]>
Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/worldstarhiphop.py
5b9779c05853ab815aa56d710476356c56c8449b
3 from .common
import InfoExtractor
6 class WorldStarHipHopIE(InfoExtractor
):
7 _VALID_URL
= r
'https?://(?:www|m)\.worldstar(?:candy|hiphop)\.com/videos/video\.php\?v=(?P<id>.*)'
9 "url": "http://www.worldstarhiphop.com/videos/video.php?v=wshh6a7q1ny0G34ZwuIO",
10 "file": "wshh6a7q1ny0G34ZwuIO.mp4",
11 "md5": "9d04de741161603bf7071bbf4e883186",
13 "title": "Video: KO Of The Week: MMA Fighter Gets Knocked Out By Swift Head Kick!"
18 def _real_extract(self
, url
):
19 m
= re
.match(self
._VALID
_URL
, url
)
20 video_id
= m
.group('id')
22 webpage_src
= self
._download
_webpage
(url
, video_id
)
24 video_url
= self
._search
_regex
(r
'so\.addVariable\("file","(.*?)"\)',
25 webpage_src
, u
'video URL')
27 if 'youtube' in video_url
:
28 self
.to_screen(u
'Youtube video detected:')
29 return self
.url_result(video_url
, ie
='Youtube')
31 if 'mp4' in video_url
:
36 video_title
= self
._html
_search
_regex
(r
"<title>(.*)</title>",
37 webpage_src
, u
'title')
39 # Getting thumbnail and if not thumbnail sets correct title for WSHH candy video.
40 thumbnail
= self
._html
_search
_regex
(r
'rel="image_src" href="(.*)" />',
41 webpage_src
, u
'thumbnail', fatal
=False)
44 _title
= r
"""candytitles.*>(.*)</span>"""
45 mobj
= re
.search(_title
, webpage_src
)
47 video_title
= mobj
.group(1)
52 'title' : video_title
,
53 'thumbnail' : thumbnail
,