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.

272 lines
11 KiB

Switch codebase to use sanitized_Request instead of compat_urllib_request.Request [downloader/dash] Use sanitized_Request [downloader/http] Use sanitized_Request [atresplayer] Use sanitized_Request [bambuser] Use sanitized_Request [bliptv] Use sanitized_Request [brightcove] Use sanitized_Request [cbs] Use sanitized_Request [ceskatelevize] Use sanitized_Request [collegerama] Use sanitized_Request [extractor/common] Use sanitized_Request [crunchyroll] Use sanitized_Request [dailymotion] Use sanitized_Request [dcn] Use sanitized_Request [dramafever] Use sanitized_Request [dumpert] Use sanitized_Request [eitb] Use sanitized_Request [escapist] Use sanitized_Request [everyonesmixtape] Use sanitized_Request [extremetube] Use sanitized_Request [facebook] Use sanitized_Request [fc2] Use sanitized_Request [flickr] Use sanitized_Request [4tube] Use sanitized_Request [gdcvault] Use sanitized_Request [extractor/generic] Use sanitized_Request [hearthisat] Use sanitized_Request [hotnewhiphop] Use sanitized_Request [hypem] Use sanitized_Request [iprima] Use sanitized_Request [ivi] Use sanitized_Request [keezmovies] Use sanitized_Request [letv] Use sanitized_Request [lynda] Use sanitized_Request [metacafe] Use sanitized_Request [minhateca] Use sanitized_Request [miomio] Use sanitized_Request [meovideo] Use sanitized_Request [mofosex] Use sanitized_Request [moniker] Use sanitized_Request [mooshare] Use sanitized_Request [movieclips] Use sanitized_Request [mtv] Use sanitized_Request [myvideo] Use sanitized_Request [neteasemusic] Use sanitized_Request [nfb] Use sanitized_Request [niconico] Use sanitized_Request [noco] Use sanitized_Request [nosvideo] Use sanitized_Request [novamov] Use sanitized_Request [nowness] Use sanitized_Request [nuvid] Use sanitized_Request [played] Use sanitized_Request [pluralsight] Use sanitized_Request [pornhub] Use sanitized_Request [pornotube] Use sanitized_Request [primesharetv] Use sanitized_Request [promptfile] Use sanitized_Request [qqmusic] Use sanitized_Request [rtve] Use sanitized_Request [safari] Use sanitized_Request [sandia] Use sanitized_Request [shared] Use sanitized_Request [sharesix] Use sanitized_Request [sina] Use sanitized_Request [smotri] Use sanitized_Request [sohu] Use sanitized_Request [spankwire] Use sanitized_Request [sportdeutschland] Use sanitized_Request [streamcloud] Use sanitized_Request [streamcz] Use sanitized_Request [tapely] Use sanitized_Request [tube8] Use sanitized_Request [tubitv] Use sanitized_Request [twitch] Use sanitized_Request [twitter] Use sanitized_Request [udemy] Use sanitized_Request [vbox7] Use sanitized_Request [veoh] Use sanitized_Request [vessel] Use sanitized_Request [vevo] Use sanitized_Request [viddler] Use sanitized_Request [videomega] Use sanitized_Request [viewvster] Use sanitized_Request [viki] Use sanitized_Request [vk] Use sanitized_Request [vodlocker] Use sanitized_Request [voicerepublic] Use sanitized_Request [wistia] Use sanitized_Request [xfileshare] Use sanitized_Request [xtube] Use sanitized_Request [xvideos] Use sanitized_Request [yandexmusic] Use sanitized_Request [youku] Use sanitized_Request [youporn] Use sanitized_Request [youtube] Use sanitized_Request [patreon] Use sanitized_Request [extractor/common] Remove unused import [nfb] PEP 8
9 years ago
