]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/comedycentral.py
91ebb0ce57136dc0076927acdca4e250774746e1
[youtubedl] / youtube_dl / extractor / comedycentral.py
1 from __future__ import unicode_literals
2
3 import re
4
5 from .mtv import MTVServicesInfoExtractor
6 from ..compat import (
7 compat_str,
8 compat_urllib_parse,
9 )
10 from ..utils import (
11 ExtractorError,
12 float_or_none,
13 unified_strdate,
14 )
15
16
17 class ComedyCentralIE(MTVServicesInfoExtractor):
18 _VALID_URL = r'''(?x)https?://(?:www\.)?cc\.com/
19 (video-clips|episodes|cc-studios|video-collections|full-episodes)
20 /(?P<title>.*)'''
21 _FEED_URL = 'http://comedycentral.com/feeds/mrss/'
22
23 _TEST = {
24 'url': 'http://www.cc.com/video-clips/kllhuv/stand-up-greg-fitzsimmons--uncensored---too-good-of-a-mother',
25 'md5': 'c4f48e9eda1b16dd10add0744344b6d8',
26 'info_dict': {
27 'id': 'cef0cbb3-e776-4bc9-b62e-8016deccb354',
28 'ext': 'mp4',
29 'title': 'CC:Stand-Up|Greg Fitzsimmons: Life on Stage|Uncensored - Too Good of a Mother',
30 'description': 'After a certain point, breastfeeding becomes c**kblocking.',
31 },
32 }
33
34
35 class ComedyCentralShowsIE(MTVServicesInfoExtractor):
36 IE_DESC = 'The Daily Show / The Colbert Report'
37 # urls can be abbreviations like :thedailyshow
38 # urls for episodes like:
39 # or urls for clips like: http://www.thedailyshow.com/watch/mon-december-10-2012/any-given-gun-day
40 # or: http://www.colbertnation.com/the-colbert-report-videos/421667/november-29-2012/moon-shattering-news
41 # or: http://www.colbertnation.com/the-colbert-report-collections/422008/festival-of-lights/79524
42 _VALID_URL = r'''(?x)^(:(?P<shortname>tds|thedailyshow)
43 |https?://(:www\.)?
44 (?P<showname>thedailyshow|thecolbertreport)\.(?:cc\.)?com/
45 ((?:full-)?episodes/(?:[0-9a-z]{6}/)?(?P<episode>.*)|
46 (?P<clip>
47 (?:(?:guests/[^/]+|videos|video-playlists|special-editions|news-team/[^/]+)/[^/]+/(?P<videotitle>[^/?#]+))
48 |(the-colbert-report-(videos|collections)/(?P<clipID>[0-9]+)/[^/]*/(?P<cntitle>.*?))
49 |(watch/(?P<date>[^/]*)/(?P<tdstitle>.*))
50 )|
51 (?P<interview>
52 extended-interviews/(?P<interID>[0-9a-z]+)/
53 (?:playlist_tds_extended_)?(?P<interview_title>[^/?#]*?)
