X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/d4ff594119bc679aa175947eb59a97bee8f966f4..82abf0abb400fbf710e03be31cc8942c21a040be:/youtube_dl/extractor/comedycentral.py
diff --git a/youtube_dl/extractor/comedycentral.py b/youtube_dl/extractor/comedycentral.py
index b245389..5b1b996 100644
--- a/youtube_dl/extractor/comedycentral.py
+++ b/youtube_dl/extractor/comedycentral.py
@@ -16,11 +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': {
@@ -29,7 +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):
@@ -151,12 +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'):
@@ -197,11 +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(
@@ -250,6 +248,8 @@ class ComedyCentralShowsIE(MTVServicesInfoExtractor):
})
self._sort_formats(formats)
+ subtitles = self._extract_subtitles(cdoc, guid)
+
virtual_id = show_name + ' ' + epTitle + ' part ' + compat_str(part_num + 1)
entries.append({
'id': guid,
@@ -260,6 +260,7 @@ class ComedyCentralShowsIE(MTVServicesInfoExtractor):
'duration': duration,
'thumbnail': thumbnail,
'description': description,
+ 'subtitles': subtitles,
})
return {