Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/ruhd.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5
   6
   7 class RUHDIE(InfoExtractor):
   8     _VALID_URL = r'https?://(?:www\.)?ruhd\.ru/play\.php\?vid=(?P<id>\d+)'
   9     _TEST = {
  10         'url': 'http://www.ruhd.ru/play.php?vid=207',
  11         'md5': 'd1a9ec4edf8598e3fbd92bb16072ba83',
  12         'info_dict': {
  13             'id': '207',
  14             'ext': 'divx',
  15             'title': 'КОТ бааааам',
  16             'description': 'классный кот)',
  17             'thumbnail': r're:^http://.*\.jpg$',
  18         }
  19     }
  20
  21     def _real_extract(self, url):
  22         video_id = self._match_id(url)
  23         webpage = self._download_webpage(url, video_id)
  24
  25         video_url = self._html_search_regex(
  26             r'<param name="src" value="([^"]+)"', webpage, 'video url')
  27         title = self._html_search_regex(
  28             r'<title>([^<]+)&nbsp;&nbsp; RUHD.ru - Видео Высокого качества №1 в России!</title>',
  29             webpage, 'title')
  30         description = self._html_search_regex(
  31             r'(?s)<div id="longdesc">(.+?)<span id="showlink">',
  32             webpage, 'description', fatal=False)
  33         thumbnail = self._html_search_regex(
  34             r'<param name="previewImage" value="([^"]+)"',
  35             webpage, 'thumbnail', fatal=False)
  36         if thumbnail:
  37             thumbnail = 'http://www.ruhd.ru' + thumbnail
  38
  39         return {
  40             'id': video_id,
  41             'url': video_url,
  42             'title': title,
  43             'description': description,
  44             'thumbnail': thumbnail,
  45         }