1
0
mirror of https://github.com/l1ving/youtube-dl synced 2024-11-27 12:02:51 +08:00
youtube-dl/youtube_dl/extractor/unistra.py

67 lines
2.1 KiB
Python
Raw Normal View History

2014-09-06 16:21:27 +08:00
from __future__ import unicode_literals
import re
from .common import InfoExtractor
2014-09-06 16:21:27 +08:00
from ..utils import qualities
class UnistraIE(InfoExtractor):
2014-09-06 16:21:27 +08:00
_VALID_URL = r'http://utv\.unistra\.fr/(?:index|video)\.php\?id_video\=(?P<id>\d+)'
_TESTS = [
{
'url': 'http://utv.unistra.fr/video.php?id_video=154',
'md5': '736f605cfdc96724d55bb543ab3ced24',
'info_dict': {
'id': '154',
'ext': 'mp4',
'title': 'M!ss Yella',
'description': 'md5:104892c71bd48e55d70b902736b81bbf',
},
},
2014-09-06 16:21:27 +08:00
{
'url': 'http://utv.unistra.fr/index.php?id_video=437',
'md5': '1ddddd6cccaae76f622ce29b8779636d',
'info_dict': {
'id': '437',
'ext': 'mp4',
'title': 'Prix Louise Weiss 2014',
'description': 'md5:cc3a8735f079f4fb6b0b570fc10c135a',
},
}
]
def _real_extract(self, url):
2014-09-06 16:21:27 +08:00
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
2014-09-05 04:18:17 +08:00
webpage = self._download_webpage(url, video_id)
2014-09-06 16:21:27 +08:00
files = set(re.findall(r'file\s*:\s*"([^"]+)"', webpage))
quality = qualities(['SD', 'HD'])
formats = []
for file_path in files:
format_id = 'HD' if file_path.endswith('-HD.mp4') else 'SD'
2014-09-05 04:18:17 +08:00
formats.append({
2014-09-06 16:21:27 +08:00
'url': 'http://vod-flash.u-strasbg.fr:8080%s' % file_path,
'format_id': format_id,
'quality': quality(format_id)
2014-09-05 04:18:17 +08:00
})
2014-09-06 16:21:27 +08:00
title = self._html_search_regex(
r'<title>UTV - (.*?)</', webpage, 'title')
description = self._html_search_regex(
r'<meta name="Description" content="(.*?)"', webpage, 'description', flags=re.DOTALL)
thumbnail = self._search_regex(
r'image: "(.*?)"', webpage, 'thumbnail')
return {
'id': video_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'formats': formats
}