You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

651 lines
24 KiB

10 years ago
10 years ago
10 years ago
  1. # coding: utf-8
  2. from __future__ import unicode_literals
  3. import collections
  4. import re
  5. import sys
  6. from .common import InfoExtractor
  7. from ..compat import compat_urlparse
  8. from ..utils import (
  9. clean_html,
  10. ExtractorError,
  11. get_element_by_class,
  12. int_or_none,
  13. orderedSet,
  14. remove_start,
  15. str_or_none,
  16. str_to_int,
  17. unescapeHTML,
  18. unified_timestamp,
  19. url_or_none,
  20. urlencode_postdata,
  21. )
  22. from .dailymotion import DailymotionIE
  23. from .pladform import PladformIE
  24. from .vimeo import VimeoIE
  25. from .youtube import YoutubeIE
  26. class VKBaseIE(InfoExtractor):
  27. _NETRC_MACHINE = 'vk'
  28. def _login(self):
  29. username, password = self._get_login_info()
  30. if username is None:
  31. return
  32. login_page, url_handle = self._download_webpage_handle(
  33. 'https://vk.com', None, 'Downloading login page')
  34. login_form = self._hidden_inputs(login_page)
  35. login_form.update({
  36. 'email': username.encode('cp1251'),
  37. 'pass': password.encode('cp1251'),
  38. })
  39. # https://new.vk.com/ serves two same remixlhk cookies in Set-Cookie header
  40. # and expects the first one to be set rather than second (see
  41. # https://github.com/ytdl-org/youtube-dl/issues/9841#issuecomment-227871201).
  42. # As of RFC6265 the newer one cookie should be set into cookie store
  43. # what actually happens.
  44. # We will workaround this VK issue by resetting the remixlhk cookie to
  45. # the first one manually.
  46. for header, cookies in url_handle.headers.items():
  47. if header.lower() != 'set-cookie':
  48. continue
  49. if sys.version_info[0] >= 3:
  50. cookies = cookies.encode('iso-8859-1')
  51. cookies = cookies.decode('utf-8')
  52. remixlhk = re.search(r'remixlhk=(.+?);.*?\bdomain=(.+?)(?:[,;]|$)', cookies)
  53. if remixlhk:
  54. value, domain = remixlhk.groups()
  55. self._set_cookie(domain, 'remixlhk', value)
  56. break
  57. login_page = self._download_webpage(
  58. 'https://login.vk.com/?act=login', None,
  59. note='Logging in',
  60. data=urlencode_postdata(login_form))
  61. if re.search(r'onLoginFailed', login_page):
  62. raise ExtractorError(
  63. 'Unable to login, incorrect username and/or password', expected=True)
  64. def _real_initialize(self):
  65. self._login()
  66. class VKIE(VKBaseIE):
  67. IE_NAME = 'vk'
  68. IE_DESC = 'VK'
  69. _VALID_URL = r'''(?x)
  70. https?://
  71. (?:
  72. (?:
  73. (?:(?:m|new)\.)?vk\.com/video_|
  74. (?:www\.)?daxab.com/
  75. )
  76. ext\.php\?(?P<embed_query>.*?\boid=(?P<oid>-?\d+).*?\bid=(?P<id>\d+).*)|
  77. (?:
  78. (?:(?:m|new)\.)?vk\.com/(?:.+?\?.*?z=)?video|
  79. (?:www\.)?daxab.com/embed/
  80. )
  81. (?P<videoid>-?\d+_\d+)(?:.*\blist=(?P<list_id>[\da-f]+))?
