1
1
mirror of https://github.com/ytdl-org/youtube-dl synced 2024-10-31 11:12:55 +01:00
youtube-dl/youtube_dl/extractor/worldstarhiphop.py
2014-11-23 20:41:03 +01:00

54 lines
1.8 KiB
Python

from __future__ import unicode_literals
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",
"md5": "9d04de741161603bf7071bbf4e883186",
"info_dict": {
"id": "wshh6a7q1ny0G34ZwuIO",
"ext": "mp4",
"title": "KO Of The Week: MMA Fighter Gets Knocked Out By Swift Head Kick!"
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
m_vevo_id = re.search(r'videoId=(.*?)&amp?', webpage)
if m_vevo_id is not None:
return self.url_result('vevo:%s' % m_vevo_id.group(1), ie='Vevo')
video_url = self._search_regex(
r'so\.addVariable\("file","(.*?)"\)', webpage, 'video URL')
if 'youtube' in video_url:
return self.url_result(video_url, ie='Youtube')
video_title = self._html_search_regex(
r'(?s)<div class="content-heading">\s*<h1>(.*?)</h1>',
webpage, '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, 'thumbnail',
fatal=False)
if not thumbnail:
_title = r'candytitles.*>(.*)</span>'
mobj = re.search(_title, webpage)
if mobj is not None:
video_title = mobj.group(1)
return {
'id': video_id,
'url': video_url,
'title': video_title,
'thumbnail': thumbnail,
}