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

   1 # encoding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7
   8
   9 class KontrTubeIE(InfoExtractor):
  10     IE_NAME = 'kontrtube'
  11     IE_DESC = 'KontrTube.ru - Труба зовёт'
  12     _VALID_URL = r'http://(?:www\.)?kontrtube\.ru/videos/(?P<id>\d+)/.+'
  13
  14     _TEST = {
  15         'url': 'http://www.kontrtube.ru/videos/2678/nad-olimpiyskoy-derevney-v-sochi-podnyat-rossiyskiy-flag/',
  16         'md5': '975a991a4926c9a85f383a736a2e6b80',
  17         'info_dict': {
  18             'id': '2678',
  19             'ext': 'mp4',
  20             'title': 'Над олимпийской деревней в Сочи поднят российский флаг',
  21             'description': 'md5:80edc4c613d5887ae8ccf1d59432be41',
  22             'thumbnail': 'http://www.kontrtube.ru/contents/videos_screenshots/2000/2678/preview.mp4.jpg',
  23             'duration': 270,
  24         }
  25     }
  26
  27     def _real_extract(self, url):
  28         mobj = re.match(self._VALID_URL, url)
  29         video_id = mobj.group('id')
  30
  31         webpage = self._download_webpage(url, video_id, 'Downloading page')
  32
  33         video_url = self._html_search_regex(r"video_url: '(.+?)/?',", webpage, 'video URL')
  34         thumbnail = self._html_search_regex(r"preview_url: '(.+?)/?',", webpage, 'video thumbnail', fatal=False)
  35         title = self._html_search_regex(r'<title>(.+?) - Труба зовёт - Интересный видеохостинг</title>', webpage,
  36             'video title')
  37         description = self._html_search_meta('description', webpage, 'video description')
  38
  39         mobj = re.search(r'<div class="col_2">Длительность: <span>(?P<minutes>\d+)м:(?P<seconds>\d+)с</span></div>',
  40             webpage)
  41         duration = int(mobj.group('minutes')) * 60 + int(mobj.group('seconds')) if mobj else None
  42
  43         view_count = self._html_search_regex(r'<div class="col_2">Просмотров: <span>(\d+)</span></div>', webpage,
  44             'view count', fatal=False)
  45         view_count = int(view_count) if view_count is not None else None
  46
  47         comment_count = None
  48         comment_str = self._html_search_regex(r'Комментарии: <span>([^<]+)</span>', webpage, 'comment count',
  49             fatal=False)
  50         if comment_str.startswith('комментариев нет'):
  51             comment_count = 0
  52         else:
  53             mobj = re.search(r'\d+ из (?P<total>\d+) комментариев', comment_str)
  54             if mobj:
  55                 comment_count = int(mobj.group('total'))
  56
  57         return {
  58             'id': video_id,
  59             'url': video_url,
  60             'thumbnail': thumbnail,
  61             'title': title,
  62             'description': description,
  63             'duration': duration,
  64             'view_count': view_count,
  65             'comment_count': comment_count,
  66         }