  82. )
  83. '''
  84. _TESTS = [
  85. {
  86. 'url': 'http://vk.com/videos-77521?z=video-77521_162222515%2Fclub77521',
  87. 'md5': '7babad3b85ea2e91948005b1b8b0cb84',
  88. 'info_dict': {
  89. 'id': '-77521_162222515',
  90. 'ext': 'mp4',
  91. 'title': 'ProtivoGunz - Хуёвая песня',
  92. 'uploader': 're:(?:Noize MC|Alexander Ilyashenko).*',
  93. 'uploader_id': '-77521',
  94. 'duration': 195,
  95. 'timestamp': 1329049880,
  96. 'upload_date': '20120212',
  97. },
  98. },
  99. {
  100. 'url': 'http://vk.com/video205387401_165548505',
  101. 'md5': '6c0aeb2e90396ba97035b9cbde548700',
  102. 'info_dict': {
  103. 'id': '205387401_165548505',
  104. 'ext': 'mp4',
  105. 'title': 'No name',
  106. 'uploader': 'Tom Cruise',
  107. 'uploader_id': '205387401',
  108. 'duration': 9,
  109. 'timestamp': 1374364108,
  110. 'upload_date': '20130720',
  111. }
  112. },
  113. {
  114. 'note': 'Embedded video',
  115. 'url': 'http://vk.com/video_ext.php?oid=32194266&id=162925554&hash=7d8c2e0d5e05aeaa&hd=1',
  116. 'md5': 'c7ce8f1f87bec05b3de07fdeafe21a0a',
  117. 'info_dict': {
  118. 'id': '32194266_162925554',
  119. 'ext': 'mp4',
  120. 'uploader': 'Vladimir Gavrin',
  121. 'title': 'Lin Dan',
  122. 'duration': 101,
  123. 'upload_date': '20120730',
  124. 'view_count': int,
  125. },
  126. 'skip': 'This video has been removed from public access.',
  127. },
  128. {
  129. # VIDEO NOW REMOVED
  130. # please update if you find a video whose URL follows the same pattern
  131. 'url': 'http://vk.com/video-8871596_164049491',
  132. 'md5': 'a590bcaf3d543576c9bd162812387666',
  133. 'note': 'Only available for registered users',
  134. 'info_dict': {
  135. 'id': '-8871596_164049491',
  136. 'ext': 'mp4',
  137. 'uploader': 'Триллеры',
  138. 'title': '► Бойцовский клуб / Fight Club 1999 [HD 720]',
  139. 'duration': 8352,
  140. 'upload_date': '20121218',
  141. 'view_count': int,
  142. },
  143. 'skip': 'Requires vk account credentials',
  144. },
  145. {
  146. 'url': 'http://vk.com/hd_kino_mania?z=video-43215063_168067957%2F15c66b9b533119788d',
  147. 'md5': '4d7a5ef8cf114dfa09577e57b2993202',
  148. 'info_dict': {
  149. 'id': '-43215063_168067957',
  150. 'ext': 'mp4',
  151. 'uploader': 'Киномания - лучшее из мира кино',
  152. 'title': ' ',
  153. 'duration': 7291,
  154. 'upload_date': '20140328',
  155. },
  156. 'skip': 'Requires vk account credentials',
  157. },
  158. {
  159. 'url': 'http://m.vk.com/video-43215063_169084319?list=125c627d1aa1cebb83&from=wall-43215063_2566540',
  160. 'md5': '0c45586baa71b7cb1d0784ee3f4e00a6',
  161. 'note': 'ivi.ru embed',
  162. 'info_dict': {
  163. 'id': '-43215063_169084319',
  164. 'ext': 'mp4',
  165. 'title': 'Книга Илая',
  166. 'duration': 6771,
  167. 'upload_date': '20140626',
  168. 'view_count': int,
  169. },
  170. 'skip': 'Only works from Russia',
  171. },
  172. {
  173. # video (removed?) only available with list id
  174. 'url': 'https://vk.com/video30481095_171201961?list=8764ae2d21f14088d4',
  175. 'md5': '091287af5402239a1051c37ec7b92913',
  176. 'info_dict': {
  177. 'id': '30481095_171201961',
  178. 'ext': 'mp4',
  179. 'title': 'ТюменцевВВ_09.07.2015',
  180. 'uploader': 'Anton Ivanov',
  181. 'duration': 109,
  182. 'upload_date': '20150709',
  183. 'view_count': int,
  184. },
  185. 'skip': 'Removed',
  186. },
  187. {
  188. # youtube embed
  189. 'url': 'https://vk.com/video276849682_170681728',
  190. 'info_dict': {
  191. 'id': 'V3K4mi0SYkc',
  192. 'ext': 'mp4',
  193. 'title': "DSWD Awards 'Children's Joy Foundation, Inc.' Certificate of Registration and License to Operate",
  194. 'description': 'md5:bf9c26cfa4acdfb146362682edd3827a',
  195. 'duration': 178,
  196. 'upload_date': '20130116',
  197. 'uploader': "Children's Joy Foundation Inc.",
  198. 'uploader_id': 'thecjf',
  199. 'view_count': int,
  200. },
  201. },
  202. {
  203. # dailymotion embed
