yt_dlp/extractor/regiotv.py

   1 from .common import InfoExtractor
   2
   3 from ..utils import (
   4     sanitized_Request,
   5     xpath_text,
   6     xpath_with_ns,
   7 )
   8
   9
  10 class RegioTVIE(InfoExtractor):
  11     _VALID_URL = r'https?://(?:www\.)?regio-tv\.de/video/(?P<id>[0-9]+)'
  12     _TESTS = [{
  13         'url': 'http://www.regio-tv.de/video/395808.html',
  14         'info_dict': {
  15             'id': '395808',
  16             'ext': 'mp4',
  17             'title': 'Wir in Ludwigsburg',
  18             'description': 'Mit unseren zuckersüßen Adventskindern, außerdem besuchen wir die Abendsterne!',
  19         }
  20     }, {
  21         'url': 'http://www.regio-tv.de/video/395808',
  22         'only_matching': True,
  23     }]
  24
  25     def _real_extract(self, url):
  26         video_id = self._match_id(url)
  27
  28         webpage = self._download_webpage(url, video_id)
  29
  30         key = self._search_regex(
  31             r'key\s*:\s*(["\'])(?P<key>.+?)\1', webpage, 'key', group='key')
  32         title = self._og_search_title(webpage)
  33
  34         SOAP_TEMPLATE = '<?xml version="1.0" encoding="utf-8"?><soap:Envelope xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:xsd="http://www.w3.org/2001/XMLSchema" xmlns:soap="http://schemas.xmlsoap.org/soap/envelope/"><soap:Body><{0} xmlns="http://v.telvi.de/"><key xsi:type="xsd:string">{1}</key></{0}></soap:Body></soap:Envelope>'
  35
  36         request = sanitized_Request(
  37             'http://v.telvi.de/',
  38             SOAP_TEMPLATE.format('GetHTML5VideoData', key).encode('utf-8'))
  39         video_data = self._download_xml(request, video_id, 'Downloading video XML')
  40
  41         NS_MAP = {
  42             'xsi': 'http://www.w3.org/2001/XMLSchema-instance',
  43             'soap': 'http://schemas.xmlsoap.org/soap/envelope/',
  44         }
  45
  46         video_url = xpath_text(
  47             video_data, xpath_with_ns('.//video', NS_MAP), 'video url', fatal=True)
  48         thumbnail = xpath_text(
  49             video_data, xpath_with_ns('.//image', NS_MAP), 'thumbnail')
  50         description = self._og_search_description(
  51             webpage) or self._html_search_meta('description', webpage)
  52
  53         return {
  54             'id': video_id,
  55             'url': video_url,
  56             'title': title,
  57             'description': description,
  58             'thumbnail': thumbnail,
  59         }