X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fcomedycentral.py;h=bd3817b56547ef31e5f810491ab9495cdef9c592;hb=ef249a2cd7a7cfbd92a030cb72e238ba4ad52604;hp=8d27af5e57348e56a924d1d633df8799343245e4;hpb=c24dfef63c55ef1a5424d11b485c3b76245448a4;p=youtube-dl diff --git a/youtube_dl/extractor/comedycentral.py b/youtube_dl/extractor/comedycentral.py index 8d27af5e5..bd3817b56 100644 --- a/youtube_dl/extractor/comedycentral.py +++ b/youtube_dl/extractor/comedycentral.py @@ -2,6 +2,7 @@ from __future__ import unicode_literals import re +from .common import InfoExtractor from .mtv import MTVServicesInfoExtractor from ..compat import ( compat_str, @@ -34,12 +35,12 @@ class ComedyCentralIE(MTVServicesInfoExtractor): 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)^(:(?Ptds|thedailyshow|cr|colbert|colbertnation|colbertreport) + _VALID_URL = r'''(?x)^(:(?Ptds|thedailyshow) |https?://(:www\.)? (?Pthedailyshow|thecolbertreport)\.(?:cc\.)?com/ ((?:full-)?episodes/(?:[0-9a-z]{6}/)?(?P.*)| @@ -49,7 +50,9 @@ class ComedyCentralShowsIE(MTVServicesInfoExtractor): |(watch/(?P[^/]*)/(?P.*)) )| (?P - extended-interviews/(?P[0-9a-z]+)/(?:playlist_tds_extended_)?(?P.*?)(/.*?)?))) + extended-interviews/(?P[0-9a-z]+)/ + (?:playlist_tds_extended_)?(?P[^/?#]*?) + (?:/[^/?#]?|[?#]|$)))) ''' _TESTS = [{ 'url': 'http://thedailyshow.cc.com/watch/thu-december-13-2012/kristen-stewart', @@ -62,6 +65,38 @@ class ComedyCentralShowsIE(MTVServicesInfoExtractor): '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, @@ -216,6 +251,8 @@ 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, @@ -226,11 +263,37 @@ class ComedyCentralShowsIE(MTVServicesInfoExtractor): 'duration': duration, 'thumbnail': thumbnail, 'description': description, + 'subtitles': subtitles, }) return { '_type': 'playlist', + 'id': epTitle, 'entries': entries, 'title': show_name + ' ' + title, 'description': description, } + +class TheDailyShowPodcastIE(InfoExtractor): + _VALID_URL = r'(?Phttps?:)?//thedailyshow\.cc\.com/podcast/(?P[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']+)?\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, + }