen('[vk] User videos %s: Found %i videos' % (page_id, len(video_ids)))
231 url_entries = [self.url_result('http://vk.com/video' + video_id, 'VK', video_id=video_id)
232 for video_id in video_ids]
233 return self.playlist_result(url_entries, page_id)