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

   1 # -*- coding: utf-8 -*-
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7
   8 from ..utils import (
   9     sanitized_Request,
  10     xpath_with_ns,
  11 )
  12
  13
  14 class RegioTVIE(InfoExtractor):
  15     _VALID_URL = r'https?://(?:www\.)?regio-tv\.de/video/(?P<id>[0-9]+).html'
  16     _TESTS = [
  17         {
  18             'url': 'http://www.regio-tv.de/video/395808.html',
  19             'info_dict': {
  20                 'id': '395808',
  21                 'ext': 'mp4',
  22                 'title': u'Wir in Ludwigsburg',
  23                 'description': u'Mit unseren zuckers\xfc\xdfen Adventskindern, au\xdferdem besuchen wir die Abendsterne!',
  24             }
  25         },
  26     ]
  27
  28     def _real_extract(self, url):
  29         mobj = re.match(self._VALID_URL, url)
  30         video_id = mobj.group('id')
  31
  32         webpage = self._download_webpage(url, video_id)
  33         key = self._html_search_regex(r''',key: "(.*?)"''', webpage, 'key')
  34
  35         title = self._html_search_regex(
  36             r'<meta property="og:title" content="\s*(.*?)\s*"\s*/?\s*>',
  37             webpage, 'title')
  38
  39         soapxml = '<?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><getHTML5VideoData xmlns="http://v.telvi.de/"><key xsi:type="xsd:string">%s</key></getHTML5VideoData></soap:Body></soap:Envelope>' % key
  40         request = sanitized_Request('http://v.telvi.de/?wsdl', soapxml)
  41         request.add_header('Origin', 'http://www.regio-tv.de')
  42         request.add_header('Referer', url)
  43         video_data = self._download_xml(request, video_id, 'video data')
  44
  45         NS_MAP = {
  46             'xsi': 'http://www.w3.org/2001/XMLSchema-instance',
  47             'soap': 'http://schemas.xmlsoap.org/soap/envelope/',
  48         }
  49
  50         url = video_data.find(xpath_with_ns('.//video', NS_MAP)).text
  51         thumbnail = video_data.find(xpath_with_ns('.//image', NS_MAP)).text
  52
  53         description = self._html_search_meta('description', webpage)
  54
  55         return {
  56             'id': video_id,
  57             'title': title,
  58             'url': url,
  59             'thumbnail': thumbnail,
  60             'description': description,
  61         }