X-Git-Url: http://git.cielonegro.org/gitweb.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fcomedycentral.py;h=5b1b99675c760a7249bcdb23ff3072af86710114;hb=e41acb63647e4aad52dff25b505bdc0bb2a6b9e6;hp=bd3817b56547ef31e5f810491ab9495cdef9c592;hpb=9ef4f12b534578ae3d3e47815492c90826c03c36;p=youtube-dl.git diff --git a/youtube_dl/extractor/comedycentral.py b/youtube_dl/extractor/comedycentral.py index bd3817b56..5b1b99675 100644 --- a/youtube_dl/extractor/comedycentral.py +++ b/youtube_dl/extractor/comedycentral.py @@ -2,7 +2,6 @@ from __future__ import unicode_literals import re -from .common import InfoExtractor from .mtv import MTVServicesInfoExtractor from ..compat import ( compat_str, @@ -17,11 +16,11 @@ from ..utils import ( class ComedyCentralIE(MTVServicesInfoExtractor): _VALID_URL = r'''(?x)https?://(?:www\.)?cc\.com/ - (video-clips|episodes|cc-studios|video-collections|full-episodes) + (video-clips|episodes|cc-studios|video-collections|full-episodes|shows) /(?P.*)''' _FEED_URL = 'http://comedycentral.com/feeds/mrss/' - _TEST = { + _TESTS = [{ 'url': 'http://www.cc.com/video-clips/kllhuv/stand-up-greg-fitzsimmons--uncensored---too-good-of-a-mother', 'md5': 'c4f48e9eda1b16dd10add0744344b6d8', 'info_dict': { @@ -30,7 +29,10 @@ class ComedyCentralIE(MTVServicesInfoExtractor): 'title': 'CC:Stand-Up|Greg Fitzsimmons: Life on Stage|Uncensored - Too Good of a Mother', 'description': 'After a certain point, breastfeeding becomes c**kblocking.', }, - } + }, { + 'url': 'http://www.cc.com/shows/the-daily-show-with-trevor-noah/interviews/6yx39d/exclusive-rand-paul-extended-interview', + 'only_matching': True, + }] class ComedyCentralShowsIE(MTVServicesInfoExtractor): @@ -152,12 +154,7 @@ class ComedyCentralShowsIE(MTVServicesInfoExtractor): mobj = re.match(self._VALID_URL, url) if mobj.group('shortname'): - if mobj.group('shortname') in ('tds', 'thedailyshow'): - url = 'http://thedailyshow.cc.com/full-episodes/' - else: - url = 'http://thecolbertreport.cc.com/full-episodes/' - mobj = re.match(self._VALID_URL, url, re.VERBOSE) - assert mobj is not None + return self.url_result('http://www.cc.com/shows/the-daily-show-with-trevor-noah/full-episodes') if mobj.group('clip'): if mobj.group('videotitle'): @@ -198,11 +195,11 @@ class ComedyCentralShowsIE(MTVServicesInfoExtractor): if len(altMovieParams) == 0: raise ExtractorError('unable to find Flash URL in webpage ' + url) else: - mMovieParams = [("http://media.mtvnservices.com/" + altMovieParams[0], altMovieParams[0])] + mMovieParams = [('http://media.mtvnservices.com/' + altMovieParams[0], altMovieParams[0])] uri = mMovieParams[0][1] # Correct cc.com in uri - uri = re.sub(r'(episode:[^.]+)(\.cc)?\.com', r'\1.cc.com', uri) + uri = re.sub(r'(episode:[^.]+)(\.cc)?\.com', r'\1.com', uri) index_url = 'http://%s.cc.com/feeds/mrss?%s' % (show_name, compat_urllib_parse.urlencode({'uri': uri})) idoc = self._download_xml( @@ -273,27 +270,3 @@ class ComedyCentralShowsIE(MTVServicesInfoExtractor): 'title': show_name + ' ' + title, 'description': description, } - -class TheDailyShowPodcastIE(InfoExtractor): - _VALID_URL = r'(?P<scheme>https?:)?//thedailyshow\.cc\.com/podcast/(?P<id>[a-z\-]+)' - _TESTS = [{ - "url": "http://thedailyshow.cc.com/podcast/episodetwelve", - 'only_matching': True, - }] - - def _real_extract(self, url): - display_id = self._match_id(url) - webpage = self._download_webpage(url, display_id) - - player_url = self._search_regex(r'<iframe(?:\s+[^>]+)?\s*src="((?:https?:)?//html5-player\.libsyn\.com/embed/episode/id/[0-9]+)', webpage, 'player URL') - if player_url.startswith('//'): - mobj = re.match(self._VALID_URL, url) - scheme = mobj.group('scheme') - if not scheme: - scheme = 'https:' - player_url = scheme + player_url - - return { - '_type': 'url_transparent', - 'url': player_url, - }