Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/firsttv.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 FirstTVIE(InfoExtractor):
  11     IE_NAME = 'firsttv'
  12     IE_DESC = 'Видеоархив - Первый канал'
  13     _VALID_URL = r'http://(?:www\.)?1tv\.ru/videoarchive/(?P<id>\d+)'
  14
  15     _TEST = {
  16         'url': 'http://www.1tv.ru/videoarchive/73390',
  17         'md5': '3de6390cf0cca4a5eae1d1d83895e5ad',
  18         'info_dict': {
  19             'id': '73390',
  20             'ext': 'mp4',
  21             'title': 'Олимпийские канатные дороги',
  22             'description': 'md5:cc730d2bf4215463e37fff6a1e277b13',
  23             'thumbnail': 'http://img1.1tv.ru/imgsize640x360/PR20140210114657.JPG',
  24             'duration': 149,
  25         },
  26         'skip': 'Only works from Russia',
  27     }
  28
  29     def _real_extract(self, url):
  30         mobj = re.match(self._VALID_URL, url)
  31         video_id = mobj.group('id')
  32
  33         webpage = self._download_webpage(url, video_id, 'Downloading page')
  34
  35         video_url = self._html_search_regex(
  36             r'''(?s)jwplayer\('flashvideoportal_1'\)\.setup\({.*?'file': '([^']+)'.*?}\);''', webpage, 'video URL')
  37
  38         title = self._html_search_regex(
  39             r'<div class="tv_translation">\s*<h1><a href="[^"]+">([^<]*)</a>', webpage, 'title')
  40         description = self._html_search_regex(
  41             r'<div class="descr">\s*<div>&nbsp;</div>\s*<p>([^<]*)</p></div>', webpage, 'description', fatal=False)
  42
  43         thumbnail = self._og_search_thumbnail(webpage)
  44         duration = self._og_search_property('video:duration', webpage, 'video duration', fatal=False)
  45
  46         like_count = self._html_search_regex(r'title="Понравилось".*?/></label> \[(\d+)\]',
  47             webpage, 'like count', fatal=False)
  48         dislike_count = self._html_search_regex(r'title="Не понравилось".*?/></label> \[(\d+)\]',
  49             webpage, 'dislike count', fatal=False)
  50
  51         return {
  52             'id': video_id,
  53             'url': video_url,
  54             'thumbnail': thumbnail,
  55             'title': title,
  56             'description': description,
  57             'duration': int_or_none(duration),
  58             'like_count': int_or_none(like_count),
  59             'dislike_count': int_or_none(dislike_count),
  60         }