Switch codebase to use sanitized_Request instead of compat_urllib_request.Request [downloader/dash] Use sanitized_Request [downloader/http] Use sanitized_Request [atresplayer] Use sanitized_Request [bambuser] Use sanitized_Request [bliptv] Use sanitized_Request [brightcove] Use sanitized_Request [cbs] Use sanitized_Request [ceskatelevize] Use sanitized_Request [collegerama] Use sanitized_Request [extractor/common] Use sanitized_Request [crunchyroll] Use sanitized_Request [dailymotion] Use sanitized_Request [dcn] Use sanitized_Request [dramafever] Use sanitized_Request [dumpert] Use sanitized_Request [eitb] Use sanitized_Request [escapist] Use sanitized_Request [everyonesmixtape] Use sanitized_Request [extremetube] Use sanitized_Request [facebook] Use sanitized_Request [fc2] Use sanitized_Request [flickr] Use sanitized_Request [4tube] Use sanitized_Request [gdcvault] Use sanitized_Request [extractor/generic] Use sanitized_Request [hearthisat] Use sanitized_Request [hotnewhiphop] Use sanitized_Request [hypem] Use sanitized_Request [iprima] Use sanitized_Request [ivi] Use sanitized_Request [keezmovies] Use sanitized_Request [letv] Use sanitized_Request [lynda] Use sanitized_Request [metacafe] Use sanitized_Request [minhateca] Use sanitized_Request [miomio] Use sanitized_Request [meovideo] Use sanitized_Request [mofosex] Use sanitized_Request [moniker] Use sanitized_Request [mooshare] Use sanitized_Request [movieclips] Use sanitized_Request [mtv] Use sanitized_Request [myvideo] Use sanitized_Request [neteasemusic] Use sanitized_Request [nfb] Use sanitized_Request [niconico] Use sanitized_Request [noco] Use sanitized_Request [nosvideo] Use sanitized_Request [novamov] Use sanitized_Request [nowness] Use sanitized_Request [nuvid] Use sanitized_Request [played] Use sanitized_Request [pluralsight] Use sanitized_Request [pornhub] Use sanitized_Request [pornotube] Use sanitized_Request [primesharetv] Use sanitized_Request [promptfile] Use sanitized_Request [qqmusic] Use sanitized_Request [rtve] Use sanitized_Request [safari] Use sanitized_Request [sandia] Use sanitized_Request [shared] Use sanitized_Request [sharesix] Use sanitized_Request [sina] Use sanitized_Request [smotri] Use sanitized_Request [sohu] Use sanitized_Request [spankwire] Use sanitized_Request [sportdeutschland] Use sanitized_Request [streamcloud] Use sanitized_Request [streamcz] Use sanitized_Request [tapely] Use sanitized_Request [tube8] Use sanitized_Request [tubitv] Use sanitized_Request [twitch] Use sanitized_Request [twitter] Use sanitized_Request [udemy] Use sanitized_Request [vbox7] Use sanitized_Request [veoh] Use sanitized_Request [vessel] Use sanitized_Request [vevo] Use sanitized_Request [viddler] Use sanitized_Request [videomega] Use sanitized_Request [viewvster] Use sanitized_Request [viki] Use sanitized_Request [vk] Use sanitized_Request [vodlocker] Use sanitized_Request [voicerepublic] Use sanitized_Request [wistia] Use sanitized_Request [xfileshare] Use sanitized_Request [xtube] Use sanitized_Request [xvideos] Use sanitized_Request [yandexmusic] Use sanitized_Request [youku] Use sanitized_Request [youporn] Use sanitized_Request [youtube] Use sanitized_Request [patreon] Use sanitized_Request [extractor/common] Remove unused import [nfb] PEP 8
9 years ago
Switch codebase to use sanitized_Request instead of compat_urllib_request.Request [downloader/dash] Use sanitized_Request [downloader/http] Use sanitized_Request [atresplayer] Use sanitized_Request [bambuser] Use sanitized_Request [bliptv] Use sanitized_Request [brightcove] Use sanitized_Request [cbs] Use sanitized_Request [ceskatelevize] Use sanitized_Request [collegerama] Use sanitized_Request [extractor/common] Use sanitized_Request [crunchyroll] Use sanitized_Request [dailymotion] Use sanitized_Request [dcn] Use sanitized_Request [dramafever] Use sanitized_Request [dumpert] Use sanitized_Request [eitb] Use sanitized_Request [escapist] Use sanitized_Request [everyonesmixtape] Use sanitized_Request [extremetube] Use sanitized_Request [facebook] Use sanitized_Request [fc2] Use sanitized_Request [flickr] Use sanitized_Request [4tube] Use sanitized_Request [gdcvault] Use sanitized_Request [extractor/generic] Use sanitized_Request [hearthisat] Use sanitized_Request [hotnewhiphop] Use sanitized_Request [hypem] Use sanitized_Request [iprima] Use sanitized_Request [ivi] Use sanitized_Request [keezmovies] Use sanitized_Request [letv] Use sanitized_Request [lynda] Use sanitized_Request [metacafe] Use sanitized_Request [minhateca] Use sanitized_Request [miomio] Use sanitized_Request [meovideo] Use sanitized_Request [mofosex] Use sanitized_Request [moniker] Use sanitized_Request [mooshare] Use sanitized_Request [movieclips] Use sanitized_Request [mtv] Use sanitized_Request [myvideo] Use sanitized_Request [neteasemusic] Use sanitized_Request [nfb] Use sanitized_Request [niconico] Use sanitized_Request [noco] Use sanitized_Request [nosvideo] Use sanitized_Request [novamov] Use sanitized_Request [nowness] Use sanitized_Request [nuvid] Use sanitized_Request [played] Use sanitized_Request [pluralsight] Use sanitized_Request [pornhub] Use sanitized_Request [pornotube] Use sanitized_Request [primesharetv] Use sanitized_Request [promptfile] Use sanitized_Request [qqmusic] Use sanitized_Request [rtve] Use sanitized_Request [safari] Use sanitized_Request [sandia] Use sanitized_Request [shared] Use sanitized_Request [sharesix] Use sanitized_Request [sina] Use sanitized_Request [smotri] Use sanitized_Request [sohu] Use sanitized_Request [spankwire] Use sanitized_Request [sportdeutschland] Use sanitized_Request [streamcloud] Use sanitized_Request [streamcz] Use sanitized_Request [tapely] Use sanitized_Request [tube8] Use sanitized_Request [tubitv] Use sanitized_Request [twitch] Use sanitized_Request [twitter] Use sanitized_Request [udemy] Use sanitized_Request [vbox7] Use sanitized_Request [veoh] Use sanitized_Request [vessel] Use sanitized_Request [vevo] Use sanitized_Request [viddler] Use sanitized_Request [videomega] Use sanitized_Request [viewvster] Use sanitized_Request [viki] Use sanitized_Request [vk] Use sanitized_Request [vodlocker] Use sanitized_Request [voicerepublic] Use sanitized_Request [wistia] Use sanitized_Request [xfileshare] Use sanitized_Request [xtube] Use sanitized_Request [xvideos] Use sanitized_Request [yandexmusic] Use sanitized_Request [youku] Use sanitized_Request [youporn] Use sanitized_Request [youtube] Use sanitized_Request [patreon] Use sanitized_Request [extractor/common] Remove unused import [nfb] PEP 8
9 years ago
Switch codebase to use sanitized_Request instead of compat_urllib_request.Request [downloader/dash] Use sanitized_Request [downloader/http] Use sanitized_Request [atresplayer] Use sanitized_Request [bambuser] Use sanitized_Request [bliptv] Use sanitized_Request [brightcove] Use sanitized_Request [cbs] Use sanitized_Request [ceskatelevize] Use sanitized_Request [collegerama] Use sanitized_Request [extractor/common] Use sanitized_Request [crunchyroll] Use sanitized_Request [dailymotion] Use sanitized_Request [dcn] Use sanitized_Request [dramafever] Use sanitized_Request [dumpert] Use sanitized_Request [eitb] Use sanitized_Request [escapist] Use sanitized_Request [everyonesmixtape] Use sanitized_Request [extremetube] Use sanitized_Request [facebook] Use sanitized_Request [fc2] Use sanitized_Request [flickr] Use sanitized_Request [4tube] Use sanitized_Request [gdcvault] Use sanitized_Request [extractor/generic] Use sanitized_Request [hearthisat] Use sanitized_Request [hotnewhiphop] Use sanitized_Request [hypem] Use sanitized_Request [iprima] Use sanitized_Request [ivi] Use sanitized_Request [keezmovies] Use sanitized_Request [letv] Use sanitized_Request [lynda] Use sanitized_Request [metacafe] Use sanitized_Request [minhateca] Use sanitized_Request [miomio] Use sanitized_Request [meovideo] Use sanitized_Request [mofosex] Use sanitized_Request [moniker] Use sanitized_Request [mooshare] Use sanitized_Request [movieclips] Use sanitized_Request [mtv] Use sanitized_Request [myvideo] Use sanitized_Request [neteasemusic] Use sanitized_Request [nfb] Use sanitized_Request [niconico] Use sanitized_Request [noco] Use sanitized_Request [nosvideo] Use sanitized_Request [novamov] Use sanitized_Request [nowness] Use sanitized_Request [nuvid] Use sanitized_Request [played] Use sanitized_Request [pluralsight] Use sanitized_Request [pornhub] Use sanitized_Request [pornotube] Use sanitized_Request [primesharetv] Use sanitized_Request [promptfile] Use sanitized_Request [qqmusic] Use sanitized_Request [rtve] Use sanitized_Request [safari] Use sanitized_Request [sandia] Use sanitized_Request [shared] Use sanitized_Request [sharesix] Use sanitized_Request [sina] Use sanitized_Request [smotri] Use sanitized_Request [sohu] Use sanitized_Request [spankwire] Use sanitized_Request [sportdeutschland] Use sanitized_Request [streamcloud] Use sanitized_Request [streamcz] Use sanitized_Request [tapely] Use sanitized_Request [tube8] Use sanitized_Request [tubitv] Use sanitized_Request [twitch] Use sanitized_Request [twitter] Use sanitized_Request [udemy] Use sanitized_Request [vbox7] Use sanitized_Request [veoh] Use sanitized_Request [vessel] Use sanitized_Request [vevo] Use sanitized_Request [viddler] Use sanitized_Request [videomega] Use sanitized_Request [viewvster] Use sanitized_Request [viki] Use sanitized_Request [vk] Use sanitized_Request [vodlocker] Use sanitized_Request [voicerepublic] Use sanitized_Request [wistia] Use sanitized_Request [xfileshare] Use sanitized_Request [xtube] Use sanitized_Request [xvideos] Use sanitized_Request [yandexmusic] Use sanitized_Request [youku] Use sanitized_Request [youporn] Use sanitized_Request [youtube] Use sanitized_Request [patreon] Use sanitized_Request [extractor/common] Remove unused import [nfb] PEP 8
9 years ago
  1. from __future__ import unicode_literals
  2. import json
  3. import re
  4. import socket
  5. from .common import InfoExtractor
  6. from ..compat import (
  7. compat_etree_fromstring,
  8. compat_http_client,
  9. compat_urllib_error,
  10. compat_urllib_parse_unquote,
  11. compat_urllib_parse_unquote_plus,
  12. )
  13. from ..utils import (
  14. error_to_compat_str,
  15. ExtractorError,
  16. limit_length,
  17. sanitized_Request,
  18. urlencode_postdata,
  19. get_element_by_id,
  20. clean_html,
  21. )
  22. class FacebookIE(InfoExtractor):
  23. _VALID_URL = r'''(?x)
  24. (?:
  25. https?://
  26. (?:\w+\.)?facebook\.com/
  27. (?:[^#]*?\#!/)?
  28. (?:
  29. (?:
  30. video/video\.php|
  31. photo\.php|
  32. video\.php|
  33. video/embed
  34. )\?(?:.*?)(?:v|video_id)=|
  35. [^/]+/videos/(?:[^/]+/)?
  36. )|
  37. facebook:
  38. )
  39. (?P<id>[0-9]+)
  40. '''
  41. _LOGIN_URL = 'https://www.facebook.com/login.php?next=http%3A%2F%2Ffacebook.com%2Fhome.php&login_attempt=1'
  42. _CHECKPOINT_URL = 'https://www.facebook.com/checkpoint/?next=http%3A%2F%2Ffacebook.com%2Fhome.php&_fb_noscript=1'
  43. _NETRC_MACHINE = 'facebook'
  44. IE_NAME = 'facebook'
  45. _CHROME_USER_AGENT = 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/48.0.2564.97 Safari/537.36'
  46. _TESTS = [{
  47. 'url': 'https://www.facebook.com/video.php?v=637842556329505&fref=nf',
  48. 'md5': '6a40d33c0eccbb1af76cf0485a052659',
  49. 'info_dict': {
  50. 'id': '637842556329505',
  51. 'ext': 'mp4',
  52. 'title': 're:Did you know Kei Nishikori is the first Asian man to ever reach a Grand Slam',
  53. 'uploader': 'Tennis on Facebook',
  54. }
  55. }, {
  56. 'note': 'Video without discernible title',