  204. 'url': 'https://vk.com/video-37468416_456239855',
  205. 'info_dict': {
  206. 'id': 'k3lz2cmXyRuJQSjGHUv',
  207. 'ext': 'mp4',
  208. 'title': 'md5:d52606645c20b0ddbb21655adaa4f56f',
  209. # TODO: fix test by fixing dailymotion description extraction
  210. 'description': 'md5:c651358f03c56f1150b555c26d90a0fd',
  211. 'uploader': 'AniLibria.Tv',
  212. 'upload_date': '20160914',
  213. 'uploader_id': 'x1p5vl5',
  214. 'timestamp': 1473877246,
  215. },
  216. 'params': {
  217. 'skip_download': True,
  218. },
  219. },
  220. {
  221. # video key is extra_data not url\d+
  222. 'url': 'http://vk.com/video-110305615_171782105',
  223. 'md5': 'e13fcda136f99764872e739d13fac1d1',
  224. 'info_dict': {
  225. 'id': '-110305615_171782105',
  226. 'ext': 'mp4',
  227. 'title': 'S-Dance, репетиции к The way show',
  228. 'uploader': 'THE WAY SHOW | 17 апреля',
  229. 'uploader_id': '-110305615',
  230. 'timestamp': 1454859345,
  231. 'upload_date': '20160207',
  232. },
  233. 'params': {
  234. 'skip_download': True,
  235. },
  236. },
  237. {
  238. # finished live stream, postlive_mp4
  239. 'url': 'https://vk.com/videos-387766?z=video-387766_456242764%2Fpl_-387766_-2',
  240. 'info_dict': {
  241. 'id': '-387766_456242764',
  242. 'ext': 'mp4',
  243. 'title': 'ИгроМир 2016 День 1 — Игромания Утром',
  244. 'uploader': 'Игромания',
  245. 'duration': 5239,
  246. # TODO: use act=show to extract view_count
  247. # 'view_count': int,
  248. 'upload_date': '20160929',
  249. 'uploader_id': '-387766',
  250. 'timestamp': 1475137527,
  251. },
  252. },
  253. {
  254. # live stream, hls and rtmp links, most likely already finished live
  255. # stream by the time you are reading this comment
  256. 'url': 'https://vk.com/video-140332_456239111',
  257. 'only_matching': True,
  258. },
  259. {
  260. # removed video, just testing that we match the pattern
  261. 'url': 'http://vk.com/feed?z=video-43215063_166094326%2Fbb50cacd3177146d7a',
  262. 'only_matching': True,
  263. },
  264. {
  265. # age restricted video, requires vk account credentials
  266. 'url': 'https://vk.com/video205387401_164765225',
  267. 'only_matching': True,
  268. },
  269. {
  270. # pladform embed
  271. 'url': 'https://vk.com/video-76116461_171554880',
  272. 'only_matching': True,
  273. },
  274. {
  275. 'url': 'http://new.vk.com/video205387401_165548505',
  276. 'only_matching': True,
  277. },
  278. {
  279. # This video is no longer available, because its author has been blocked.
  280. 'url': 'https://vk.com/video-10639516_456240611',
  281. 'only_matching': True,
  282. },
  283. {
  284. # The video is not available in your region.
  285. 'url': 'https://vk.com/video-51812607_171445436',
  286. 'only_matching': True,
  287. }]
  288. def _real_extract(self, url):
  289. mobj = re.match(self._VALID_URL, url)
  290. video_id = mobj.group('videoid')
  291. if video_id:
  292. info_url = 'https://vk.com/al_video.php?act=show_inline&al=1&video=' + video_id
  293. # Some videos (removed?) can only be downloaded with list id specified
  294. list_id = mobj.group('list_id')
  295. if list_id:
  296. info_url += '&list=%s' % list_id
  297. else:
  298. info_url = 'http://vk.com/video_ext.php?' + mobj.group('embed_query')
  299. video_id = '%s_%s' % (mobj.group('oid'), mobj.group('id'))
  300. info_page = self._download_webpage(info_url, video_id)
  301. error_message = self._html_search_regex(
  302. [r'(?s)<!><div[^>]+class="video_layer_message"[^>]*>(.+?)</div>',
  303. r'(?s)<div[^>]+id="video_ext_msg"[^>]*>(.+?)</div>'],
  304. info_page, 'error message', default=None)
  305. if error_message:
  306. raise ExtractorError(error_message, expected=True)
  307. if re.search(r'<!>/login\.php\?.*\bact=security_check', info_page):
  308. raise ExtractorError(
  309. 'You are trying to log in from an unusual location. You should confirm ownership at vk.com to log in with this IP.',
  310. expected=True)
