1
0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-12-13 09:06:36 +01:00
yt-dlp/youtube_dl/extractor/worldstarhiphop.py
2013-07-29 14:39:14 -07:00

71 lines
2.3 KiB
Python

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>.*)'
_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!"
}
}
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)
video_url = re.search(r'videoId=(.*?)&amp?',
webpage_src)
if video_url:
self.to_screen(u'Vevo video detected:')
return self.url_result('vevo:%s' % video_url.group(1), ie='Vevo')
video_url = self._search_regex(r'so\.addVariable\("file","(.*?)"\)',
webpage_src, u'video URL')
if video_url is None:
video_url = self._search_regex(r'videoId=(.*?)&amp?',
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')
if 'youtube' in video_url:
self.to_screen(u'Youtube video detected:')
return self.url_result(video_url, ie='Youtube')
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