]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/comedycentral.py
ed3986f313a149f0db4a69dc92762730297ced1a
[youtubedl] / youtube_dl / extractor / comedycentral.py
1 from __future__ import unicode_literals
2
3 import re
4
5 from .common import InfoExtractor
6 from .mtv import MTVServicesInfoExtractor
7 from ..utils import (
8 compat_str,
9 compat_urllib_parse,
10
11 ExtractorError,
12 unified_strdate,
13 )
14
15
16 class ComedyCentralIE(MTVServicesInfoExtractor):
17 _VALID_URL = r'''(?x)https?://(?:www\.)?comedycentral\.com/
18 (video-clips|episodes|cc-studios|video-collections)
19 /(?P<title>.*)'''
20 _FEED_URL = 'http://comedycentral.com/feeds/mrss/'
21
22 _TEST = {
23 'url': 'http://www.comedycentral.com/video-clips/kllhuv/stand-up-greg-fitzsimmons--uncensored---too-good-of-a-mother',
24 'md5': '4167875aae411f903b751a21f357f1ee',
25 'info_dict': {
26 'id': 'cef0cbb3-e776-4bc9-b62e-8016deccb354',
27 'ext': 'mp4',
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.',
30 },
31 }
32
33
34 class ComedyCentralShowsIE(InfoExtractor):
35 IE_DESC = 'The Daily Show / 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"""^(:(?P<shortname>tds|thedailyshow|cr|colbert|colbertnation|colbertreport)
42 |(https?://)?(www\.)?
43 (?P<showname>thedailyshow|colbertnation)\.com/
44 (full-episodes/(?P<episode>.*)|
45 (?P<clip>
46 (the-colbert-report-(videos|collections)/(?P<clipID>[0-9]+)/[^/]*/(?P<cntitle>.*?))
47 |(watch/(?P<date>[^/]*)/(?P<tdstitle>.*)))|
48 (?P<interview>
49 extended-interviews/(?P<interID>[0-9]+)/playlist_tds_extended_(?P<interview_title>.*?)/.*?)))
50 $"""
51 _TEST = {
52 'url': 'http://www.thedailyshow.com/watch/thu-december-13-2012/kristen-stewart',
53 'file': '422212.mp4',
54 'md5': '4e2f5cb088a83cd8cdb7756132f9739d',
55 'info_dict': {
56 "upload_date": "20121214",
57 "description": "Kristen Stewart",
58 "uploader": "thedailyshow",
59 "title": "thedailyshow-kristen-stewart part 1"
60 }
61 }
62
63 _available_formats = ['3500', '2200', '1700', '1200', '750', '400']
64
65 _video_extensions = {
66 '3500': 'mp4',
67 '2200': 'mp4',
68 '1700': 'mp4',
69 '1200': 'mp4',
70 '750': 'mp4',
71 '400': 'mp4',
72 }
73 _video_dimensions = {
74 '3500': (1280, 720),
75 '2200': (960, 540),
76 '1700': (768, 432),
77 '1200': (640, 360),
78 '750': (512, 288),
79 '400': (384, 216),
80 }
81
82 @classmethod
83 def suitable(cls, url):
84 """Receives a URL and returns True if suitable for this IE."""