  57. 'url': 'https://www.facebook.com/video.php?v=274175099429670',
  58. 'info_dict': {
  59. 'id': '274175099429670',
  60. 'ext': 'mp4',
  61. 'title': 'Facebook video #274175099429670',
  62. 'uploader': 'Asif Nawab Butt',
  63. },
  64. 'expected_warnings': [
  65. 'title'
  66. ]
  67. }, {
  68. 'note': 'Video with DASH manifest',
  69. 'url': 'https://www.facebook.com/video.php?v=957955867617029',
  70. 'md5': '54706e4db4f5ad58fbad82dde1f1213f',
  71. 'info_dict': {
  72. 'id': '957955867617029',
  73. 'ext': 'mp4',
  74. 'title': 'When you post epic content on instagram.com/433 8 million followers, this is ...',
  75. 'uploader': 'Demy de Zeeuw',
  76. },
  77. }, {
  78. 'url': 'https://www.facebook.com/video.php?v=10204634152394104',
  79. 'only_matching': True,
  80. }, {
  81. 'url': 'https://www.facebook.com/amogood/videos/1618742068337349/?fref=nf',
  82. 'only_matching': True,
  83. }, {
  84. 'url': 'https://www.facebook.com/ChristyClarkForBC/videos/vb.22819070941/10153870694020942/?type=2&theater',
  85. 'only_matching': True,
  86. }, {
  87. 'url': 'facebook:544765982287235',
  88. 'only_matching': True,
  89. }]
  90. def _login(self):
  91. (useremail, password) = self._get_login_info()
  92. if useremail is None:
  93. return
  94. login_page_req = sanitized_Request(self._LOGIN_URL)
  95. self._set_cookie('facebook.com', 'locale', 'en_US')
  96. login_page = self._download_webpage(login_page_req, None,
  97. note='Downloading login page',
  98. errnote='Unable to download login page')
  99. lsd = self._search_regex(
  100. r'<input type="hidden" name="lsd" value="([^"]*)"',
  101. login_page, 'lsd')
  102. lgnrnd = self._search_regex(r'name="lgnrnd" value="([^"]*?)"', login_page, 'lgnrnd')
  103. login_form = {
  104. 'email': useremail,
  105. 'pass': password,
  106. 'lsd': lsd,
  107. 'lgnrnd': lgnrnd,
  108. 'next': 'http://facebook.com/home.php',
  109. 'default_persistent': '0',
  110. 'legacy_return': '1',
  111. 'timezone': '-60',
  112. 'trynum': '1',
  113. }
  114. request = sanitized_Request(self._LOGIN_URL, urlencode_postdata(login_form))
  115. request.add_header('Content-Type', 'application/x-www-form-urlencoded')
  116. try:
  117. login_results = self._download_webpage(request, None,
  118. note='Logging in', errnote='unable to fetch login page')
  119. if re.search(r'<form(.*)name="login"(.*)</form>', login_results) is not None:
  120. error = self._html_search_regex(
  121. r'(?s)<div[^>]+class=(["\']).*?login_error_box.*?\1[^>]*><div[^>]*>.*?</div><div[^>]*>(?P<error>.+?)</div>',
  122. login_results, 'login error', default=None, group='error')
  123. if error:
  124. raise ExtractorError('Unable to login: %s' % error, expected=True)
  125. self._downloader.report_warning('unable to log in: bad username/password, or exceeded login rate limit (~3/min). Check credentials or wait.')
  126. return
  127. fb_dtsg = self._search_regex(
  128. r'name="fb_dtsg" value="(.+?)"', login_results, 'fb_dtsg', default=None)
  129. h = self._search_regex(
  130. r'name="h"\s+(?:\w+="[^"]+"\s+)*?value="([^"]+)"', login_results, 'h', default=None)
  131. if not fb_dtsg or not h:
  132. return
  133. check_form = {
  134. 'fb_dtsg': fb_dtsg,
  135. 'h': h,
  136. 'name_action_selected': 'dont_save',
  137. }
  138. check_req = sanitized_Request(self._CHECKPOINT_URL, urlencode_postdata(check_form))
  139. check_req.add_header('Content-Type', 'application/x-www-form-urlencoded')
  140. check_response = self._download_webpage(check_req, None,
  141. note='Confirming login')
  142. if re.search(r'id="checkpointSubmitButton"', check_response) is not None:
  143. self._downloader.report_warning('Unable to confirm login, you have to login in your browser and authorize the login.')
