X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/bddc9fc577d16b1428924bf8a5c37ef1d9295f14..ab926e5dbeca04924d1628992210084e67368d25:/youtube_dl/extractor/comedycentral.py diff --git a/youtube_dl/extractor/comedycentral.py b/youtube_dl/extractor/comedycentral.py index 1bb3590..d08b909 100644 --- a/youtube_dl/extractor/comedycentral.py +++ b/youtube_dl/extractor/comedycentral.py @@ -1,179 +1,142 @@ -import re -import xml.etree.ElementTree +from __future__ import unicode_literals +from .mtv import MTVServicesInfoExtractor from .common import InfoExtractor -from ..utils import ( - compat_str, - compat_urllib_parse, - - ExtractorError, - unified_strdate, -) - - -class ComedyCentralIE(InfoExtractor): - """Information extractor for The Daily Show and Colbert Report """ - - # urls can be abbreviations like :thedailyshow or :colbert - # 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"""^(:(?Ptds|thedailyshow|cr|colbert|colbertnation|colbertreport) - |(https?://)?(www\.)? - (?Pthedailyshow|colbertnation)\.com/ - (full-episodes/(?P.*)| - (?P - (the-colbert-report-(videos|collections)/(?P[0-9]+)/[^/]*/(?P.*?)) - |(watch/(?P[^/]*)/(?P.*))))) - $""" - - _available_formats = ['3500', '2200', '1700', '1200', '750', '400'] - - _video_extensions = { - '3500': 'mp4', - '2200': 'mp4', - '1700': 'mp4', - '1200': 'mp4', - '750': 'mp4', - '400': 'mp4', - } - _video_dimensions = { - '3500': '1280x720', - '2200': '960x540', - '1700': '768x432', - '1200': '640x360', - '750': '512x288', - '400': '384x216', - } - - @classmethod - def suitable(cls, url): - """Receives a URL and returns True if suitable for this IE.""" - return re.match(cls._VALID_URL, url, re.VERBOSE) is not None - - def _print_formats(self, formats): - print('Available formats:') - for x in formats: - print('%s\t:\t%s\t[%s]' %(x, self._video_extensions.get(x, 'mp4'), self._video_dimensions.get(x, '???'))) +class ComedyCentralIE(MTVServicesInfoExtractor): + _VALID_URL = r'''(?x)https?://(?:www\.)?cc\.com/ + (video-clips|episodes|cc-studios|video-collections|shows(?=/[^/]+/(?!full-episodes))) + /(?P.*)''' + _FEED_URL = 'http://comedycentral.com/feeds/mrss/' + + _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', + 'ext': 'mp4', + 'title': 'CC:Stand-Up|August 18, 2013|1|0101|Uncensored - Too Good of a Mother', + 'description': 'After a certain point, breastfeeding becomes c**kblocking.', + 'timestamp': 1376798400, + 'upload_date': '20130818', + }, + }, { + 'url': 'http://www.cc.com/shows/the-daily-show-with-trevor-noah/interviews/6yx39d/exclusive-rand-paul-extended-interview', + 'only_matching': True, + }] + + +class ComedyCentralFullEpisodesIE(MTVServicesInfoExtractor): + _VALID_URL = r'''(?x)https?://(?:www\.)?cc\.com/ + (?:full-episodes|shows(?=/[^/]+/full-episodes)) + /(?P<id>[^?]+)''' + _FEED_URL = 'http://comedycentral.com/feeds/mrss/' + + _TESTS = [{ + 'url': 'http://www.cc.com/full-episodes/pv391a/the-daily-show-with-trevor-noah-november-28--2016---ryan-speedo-green-season-22-ep-22028', + 'info_dict': { + 'description': 'Donald Trump is accused of exploiting his president-elect status for personal gain, Cuban leader Fidel Castro dies, and Ryan Speedo Green discusses "Sing for Your Life."', + 'title': 'November 28, 2016 - Ryan Speedo Green', + }, + 'playlist_count': 4, + }, { + 'url': 'http://www.cc.com/shows/the-daily-show-with-trevor-noah/full-episodes', + 