from .mtv import MTVServicesInfoExtractor
from ..compat import (
compat_str,
- compat_urllib_parse,
+ compat_urllib_parse_urlencode,
)
from ..utils import (
ExtractorError,
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<title>.*)'''
_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': {
'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):
# or: http://www.colbertnation.com/the-colbert-report-collections/422008/festival-of-lights/79524
_VALID_URL = r'''(?x)^(:(?P<shortname>tds|thedailyshow)
|https?://(:www\.)?
- (?P<showname>thedailyshow|thecolbertreport)\.(?:cc\.)?com/
+ (?P<showname>thedailyshow|thecolbertreport|tosh)\.(?:cc\.)?com/
((?:full-)?episodes/(?:[0-9a-z]{6}/)?(?P<episode>.*)|
(?P<clip>
- (?:(?:guests/[^/]+|videos|video-playlists|special-editions|news-team/[^/]+)/[^/]+/(?P<videotitle>[^/?#]+))
+ (?:(?:guests/[^/]+|videos|video-(?:clips|playlists)|special-editions|news-team/[^/]+)/[^/]+/(?P<videotitle>[^/?#]+))
|(the-colbert-report-(videos|collections)/(?P<clipID>[0-9]+)/[^/]*/(?P<cntitle>.*?))
|(watch/(?P<date>[^/]*)/(?P<tdstitle>.*))
)|
(?P<interview>
- extended-interviews/(?P<interID>[0-9a-z]+)/(?:playlist_tds_extended_)?(?P<interview_title>.*?)(/.*?)?)))
+ extended-interviews/(?P<interID>[0-9a-z]+)/
+ (?:playlist_tds_extended_)?(?P<interview_title>[^/?#]*?)
+ (?:/[^/?#]?|[?#]|$))))
'''
_TESTS = [{
'url': 'http://thedailyshow.cc.com/watch/thu-december-13-2012/kristen-stewart',
'uploader': 'thedailyshow',
'title': 'thedailyshow kristen-stewart part 1',
}
+ }, {
+ 'url': 'http://thedailyshow.cc.com/extended-interviews/b6364d/sarah-chayes-extended-interview',
+ 'info_dict': {
+ 'id': 'sarah-chayes-extended-interview',
+ 'description': 'Carnegie Endowment Senior Associate Sarah Chayes discusses how corrupt institutions function throughout the world in her book "Thieves of State: Why Corruption Threatens Global Security."',
+ 'title': 'thedailyshow Sarah Chayes Extended Interview',
+ },
+ 'playlist': [
+ {
+ 'info_dict': {
+ 'id': '0baad492-cbec-4ec1-9e50-ad91c291127f',
+ 'ext': 'mp4',
+ 'upload_date': '20150129',
+ 'description': 'Carnegie Endowment Senior Associate Sarah Chayes discusses how corrupt institutions function throughout the world in her book "Thieves of State: Why Corruption Threatens Global Security."',
+ 'uploader': 'thedailyshow',
+ 'title': 'thedailyshow sarah-chayes-extended-interview part 1',
+ },
+ },
+ {
+ 'info_dict': {
+ 'id': '1e4fb91b-8ce7-4277-bd7c-98c9f1bbd283',
+ 'ext': 'mp4',
+ 'upload_date': '20150129',
+ 'description': 'Carnegie Endowment Senior Associate Sarah Chayes discusses how corrupt institutions function throughout the world in her book "Thieves of State: Why Corruption Threatens Global Security."',
+ 'uploader': 'thedailyshow',
+ 'title': 'thedailyshow sarah-chayes-extended-interview part 2',
+ },
+ },
+ ],
+ 'params': {
+ 'skip_download': True,
+ },
}, {
'url': 'http://thedailyshow.cc.com/extended-interviews/xm3fnq/andrew-napolitano-extended-interview',
'only_matching': True,
}, {
'url': 'http://thedailyshow.cc.com/news-team/michael-che/7wnfel/we-need-to-talk-about-israel',
'only_matching': True,
+ }, {
+ 'url': 'http://tosh.cc.com/video-clips/68g93d/twitter-users-share-summer-plans',
+ 'only_matching': True,
}]
_available_formats = ['3500', '2200', '1700', '1200', '750', '400']
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'):
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}))
+ index_url = 'http://%s.cc.com/feeds/mrss?%s' % (show_name, compat_urllib_parse_urlencode({'uri': uri}))
idoc = self._download_xml(
index_url, epTitle,
'Downloading show index', 'Unable to download episode index')
})
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,
'duration': duration,
'thumbnail': thumbnail,
'description': description,
+ 'subtitles': subtitles,
})
return {
'_type': 'playlist',
+ 'id': epTitle,
'entries': entries,
'title': show_name + ' ' + title,
'description': description,
projects / youtube-dl / blobdiff