4e96e78c34312c382345e974cd66cbfcfd21ae57
[youtube-dl] / youtube_dl / extractor / nbc.py
1 from __future__ import unicode_literals
2
3 import re
4
5 from .common import InfoExtractor
6 from .theplatform import ThePlatformIE
7 from ..utils import (
8     find_xpath_attr,
9     lowercase_escape,
10     smuggle_url,
11     unescapeHTML,
12     update_url_query,
13 )
14
15
16 class NBCIE(InfoExtractor):
17     _VALID_URL = r'https?://(?:www\.)?nbc\.com/(?:[^/]+/)+(?P<id>n?\d+)'
18
19     _TESTS = [
20         {
21             'url': 'http://www.nbc.com/the-tonight-show/segments/112966',
22             'info_dict': {
23                 'id': '112966',
24                 'ext': 'mp4',
25                 'title': 'Jimmy Fallon Surprises Fans at Ben & Jerry\'s',
26                 'description': 'Jimmy gives out free scoops of his new "Tonight Dough" ice cream flavor by surprising customers at the Ben & Jerry\'s scoop shop.',
27                 'timestamp': 1424246400,
28                 'upload_date': '20150218',
29                 'uploader': 'NBCU-COM',
30             },
31             'params': {
32                 # m3u8 download
33                 'skip_download': True,
34             },
35         },
36         {
37             'url': 'http://www.nbc.com/the-tonight-show/episodes/176',
38             'info_dict': {
39                 'id': '176',
40                 'ext': 'flv',
41                 'title': 'Ricky Gervais, Steven Van Zandt, ILoveMakonnen',
42                 'description': 'A brand new episode of The Tonight Show welcomes Ricky Gervais, Steven Van Zandt and ILoveMakonnen.',
43             },
44             'skip': '404 Not Found',
45         },
46         {
47             'url': 'http://www.nbc.com/saturday-night-live/video/star-wars-teaser/2832821',
48             'info_dict': {
49                 'id': '2832821',
50                 'ext': 'mp4',
51                 'title': 'Star Wars Teaser',
52                 'description': 'md5:0b40f9cbde5b671a7ff62fceccc4f442',
53                 'timestamp': 1417852800,
54                 'upload_date': '20141206',
55                 'uploader': 'NBCU-COM',
56             },
57             'params': {
58                 # m3u8 download
59                 'skip_download': True,
60             },
61             'skip': 'Only works from US',
62         },
63         {
64             # This video has expired but with an escaped embedURL
65             'url': 'http://www.nbc.com/parenthood/episode-guide/season-5/just-like-at-home/515',
66             'only_matching': True,
67         },
68         {
69             # HLS streams requires the 'hdnea3' cookie
70             'url': 'http://www.nbc.com/Kings/video/goliath/n1806',
71             'info_dict': {
72                 'id': 'n1806',
73                 'ext': 'mp4',
74                 'title': 'Goliath',
75                 'description': 'When an unknown soldier saves the life of the King\'s son in battle, he\'s thrust into the limelight and politics of the kingdom.',
76                 'timestamp': 1237100400,
77                 'upload_date': '20090315',
78                 'uploader': 'NBCU-COM',
79             },
80             'params': {
81                 'skip_download': True,
82             },
83             'skip': 'Only works from US',
84         }
85     ]
86
87     def _real_extract(self, url):
88         video_id = self._match_id(url)
89         webpage = self._download_webpage(url, video_id)
90         theplatform_url = unescapeHTML(lowercase_escape(self._html_search_regex(
91             [
92                 r'(?:class="video-player video-player-full" data-mpx-url|class="player" src)="(.*?)"',
93                 r'<iframe[^>]+src="((?:https?:)?//player\.theplatform\.com/[^"]+)"',
94                 r'"embedURL"\s*:\s*"([^"]+)"'
95             ],
96             webpage, 'theplatform url').replace('_no_endcard', '').replace('\\/', '/')))
97         if theplatform_url.startswith('//'):
98             theplatform_url = 'http:' + theplatform_url
99         return {
100             '_type': 'url_transparent',
101             'ie_key': 'ThePlatform',
102             'url': smuggle_url(theplatform_url, {'source_url': url}),
103             'id': video_id,
104         }
105
106