'only_matching': True, + }] + def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url, re.VERBOSE) - if mobj is None: - raise ExtractorError(u'Invalid URL: %s' % url) - - if mobj.group('shortname'): - if mobj.group('shortname') in ('tds', 'thedailyshow'): - url = u'http://www.thedailyshow.com/full-episodes/' - else: - url = u'http://www.colbertnation.com/full-episodes/' - mobj = re.match(self._VALID_URL, url, re.VERBOSE) - assert mobj is not None - - if mobj.group('clip'): - if mobj.group('showname') == 'thedailyshow': - epTitle = mobj.group('tdstitle') - else: - epTitle = mobj.group('cntitle') - dlNewest = False - else: - dlNewest = not mobj.group('episode') - if dlNewest: - epTitle = mobj.group('showname') - else: - epTitle = mobj.group('episode') - - self.report_extraction(epTitle) - webpage,htmlHandle = self._download_webpage_handle(url, epTitle) - if dlNewest: - url = htmlHandle.geturl() - mobj = re.match(self._VALID_URL, url, re.VERBOSE) - if mobj is None: - raise ExtractorError(u'Invalid redirected URL: ' + url) - if mobj.group('episode') == '': - raise ExtractorError(u'Redirected URL is still not specific: ' + url) - epTitle = mobj.group('episode') - - mMovieParams = re.findall('(?:<param name="movie" value="|var url = ")(http://media.mtvnservices.com/([^"]*(?:episode|video).*?:.*?))"', webpage) - - if len(mMovieParams) == 0: - # The Colbert Report embeds the information in a without - # a URL prefix; so extract the alternate reference - # and then add the URL prefix manually. - - altMovieParams = re.findall('data-mgid="([^"]*(?:episode|video).*?:.*?)"', webpage) - if len(altMovieParams) == 0: - raise ExtractorError(u'unable to find Flash URL in webpage ' + url) - else: - mMovieParams = [("http://media.mtvnservices.com/" + altMovieParams[0], altMovieParams[0])] - - uri = mMovieParams[0][1] - indexUrl = 'http://shadow.comedycentral.com/feeds/video_player/mrss/?' + compat_urllib_parse.urlencode({'uri': uri}) - indexXml = self._download_webpage(indexUrl, epTitle, - u'Downloading show index', - u'unable to download episode index') - - results = [] - - idoc = xml.etree.ElementTree.fromstring(indexXml) - itemEls = idoc.findall('.//item') - for partNum,itemEl in enumerate(itemEls): - mediaId = itemEl.findall('./guid')[0].text - shortMediaId = mediaId.split(':')[-1] - showId = mediaId.split(':')[-2].replace('.com', '') - officialTitle = itemEl.findall('./title')[0].text - officialDate = unified_strdate(itemEl.findall('./pubDate')[0].text) - - configUrl = ('http://www.comedycentral.com/global/feeds/entertainment/media/mediaGenEntertainment.jhtml?' + - compat_urllib_parse.urlencode({'uri': mediaId})) - configXml = self._download_webpage(configUrl, epTitle, - u'Downloading configuration for %s' % shortMediaId) - - cdoc = xml.etree.ElementTree.fromstring(configXml) - turls = [] - for rendition in cdoc.findall('.//rendition'): - finfo = (rendition.attrib['bitrate'], rendition.findall('./src')[0].text) - turls.append(finfo) - - if len(turls) == 0: - self._downloader.report_error(u'unable to download ' + mediaId + ': No videos found') - continue - - if self._downloader.params.get('listformats', None): - self._print_formats([i[0] for i in turls]) - return - - # For now, just pick the highest bitrate - format,rtmp_video_url = turls[-1] - - # Get the format arg from the arg stream - req_format = self._downloader.params.get('format', None) - - # Select format if we can find one - for f,v in turls: - if f == req_format: - format, rtmp_video_url = f, v - break - - m = re.match(r'^rtmpe?://.