]>
Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/nba.py
3 from .common
import InfoExtractor
9 class NBAIE(InfoExtractor
):
10 _VALID_URL
= r
'^(?:https?://)?(?:watch\.|www\.)?nba\.com/(?:nba/)?video(/[^?]*?)(?:/index\.html)?(?:\?.*)?$'
12 u
'url': u
'http://www.nba.com/video/games/nets/2012/12/04/0021200253-okc-bkn-recap.nba/index.html',
13 u
'file': u
'0021200253-okc-bkn-recap.nba.mp4',
14 u
'md5': u
'c0edcfc37607344e2ff8f13c378c88a4',
16 u
"description": u
"Kevin Durant scores 32 points and dishes out six assists as the Thunder beat the Nets in Brooklyn.",
17 u
"title": u
"Thunder vs. Nets"
21 def _real_extract(self
, url
):
22 mobj
= re
.match(self
._VALID
_URL
, url
)
24 raise ExtractorError(u
'Invalid URL: %s' % url
)
26 video_id
= mobj
.group(1)
28 webpage
= self
._download
_webpage
(url
, video_id
)
30 video_url
= u
'http://ht-mobile.cdn.turner.com/nba/big' + video_id
+ '_nba_1280x720.mp4'
32 shortened_video_id
= video_id
.rpartition('/')[2]
33 title
= self
._html
_search
_regex
(r
'<meta property="og:title" content="(.*?)"',
34 webpage
, 'title', default
=shortened_video_id
).replace('NBA.com: ', '')
36 # It isn't there in the HTML it returns to us
37 # uploader_date = self._html_search_regex(r'<b>Date:</b> (.*?)</div>', webpage, 'upload_date', fatal=False)
39 description
= self
._html
_search
_regex
(r
'<meta name="description" (?:content|value)="(.*?)" />', webpage
, 'description', fatal
=False)
42 'id': shortened_video_id
,
46 # 'uploader_date': uploader_date,
47 'description': description
,