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

   1 # -*- coding: utf-8 -*-
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7
   8
   9 class RUHDIE(InfoExtractor):
  10     _VALID_URL = r'http://(?:www\.)?ruhd\.ru/play\.php\?vid=(?P<id>\d+)'
  11     _TEST = {
  12         'url': 'http://www.ruhd.ru/play.php?vid=207',
  13         'md5': 'd1a9ec4edf8598e3fbd92bb16072ba83',
  14         'info_dict': {
  15             'id': '207',
  16             'ext': 'divx',
  17             'title': 'КОТ бааааам',
  18             'description': 'классный кот)',
  19             'thumbnail': 're:^http://.*\.jpg$',
  20         }
  21     }
  22
  23     def _real_extract(self, url):
  24         mobj = re.match(self._VALID_URL, url)
  25         video_id = mobj.group('id')
  26
  27         webpage = self._download_webpage(url, video_id)
  28
  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>([^<]+)&nbsp;&nbsp; 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)
  37         if thumbnail:
  38             thumbnail = 'http://www.ruhd.ru' + thumbnail
  39
  40         return {
  41             'id': video_id,
  42             'url': video_url,
  43             'title': title,
  44             'description': description,
  45             'thumbnail': thumbnail,
  46         }