youtube_dl/extractor/unistra.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import qualities
   7
   8
   9 class UnistraIE(InfoExtractor):
  10     _VALID_URL = r'https?://utv\.unistra\.fr/(?:index|video)\.php\?id_video\=(?P<id>\d+)'
  11
  12     _TESTS = [
  13         {
  14             'url': 'http://utv.unistra.fr/video.php?id_video=154',
  15             'md5': '736f605cfdc96724d55bb543ab3ced24',
  16             'info_dict': {
  17                 'id': '154',
  18                 'ext': 'mp4',
  19                 'title': 'M!ss Yella',
  20                 'description': 'md5:104892c71bd48e55d70b902736b81bbf',
  21             },
  22         },
  23         {
  24             'url': 'http://utv.unistra.fr/index.php?id_video=437',
  25             'md5': '1ddddd6cccaae76f622ce29b8779636d',
  26             'info_dict': {
  27                 'id': '437',
  28                 'ext': 'mp4',
  29                 'title': 'Prix Louise Weiss 2014',
  30                 'description': 'md5:cc3a8735f079f4fb6b0b570fc10c135a',
  31             },
  32         }
  33     ]
  34
  35     def _real_extract(self, url):
  36         mobj = re.match(self._VALID_URL, url)
  37         video_id = mobj.group('id')
  38
  39         webpage = self._download_webpage(url, video_id)
  40
  41         files = set(re.findall(r'file\s*:\s*"(/[^"]+)"', webpage))
  42
  43         quality = qualities(['SD', 'HD'])
  44         formats = []
  45         for file_path in files:
  46             format_id = 'HD' if file_path.endswith('-HD.mp4') else 'SD'
  47             formats.append({
  48                 'url': 'http://vod-flash.u-strasbg.fr:8080%s' % file_path,
  49                 'format_id': format_id,
  50                 'quality': quality(format_id)
  51             })
  52         self._sort_formats(formats)
  53
  54         title = self._html_search_regex(
  55             r'<title>UTV - (.*?)</', webpage, 'title')
  56         description = self._html_search_regex(
  57             r'<meta name="Description" content="(.*?)"', webpage, 'description', flags=re.DOTALL)
  58         thumbnail = self._search_regex(
  59             r'image: "(.*?)"', webpage, 'thumbnail')
  60
  61         return {
  62             'id': video_id,
  63             'title': title,
  64             'description': description,
  65             'thumbnail': thumbnail,
  66             'formats': formats
  67         }