X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/bc5059672e222ec4df4fe3983c399c0d0fca84d5..a5a28b1eabe0533f26d23c4157c97144215b22b7:/youtube_dl/extractor/comedycentral.py
diff --git a/youtube_dl/extractor/comedycentral.py b/youtube_dl/extractor/comedycentral.py
index 53579aa..d08b909 100644
--- a/youtube_dl/extractor/comedycentral.py
+++ b/youtube_dl/extractor/comedycentral.py
@@ -1,204 +1,142 @@
-import re
+from __future__ import unicode_literals
-from .common import InfoExtractor
from .mtv import MTVServicesInfoExtractor
-from ..utils import (
- compat_str,
- compat_urllib_parse,
-
- ExtractorError,
- unified_strdate,
-)
+from .common import InfoExtractor
class ComedyCentralIE(MTVServicesInfoExtractor):
- _VALID_URL = r'http://www.comedycentral.com/(video-clips|episodes|cc-studios)/(?P
.*)'
- _FEED_URL = u'http://comedycentral.com/feeds/mrss/'
-
- _TEST = {
- u'url': u'http://www.comedycentral.com/video-clips/kllhuv/stand-up-greg-fitzsimmons--uncensored---too-good-of-a-mother',
- u'md5': u'4167875aae411f903b751a21f357f1ee',
- u'info_dict': {
- u'id': u'cef0cbb3-e776-4bc9-b62e-8016deccb354',
- u'ext': u'mp4',
- u'title': u'Uncensored - Greg Fitzsimmons - Too Good of a Mother',
- u'description': u'After a certain point, breastfeeding becomes c**kblocking.',
+ _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[^?]+)'''
+ _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)
- title = mobj.group('title')
- webpage = self._download_webpage(url, title)
- mgid = self._search_regex(r'data-mgid="(?Pmgid:.*?)"',
- webpage, u'mgid')
- return self._get_videos_info(mgid)
-
-
-class ComedyCentralShowsIE(InfoExtractor):
- IE_DESC = u'The Daily Show / 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.*)))|
- (?P
- extended-interviews/(?P[0-9]+)/playlist_tds_extended_(?P.*?)/.*?)))
- $"""
- _TEST = {
- u'url': u'http://www.thedailyshow.com/watch/thu-december-13-2012/kristen-stewart',
- u'file': u'422212.mp4',
- u'md5': u'4e2f5cb088a83cd8cdb7756132f9739d',
- u'info_dict': {
- u"upload_date": u"20121214",
- u"description": u"Kristen Stewart",
- u"uploader": u"thedailyshow",
- u"title": u"thedailyshow-kristen-stewart part 1"
- }
- }
-
- _available_formats = ['3500', '2200', '1700', '1200', '750', '400']
-
- _video_extensions = {
- '3500': 'mp4',
- '2200': 'mp4',
- '1700': 'mp4',
- '1200': 'mp4',
- '750': 'mp4',
- '400': 'mp4',
- }
- _video_dimensions = {
- '3500': (1280, 720),
- '2200': (960, 540),
- '1700': (768, 432),
- '1200': (640, 360),
- '750': (512, 288),
- '400': (384, 216),
- }
-
- @classmethod
- def suitable(cls, url):
- """Receives a URL and returns True if suitable for this IE."""
- return re.match(cls._VALID_URL, url, re.VERBOSE) is not None
-
- @staticmethod
- def _transform_rtmp_url(rtmp_video_url):
- m = re.match(r'^rtmpe?://.*?/(?Pgsp.comedystor/.*)$', 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/'
- return base + m.group('finalid')
+ 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[^/?#]+)'
+ _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',
+ '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[^/?#&]+)'
+ _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):
- 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
- elif mobj.group('interview'):
- epTitle = mobj.group('interview_title')
- 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('(?:(?:(?!\1).)+)\1',
+ webpage, 'mrss url', group='url')
+
+ return self._get_videos_info_from_url(mrss_url, video_id)
+
+
+class ComedyCentralShortnameIE(InfoExtractor):
+ _VALID_URL = r'^:(?Ptds|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])