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+)/.+'
  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             'ext': 'mp4',
  21             'title': 'Над олимпийской деревней в Сочи поднят российский флаг',
  22             'description': 'md5:80edc4c613d5887ae8ccf1d59432be41',
  23             'thumbnail': 'http://www.kontrtube.ru/contents/videos_screenshots/2000/2678/preview.mp4.jpg',
  24             'duration': 270,
  25         }
  26     }
  27
  28     def _real_extract(self, url):
  29         mobj = re.match(self._VALID_URL, url)
  30         video_id = mobj.group('id')
  31
  32         webpage = self._download_webpage(url, video_id, 'Downloading page')
  33
  34         video_url = self._html_search_regex(r"video_url: '(.+?)/?',", webpage, 'video URL')
  35         thumbnail = self._html_search_regex(r"preview_url: '(.+?)/?',", webpage, 'video thumbnail', fatal=False)
  36         title = self._html_search_regex(
  37             r'<title>(.+?)</title>', webpage, 'video title')
  38         description = self._html_search_meta('description', webpage, 'video description')
  39
  40         mobj = re.search(
  41             r'<div class="col_2">Длительность: <span>(?P<minutes>\d+)м:(?P<seconds>\d+)с</span></div>', webpage)
  42         duration = int(mobj.group('minutes')) * 60 + int(mobj.group('seconds')) if mobj else None
  43
  44         view_count = self._html_search_regex(
  45             r'<div class="col_2">Просмотров: <span>(\d+)</span></div>', webpage, 'view count', fatal=False)
  46
  47         comment_count = None
  48         comment_str = self._html_search_regex(
  49             r'Комментарии: <span>([^<]+)</span>', webpage, 'comment count', 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 = 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': int_or_none(view_count),
  65             'comment_count': int_or_none(comment_count),
  66         }