import re from .common import InfoExtractor class RedTubeIE(InfoExtractor): _VALID_URL = r'http://(?:www\.)?redtube\.com/(?P[0-9]+)' _TEST = { u'url': u'http://www.redtube.com/66418', u'file': u'66418.mp4', # md5 varies from time to time, as in # https://travis-ci.org/rg3/youtube-dl/jobs/14052463#L295 #u'md5': u'7b8c22b5e7098a3e1c09709df1126d2d', u'info_dict': { u"title": u"Sucked on a toilet", u"age_limit": 18, } } def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') video_extension = 'mp4' webpage = self._download_webpage(url, video_id) self.report_extraction(video_id) video_url = self._html_search_regex( r'', webpage, u'video URL') video_title = self._html_search_regex( r'

(.+?)

', webpage, u'title') video_thumbnail = self._html_search_regex( r'playerInnerHTML.+?