54 (?:/[^/?#]?|[?#]|$))))
55 '''
56 _TESTS = [{
57 'url': 'http://thedailyshow.cc.com/watch/thu-december-13-2012/kristen-stewart',
58 'md5': '4e2f5cb088a83cd8cdb7756132f9739d',
59 'info_dict': {
60 'id': 'ab9ab3e7-5a98-4dbe-8b21-551dc0523d55',
61 'ext': 'mp4',
62 'upload_date': '20121213',
63 'description': 'Kristen Stewart learns to let loose in "On the Road."',
64 'uploader': 'thedailyshow',
65 'title': 'thedailyshow kristen-stewart part 1',
66 }
67 }, {
68 'url': 'http://thedailyshow.cc.com/extended-interviews/b6364d/sarah-chayes-extended-interview',
69 'info_dict': {
70 'id': 'sarah-chayes-extended-interview',
71 '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."',
72 'title': 'thedailyshow Sarah Chayes Extended Interview',
73 },
74 'playlist': [
75 {
76 'info_dict': {
77 'id': '0baad492-cbec-4ec1-9e50-ad91c291127f',
78 'ext': 'mp4',
79 'upload_date': '20150129',
80 '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."',
81 'uploader': 'thedailyshow',
82 'title': 'thedailyshow sarah-chayes-extended-interview part 1',
83 },
84 },
85 {
86 'info_dict': {
87 'id': '1e4fb91b-8ce7-4277-bd7c-98c9f1bbd283',
88 'ext': 'mp4',
89 'upload_date': '20150129',
90 '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."',
91 'uploader': 'thedailyshow',
92 'title': 'thedailyshow sarah-chayes-extended-interview part 2',
93 },
94 },
95 ],
96 'params': {
97 'skip_download': True,
98 },
99 }, {
100 'url': 'http://thedailyshow.cc.com/extended-interviews/xm3fnq/andrew-napolitano-extended-interview',
101 'only_matching': True,
102 }, {
103 'url': 'http://thecolbertreport.cc.com/videos/29w6fx/-realhumanpraise-for-fox-news',
104 'only_matching': True,
105 }, {
106 'url': 'http://thecolbertreport.cc.com/videos/gh6urb/neil-degrasse-tyson-pt--1?xrs=eml_col_031114',
107 'only_matching': True,
108 }, {
109 'url': 'http://thedailyshow.cc.com/guests/michael-lewis/3efna8/exclusive---michael-lewis-extended-interview-pt--3',
110 'only_matching': True,
111 }, {
112 'url': 'http://thedailyshow.cc.com/episodes/sy7yv0/april-8--2014---denis-leary',
113 'only_matching': True,
114 }, {
115 'url': 'http://thecolbertreport.cc.com/episodes/8ase07/april-8--2014---jane-goodall',
116 'only_matching': True,
117 }, {
118 'url': 'http://thedailyshow.cc.com/video-playlists/npde3s/the-daily-show-19088-highlights',
119 'only_matching': True,
120 }, {
121 'url': 'http://thedailyshow.cc.com/video-playlists/t6d9sg/the-daily-show-20038-highlights/be3cwo',
122 'only_matching': True,
123 }, {
124 'url': 'http://thedailyshow.cc.com/special-editions/2l8fdb/special-edition---a-look-back-at-food',
125 'only_matching': True,
126 }, {
127 'url': 'http://thedailyshow.cc.com/news-team/michael-che/7wnfel/we-need-to-talk-about-israel',
128 'only_matching': True,
129 }]
130
131 _available_formats = ['3500', '2200', '1700', '1200', '750', '400']
132
133 _video_extensions = {
134 '3500': 'mp4',
135 '2200': 'mp4',
136 '1700': 'mp4',
137 '1200': 'mp4',
138 '750': 'mp4',
139 '400': 'mp4',
140 }
141 _video_dimensions = {
142 '3500': (1280, 720),
143 '2200': (960, 540),
144 '1700': (768, 432),
145 '1200': (640, 360),
146 '750': (512, 288),
147 '400': (384, 216),
148 }
149
150 def _real_extract(self, url):
151 mobj = re.match(self._VALID_URL, url)
152
153 if mobj.group('shortname'):
154 if mobj.group('shortname') in ('tds', 'thedailyshow'):
155 url = 'http://thedailyshow.cc.com/full-episodes/'
156 else:
157 url = 'http://thecolbertreport.cc.com/full-episodes/'
158 mobj = re.match(self._VALID_URL, url, re.VERBOSE)
159 assert mobj is not None
160
161 if mobj.group('clip'):
162 if mobj.group('videotitle'):
163 epTitle = mobj.group('videotitle')
164 elif mobj.group('showname') == 'thedailyshow':
165 epTitle = mobj.group('tdstitle')
166 else:
167 epTitle = mobj.group('cntitle')
168 dlNewest = False
169 elif mobj.group('interview'):
170 epTitle = mobj.group('interview_title')
171 dlNewest = False
172 else:
173 dlNewest = not mobj.group('episode')
174 if dlNewest:
175 epTitle = mobj.group('showname')
176 else:
177 epTitle = mobj.group('episode')
178 show_name = mobj.group('showname')
179
180 webpage, htmlHandle = self._download_webpage_handle(url, epTitle)
181 if dlNewest:
182 url = htmlHandle.geturl()
183 mobj = re.match(self._VALID_URL, url, re.VERBOSE)
184 if mobj is None:
185 raise ExtractorError('Invalid redirected URL: ' + url)
186 if mobj.group('episode') == '':
187 raise ExtractorError('Redirected URL is still not specific: ' + url)
188 epTitle = (mobj.group('episode') or mobj.group('videotitle')).rpartition('/')[-1]
189
190 mMovieParams = re.findall('(?:<param name="movie" value="|var url = ")(http://media.mtvnservices.com/([^"]*(?:episode|video).*?:.*?))"', webpage)
191 if len(mMovieParams) == 0:
192 # The Colbert Report embeds the information in a without
193 # a URL prefix; so extract the alternate reference
194 # and then add the URL prefix manually.
