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 from ..utils import int_or_none
   8
   9
  10 class KontrTubeIE(InfoExtractor):
  11     IE_NAME = 'kontrtube'
  12     IE_DESC = 'KontrTube.ru - Труба зовёт'
  13     _VALID_URL = r'http://(?:www\.)?kontrtube\.ru/videos/(?P<id>\d+)/(?P<display_id>[^/]+)/'
  14
  15     _TEST = {
  16         'url': 'http://www.kontrtube.ru/videos/2678/nad-olimpiyskoy-derevney-v-sochi-podnyat-rossiyskiy-flag/',
  17         'md5': '975a991a4926c9a85f383a736a2e6b80',
  18         'info_dict': {
  19             'id': '2678',
  20             'display_id': 'nad-olimpiyskoy-derevney-v-sochi-podnyat-rossiyskiy-flag',
  21             'ext': 'mp4',
  22             'title': 'Над олимпийской деревней в Сочи поднят российский флаг',
  23             'description': 'md5:80edc4c613d5887ae8ccf1d59432be41',
  24             'thumbnail': 'http://www.kontrtube.ru/contents/videos_screenshots/2000/2678/preview.mp4.jpg',
  25             'duration': 270,
  26         }
  27     }
  28
  29     def _real_extract(self, url):
  30         mobj = re.match(self._VALID_URL, url)
  31         video_id = mobj.group('id')
  32         display_id = mobj.group('display_id')
  33
  34         webpage = self._download_webpage(
  35             url, display_id, 'Downloading page')
  36
  37         video_url = self._html_search_regex(
  38             r"video_url\s*:\s*'(.+?)/?',", webpage, 'video URL')
  39         thumbnail = self._html_search_regex(
  40             r"preview_url\s*:\s*'(.+?)/?',", webpage, 'video thumbnail', fatal=False)
  41         title = self._html_search_regex(
  42             r'<title>(.+?)</title>', webpage, 'video title')
  43         description = self._html_search_meta(
  44             'description', webpage, 'video description')
  45
  46         mobj = re.search(
  47             r'<div class="col_2">Длительность: <span>(?P<minutes>\d+)м:(?P<seconds>\d+)с</span></div>',
  48             webpage)
  49         duration = int(mobj.group('minutes')) * 60 + int(mobj.group('seconds')) if mobj else None
  50
  51         view_count = self._html_search_regex(
  52             r'<div class="col_2">Просмотров: <span>(\d+)</span></div>',
  53             webpage, 'view count', fatal=False)
  54
  55         comment_count = None
  56         comment_str = self._html_search_regex(
  57             r'Комментарии: <span>([^<]+)</span>', webpage, 'comment count', fatal=False)
  58         if comment_str.startswith('комментариев нет'):
  59             comment_count = 0
  60         else:
  61             mobj = re.search(r'\d+ из (?P<total>\d+) комментариев', comment_str)
  62             if mobj:
  63                 comment_count = mobj.group('total')
  64
  65         return {
  66             'id': video_id,
  67             'display_id': display_id,
  68             'url': video_url,
  69             'thumbnail': thumbnail,
  70             'title': title,
  71             'description': description,
  72             'duration': duration,
  73             'view_count': int_or_none(view_count),
  74             'comment_count': int_or_none(comment_count),
  75         }