yt_dlp/extractor/unistra.py

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