Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/gazeta.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 GazetaIE(InfoExtractor):
  10     _VALID_URL = r'(?P<url>https?://(?:www\.)?gazeta\.ru/(?:[^/]+/)?video/(?:(?:main|\d{4}/\d{2}/\d{2})/)?(?P<id>[A-Za-z0-9-_.]+)\.s?html)'
  11     _TESTS = [{
  12         'url': 'http://www.gazeta.ru/video/main/zadaite_vopros_vladislavu_yurevichu.shtml',
  13         'md5': 'd49c9bdc6e5a7888f27475dc215ee789',
  14         'info_dict': {
  15             'id': '205566',
  16             'ext': 'mp4',
  17             'title': '«70–80 процентов гражданских в Донецке на грани голода»',
  18             'description': 'md5:38617526050bd17b234728e7f9620a71',
  19             'thumbnail': 're:^https?://.*\.jpg',
  20         },
  21     }, {
  22         'url': 'http://www.gazeta.ru/lifestyle/video/2015/03/08/master-klass_krasivoi_byt._delaem_vesennii_makiyazh.shtml',
  23         'only_matching': True,
  24     }]
  25
  26     def _real_extract(self, url):
  27         mobj = re.match(self._VALID_URL, url)
  28
  29         display_id = mobj.group('id')
  30         embed_url = '%s?p=embed' % mobj.group('url')
  31         embed_page = self._download_webpage(
  32             embed_url, display_id, 'Downloading embed page')
  33
  34         video_id = self._search_regex(
  35             r'<div[^>]*?class="eagleplayer"[^>]*?data-id="([^"]+)"', embed_page, 'video id')
  36
  37         return self.url_result(
  38             'eagleplatform:gazeta.media.eagleplatform.com:%s' % video_id, 'EaglePlatform')