1
0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-05 10:42:37 +01:00
yt-dlp/youtube_dl/extractor/unistra.py
Jaime Marquínez Ferrándiz f527115b5f Rename utv.py to unistra.py and extract more info
There are other sites that could be named utv, which would conflict if they are added
2013-08-22 13:19:35 +02:00

33 lines
1.2 KiB
Python

import re
from .common import InfoExtractor
class UnistraIE(InfoExtractor):
_VALID_URL = r'http://utv.unistra.fr/(?:index|video).php\?id_video\=(\d+)'
_TEST = {
u'url': u'http://utv.unistra.fr/video.php?id_video=154',
u'file': u'154.mp4',
u'md5': u'736f605cfdc96724d55bb543ab3ced24',
u'info_dict': {
u'title': u'M!ss Yella',
u'description': u'md5:75e8439a3e2981cd5d4b6db232e8fdfc',
},
}
def _real_extract(self, url):
id = re.match(self._VALID_URL, url).group(1)
webpage = self._download_webpage(url, id)
file = re.search(r'file: "(.*?)",', webpage).group(1)
title = self._html_search_regex(r'<title>UTV - (.*?)</', webpage, u'title')
video_url = 'http://vod-flash.u-strasbg.fr:8080/' + file
return {'id': id,
'title': title,
'ext': 'mp4',
'url': video_url,
'description': self._html_search_regex(r'<meta name="Description" content="(.*?)"', webpage, u'description', flags=re.DOTALL),
'thumbnail': self._search_regex(r'image: "(.*?)"', webpage, u'thumbnail'),
}