1 # -*- coding: utf-8 -*-
2 from __future__ import unicode_literals
6 from .common import InfoExtractor
9 class RUHDIE(InfoExtractor):
10 _VALID_URL = r'http://(?:www\.)?ruhd\.ru/play\.php\?vid=(?P<id>\d+)'
12 'url': 'http://www.ruhd.ru/play.php?vid=207',
13 'md5': 'd1a9ec4edf8598e3fbd92bb16072ba83',
17 'title': 'КОТ бааааам',
18 'description': 'классный кот)',
19 'thumbnail': 're:^http://.*\.jpg$',
23 def _real_extract(self, url):
24 mobj = re.match(self._VALID_URL, url)
25 video_id = mobj.group('id')
27 webpage = self._download_webpage(url, video_id)
29 video_url = self._html_search_regex(
30 r'<param name="src" value="([^"]+)"', webpage, 'video url')
31 title = self._html_search_regex(
32 r'<title>([^<]+) RUHD.ru - Видео Высокого качества №1 в России!</title>', webpage, 'title')
33 description = self._html_search_regex(
34 r'(?s)<div id="longdesc">(.+?)<span id="showlink">', webpage, 'description', fatal=False)
35 thumbnail = self._html_search_regex(
36 r'<param name="previewImage" value="([^"]+)"', webpage, 'thumbnail', fatal=False)
38 thumbnail = 'http://www.ruhd.ru' + thumbnail
44 'description': description,
45 'thumbnail': thumbnail,