1 from __future__ import unicode_literals
5 from .common import InfoExtractor
6 from .mtv import MTVServicesInfoExtractor
16 class ComedyCentralIE(MTVServicesInfoExtractor):
17 _VALID_URL = r'''(?x)https?://(?:www\.)?cc\.com/
18 (video-clips|episodes|cc-studios|video-collections|full-episodes)
20 _FEED_URL = 'http://comedycentral.com/feeds/mrss/'
23 'url': 'http://www.cc.com/video-clips/kllhuv/stand-up-greg-fitzsimmons--uncensored---too-good-of-a-mother',
24 'md5': 'c4f48e9eda1b16dd10add0744344b6d8',
26 'id': 'cef0cbb3-e776-4bc9-b62e-8016deccb354',
28 'title': 'CC:Stand-Up|Greg Fitzsimmons: Life on Stage|Uncensored - Too Good of a Mother',
29 'description': 'After a certain point, breastfeeding becomes c**kblocking.',
34 class ComedyCentralShowsIE(InfoExtractor):
35 IE_DESC = 'The Daily Show / The Colbert Report'
36 # urls can be abbreviations like :thedailyshow or :colbert
37 # urls for episodes like:
38 # or urls for clips like: http://www.thedailyshow.com/watch/mon-december-10-2012/any-given-gun-day
39 # or: http://www.colbertnation.com/the-colbert-report-videos/421667/november-29-2012/moon-shattering-news
40 # or: http://www.colbertnation.com/the-colbert-report-collections/422008/festival-of-lights/79524
41 _VALID_URL = r'''(?x)^(:(?P<shortname>tds|thedailyshow|cr|colbert|colbertnation|colbertreport)
43 (?P<showname>thedailyshow|thecolbertreport)\.(?:cc\.)?com/
44 ((?:full-)?episodes/(?:[0-9a-z]{6}/)?(?P<episode>.*)|
46 (?:(?:guests/[^/]+|videos|video-playlists|special-editions)/[^/]+/(?P<videotitle>[^/?#]+))
47 |(the-colbert-report-(videos|collections)/(?P<clipID>[0-9]+)/[^/]*/(?P<cntitle>.*?))
48 |(watch/(?P<date>[^/]*)/(?P<tdstitle>.*))
51 extended-interviews/(?P<interID>[0-9a-z]+)/(?:playlist_tds_extended_)?(?P<interview_title>.*?)(/.*?)?)))
54 'url': 'http://thedailyshow.cc.com/watch/thu-december-13-2012/kristen-stewart',
55 'md5': '4e2f5cb088a83cd8cdb7756132f9739d',
57 'id': 'ab9ab3e7-5a98-4dbe-8b21-551dc0523d55',
59 'upload_date': '20121213',
60 'description': 'Kristen Stewart learns to let loose in "On the Road."',
61 'uploader': 'thedailyshow',
62 'title': 'thedailyshow kristen-stewart part 1',
65 'url': 'http://thedailyshow.cc.com/extended-interviews/xm3fnq/andrew-napolitano-extended-interview',
66 'only_matching': True,
68 'url': 'http://thecolbertreport.cc.com/videos/29w6fx/-realhumanpraise-for-fox-news',
69 'only_matching': True,
71 'url': 'http://thecolbertreport.cc.com/videos/gh6urb/neil-degrasse-tyson-pt--1?xrs=eml_col_031114',
72 'only_matching': True,
74 'url': 'http://thedailyshow.cc.com/guests/michael-lewis/3efna8/exclusive---michael-lewis-extended-interview-pt--3',
75 'only_matching': True,
77 'url': 'http://thedailyshow.cc.com/episodes/sy7yv0/april-8--2014---denis-leary',
78 'only_matching': True,
80 'url': 'http://thecolbertreport.cc.com/episodes/8ase07/april-8--2014---jane-goodall',
81 'only_matching': True,
83 'url': 'http://thedailyshow.cc.com/video-playlists/npde3s/the-daily-show-19088-highlights',
84 'only_matching': True,
86 'url': 'http://thedailyshow.cc.com/special-editions/2l8fdb/special-edition---a-look-back-at-food',
87 'only_matching': True,
90 _available_formats = ['3500', '2200', '1700', '1200', '750', '400']
100 _video_dimensions = {
110 def _transform_rtmp_url(rtmp_video_url):
111 m = re.match(r'^rtmpe?://.*?/(?P<finalid>gsp\.comedystor/.*)$', rtmp_video_url)
113 raise ExtractorError('Cannot transform RTMP url')
114 base = 'http://mtvnmobile.vo.llnwd.net/kip0/_pxn=1+_pxI0=Ripod-h264+_pxL0=undefined+_pxM0=+_pxK=18639+_pxE=mp4/44620/mtvnorigin/'
115 return base + m.group('finalid')
117 def _real_extract(self, url):
118 mobj = re.match(self._VALID_URL, url, re.VERBOSE)
120 raise ExtractorError('Invalid URL: %s' % url)
