]> Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/regiotv.py
Update upstream source from tag 'upstream/2019.09.28'
[youtubedl] / youtube_dl / extractor / regiotv.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 from .common import InfoExtractor
5
6 from ..utils import (
7 sanitized_Request,
8 xpath_text,
9 xpath_with_ns,
10 )
11
12
13 class RegioTVIE(InfoExtractor):
14 _VALID_URL = r'https?://(?:www\.)?regio-tv\.de/video/(?P<id>[0-9]+)'
15 _TESTS = [{
16 'url': 'http://www.regio-tv.de/video/395808.html',
17 'info_dict': {
18 'id': '395808',
19 'ext': 'mp4',
20 'title': 'Wir in Ludwigsburg',
21 'description': 'Mit unseren zuckersüßen Adventskindern, außerdem besuchen wir die Abendsterne!',
22 }
23 }, {
24 'url': 'http://www.regio-tv.de/video/395808',
25 'only_matching': True,
26 }]
27
28 def _real_extract(self, url):
29 video_id = self._match_id(url)
30
31 webpage = self._download_webpage(url, video_id)
32
33 key = self._search_regex(
34 r'key\s*:\s*(["\'])(?P<key>.+?)\1', webpage, 'key', group='key')
35 title = self._og_search_title(webpage)
36
37 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>'
38
39 request = sanitized_Request(
40 'http://v.telvi.de/',
41 SOAP_TEMPLATE.format('GetHTML5VideoData', key).encode('utf-8'))
42 video_data = self._download_xml(request, video_id, 'Downloading video XML')
43
44 NS_MAP = {
45 'xsi': 'http://www.w3.org/2001/XMLSchema-instance',
46 'soap': 'http://schemas.xmlsoap.org/soap/envelope/',
47 }
48
49 video_url = xpath_text(
50 video_data, xpath_with_ns('.//video', NS_MAP), 'video url', fatal=True)
51 thumbnail = xpath_text(
52 video_data, xpath_with_ns('.//image', NS_MAP), 'thumbnail')
53 description = self._og_search_description(
54 webpage) or self._html_search_meta('description', webpage)
55
56 return {
57 'id': video_id,
58 'url': video_url,
59 'title': title,
60 'description': description,
61 'thumbnail': thumbnail,
62 }