  311. ERROR_COPYRIGHT = 'Video %s has been removed from public access due to rightholder complaint.'
  312. ERRORS = {
  313. r'>Видеозапись .*? была изъята из публичного доступа в связи с обращением правообладателя.<':
  314. ERROR_COPYRIGHT,
  315. r'>The video .*? was removed from public access by request of the copyright holder.<':
  316. ERROR_COPYRIGHT,
  317. r'<!>Please log in or <':
  318. 'Video %s is only available for registered users, '
  319. 'use --username and --password options to provide account credentials.',
  320. r'<!>Unknown error':
  321. 'Video %s does not exist.',
  322. r'<!>Видео временно недоступно':
  323. 'Video %s is temporarily unavailable.',
  324. r'<!>Access denied':
  325. 'Access denied to video %s.',
  326. r'<!>Видеозапись недоступна, так как её автор был заблокирован.':
  327. 'Video %s is no longer available, because its author has been blocked.',
  328. r'<!>This video is no longer available, because its author has been blocked.':
  329. 'Video %s is no longer available, because its author has been blocked.',
  330. r'<!>This video is no longer available, because it has been deleted.':
  331. 'Video %s is no longer available, because it has been deleted.',
  332. r'<!>The video .+? is not available in your region.':
  333. 'Video %s is not available in your region.',
  334. }
  335. for error_re, error_msg in ERRORS.items():
  336. if re.search(error_re, info_page):
  337. raise ExtractorError(error_msg % video_id, expected=True)
  338. youtube_url = YoutubeIE._extract_url(info_page)
  339. if youtube_url:
  340. return self.url_result(youtube_url, ie=YoutubeIE.ie_key())
  341. vimeo_url = VimeoIE._extract_url(url, info_page)
  342. if vimeo_url is not None:
  343. return self.url_result(vimeo_url)
  344. pladform_url = PladformIE._extract_url(info_page)
  345. if pladform_url:
  346. 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)
  353. dailymotion_urls = DailymotionIE._extract_urls(info_page)
  354. if dailymotion_urls:
  355. return self.url_result(dailymotion_urls[0], DailymotionIE.ie_key())
  356. m_opts = re.search(r'(?s)var\s+opts\s*=\s*({.+?});', info_page)
  357. if m_opts:
  358. m_opts_url = re.search(r"url\s*:\s*'((?!/\b)[^']+)", m_opts.group(1))
  359. if m_opts_url:
  360. opts_url = m_opts_url.group(1)
  361. if opts_url.startswith('//'):
  362. opts_url = 'http:' + opts_url
  363. return self.url_result(opts_url)
  364. # vars does not look to be served anymore since 24.10.2016
  365. data = self._parse_json(
  366. self._search_regex(
  367. r'var\s+vars\s*=\s*({.+?});', info_page, 'vars', default='{}'),
  368. video_id, fatal=False)
  369. # <!json> is served instead
  370. if not data:
  371. data = self._parse_json(
  372. self._search_regex(
  373. [r'<!json>\s*({.+?})\s*<!>', r'<!json>\s*({.+})'],
  374. info_page, 'json', default='{}'),
  375. video_id)
  376. if data:
  377. data = data['player']['params'][0]
  378. if not data:
  379. data = self._parse_json(
  380. self._search_regex(
  381. r'var\s+playerParams\s*=\s*({.+?})\s*;\s*\n', info_page,
  382. 'player params'),
  383. video_id)['params'][0]
  384. title = unescapeHTML(data['md_title'])
  385. # 2 = live
  386. # 3 = post live (finished live)
  387. is_live = data.get('live') == 2
  388. if is_live:
  389. title = self._live_title(title)
  390. timestamp = unified_timestamp(self._html_search_regex(
  391. r'class=["\']mv_info_date[^>]+>([^<]+)(?:<|from)', info_page,
  392. 'upload date', default=None)) or int_or_none(data.get('date'))