107 class NBCSportsVPlayerIE(InfoExtractor):
108     _VALID_URL = r'https?://vplayer\.nbcsports\.com/(?:[^/]+/)+(?P<id>[0-9a-zA-Z_]+)'
109
110     _TESTS = [{
111         'url': 'https://vplayer.nbcsports.com/p/BxmELC/nbcsports_share/select/9CsDKds0kvHI',
112         'info_dict': {
113             'id': '9CsDKds0kvHI',
114             'ext': 'flv',
115             'description': 'md5:df390f70a9ba7c95ff1daace988f0d8d',
116             'title': 'Tyler Kalinoski hits buzzer-beater to lift Davidson',
117             'timestamp': 1426270238,
118             'upload_date': '20150313',
119             'uploader': 'NBCU-SPORTS',
120         }
121     }, {
122         'url': 'http://vplayer.nbcsports.com/p/BxmELC/nbc_embedshare/select/_hqLjQ95yx8Z',
123         'only_matching': True,
124     }]
125
126     @staticmethod
127     def _extract_url(webpage):
128         iframe_m = re.search(
129             r'<iframe[^>]+src="(?P<url>https?://vplayer\.nbcsports\.com/[^"]+)"', webpage)
130         if iframe_m:
131             return iframe_m.group('url')
132
133     def _real_extract(self, url):
134         video_id = self._match_id(url)
135         webpage = self._download_webpage(url, video_id)
136         theplatform_url = self._og_search_video_url(webpage)
137         return self.url_result(theplatform_url, 'ThePlatform')
138
139
140 class NBCSportsIE(InfoExtractor):
141     # Does not include https because its certificate is invalid
142     _VALID_URL = r'https?://(?:www\.)?nbcsports\.com//?(?:[^/]+/)+(?P<id>[0-9a-z-]+)'
143
144     _TEST = {
145         'url': 'http://www.nbcsports.com//college-basketball/ncaab/tom-izzo-michigan-st-has-so-much-respect-duke',
146         'info_dict': {
147             'id': 'PHJSaFWbrTY9',
148             'ext': 'flv',
149             'title': 'Tom Izzo, Michigan St. has \'so much respect\' for Duke',
150             'description': 'md5:ecb459c9d59e0766ac9c7d5d0eda8113',
151             'uploader': 'NBCU-SPORTS',
152             'upload_date': '20150330',
153             'timestamp': 1427726529,
154         }
155     }
156
157     def _real_extract(self, url):
158         video_id = self._match_id(url)
159         webpage = self._download_webpage(url, video_id)
160         return self.url_result(
161             NBCSportsVPlayerIE._extract_url(webpage), 'NBCSportsVPlayer')
162
163
164 class CSNNEIE(InfoExtractor):
165     _VALID_URL = r'https?://(?:www\.)?csnne\.com/video/(?P<id>[0-9a-z-]+)'
166
167     _TEST = {
168         'url': 'http://www.csnne.com/video/snc-evening-update-wright-named-red-sox-no-5-starter',
169         'info_dict': {
170             'id': 'yvBLLUgQ8WU0',
171             'ext': 'mp4',
172             'title': 'SNC evening update: Wright named Red Sox\' No. 5 starter.',
173             'description': 'md5:1753cfee40d9352b19b4c9b3e589b9e3',
174             'timestamp': 1459369979,
175             'upload_date': '20160330',
176             'uploader': 'NBCU-SPORTS',
177         }
178     }
179
180     def _real_extract(self, url):
181         display_id = self._match_id(url)
182         webpage = self._download_webpage(url, display_id)
183         return {
184             '_type': 'url_transparent',
185             'ie_key': 'ThePlatform',
186             'url': self._html_search_meta('twitter:player:stream', webpage),
187             'display_id': display_id,
188         }
189
190
191 class NBCNewsIE(ThePlatformIE):
192     _VALID_URL = r'''(?x)https?://(?:www\.)?(?:nbcnews|today|msnbc)\.com/
193         (?:video/.+?/(?P<id>\d+)|
194         ([^/]+/)*(?:.*-)?(?P<mpx_id>[^/?]+))
195         '''
196
197     _TESTS = [
198         {
199             'url': 'http://www.nbcnews.com/video/nbc-news/52753292',
200             'md5': '47abaac93c6eaf9ad37ee6c4463a5179',
201             'info_dict': {
202                 'id': '52753292',
203                 'ext': 'flv',
204                 'title': 'Crew emerges after four-month Mars food study',
205                 'description': 'md5:24e632ffac72b35f8b67a12d1b6ddfc1',
206             },
207         },
208         {
209             'url': 'http://www.nbcnews.com/watch/nbcnews-com/how-twitter-reacted-to-the-snowden-interview-269389891880',
210             'md5': 'af1adfa51312291a017720403826bb64',
