yt_dlp/extractor/ruhd.py

   1 from .common import InfoExtractor
   2
   3
   4 class RUHDIE(InfoExtractor):
   5     _VALID_URL = r'https?://(?:www\.)?ruhd\.ru/play\.php\?vid=(?P<id>\d+)'
   6     _TEST = {
   7         'url': 'http://www.ruhd.ru/play.php?vid=207',
   8         'md5': 'd1a9ec4edf8598e3fbd92bb16072ba83',
   9         'info_dict': {
  10             'id': '207',
  11             'ext': 'divx',
  12             'title': 'КОТ бааааам',
  13             'description': 'классный кот)',
  14             'thumbnail': r're:^http://.*\.jpg$',
  15         }
  16     }
  17
  18     def _real_extract(self, url):
  19         video_id = self._match_id(url)
  20         webpage = self._download_webpage(url, video_id)
  21
  22         video_url = self._html_search_regex(
  23             r'<param name="src" value="([^"]+)"', webpage, 'video url')
  24         title = self._html_search_regex(
  25             r'<title>([^<]+)&nbsp;&nbsp; RUHD\.ru - Видео Высокого качества №1 в России!</title>',
  26             webpage, 'title')
  27         description = self._html_search_regex(
  28             r'(?s)<div id="longdesc">(.+?)<span id="showlink">',
  29             webpage, 'description', fatal=False)
  30         thumbnail = self._html_search_regex(
  31             r'<param name="previewImage" value="([^"]+)"',
  32             webpage, 'thumbnail', fatal=False)
  33         if thumbnail:
  34             thumbnail = 'http://www.ruhd.ru' + thumbnail
  35
  36         return {
  37             'id': video_id,
  38             'url': video_url,
  39             'title': title,
  40             'description': description,
  41             'thumbnail': thumbnail,
  42         }