X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/c512650955de0b16d37e7fa7fb29ea0985e415bb..d1d8237037fb87a57bd1d073c3b9e642d4a75016:/youtube_dl/extractor/comedycentral.py diff --git a/youtube_dl/extractor/comedycentral.py b/youtube_dl/extractor/comedycentral.py index ba4d73a..2b6aaa3 100644 --- a/youtube_dl/extractor/comedycentral.py +++ b/youtube_dl/extractor/comedycentral.py @@ -2,11 +2,12 @@ from __future__ import unicode_literals import re -from .common import InfoExtractor from .mtv import MTVServicesInfoExtractor -from ..utils import ( +from ..compat import ( compat_str, - compat_urllib_parse, + compat_urllib_parse_urlencode, +) +from ..utils import ( ExtractorError, float_or_none, unified_strdate, @@ -14,13 +15,13 @@ from ..utils import ( class ComedyCentralIE(MTVServicesInfoExtractor): - _VALID_URL = r'''(?x)https?://(?:www\.)?(comedycentral|cc)\.com/ - (video-clips|episodes|cc-studios|video-collections) + _VALID_URL = r'''(?x)https?://(?:www\.)?cc\.com/ + (video-clips|episodes|cc-studios|video-collections|full-episodes|shows) /(?P.*)''' _FEED_URL = 'http://comedycentral.com/feeds/mrss/' - _TEST = { - 'url': 'http://www.comedycentral.com/video-clips/kllhuv/stand-up-greg-fitzsimmons--uncensored---too-good-of-a-mother', + _TESTS = [{ + 'url': 'http://www.cc.com/video-clips/kllhuv/stand-up-greg-fitzsimmons--uncensored---too-good-of-a-mother', 'md5': 'c4f48e9eda1b16dd10add0744344b6d8', 'info_dict': { 'id': 'cef0cbb3-e776-4bc9-b62e-8016deccb354', @@ -28,29 +29,34 @@ 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(InfoExtractor): +class ComedyCentralShowsIE(MTVServicesInfoExtractor): IE_DESC = 'The Daily Show / The Colbert Report' - # urls can be abbreviations like :thedailyshow or :colbert + # urls can be abbreviations like :thedailyshow # urls for episodes like: # or urls for clips like: http://www.thedailyshow.com/watch/mon-december-10-2012/any-given-gun-day # or: http://www.colbertnation.com/the-colbert-report-videos/421667/november-29-2012/moon-shattering-news # or: http://www.colbertnation.com/the-colbert-report-collections/422008/festival-of-lights/79524 - _VALID_URL = r'''(?x)^(:(?P<shortname>tds|thedailyshow|cr|colbert|colbertnation|colbertreport) + _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)/[^/]+/(?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>.*?)(/.*?)?))) - (?:[?#].*|$)''' - _TEST = { + extended-interviews/(?P<interID>[0-9a-z]+)/ + (?:playlist_tds_extended_)?(?P<interview_title>[^/?#]*?) + (?:/[^/?#]?|[?#]|$)))) + ''' + _TESTS = [{ 'url': 'http://thedailyshow.cc.com/watch/thu-december-13-2012/kristen-stewart', 'md5': '4e2f5cb088a83cd8cdb7756132f9739d', 'info_dict': { @@ -61,7 +67,72 @@ class ComedyCentralShowsIE(InfoExtractor): '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://thecolbertreport.cc.com/videos/29w6fx/-realhumanpraise-for-fox-news', + 'only_matching': True, + }, { + 'url': 'http://thecolbertreport.cc.com/videos/gh6urb/neil-degrasse-tyson-pt--1?xrs=eml_col_031114', + 'only_matching': True, + }, { + 'url': 'http://thedailyshow.cc.com/guests/michael-lewis/3efna8/exclusive---michael-lewis-extended-interview-pt--3', + 'only_matching': True, + }, { + 'url': 'http://thedailyshow.cc.com/episodes/sy7yv0/april-8--2014---denis-leary', + 'only_matching': True, + }, { + 'url': 'http://thecolbertreport.cc.com/episodes/8ase07/april-8--2014---jane-goodall', + 'only_matching': True, + }, { + 'url': 'http://thedailyshow.cc.com/video-playlists/npde3s/the-daily-show-19088-highlights', + 'only_matching': True, + }, { + 'url': 'http://thedailyshow.cc.com/video-playlists/t6d9sg/the-daily-show-20038-highlights/be3cwo', + 'only_matching': True, + }, { + 'url': 'http://thedailyshow.cc.com/special-editions/2l8fdb/special-edition---a-look-back-at-food', + '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'] @@ -82,26 +153,11 @@ class ComedyCentralShowsIE(InfoExtractor): '400': (384, 216), } - @staticmethod - def _transform_rtmp_url(rtmp_video_url): - m = re.match(r'^rtmpe?://.*?/(?P<finalid>gsp\.comedystor/.*)$', rtmp_video_url) - if not m: - raise ExtractorError('Cannot transform RTMP url') - base = 'http://mtvnmobile.vo.llnwd.net/kip0/_pxn=1+_pxI0=Ripod-h264+_pxL0=undefined+_pxM0=+_pxK=18639+_pxE=mp4/44620/mtvnorigin/' - return base + m.group('finalid') - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url, re.VERBOSE) - if mobj is None: - raise ExtractorError('Invalid URL: %s' % url) + 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'): @@ -130,7 +186,7 @@ class ComedyCentralShowsIE(InfoExtractor): raise ExtractorError('Invalid redirected URL: ' + url) if mobj.group('episode') == '': raise ExtractorError('Redirected URL is still not specific: ' + url) - epTitle = mobj.group('episode').rpartition('/')[-1] + epTitle = (mobj.group('episode') or mobj.group('videotitle')).rpartition('/')[-1] mMovieParams = re.findall('(?:<param name="movie" value="|var url = ")(http://media.mtvnservices.com/([^"]*(?:episode|video).*?:.*?))"', webpage) if len(mMovieParams) == 0: @@ -142,13 +198,13 @@ class ComedyCentralShowsIE(InfoExtractor): 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') @@ -195,6 +251,8 @@ class ComedyCentralShowsIE(InfoExtractor): }) 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, @@ -205,10 +263,12 @@ class ComedyCentralShowsIE(InfoExtractor): 'duration': duration, 'thumbnail': thumbnail, 'description': description, + 'subtitles': subtitles, }) return { '_type': 'playlist', + 'id': epTitle, 'entries': entries, 'title': show_name + ' ' + title, 'description': description,