]>
Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/cspan.py
1 from __future__
import unicode_literals
5 from . common
import InfoExtractor
13 class CSpanIE ( InfoExtractor
):
14 _VALID_URL
= r
'http://(?:www\.)?c-span\.org/video/\?(?P<id>[0-9a-f]+)'
17 'url' : 'http://www.c-span.org/video/?313572-1/HolderonV' ,
18 'md5' : '8e44ce11f0f725527daccc453f553eb0' ,
22 'title' : 'Attorney General Eric Holder on Voting Rights Act Decision' ,
23 'description' : 'Attorney General Eric Holder spoke to reporters following the Supreme Court decision in Shelby County v. Holder in which the court ruled that the preclearance provisions of the Voting Rights Act could not be enforced until Congress established new guidelines for review.' ,
25 'skip' : 'Regularly fails on travis, for unknown reasons' ,
27 'url' : 'http://www.c-span.org/video/?c4486943/cspan-international-health-care-models' ,
28 # For whatever reason, the served video alternates between
30 #'md5': 'dbb0f047376d457f2ab8b3929cbb2d0c',
34 'title' : 'International Health Care Models' ,
35 'description' : 'md5:7a985a2d595dba00af3d9c9f0783c967' ,
38 'url' : 'http://www.c-span.org/video/?318608-1/gm-ignition-switch-recall' ,
41 'title' : 'General Motors Ignition Switch Recall' ,
43 'playlist_duration_sum' : 14855 ,
46 def _real_extract ( self
, url
):
47 mobj
= re
. match ( self
._ VALID
_U RL
, url
)
48 page_id
= mobj
. group ( 'id' )
49 webpage
= self
._ download
_ webpage
( url
, page_id
)
50 video_id
= self
._ search
_ regex
( r
'progid=\' ?
([ 0 - 9 ]+) \' ?
> ', webpage, ' video
id ')
52 description = self._html_search_regex(
54 # The full description
55 r' < div
class = \' expandable
\' >(.* ?
)< a href
= \' #\'',
56 # If the description is small enough the other div is not
57 # present, otherwise this is a stripped version
58 r
'<p class=\' initial
\' >(.* ?
)</ p
> '
60 webpage, ' description
', flags=re.DOTALL)
62 info_url = ' http
:// c
- spanvideo
. org
/ videoLibrary
/ assets
/ player
/ ajax
- player
. php?os
= android
& html5
= program
& id = ' + video_id
63 data = self._download_json(info_url, video_id)
65 doc = self._download_xml(
66 ' http
:// www
. c
- span
. org
/ common
/ services
/ flashXml
. php?programid
= ' + video_id,
69 title = find_xpath_attr(doc, ' .// string
', ' name
', ' title
').text
70 thumbnail = find_xpath_attr(doc, ' .// string
', ' name
', ' poster
').text
72 files = data[' video
'][' files
']
75 ' id ': ' %s _ %d ' % (video_id, partnum + 1),
77 title if len(files) == 1 else
78 ' %s part
%d ' % (title, partnum + 1)),
79 ' url
': unescapeHTML(f[' path
'][' #text']),
80 'description' : description
,
81 'thumbnail' : thumbnail
,
82 'duration' : int_or_none ( f
. get ( 'length' , {}). get ( '#text' )),
83 } for partnum
, f
in enumerate ( files
)]