Extract the base_url for the XML download from the JS snippet's 'server' variable.

This commit is contained in:
Elias Probst 2014-06-21 01:00:48 +02:00
parent a20575e8ae
commit 8bfb6723cb

View File

@ -33,7 +33,13 @@ class SpiegelIE(InfoExtractor):
video_title = self._html_search_regex( video_title = self._html_search_regex(
r'<div class="module-title">(.*?)</div>', webpage, 'title') r'<div class="module-title">(.*?)</div>', webpage, 'title')
xml_url = 'http://video2.spiegel.de/flash/' + video_id + '.xml' base_url = self._search_regex(
r'var\s+server\s+=\s+\"(http://video\d*\.spiegel\.de/flash/\d+/\d+/)\";',
webpage,
'base_url',
)
xml_url = base_url + video_id + '.xml'
idoc = self._download_xml( idoc = self._download_xml(
xml_url, video_id, xml_url, video_id,
note='Downloading XML', errnote='Failed to download XML from "{0}"'.format(xml_url)) note='Downloading XML', errnote='Failed to download XML from "{0}"'.format(xml_url))