  393. view_count = str_to_int(self._search_regex(
  394. r'class=["\']mv_views_count[^>]+>\s*([\d,.]+)',
  395. info_page, 'view count', default=None))
  396. formats = []
  397. for format_id, format_url in data.items():
  398. format_url = url_or_none(format_url)
  399. if not format_url or not format_url.startswith(('http', '//', 'rtmp')):
  400. continue
  401. if (format_id.startswith(('url', 'cache')) or
  402. format_id in ('extra_data', 'live_mp4', 'postlive_mp4')):
  403. height = int_or_none(self._search_regex(
  404. r'^(?:url|cache)(\d+)', format_id, 'height', default=None))
  405. formats.append({
  406. 'format_id': format_id,
  407. 'url': format_url,
  408. 'height': height,
  409. })
  410. elif format_id == 'hls':
  411. formats.extend(self._extract_m3u8_formats(
  412. format_url, video_id, 'mp4', 'm3u8_native',
  413. m3u8_id=format_id, fatal=False, live=is_live))
  414. elif format_id == 'rtmp':
  415. formats.append({
  416. 'format_id': format_id,
  417. 'url': format_url,
  418. 'ext': 'flv',
  419. })
  420. self._sort_formats(formats)
  421. return {
  422. 'id': video_id,
  423. 'formats': formats,
  424. 'title': title,
  425. 'thumbnail': data.get('jpg'),
  426. 'uploader': data.get('md_author'),
  427. 'uploader_id': str_or_none(data.get('author_id')),
  428. 'duration': data.get('duration'),
  429. 'timestamp': timestamp,
  430. 'view_count': view_count,
  431. 'like_count': int_or_none(data.get('liked')),
  432. 'dislike_count': int_or_none(data.get('nolikes')),
  433. 'is_live': is_live,
  434. }
  435. class VKUserVideosIE(VKBaseIE):
  436. IE_NAME = 'vk:uservideos'
  437. IE_DESC = "VK - User's Videos"
  438. _VALID_URL = r'https?://(?:(?:m|new)\.)?vk\.com/videos(?P<id>-?[0-9]+)(?!\?.*\bz=video)(?:[/?#&]|$)'
  439. _TEMPLATE_URL = 'https://vk.com/videos'
  440. _TESTS = [{
  441. 'url': 'http://vk.com/videos205387401',
  442. 'info_dict': {
  443. 'id': '205387401',
  444. 'title': "Tom Cruise's Videos",
  445. },
  446. 'playlist_mincount': 4,
  447. }, {
  448. 'url': 'http://vk.com/videos-77521',
  449. 'only_matching': True,
  450. }, {
  451. 'url': 'http://vk.com/videos-97664626?section=all',
  452. 'only_matching': True,
  453. }, {
  454. 'url': 'http://m.vk.com/videos205387401',
  455. 'only_matching': True,
  456. }, {
  457. 'url': 'http://new.vk.com/videos205387401',
  458. 'only_matching': True,
  459. }]
  460. def _real_extract(self, url):
  461. page_id = self._match_id(url)
  462. webpage = self._download_webpage(url, page_id)
  463. entries = [
  464. self.url_result(
  465. 'http://vk.com/video' + video_id, 'VK', video_id=video_id)
  466. for video_id in orderedSet(re.findall(r'href="/video(-?[0-9_]+)"', webpage))]
  467. title = unescapeHTML(self._search_regex(
  468. r'<title>\s*([^<]+?)\s+\|\s+\d+\s+videos',
  469. webpage, 'title', default=page_id))
  470. return self.playlist_result(entries, page_id, title)
  471. class VKWallPostIE(VKBaseIE):
  472. IE_NAME = 'vk:wallpost'
  473. _VALID_URL = r'https?://(?:(?:(?:(?:m|new)\.)?vk\.com/(?:[^?]+\?.*\bw=)?wall(?P<id>-?\d+_\d+)))'
  474. _TESTS = [{
  475. # public page URL, audio playlist
  476. 'url': 'https://vk.com/bs.official?w=wall-23538238_35',
  477. 'info_dict': {
  478. 'id': '23538238_35',
  479. 'title': 'Black Shadow - Wall post 23538238_35',
  480. 'description': 'md5:3f84b9c4f9ef499731cf1ced9998cc0c',
  481. },
  482. 'playlist': [{
  483. 'md5': '5ba93864ec5b85f7ce19a9af4af080f6',
  484. 'info_dict': {
  485. 'id': '135220665_111806521',