195
196 altMovieParams = re.findall('data-mgid="([^"]*(?:episode|video|playlist).*?:.*?)"', webpage)
197 if len(altMovieParams) == 0:
198 raise ExtractorError('unable to find Flash URL in webpage ' + url)
199 else:
200 mMovieParams = [("http://media.mtvnservices.com/" + altMovieParams[0], altMovieParams[0])]
201
202 uri = mMovieParams[0][1]
203 # Correct cc.com in uri
204 uri = re.sub(r'(episode:[^.]+)(\.cc)?\.com', r'\1.com', uri)
205
206 index_url = 'http://%s.cc.com/feeds/mrss?%s' % (show_name, compat_urllib_parse.urlencode({'uri': uri}))
207 idoc = self._download_xml(
208 index_url, epTitle,
209 'Downloading show index', 'Unable to download episode index')
210
211 title = idoc.find('./channel/title').text
212 description = idoc.find('./channel/description').text
213
214 entries = []
215 item_els = idoc.findall('.//item')
216 for part_num, itemEl in enumerate(item_els):
217 upload_date = unified_strdate(itemEl.findall('./pubDate')[0].text)
218 thumbnail = itemEl.find('.//{http://search.yahoo.com/mrss/}thumbnail').attrib.get('url')
219
220 content = itemEl.find('.//{http://search.yahoo.com/mrss/}content')
221 duration = float_or_none(content.attrib.get('duration'))
222 mediagen_url = content.attrib['url']
223 guid = itemEl.find('./guid').text.rpartition(':')[-1]
224
225 cdoc = self._download_xml(
226 mediagen_url, epTitle,
227 'Downloading configuration for segment %d / %d' % (part_num + 1, len(item_els)))
228
229 turls = []
230 for rendition in cdoc.findall('.//rendition'):
231 finfo = (rendition.attrib['bitrate'], rendition.findall('./src')[0].text)
232 turls.append(finfo)
233
234 formats = []
235 for format, rtmp_video_url in turls:
236 w, h = self._video_dimensions.get(format, (None, None))
237 formats.append({
238 'format_id': 'vhttp-%s' % format,
239 'url': self._transform_rtmp_url(rtmp_video_url),
240 'ext': self._video_extensions.get(format, 'mp4'),
241 'height': h,
242 'width': w,
243 })
244 formats.append({
245 'format_id': 'rtmp-%s' % format,
246 'url': rtmp_video_url.replace('viacomccstrm', 'viacommtvstrm'),
247 'ext': self._video_extensions.get(format, 'mp4'),
248 'height': h,
249 'width': w,
250 })
251 self._sort_formats(formats)
252
253 subtitles = self._extract_subtitles(cdoc, guid)
254
255 virtual_id = show_name + ' ' + epTitle + ' part ' + compat_str(part_num + 1)
256 entries.append({
257 'id': guid,
258 'title': virtual_id,
259 'formats': formats,
260 'uploader': show_name,
261 'upload_date': upload_date,
262 'duration': duration,
263 'thumbnail': thumbnail,
264 'description': description,
265 'subtitles': subtitles,
266 })
267
268 return {
269 '_type': 'playlist',
270 'id': epTitle,
271 'entries': entries,
272 'title': show_name + ' ' + title,
273 'description': description,
274 }