*?/(?P<finalid>gsp.comedystor/.*)$', rtmp_video_url) - if not m: - raise ExtractorError(u'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/' - video_url = base + m.group('finalid') - - effTitle = showId + u'-' + epTitle + u' part ' + compat_str(partNum+1) - info = { - 'id': shortMediaId, - 'url': video_url, - 'uploader': showId, - 'upload_date': officialDate, - 'title': effTitle, + playlist_id = self._match_id(url) + webpage = self._download_webpage(url, playlist_id) + mgid = self._extract_triforce_mgid(webpage, data_zone='t2_lc_promo1') + videos_info = self._get_videos_info(mgid) + return videos_info + + +class ToshIE(MTVServicesInfoExtractor): + IE_DESC = 'Tosh.0' + _VALID_URL = r'^https?://tosh\.cc\.com/video-(?:clips|collections)/[^/]+/(?P<videotitle>[^/?#]+)' + _FEED_URL = 'http://tosh.cc.com/feeds/mrss' + + _TESTS = [{ + 'url': 'http://tosh.cc.com/video-clips/68g93d/twitter-users-share-summer-plans', + 'info_dict': { + 'description': 'Tosh asked fans to share their summer plans.', + 'title': 'Twitter Users Share Summer Plans', + }, + 'playlist': [{ + 'md5': 'f269e88114c1805bb6d7653fecea9e06', + 'info_dict': { + 'id': '90498ec2-ed00-11e0-aca6-0026b9414f30', 'ext': 'mp4', - 'format': format, - 'thumbnail': None, - 'description': officialTitle, - } - results.append(info) + 'title': 'Tosh.0|June 9, 2077|2|211|Twitter Users Share Summer Plans', + 'description': 'Tosh asked fans to share their summer plans.', + 'thumbnail': r're:^https?://.*\.jpg', + # It's really reported to be published on year 2077 + 'upload_date': '20770610', + 'timestamp': 3390510600, + 'subtitles': { + 'en': 'mincount:3', + }, + }, + }] + }, { + 'url': 'http://tosh.cc.com/video-collections/x2iz7k/just-plain-foul/m5q4fp', + 'only_matching': True, + }] + + +class ComedyCentralTVIE(MTVServicesInfoExtractor): + _VALID_URL = r'https?://(?:www\.)?comedycentral\.tv/(?:staffeln|shows)/(?P<id>[^/?#&]+)' + _TESTS = [{ + 'url': 'http://www.comedycentral.tv/staffeln/7436-the-mindy-project-staffel-4', + 'info_dict': { + 'id': 'local_playlist-f99b626bdfe13568579a', + 'ext': 'flv', + 'title': 'Episode_the-mindy-project_shows_season-4_episode-3_full-episode_part1', + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + }, { + 'url': 'http://www.comedycentral.tv/shows/1074-workaholics', + 'only_matching': True, + }, { + 'url': 'http://www.comedycentral.tv/shows/1727-the-mindy-project/bonus', + 'only_matching': True, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + + mrss_url = self._search_regex( + r'data-mrss=(["\'])(?P<url>(?:(?!\1).)+)\1', + webpage, 'mrss url', group='url') - return results + return self._get_videos_info_from_url(mrss_url, video_id) + + +class ComedyCentralShortnameIE(InfoExtractor): + _VALID_URL = r'^:(?P<id>tds|thedailyshow|theopposition)$' + _TESTS = [{ + 'url': ':tds', + 'only_matching': True, + }, { + 'url': ':thedailyshow', + 'only_matching': True, + }, { + 'url': ':theopposition', + 'only_matching': True, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + shortcut_map = { + 'tds': 'http://www.cc.com/shows/the-daily-show-with-trevor-noah/full-episodes', + 'thedailyshow': 'http://www.cc.com/shows/the-daily-show-with-trevor-noah/full-episodes', + 'theopposition': 'http://www.cc.com/shows/the-opposition-with-jordan-klepper/full-episodes', + } + return self.url_result(shortcut_map[video_id])