0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-10-31 23:02:40 +00:00
yt-dlp/youtube_dl/extractor/worldstarhiphop.py
Philipp Hagemeister 6b47c7f24e Allow moving tests into IE files
Allow adding download tests right in the IE file.
This will cut down on merge conflicts and make it more likely that new IE authors will add tests right away.
2013-06-27 18:28:45 +02:00

56 lines
1.8 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 = self._search_regex(r'so\.addVariable\("file","(.*?)"\)',
webpage_src, u'video URL')
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