85 return re.match(cls._VALID_URL, url, re.VERBOSE) is not None
86
87 @staticmethod
88 def _transform_rtmp_url(rtmp_video_url):
89 m = re.match(r'^rtmpe?://.*?/(?P<finalid>gsp\.comedystor/.*)$', rtmp_video_url)
90 if not m:
91 raise ExtractorError('Cannot transform RTMP url')
92 base = 'http://mtvnmobile.vo.llnwd.net/kip0/_pxn=1+_pxI0=Ripod-h264+_pxL0=undefined+_pxM0=+_pxK=18639+_pxE=mp4/44620/mtvnorigin/'
93 return base + m.group('finalid')
94
95 def _real_extract(self, url):
96 mobj = re.match(self._VALID_URL, url, re.VERBOSE)
97 if mobj is None:
98 raise ExtractorError('Invalid URL: %s' % url)
99
100 if mobj.group('shortname'):
101 if mobj.group('shortname') in ('tds', 'thedailyshow'):
102 url = 'http://www.thedailyshow.com/full-episodes/'
103 else:
104 url = 'http://www.colbertnation.com/full-episodes/'
105 mobj = re.match(self._VALID_URL, url, re.VERBOSE)
106 assert mobj is not None
107
108 if mobj.group('clip'):
109 if mobj.group('showname') == 'thedailyshow':
110 epTitle = mobj.group('tdstitle')
111 else:
112 epTitle = mobj.group('cntitle')
113 dlNewest = False
114 elif mobj.group('interview'):
115 epTitle = mobj.group('interview_title')
116 dlNewest = False
117 else:
118 dlNewest = not mobj.group('episode')
119 if dlNewest:
120 epTitle = mobj.group('showname')
121 else:
122 epTitle = mobj.group('episode')
123
124 self.report_extraction(epTitle)
125 webpage,htmlHandle = self._download_webpage_handle(url, epTitle)
126 if dlNewest:
127 url = htmlHandle.geturl()
128 mobj = re.match(self._VALID_URL, url, re.VERBOSE)
129 if mobj is None:
130 raise ExtractorError('Invalid redirected URL: ' + url)
131 if mobj.group('episode') == '':
132 raise ExtractorError('Redirected URL is still not specific: ' + url)
133 epTitle = mobj.group('episode')
134
135 mMovieParams = re.findall('(?:<param name="movie" value="|var url = ")(http://media.mtvnservices.com/([^"]*(?:episode|video).*?:.*?))"', webpage)
136
137 if len(mMovieParams) == 0:
138 # The Colbert Report embeds the information in a without
139 # a URL prefix; so extract the alternate reference
140 # and then add the URL prefix manually.
141
142 altMovieParams = re.findall('data-mgid="([^"]*(?:episode|video).*?:.*?)"', webpage)
143 if len(altMovieParams) == 0:
144 raise ExtractorError('unable to find Flash URL in webpage ' + url)
145 else:
146 mMovieParams = [("http://media.mtvnservices.com/" + altMovieParams[0], altMovieParams[0])]
147
148 uri = mMovieParams[0][1]
149 indexUrl = 'http://shadow.comedycentral.com/feeds/video_player/mrss/?' + compat_urllib_parse.urlencode({'uri': uri})
150 idoc = self._download_xml(indexUrl, epTitle,
151 'Downloading show index',
152 'unable to download episode index')
153
154 results = []
155
156 itemEls = idoc.findall('.//item')
157 for partNum,itemEl in enumerate(itemEls):
158 mediaId = itemEl.findall('./guid')[0].text
159 shortMediaId = mediaId.split(':')[-1]
160 showId = mediaId.split(':')[-2].replace('.com', '')
161 officialTitle = itemEl.findall('./title')[0].text
162 officialDate = unified_strdate(itemEl.findall('./pubDate')[0].text)
163
164 configUrl = ('http://www.comedycentral.com/global/feeds/entertainment/media/mediaGenEntertainment.jhtml?' +
165 compat_urllib_parse.urlencode({'uri': mediaId}))
166 cdoc = self._download_xml(configUrl, epTitle,
167 'Downloading configuration for %s' % shortMediaId)
168
169 turls = []
170 for rendition in cdoc.findall('.//rendition'):
171 finfo = (rendition.attrib['bitrate'], rendition.findall('./src')[0].text)
172 turls.append(finfo)
173
174 if len(turls) == 0:
175 self._downloader.report_error('unable to download ' + mediaId + ': No videos found')
176 continue
177
178 formats = []
179 for format, rtmp_video_url in turls:
180 w, h = self._video_dimensions.get(format, (None, None))
181 formats.append({
182 'url': self._transform_rtmp_url(rtmp_video_url),
183 'ext': self._video_extensions.get(format, 'mp4'),
184 'format_id': format,
185 'height': h,
186 'width': w,
187 })
188
189 effTitle = showId + '-' + epTitle + ' part ' + compat_str(partNum+1)
190 results.append({
191 'id': shortMediaId,
192 'formats': formats,
193 'uploader': showId,
194 'upload_date': officialDate,
195 'title': effTitle,
196 'thumbnail': None,
197 'description': compat_str(officialTitle),
198 })
199
200 return results