]>
jfr.im git - yt-dlp.git/blob - youtube_dl/extractor/nbc.py
1 from __future__
import unicode_literals
5 from . common
import InfoExtractor
6 from .. compat
import compat_HTTPError
16 class NBCIE ( InfoExtractor
):
17 _VALID_URL
= r
'https?://www\.nbc\.com/(?:[^/]+/)+(?P<id>n?\d+)'
21 'url' : 'http://www.nbc.com/the-tonight-show/segments/112966' ,
22 # md5 checksum is not stable
26 'title' : 'Jimmy Fallon Surprises Fans at Ben & Jerry \' s' ,
27 'description' : 'Jimmy gives out free scoops of his new "Tonight Dough" ice cream flavor by surprising customers at the Ben & Jerry \' s scoop shop.' ,
31 'url' : 'http://www.nbc.com/the-tonight-show/episodes/176' ,
35 'title' : 'Ricky Gervais, Steven Van Zandt, ILoveMakonnen' ,
36 'description' : 'A brand new episode of The Tonight Show welcomes Ricky Gervais, Steven Van Zandt and ILoveMakonnen.' ,
38 'skip' : 'Only works from US' ,
41 'url' : 'http://www.nbc.com/saturday-night-live/video/star-wars-teaser/2832821' ,
45 'title' : 'Star Wars Teaser' ,
46 'description' : 'md5:0b40f9cbde5b671a7ff62fceccc4f442' ,
48 'skip' : 'Only works from US' ,
51 # This video has expired but with an escaped embedURL
52 'url' : 'http://www.nbc.com/parenthood/episode-guide/season-5/just-like-at-home/515' ,
57 def _real_extract ( self
, url
):
58 video_id
= self
._ match
_ id
( url
)
59 webpage
= self
._ download
_ webpage
( url
, video_id
)
60 theplatform_url
= unescapeHTML ( lowercase_escape ( self
._ html
_ search
_ regex
(
62 r
'(?:class="video-player video-player-full" data-mpx-url|class="player" src)="(.*?)"' ,
63 r
'<iframe[^>]+src="((?:https?:)?//player\.theplatform\.com/[^"]+)"' ,
64 r
'"embedURL"\s*:\s*"([^"]+)"'
66 webpage
, 'theplatform url' ). replace ( '_no_endcard' , '' ). replace ( ' \\ /' , '/' )))
67 if theplatform_url
. startswith ( '//' ):
68 theplatform_url
= 'http:' + theplatform_url
69 return self
. url_result ( smuggle_url ( theplatform_url
, {'source_url': url}
))
72 class NBCSportsVPlayerIE ( InfoExtractor
):
73 _VALID_URL
= r
'https?://vplayer\.nbcsports\.com/(?:[^/]+/)+(?P<id>[0-9a-zA-Z_]+)'
76 'url' : 'https://vplayer.nbcsports.com/p/BxmELC/nbcsports_share/select/9CsDKds0kvHI' ,
80 'description' : 'md5:df390f70a9ba7c95ff1daace988f0d8d' ,
81 'title' : 'Tyler Kalinoski hits buzzer-beater to lift Davidson' ,
84 'url' : 'http://vplayer.nbcsports.com/p/BxmELC/nbc_embedshare/select/_hqLjQ95yx8Z' ,
85 'only_matching' : True ,
89 def _extract_url ( webpage
):
91 r
'<iframe[^>]+src="(?P<url>https?://vplayer\.nbcsports\.com/[^"]+)"' , webpage
)
93 return iframe_m
. group ( 'url' )
95 def _real_extract ( self
, url
):
96 video_id
= self
._ match
_ id
( url
)
97 webpage
= self
._ download
_ webpage
( url
, video_id
)
98 theplatform_url
= self
._ og
_ search
_ video
_u rl
( webpage
)
99 return self
. url_result ( theplatform_url
, 'ThePlatform' )
102 class NBCSportsIE ( InfoExtractor
):
103 # Does not include https becuase its certificate is invalid
104 _VALID_URL
= r
'http://www\.nbcsports\.com//?(?:[^/]+/)+(?P<id>[0-9a-z-]+)'
107 'url' : 'http://www.nbcsports.com//college-basketball/ncaab/tom-izzo-michigan-st-has-so-much-respect-duke' ,
109 'id' : 'PHJSaFWbrTY9' ,
111 'title' : 'Tom Izzo, Michigan St. has \' so much respect \' for Duke' ,
112 'description' : 'md5:ecb459c9d59e0766ac9c7d5d0eda8113' ,
116 def _real_extract ( self
, url
):
117 video_id
= self
._ match
_ id
( url
)
118 webpage
= self
._ download
_ webpage
( url
, video_id
)
119 return self
. url_result (
120 NBCSportsVPlayerIE
._ extract
_u rl
( webpage
), 'NBCSportsVPlayer' )
123 class NBCNewsIE ( InfoExtractor
):
124 _VALID_URL
= r
'''(?x)https?://(?:www\.)?nbcnews\.com/
125 (?:video/.+?/(?P<id>\d+)|
126 (?:watch|feature|nightly-news)/[^/]+/(?P<title>.+))
131 'url' : 'http://www.nbcnews.com/video/nbc-news/52753292' ,
132 'md5' : '47abaac93c6eaf9ad37ee6c4463a5179' ,
136 'title' : 'Crew emerges after four-month Mars food study' ,