211             'info_dict': {
212                 'id': 'p_tweet_snow_140529',
213                 'ext': 'mp4',
214                 'title': 'How Twitter Reacted To The Snowden Interview',
215                 'description': 'md5:65a0bd5d76fe114f3c2727aa3a81fe64',
216                 'uploader': 'NBCU-NEWS',
217                 'timestamp': 1401363060,
218                 'upload_date': '20140529',
219             },
220         },
221         {
222             'url': 'http://www.nbcnews.com/feature/dateline-full-episodes/full-episode-family-business-n285156',
223             'md5': 'fdbf39ab73a72df5896b6234ff98518a',
224             'info_dict': {
225                 'id': '529953347624',
226                 'ext': 'mp4',
227                 'title': 'FULL EPISODE: Family Business',
228                 'description': 'md5:757988edbaae9d7be1d585eb5d55cc04',
229             },
230             'skip': 'This page is unavailable.',
231         },
232         {
233             'url': 'http://www.nbcnews.com/nightly-news/video/nightly-news-with-brian-williams-full-broadcast-february-4-394064451844',
234             'md5': '73135a2e0ef819107bbb55a5a9b2a802',
235             'info_dict': {
236                 'id': 'nn_netcast_150204',
237                 'ext': 'mp4',
238                 'title': 'Nightly News with Brian Williams Full Broadcast (February 4)',
239                 'description': 'md5:1c10c1eccbe84a26e5debb4381e2d3c5',
240                 'timestamp': 1423104900,
241                 'uploader': 'NBCU-NEWS',
242                 'upload_date': '20150205',
243             },
244         },
245         {
246             'url': 'http://www.nbcnews.com/business/autos/volkswagen-11-million-vehicles-could-have-suspect-software-emissions-scandal-n431456',
247             'md5': 'a49e173825e5fcd15c13fc297fced39d',
248             'info_dict': {
249                 'id': 'x_lon_vwhorn_150922',
250                 'ext': 'mp4',
251                 'title': 'Volkswagen U.S. Chief:\xa0 We Have Totally Screwed Up',
252                 'description': 'md5:c8be487b2d80ff0594c005add88d8351',
253                 'upload_date': '20150922',
254                 'timestamp': 1442917800,
255                 'uploader': 'NBCU-NEWS',
256             },
257         },
258         {
259             'url': 'http://www.today.com/video/see-the-aurora-borealis-from-space-in-stunning-new-nasa-video-669831235788',
260             'md5': '118d7ca3f0bea6534f119c68ef539f71',
261             'info_dict': {
262                 'id': 'tdy_al_space_160420',
263                 'ext': 'mp4',
264                 'title': 'See the aurora borealis from space in stunning new NASA video',
265                 'description': 'md5:74752b7358afb99939c5f8bb2d1d04b1',
266                 'upload_date': '20160420',
267                 'timestamp': 1461152093,
268                 'uploader': 'NBCU-NEWS',
269             },
270         },
271         {
272             'url': 'http://www.msnbc.com/all-in-with-chris-hayes/watch/the-chaotic-gop-immigration-vote-314487875924',
273             'md5': '6d236bf4f3dddc226633ce6e2c3f814d',
274             'info_dict': {
275                 'id': 'n_hayes_Aimm_140801_272214',
276                 'ext': 'mp4',
277                 'title': 'The chaotic GOP immigration vote',
278                 'description': 'The Republican House votes on a border bill that has no chance of getting through the Senate or signed by the President and is drawing criticism from all sides.',
279                 'thumbnail': 're:^https?://.*\.jpg$',
280                 'timestamp': 1406937606,
281                 'upload_date': '20140802',
282                 'uploader': 'NBCU-NEWS',
283             },
284         },
285         {
286             'url': 'http://www.nbcnews.com/watch/dateline/full-episode--deadly-betrayal-386250819952',
287             'only_matching': True,
288         },
289         {
290             # From http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html
291             'url': 'http://www.nbcnews.com/widget/video-embed/701714499682',
292             'only_matching': True,
293         },
294     ]
295
296     def _real_extract(self, url):
297         mobj = re.match(self._VALID_URL, url)
