2013-06-23 20:04:08 +00:00
|
|
|
import re
|
|
|
|
|
|
|
|
|
|
from .common import InfoExtractor
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class WorldStarHipHopIE(InfoExtractor):
|
|
|
|
|
_VALID_URL = r'https?://(?:www|m)\.worldstar(?:candy|hiphop)\.com/videos/video\.php\?v=(?P<id>.*)'
|
2013-06-27 16:28:45 +00:00
|
|
|
_TEST = {
|
|
|
|
|
"url": "http://www.worldstarhiphop.com/videos/video.php?v=wshh6a7q1ny0G34ZwuIO",
|
|
|
|
|
"file": "wshh6a7q1ny0G34ZwuIO.mp4",
|
|
|
|
|
"md5": "9d04de741161603bf7071bbf4e883186",
|
|
|
|
|
"info_dict": {
|
|
|
|
|
"title": "Video: KO Of The Week: MMA Fighter Gets Knocked Out By Swift Head Kick!"
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2013-06-23 20:04:08 +00:00
|
|
|
|
|
|
|
|
def _real_extract(self, url):
|
|
|
|
|
m = re.match(self._VALID_URL, url)
|
|
|
|
|
video_id = m.group('id')
|
|
|
|
|
|
|
|
|
|
webpage_src = self._download_webpage(url, video_id)
|
|
|
|
|
|
2013-07-29 21:39:14 +00:00
|
|
|
video_url = re.search(r'videoId=(.*?)&?',
|
|
|
|
|
webpage_src)
|
2013-07-29 19:24:26 +00:00
|
|
|
|
2013-07-29 19:11:57 +00:00
|
|
|
if video_url:
|
|
|
|
|
self.to_screen(u'Vevo video detected:')
|
2013-07-29 21:39:14 +00:00
|
|
|
return self.url_result('vevo:%s' % video_url.group(1), ie='Vevo')
|
2013-07-29 19:11:57 +00:00
|
|
|
|
2013-06-23 20:04:08 +00:00
|
|
|
video_url = self._search_regex(r'so\.addVariable\("file","(.*?)"\)',
|
|
|
|
|
webpage_src, u'video URL')
|
|
|
|
|
|
2013-07-29 21:39:14 +00:00
|
|
|
if video_url is None:
|
2013-07-29 19:24:26 +00:00
|
|
|
video_url = self._search_regex(r'videoId=(.*?)&?',
|
|
|
|
|
webpage_src, u'video URL')
|
|
|
|
|
self.to_screen(u'Vevo video detected:')
|
|
|
|
|
vevo_id = 'vevo:%s' % video_url
|
|
|
|
|
return self.url_result(vevo_id, ie='Vevo')
|
|
|
|
|
|
2013-06-25 01:58:49 +00:00
|
|
|
if 'youtube' in video_url:
|
|
|
|
|
self.to_screen(u'Youtube video detected:')
|
2013-06-25 20:07:31 +00:00
|
|
|
return self.url_result(video_url, ie='Youtube')
|
2013-06-25 01:58:49 +00:00
|
|
|
|
2013-06-23 20:04:08 +00:00
|
|
|
if 'mp4' in video_url:
|
|
|
|
|
ext = 'mp4'
|
|
|
|
|
else:
|
|
|
|
|
ext = 'flv'
|
|
|
|
|
|
|
|
|
|
video_title = self._html_search_regex(r"<title>(.*)</title>",
|
|
|
|
|
webpage_src, u'title')
|
|
|
|
|
|
|
|
|
|
# Getting thumbnail and if not thumbnail sets correct title for WSHH candy video.
|
|
|
|
|
thumbnail = self._html_search_regex(r'rel="image_src" href="(.*)" />',
|
|
|
|
|
webpage_src, u'thumbnail', fatal=False)
|
|
|
|
|
|
|
|
|
|
if not thumbnail:
|
|
|
|
|
_title = r"""candytitles.*>(.*)</span>"""
|
|
|
|
|
mobj = re.search(_title, webpage_src)
|
|
|
|
|
if mobj is not None:
|
|
|
|
|
video_title = mobj.group(1)
|
|
|
|
|
|
|
|
|
|
results = [{
|
|
|
|
|
'id': video_id,
|
|
|
|
|
'url' : video_url,
|
|
|
|
|
'title' : video_title,
|
|
|
|
|
'thumbnail' : thumbnail,
|
|
|
|
|
'ext' : ext,
|
|
|
|
|
}]
|
|
|
|
|
return results
|