137 'description' : 'md5:24e632ffac72b35f8b67a12d1b6ddfc1' ,
141 'url' : 'http://www.nbcnews.com/feature/edward-snowden-interview/how-twitter-reacted-snowden-interview-n117236' ,
142 'md5' : 'b2421750c9f260783721d898f4c42063' ,
144 'id' : 'I1wpAI_zmhsQ' ,
146 'title' : 'How Twitter Reacted To The Snowden Interview' ,
147 'description' : 'md5:65a0bd5d76fe114f3c2727aa3a81fe64' ,
149 'add_ie' : [ 'ThePlatform' ],
152 'url' : 'http://www.nbcnews.com/feature/dateline-full-episodes/full-episode-family-business-n285156' ,
153 'md5' : 'fdbf39ab73a72df5896b6234ff98518a' ,
155 'id' : 'Wjf9EDR3A_60' ,
157 'title' : 'FULL EPISODE: Family Business' ,
158 'description' : 'md5:757988edbaae9d7be1d585eb5d55cc04' ,
162 'url' : 'http://www.nbcnews.com/nightly-news/video/nightly-news-with-brian-williams-full-broadcast-february-4-394064451844' ,
163 'md5' : 'b5dda8cddd8650baa0dcb616dd2cf60d' ,
165 'id' : 'sekXqyTVnmN3' ,
167 'title' : 'Nightly News with Brian Williams Full Broadcast (February 4)' ,
168 'description' : 'md5:1c10c1eccbe84a26e5debb4381e2d3c5' ,
172 'url' : 'http://www.nbcnews.com/watch/dateline/full-episode--deadly-betrayal-386250819952' ,
173 'only_matching' : True ,
177 def _real_extract ( self
, url
):
178 mobj
= re
. match ( self
._ VALID
_U RL
, url
)
179 video_id
= mobj
. group ( 'id' )
180 if video_id
is not None :
181 all_info
= self
._ download
_ xml
( 'http://www.nbcnews.com/id/ %s /displaymode/1219' % video_id
, video_id
)
182 info
= all_info
. find ( 'video' )
186 'title' : info
. find ( 'headline' ). text
,
188 'url' : find_xpath_attr ( info
, 'media' , 'type' , 'flashVideo' ). text
,
189 'description' : info
. find ( 'caption' ). text
,
190 'thumbnail' : find_xpath_attr ( info
, 'media' , 'type' , 'thumbnail' ). text
,
193 # "feature" and "nightly-news" pages use theplatform.com
194 title
= mobj
. group ( 'title' )
195 webpage
= self
._ download
_ webpage
( url
, title
)
196 bootstrap_json
= self
._ search
_ regex
(
197 r
'var\s+(?:bootstrapJson|playlistData)\s*=\s*( {.+} );?\s*$' ,
198 webpage
, 'bootstrap json' , flags
= re
. MULTILINE
)
199 bootstrap
= self
._ parse
_ json
( bootstrap_json
, video_id
)
200 info
= bootstrap
[ 'results' ][ 0 ][ 'video' ]
201 mpxid
= info
[ 'mpxId' ]
204 info
[ 'fallbackPlaylistUrl' ],
205 info
[ 'associatedPlaylistUrl' ],
208 for base_url
in base_urls
:
211 playlist_url
= base_url
+ '?form=MPXNBCNewsAPI'
214 all_videos
= self
._ download
_ json
( playlist_url
, title
)
215 except ExtractorError
as ee
:
216 if isinstance ( ee
. cause
, compat_HTTPError
):
220 if not all_videos
or 'videos' not in all_videos
:
224 info
= next ( v
for v
in all_videos
[ 'videos' ] if v
[ 'mpxId' ] == mpxid
)
226 except StopIteration :
230 raise ExtractorError ( 'Could not find video in playlists' )
234 # We get the best quality video
235 'url' : info
[ 'videoAssets' ][- 1 ][ 'publicUrl' ],
236 'ie_key' : 'ThePlatform' ,
240 class MSNBCIE ( InfoExtractor
):
241 # https URLs redirect to corresponding http ones
242 _VALID_URL
= r
'http://www\.msnbc\.com/[^/]+/watch/(?P<id>[^/]+)'
244 'url' : 'http://www.msnbc.com/all-in-with-chris-hayes/watch/the-chaotic-gop-immigration-vote-314487875924' ,
245 'md5' : '6d236bf4f3dddc226633ce6e2c3f814d' ,
247 'id' : 'n_hayes_Aimm_140801_272214' ,
249 'title' : 'The chaotic GOP immigration vote' ,
250 'description' : 'The Republican House votes on a border bill that has no chance of getting through the Senate or signed by the President and is drawing criticism from all sides.' ,
251 'thumbnail' : 're:^https?://.*\.jpg$' ,
252 'timestamp' : 1406937606 ,
253 'upload_date' : '20140802' ,
254 'categories' : [ 'MSNBC/Topics/Franchise/Best of last night' , 'MSNBC/Topics/General/Congress' ],
258 def _real_extract ( self
, url
):
259 video_id
= self
._ match
_ id
( url
)
260 webpage
= self
._ download
_ webpage
( url
, video_id
)
261 embed_url
= self
._ html
_ search
_ meta
( 'embedURL' , webpage
)
262 return self
. url_result ( embed_url
)