122 if mobj.group('shortname'):
123 if mobj.group('shortname') in ('tds', 'thedailyshow'):
124 url = 'http://thedailyshow.cc.com/full-episodes/'
126 url = 'http://thecolbertreport.cc.com/full-episodes/'
127 mobj = re.match(self._VALID_URL, url, re.VERBOSE)
128 assert mobj is not None
130 if mobj.group('clip'):
131 if mobj.group('videotitle'):
132 epTitle = mobj.group('videotitle')
133 elif mobj.group('showname') == 'thedailyshow':
134 epTitle = mobj.group('tdstitle')
136 epTitle = mobj.group('cntitle')
138 elif mobj.group('interview'):
139 epTitle = mobj.group('interview_title')
142 dlNewest = not mobj.group('episode')
144 epTitle = mobj.group('showname')
146 epTitle = mobj.group('episode')
147 show_name = mobj.group('showname')
149 webpage, htmlHandle = self._download_webpage_handle(url, epTitle)
151 url = htmlHandle.geturl()
152 mobj = re.match(self._VALID_URL, url, re.VERBOSE)
154 raise ExtractorError('Invalid redirected URL: ' + url)
155 if mobj.group('episode') == '':
156 raise ExtractorError('Redirected URL is still not specific: ' + url)
157 epTitle = (mobj.group('episode') or mobj.group('videotitle')).rpartition('/')[-1]
159 mMovieParams = re.findall('(?:<param name="movie" value="|var url = ")(http://media.mtvnservices.com/([^"]*(?:episode|video).*?:.*?))"', webpage)
160 if len(mMovieParams) == 0:
161 # The Colbert Report embeds the information in a without
162 # a URL prefix; so extract the alternate reference
163 # and then add the URL prefix manually.
165 altMovieParams = re.findall('data-mgid="([^"]*(?:episode|video|playlist).*?:.*?)"', webpage)
166 if len(altMovieParams) == 0:
167 raise ExtractorError('unable to find Flash URL in webpage ' + url)
169 mMovieParams = [("http://media.mtvnservices.com/" + altMovieParams[0], altMovieParams[0])]
171 uri = mMovieParams[0][1]
172 # Correct cc.com in uri
173 uri = re.sub(r'(episode:[^.]+)(\.cc)?\.com', r'\1.cc.com', uri)
175 index_url = 'http://%s.cc.com/feeds/mrss?%s' % (show_name, compat_urllib_parse.urlencode({'uri': uri}))
176 idoc = self._download_xml(
178 'Downloading show index', 'Unable to download episode index')
180 title = idoc.find('./channel/title').text
181 description = idoc.find('./channel/description').text
184 item_els = idoc.findall('.//item')
185 for part_num, itemEl in enumerate(item_els):
186 upload_date = unified_strdate(itemEl.findall('./pubDate')[0].text)
187 thumbnail = itemEl.find('.//{http://search.yahoo.com/mrss/}thumbnail').attrib.get('url')
189 content = itemEl.find('.//{http://search.yahoo.com/mrss/}content')
190 duration = float_or_none(content.attrib.get('duration'))
191 mediagen_url = content.attrib['url']
192 guid = itemEl.find('./guid').text.rpartition(':')[-1]
194 cdoc = self._download_xml(
195 mediagen_url, epTitle,
196 'Downloading configuration for segment %d / %d' % (part_num + 1, len(item_els)))
199 for rendition in cdoc.findall('.//rendition'):
200 finfo = (rendition.attrib['bitrate'], rendition.findall('./src')[0].text)
204 for format, rtmp_video_url in turls:
205 w, h = self._video_dimensions.get(format, (None, None))
207 'format_id': 'vhttp-%s' % format,
208 'url': self._transform_rtmp_url(rtmp_video_url),
209 'ext': self._video_extensions.get(format, 'mp4'),
214 'format_id': 'rtmp-%s' % format,
215 'url': rtmp_video_url.replace('viacomccstrm', 'viacommtvstrm'),
216 'ext': self._video_extensions.get(format, 'mp4'),
220 self._sort_formats(formats)
222 virtual_id = show_name + ' ' + epTitle + ' part ' + compat_str(part_num + 1)
227 'uploader': show_name,
228 'upload_date': upload_date,
229 'duration': duration,
230 'thumbnail': thumbnail,
231 'description': description,
237 'title': show_name + ' ' + title,
238 'description': description,