]>
Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/cnn.py
1 from __future__
import unicode_literals
5 from . common
import InfoExtractor
6 from . turner
import TurnerBaseIE
7 from .. utils
import url_basename
10 class CNNIE ( TurnerBaseIE
):
11 _VALID_URL
= r
'''(?x)https?://(?:(?P<sub_domain>edition|www|money)\.)?cnn\.com/(?:video/(?:data/.+?|\?)/)?videos?/
12 (?P<path>.+?/(?P<title>[^/]+?)(?:\.(?:[a-z\-]+)|(?=&)))'''
15 'url' : 'http://edition.cnn.com/video/?/video/sports/2013/06/09/nadal-1-on-1.cnn' ,
16 'md5' : '3e6121ea48df7e2259fe73a0628605c4' ,
18 'id' : 'sports/2013/06/09/nadal-1-on-1.cnn' ,
20 'title' : 'Nadal wins 8th French Open title' ,
21 'description' : 'World Sport \' s Amanda Davies chats with 2013 French Open champion Rafael Nadal.' ,
23 'upload_date' : '20130609' ,
25 'expected_warnings' : [ 'Failed to download m3u8 information' ],
27 'url' : 'http://edition.cnn.com/video/?/video/us/2013/08/21/sot-student-gives-epic-speech.georgia-institute-of-technology&utm_source=feedburner&utm_medium=feed&utm_campaign=Feed%3A+rss%2Fcnn_topstories+%28RSS%3A+Top+Stories%29' ,
28 'md5' : 'b5cc60c60a3477d185af8f19a2a26f4e' ,
30 'id' : 'us/2013/08/21/sot-student-gives-epic-speech.georgia-institute-of-technology' ,
32 'title' : "Student's epic speech stuns new freshmen" ,
33 'description' : "A Georgia Tech student welcomes the incoming freshmen with an epic speech backed by music from \" 2001: A Space Odyssey. \" " ,
34 'upload_date' : '20130821' ,
36 'expected_warnings' : [ 'Failed to download m3u8 information' ],
38 'url' : 'http://www.cnn.com/video/data/2.0/video/living/2014/12/22/growing-america-nashville-salemtown-board-episode-1.hln.html' ,
39 'md5' : 'f14d02ebd264df951feb2400e2c25a1b' ,
41 'id' : 'living/2014/12/22/growing-america-nashville-salemtown-board-episode-1.hln' ,
43 'title' : 'Nashville Ep. 1: Hand crafted skateboards' ,
44 'description' : 'md5:e7223a503315c9f150acac52e76de086' ,
45 'upload_date' : '20141222' ,
47 'expected_warnings' : [ 'Failed to download m3u8 information' ],
49 'url' : 'http://money.cnn.com/video/news/2016/08/19/netflix-stunning-stats.cnnmoney/index.html' ,
50 'md5' : '52a515dc1b0f001cd82e4ceda32be9d1' ,
52 'id' : '/video/news/2016/08/19/netflix-stunning-stats.cnnmoney' ,
54 'title' : '5 stunning stats about Netflix' ,
55 'description' : 'Did you know that Netflix has more than 80 million members? Here are five facts about the online video distributor that you probably didn \' t know.' ,
56 'upload_date' : '20160819' ,
60 'skip_download' : True ,
63 'url' : 'http://cnn.com/video/?/video/politics/2015/03/27/pkg-arizona-senator-church-attendance-mandatory.ktvk' ,
64 'only_matching' : True ,
66 'url' : 'http://cnn.com/video/?/video/us/2015/04/06/dnt-baker-refuses-anti-gay-order.wkmg' ,
67 'only_matching' : True ,
69 'url' : 'http://edition.cnn.com/videos/arts/2016/04/21/olympic-games-cultural-a-z-brazil.cnn' ,
70 'only_matching' : True ,
74 # http://edition.cnn.com/.element/apps/cvp/3.0/cfg/spider/cnn/expansion/config.xml
76 'data_src' : 'http://edition.cnn.com/video/data/3.0/video/ %s /index.xml' ,
77 'media_src' : 'http://pmd.cdn.turner.com/cnn/big' ,
79 # http://money.cnn.com/.element/apps/cvp2/cfg/config.xml
81 'data_src' : 'http://money.cnn.com/video/data/4.0/video/ %s .xml' ,
82 'media_src' : 'http://ht3.cdn.turner.com/money/big' ,
86 def _extract_timestamp ( self
, video_data
):
87 # TODO: fix timestamp extraction
90 def _real_extract ( self
, url
):
91 sub_domain
, path
, page_title
= re
. match ( self
._ VALID
_U RL
, url
). groups ()
92 if sub_domain
not in ( 'money' , 'edition' ):
93 sub_domain
= 'edition'
94 config
= self
._ CONFIG
[ sub_domain
]
95 return self
._ extract
_ cvp
_ info
(
96 config
[ 'data_src' ] % path
, page_title
, {
98 'media_src' : config
[ 'media_src' ],
103 class CNNBlogsIE ( InfoExtractor
):
104 _VALID_URL
= r
'https?://[^\.]+\.blogs\.cnn\.com/.+'
106 'url' : 'http://reliablesources.blogs.cnn.com/2014/02/09/criminalizing-journalism/' ,
107 'md5' : '3e56f97b0b6ffb4b79f4ea0749551084' ,
109 'id' : 'bestoftv/2014/02/09/criminalizing-journalism.cnn' ,
111 'title' : 'Criminalizing journalism?' ,
112 'description' : 'Glenn Greenwald responds to comments made this week on Capitol Hill that journalists could be criminal accessories.' ,
113 'upload_date' : '20140209' ,
115 'expected_warnings' : [ 'Failed to download m3u8 information' ],
119 def _real_extract ( self
, url
):
120 webpage
= self
._ download
_ webpage
( url
, url_basename ( url
))
121 cnn_url
= self
._ html
_ search
_ regex
( r
'data-url="(.+?)"' , webpage
, 'cnn url' )
122 return self
. url_result ( cnn_url
, CNNIE
. ie_key ())
125 class CNNArticleIE ( InfoExtractor
):
126 _VALID_URL
= r
'https?://(?:(?:edition|www)\.)?cnn\.com/(?!videos?/)'
128 'url' : 'http://www.cnn.com/2014/12/21/politics/obama-north-koreas-hack-not-war-but-cyber-vandalism/' ,
129 'md5' : '689034c2a3d9c6dc4aa72d65a81efd01' ,
131 'id' : 'bestoftv/2014/12/21/ip-north-korea-obama.cnn' ,
133 'title' : 'Obama: Cyberattack not an act of war' ,
134 'description' : 'md5:0a802a40d2376f60e6b04c8d5bcebc4b' ,
135 'upload_date' : '20141221' ,
137 'expected_warnings' : [ 'Failed to download m3u8 information' ],
141 def _real_extract ( self
, url
):
142 webpage
= self
._ download
_ webpage
( url
, url_basename ( url
))
143 cnn_url
= self
._ html
_ search
_ regex
( r
"video:\s*'([^']+)'" , webpage
, 'cnn url' )
144 return self
. url_result ( 'http://cnn.com/video/?/video/' + cnn_url
, CNNIE
. ie_key ())