X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/a4f82408d9a3d921d9c2af7e4d757f44737dc7ea..5ea61d104de9ca8a7d19d63d83173eb7391081d2:/youtube_dl/extractor/redtube.py diff --git a/youtube_dl/extractor/redtube.py b/youtube_dl/extractor/redtube.py index d1e12dd..d6054d7 100644 --- a/youtube_dl/extractor/redtube.py +++ b/youtube_dl/extractor/redtube.py @@ -1,40 +1,34 @@ from __future__ import unicode_literals -import re - from .common import InfoExtractor +from ..utils import ExtractorError class RedTubeIE(InfoExtractor): _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', + 'md5': '7b8c22b5e7098a3e1c09709df1126d2d', 'info_dict': { - "title": "Sucked on a toilet", - "age_limit": 18, + 'id': '66418', + 'ext': 'mp4', + '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_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - self.report_extraction(video_id) + if any(s in webpage for s in ['video-deleted-info', '>This video has been removed']): + raise ExtractorError('Video %s has been removed' % video_id, expected=True) video_url = self._html_search_regex( - r'', webpage, u'video URL') - + r'', webpage, 'video URL') video_title = self._html_search_regex( r'

(.+?)

', - webpage, u'title') - + webpage, 'title') video_thumbnail = self._og_search_thumbnail(webpage) # No self-labeling, but they describe themselves as @@ -44,7 +38,7 @@ class RedTubeIE(InfoExtractor): return { 'id': video_id, 'url': video_url, - 'ext': video_extension, + 'ext': 'mp4', 'title': video_title, 'thumbnail': video_thumbnail, 'age_limit': age_limit,