X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/bddc9fc577d16b1428924bf8a5c37ef1d9295f14..099764c0c91f4ad7db03d9347798f8619383ea7e:/youtube_dl/extractor/redtube.py diff --git a/youtube_dl/extractor/redtube.py b/youtube_dl/extractor/redtube.py index ebc4e23..d1e12dd 100644 --- a/youtube_dl/extractor/redtube.py +++ b/youtube_dl/extractor/redtube.py @@ -1,29 +1,51 @@ +from __future__ import unicode_literals + import re from .common import InfoExtractor class RedTubeIE(InfoExtractor): - _VALID_URL = r'(?:http://)?(?:www\.)?redtube\.com/(?P[0-9]+)' - - def _real_extract(self,url): + _VALID_URL = r'http://(?:www\.)?redtube\.com/(?P[0-9]+)' + _TEST = { + 'url': 'http://www.redtube.com/66418', + 'file': '66418.mp4', + # md5 varies from time to time, as in + # https://travis-ci.org/rg3/youtube-dl/jobs/14052463#L295 + #'md5': u'7b8c22b5e7098a3e1c09709df1126d2d', + 'info_dict': { + "title": "Sucked on a toilet", + "age_limit": 18, + } + } + + def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') - video_extension = 'mp4' + 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_url = self._html_search_regex( + r'', webpage, u'video URL') - video_title = self._html_search_regex('

(.+?)

', + video_title = self._html_search_regex( + r'

(.+?)

', webpage, u'title') - return [{ - 'id': video_id, - 'url': video_url, - 'ext': video_extension, - 'title': video_title, - }] + video_thumbnail = self._og_search_thumbnail(webpage) + + # No self-labeling, but they describe themselves as + # "Home of Videos Porno" + age_limit = 18 + + return { + 'id': video_id, + 'url': video_url, + 'ext': video_extension, + 'title': video_title, + 'thumbnail': video_thumbnail, + 'age_limit': age_limit, + }