  486. 'ext': 'mp3',
  487. 'title': 'Black Shadow - Слепое Верование',
  488. 'duration': 370,
  489. 'uploader': 'Black Shadow',
  490. 'artist': 'Black Shadow',
  491. 'track': 'Слепое Верование',
  492. },
  493. }, {
  494. 'md5': '4cc7e804579122b17ea95af7834c9233',
  495. 'info_dict': {
  496. 'id': '135220665_111802303',
  497. 'ext': 'mp3',
  498. 'title': 'Black Shadow - Война - Негасимое Бездны Пламя!',
  499. 'duration': 423,
  500. 'uploader': 'Black Shadow',
  501. 'artist': 'Black Shadow',
  502. 'track': 'Война - Негасимое Бездны Пламя!',
  503. },
  504. 'params': {
  505. 'skip_download': True,
  506. },
  507. }],
  508. 'params': {
  509. 'usenetrc': True,
  510. },
  511. 'skip': 'Requires vk account credentials',
  512. }, {
  513. # single YouTube embed, no leading -
  514. 'url': 'https://vk.com/wall85155021_6319',
  515. 'info_dict': {
  516. 'id': '85155021_6319',
  517. 'title': 'Sergey Gorbunov - Wall post 85155021_6319',
  518. },
  519. 'playlist_count': 1,
  520. 'params': {
  521. 'usenetrc': True,
  522. },
  523. 'skip': 'Requires vk account credentials',
  524. }, {
  525. # wall page URL
  526. 'url': 'https://vk.com/wall-23538238_35',
  527. 'only_matching': True,
  528. }, {
  529. # mobile wall page URL
  530. 'url': 'https://m.vk.com/wall-23538238_35',
  531. 'only_matching': True,
  532. }]
  533. def _real_extract(self, url):
  534. post_id = self._match_id(url)
  535. wall_url = 'https://vk.com/wall%s' % post_id
  536. post_id = remove_start(post_id, '-')
  537. webpage = self._download_webpage(wall_url, post_id)
  538. error = self._html_search_regex(
  539. r'>Error</div>\s*<div[^>]+class=["\']body["\'][^>]*>([^<]+)',
  540. webpage, 'error', default=None)
  541. if error:
  542. raise ExtractorError('VK said: %s' % error, expected=True)
  543. description = clean_html(get_element_by_class('wall_post_text', webpage))
  544. uploader = clean_html(get_element_by_class('author', webpage))
  545. thumbnail = self._og_search_thumbnail(webpage)
  546. entries = []
  547. audio_ids = re.findall(r'data-full-id=["\'](\d+_\d+)', webpage)
  548. if audio_ids:
  549. al_audio = self._download_webpage(
  550. 'https://vk.com/al_audio.php', post_id,
  551. note='Downloading audio info', fatal=False,
  552. data=urlencode_postdata({
  553. 'act': 'reload_audio',
  554. 'al': '1',
  555. 'ids': ','.join(audio_ids)
  556. }))
  557. if al_audio:
  558. Audio = collections.namedtuple(
  559. 'Audio', ['id', 'user_id', 'url', 'track', 'artist', 'duration'])
  560. audios = self._parse_json(
  561. self._search_regex(
  562. r'<!json>(.+?)<!>', al_audio, 'audios', default='[]'),
  563. post_id, fatal=False, transform_source=unescapeHTML)
  564. if isinstance(audios, list):
  565. for audio in audios:
  566. a = Audio._make(audio[:6])
  567. entries.append({
  568. 'id': '%s_%s' % (a.user_id, a.id),
  569. 'url': a.url,
  570. 'title': '%s - %s' % (a.artist, a.track) if a.artist and a.track else a.id,
  571. 'thumbnail': thumbnail,
  572. 'duration': a.duration,
  573. 'uploader': uploader,
  574. 'artist': a.artist,
  575. 'track': a.track,
  576. })
  577. for video in re.finditer(
  578. r'<a[^>]+href=(["\'])(?P<url>/video(?:-?[\d_]+).*?)\1', webpage):
  579. entries.append(self.url_result(
  580. compat_urlparse.urljoin(url, video.group('url')), VKIE.ie_key()))
  581. title = 'Wall post %s' % post_id
  582. return self.playlist_result(
  583. orderedSet(entries), post_id,
  584. '%s - %s' % (uploader, title) if uploader else title,
  585. description)