_ Git - youtube-dl/blob - youtube_dl/extractor/tvnoe.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .jwplatform import JWPlatformBaseIE
   5 from ..utils import clean_html, get_element_by_class, js_to_json
   6
   7
   8 class TVNoeIE(JWPlatformBaseIE):
   9     _VALID_URL = r'https?://(www\.)?tvnoe\.cz/video/(?P<id>[0-9]+)'
  10     _TEST = {
  11         'url': 'http://www.tvnoe.cz/video/10362',
  12         'md5': 'aee983f279aab96ec45ab6e2abb3c2ca',
  13         'info_dict': {
  14             'id': '10362',
  15             'ext': 'mp4',
  16             'series': 'Noční univerzita',
  17             'title': 'prof. Tomáš Halík, Th.D. - ' +
  18                      'Návrat náboženství a střet civilizací',
  19             'description': 'md5:f337bae384e1a531a52c55ebc50fff41',
  20         }
  21     }
  22
  23     def _real_extract(self, url):
  24         video_id = self._match_id(url)
  25         webpage = self._download_webpage(url, video_id)
  26
  27         iframe_url = self._search_regex(r'<iframe[^>]+src="([^"]+)"',
  28                                         webpage, 'iframe src attribute')
  29
  30         ifs_page = self._download_webpage(iframe_url, video_id)
  31         jwplayer_data = self._parse_json(self._find_jwplayer_data(ifs_page),
  32                                          video_id, transform_source=js_to_json)
  33         info_dict = self._parse_jwplayer_data(
  34             jwplayer_data, video_id, require_title=False, base_url=iframe_url)
  35
  36         info_dict.update({
  37             'id': video_id,
  38             'title': clean_html(
  39                get_element_by_class('field-name-field-podnazev', webpage)),
  40             'description': clean_html(get_element_by_class('field-name-body',
  41                                                            webpage)),
  42             'series': clean_html(get_element_by_class('title', webpage))
  43         })
  44         return info_dict