298         video_id = mobj.group('id')
299         if video_id is not None:
300             all_info = self._download_xml('http://www.nbcnews.com/id/%s/displaymode/1219' % video_id, video_id)
301             info = all_info.find('video')
302
303             return {
304                 'id': video_id,
305                 'title': info.find('headline').text,
306                 'ext': 'flv',
307                 'url': find_xpath_attr(info, 'media', 'type', 'flashVideo').text,
308                 'description': info.find('caption').text,
309                 'thumbnail': find_xpath_attr(info, 'media', 'type', 'thumbnail').text,
310             }
311         else:
312             # "feature" and "nightly-news" pages use theplatform.com
313             video_id = mobj.group('mpx_id')
314             webpage = self._download_webpage(url, video_id)
315
316             filter_param = 'byId'
317             bootstrap_json = self._search_regex(
318                 [r'(?m)(?:var\s+(?:bootstrapJson|playlistData)|NEWS\.videoObj)\s*=\s*({.+});?\s*$',
319                  r'videoObj\s*:\s*({.+})', r'data-video="([^"]+)"',
320                  r'jQuery\.extend\(Drupal\.settings\s*,\s*({.+?})\);'],
321                 webpage, 'bootstrap json', default=None)
322             if bootstrap_json:
323                 bootstrap = self._parse_json(
324                     bootstrap_json, video_id, transform_source=unescapeHTML)
325
326                 info = None
327                 if 'results' in bootstrap:
328                     info = bootstrap['results'][0]['video']
329                 elif 'video' in bootstrap:
330                     info = bootstrap['video']
331                 elif 'msnbcVideoInfo' in bootstrap:
332                     info = bootstrap['msnbcVideoInfo']['meta']
333                 elif 'msnbcThePlatform' in bootstrap:
334                     info = bootstrap['msnbcThePlatform']['videoPlayer']['video']
335                 else:
336                     info = bootstrap
337
338                 if 'guid' in info:
339                     video_id = info['guid']
340                     filter_param = 'byGuid'
341                 elif 'mpxId' in info:
342                     video_id = info['mpxId']
343
344             return {
345                 '_type': 'url_transparent',
346                 'id': video_id,
347                 # http://feed.theplatform.com/f/2E2eJC/nbcnews also works
348                 'url': update_url_query('http://feed.theplatform.com/f/2E2eJC/nnd_NBCNews', {filter_param: video_id}),
349                 'ie_key': 'ThePlatformFeed',
350             }
351
352
353 class NBCOlympicsIE(InfoExtractor):
354     _VALID_URL = r'https?://www\.nbcolympics\.com/video/(?P<id>[a-z-]+)'
355
356     _TEST = {
357         # Geo-restricted to US
358         'url': 'http://www.nbcolympics.com/video/justin-roses-son-leo-was-tears-after-his-dad-won-gold',
359         'md5': '54fecf846d05429fbaa18af557ee523a',
360         'info_dict': {
361             'id': 'WjTBzDXx5AUq',
362             'display_id': 'justin-roses-son-leo-was-tears-after-his-dad-won-gold',
363             'ext': 'mp4',
364             'title': 'Rose\'s son Leo was in tears after his dad won gold',
365             'description': 'Olympic gold medalist Justin Rose gets emotional talking to the impact his win in men\'s golf has already had on his children.',
366             'timestamp': 1471274964,
367             'upload_date': '20160815',
368             'uploader': 'NBCU-SPORTS',
369         },
370     }
371
372     def _real_extract(self, url):
373         display_id = self._match_id(url)
374
375         webpage = self._download_webpage(url, display_id)
376
377         drupal_settings = self._parse_json(self._search_regex(
378             r'jQuery\.extend\(Drupal\.settings\s*,\s*({.+?})\);',
379             webpage, 'drupal settings'), display_id)
380
381         iframe_url = drupal_settings['vod']['iframe_url']
382         theplatform_url = iframe_url.replace(
383             'vplayer.nbcolympics.com', 'player.theplatform.com')
384
385         return {
386             '_type': 'url_transparent',
387             'url': theplatform_url,
388             'ie_key': ThePlatformIE.ie_key(),
389             'display_id': display_id,
390         }