[regiotv] Improve extraction (Closes #7915)

This commit is contained in:
Sergey M․ 2015-12-31 22:12:47 +06:00
parent c43fda4c1a
commit 34a9da136f

View file

@ -1,61 +1,62 @@
# -*- coding: utf-8 -*- # coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
sanitized_Request, sanitized_Request,
xpath_text,
xpath_with_ns, xpath_with_ns,
) )
class RegioTVIE(InfoExtractor): class RegioTVIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?regio-tv\.de/video/(?P<id>[0-9]+).html' _VALID_URL = r'https?://(?:www\.)?regio-tv\.de/video/(?P<id>[0-9]+)'
_TESTS = [ _TESTS = [{
{
'url': 'http://www.regio-tv.de/video/395808.html', 'url': 'http://www.regio-tv.de/video/395808.html',
'info_dict': { 'info_dict': {
'id': '395808', 'id': '395808',
'ext': 'mp4', 'ext': 'mp4',
'title': u'Wir in Ludwigsburg', 'title': 'Wir in Ludwigsburg',
'description': u'Mit unseren zuckers\xfc\xdfen Adventskindern, au\xdferdem besuchen wir die Abendsterne!', 'description': 'Mit unseren zuckersüßen Adventskindern, außerdem besuchen wir die Abendsterne!',
} }
}, }, {
] 'url': 'http://www.regio-tv.de/video/395808',
'only_matching': True,
}]
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) video_id = self._match_id(url)
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
key = self._html_search_regex(r''',key: "(.*?)"''', webpage, 'key')
title = self._html_search_regex( key = self._search_regex(
r'<meta property="og:title" content="\s*(.*?)\s*"\s*/?\s*>', r'key\s*:\s*(["\'])(?P<key>.+?)\1', webpage, 'key', group='key')
webpage, 'title') title = self._og_search_title(webpage)
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 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>'
request = sanitized_Request('http://v.telvi.de/?wsdl', soapxml)
request.add_header('Origin', 'http://www.regio-tv.de') request = sanitized_Request(
request.add_header('Referer', url) 'http://v.telvi.de/',
video_data = self._download_xml(request, video_id, 'video data') SOAP_TEMPLATE.format('GetHTML5VideoData', key).encode('utf-8'))
video_data = self._download_xml(request, video_id, 'Downloading video XML')
NS_MAP = { NS_MAP = {
'xsi': 'http://www.w3.org/2001/XMLSchema-instance', 'xsi': 'http://www.w3.org/2001/XMLSchema-instance',
'soap': 'http://schemas.xmlsoap.org/soap/envelope/', 'soap': 'http://schemas.xmlsoap.org/soap/envelope/',
} }
url = video_data.find(xpath_with_ns('.//video', NS_MAP)).text video_url = xpath_text(
thumbnail = video_data.find(xpath_with_ns('.//image', NS_MAP)).text video_data, xpath_with_ns('.//video', NS_MAP), 'video url', fatal=True)
thumbnail = xpath_text(
description = self._html_search_meta('description', webpage) video_data, xpath_with_ns('.//image', NS_MAP), 'thumbnail')
description = self._og_search_description(
webpage) or self._html_search_meta('description', webpage)
return { return {
'id': video_id, 'id': video_id,
'url': video_url,
'title': title, 'title': title,
'url': url,
'thumbnail': thumbnail,
'description': description, 'description': description,
'thumbnail': thumbnail,
} }