  144. except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
  145. self._downloader.report_warning('unable to log in: %s' % error_to_compat_str(err))
  146. return
  147. def _real_initialize(self):
  148. self._login()
  149. def _real_extract(self, url):
  150. video_id = self._match_id(url)
  151. req = sanitized_Request('https://www.facebook.com/video/video.php?v=%s' % video_id)
  152. req.add_header('User-Agent', self._CHROME_USER_AGENT)
  153. webpage = self._download_webpage(req, video_id)
  154. video_data = None
  155. BEFORE = '{swf.addParam(param[0], param[1]);});\n'
  156. AFTER = '.forEach(function(variable) {swf.addVariable(variable[0], variable[1]);});'
  157. m = re.search(re.escape(BEFORE) + '(.*?)' + re.escape(AFTER), webpage)
  158. if m:
  159. data = dict(json.loads(m.group(1)))
  160. params_raw = compat_urllib_parse_unquote(data['params'])
  161. video_data = json.loads(params_raw)['video_data']
  162. def video_data_list2dict(video_data):
  163. ret = {}
  164. for item in video_data:
  165. format_id = item['stream_type']
  166. ret.setdefault(format_id, []).append(item)
  167. return ret
  168. if not video_data:
  169. server_js_data = self._parse_json(self._search_regex(
  170. r'handleServerJS\(({.+})\);', webpage, 'server js data'), video_id)
  171. for item in server_js_data['instances']:
  172. if item[1][0] == 'VideoConfig':
  173. video_data = video_data_list2dict(item[2][0]['videoData'])
  174. break
  175. if not video_data:
  176. m_msg = re.search(r'class="[^"]*uiInterstitialContent[^"]*"><div>(.*?)</div>', webpage)
  177. if m_msg is not None:
  178. raise ExtractorError(
  179. 'The video is not available, Facebook said: "%s"' % m_msg.group(1),
  180. expected=True)
  181. else:
  182. raise ExtractorError('Cannot parse data')
  183. formats = []
  184. for format_id, f in video_data.items():
  185. if not f or not isinstance(f, list):
  186. continue
  187. for quality in ('sd', 'hd'):
  188. for src_type in ('src', 'src_no_ratelimit'):
  189. src = f[0].get('%s_%s' % (quality, src_type))
  190. if src:
  191. formats.append({
  192. 'format_id': '%s_%s_%s' % (format_id, quality, src_type),
  193. 'url': src,
  194. 'preference': -10 if format_id == 'progressive' else 0,
  195. })
  196. dash_manifest = f[0].get('dash_manifest')
  197. if dash_manifest:
  198. formats.extend(self._parse_mpd_formats(
  199. compat_etree_fromstring(compat_urllib_parse_unquote_plus(dash_manifest))))
  200. if not formats:
  201. raise ExtractorError('Cannot find video formats')
  202. self._sort_formats(formats)
  203. video_title = self._html_search_regex(
  204. r'<h2\s+[^>]*class="uiHeaderTitle"[^>]*>([^<]*)</h2>', webpage, 'title',
  205. default=None)
  206. if not video_title:
  207. video_title = self._html_search_regex(
  208. r'(?s)<span class="fbPhotosPhotoCaption".*?id="fbPhotoPageCaption"><span class="hasCaption">(.*?)</span>',
  209. webpage, 'alternative title', default=None)
  210. video_title = limit_length(video_title, 80)
  211. if not video_title:
  212. video_title = 'Facebook video #%s' % video_id
  213. uploader = clean_html(get_element_by_id('fbPhotoPageAuthorName', webpage))
  214. return {
  215. 'id': video_id,
  216. 'title': video_title,
  217. 'formats': formats,
  218. 'uploader': uploader,
  219. }
  220. class FacebookPostIE(InfoExtractor):
  221. IE_NAME = 'facebook:post'
  222. _VALID_URL = r'https?://(?:\w+\.)?facebook\.com/[^/]+/posts/(?P<id>\d+)'
  223. _TEST = {
  224. 'url': 'https://www.facebook.com/maxlayn/posts/10153807558977570',
  225. 'md5': '037b1fa7f3c2d02b7a0d7bc16031ecc6',
  226. 'info_dict': {
  227. 'id': '544765982287235',
  228. 'ext': 'mp4',
  229. 'title': '"What are you doing running in the snow?"',
  230. 'uploader': 'FailArmy',
  231. }
  232. }
  233. def _real_extract(self, url):
  234. post_id = self._match_id(url)
  235. webpage = self._download_webpage(url, post_id)
  236. entries = [
  237. self.url_result('facebook:%s' % video_id, FacebookIE.ie_key())
  238. for video_id in self._parse_json(
  239. self._search_regex(
  240. r'(["\'])video_ids\1\s*:\s*(?P<ids>\[.+?\])',
  241. webpage, 'video ids', group='ids'),
  242. post_id)]
  243. return self.playlist_result(entries, post_id)