yt_dlp/extractor/tvnoe.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     clean_html,
   4     get_element_by_class,
   5     js_to_json,
   6 )
   7
   8
   9 class TVNoeIE(InfoExtractor):
  10     _WORKING = False
  11     _VALID_URL = r'https?://(?:www\.)?tvnoe\.cz/video/(?P<id>[0-9]+)'
  12     _TEST = {
  13         'url': 'http://www.tvnoe.cz/video/10362',
  14         'md5': 'aee983f279aab96ec45ab6e2abb3c2ca',
  15         'info_dict': {
  16             'id': '10362',
  17             'ext': 'mp4',
  18             'series': 'Noční univerzita',
  19             'title': 'prof. Tomáš Halík, Th.D. - Návrat náboženství a střet civilizací',
  20             'description': 'md5:f337bae384e1a531a52c55ebc50fff41',
  21         },
  22     }
  23
  24     def _real_extract(self, url):
  25         video_id = self._match_id(url)
  26         webpage = self._download_webpage(url, video_id)
  27
  28         iframe_url = self._search_regex(
  29             r'<iframe[^>]+src="([^"]+)"', webpage, 'iframe URL')
  30
  31         ifs_page = self._download_webpage(iframe_url, video_id)
  32         jwplayer_data = self._find_jwplayer_data(
  33             ifs_page, video_id, transform_source=js_to_json)
  34         info_dict = self._parse_jwplayer_data(
  35             jwplayer_data, video_id, require_title=False, base_url=iframe_url)
  36
  37         info_dict.update({
  38             'id': video_id,
  39             'title': clean_html(get_element_by_class(
  40                 'field-name-field-podnazev', webpage)),
  41             'description': clean_html(get_element_by_class(
  42                 'field-name-body', webpage)),
  43             'series': clean_html(get_element_by_class('title', webpage)),
  44         })
  45
  46         return info_dict