1
0
mirror of https://codeberg.org/polarisfm/youtube-dl synced 2024-12-05 06:37:54 +01:00
youtube-dl/youtube_dl/extractor/worldstarhiphop.py

41 lines
1.3 KiB
Python
Raw Normal View History

2014-03-23 13:49:15 +01:00
from __future__ import unicode_literals
2013-06-23 22:04:08 +02:00
from .common import InfoExtractor
class WorldStarHipHopIE(InfoExtractor):
_VALID_URL = r'https?://(?:www|m)\.worldstar(?:candy|hiphop)\.com/(?:videos|android)/video\.php\?.*?\bv=(?P<id>[^&]+)'
_TESTS = [{
2016-02-14 10:37:17 +01:00
'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!'
}
}, {
'url': 'http://m.worldstarhiphop.com/android/video.php?v=wshh6a7q1ny0G34ZwuIO',
'only_matching': True,
}]
2013-06-23 22:04:08 +02:00
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
2013-06-23 22:04:08 +02:00
entries = self._parse_html5_media_entries(url, webpage, video_id)
2013-06-23 22:04:08 +02:00
if not entries:
return self.url_result(url, 'Generic')
title = self._html_search_regex(
[r'(?s)<div class="content-heading">\s*<h1>(.*?)</h1>',
r'<span[^>]+class="tc-sp-pinned-title">(.*)</span>'],
webpage, 'title')
2013-06-23 22:04:08 +02:00
info = entries[0]
info.update({
2014-03-23 13:49:15 +01:00
'id': video_id,
'title': title,
})
return info