From 8bfb6723cb5bd9cb7a4c843e12688b26ab14d17a Mon Sep 17 00:00:00 2001 From: Elias Probst Date: Sat, 21 Jun 2014 01:00:48 +0200 Subject: [PATCH] Extract the base_url for the XML download from the JS snippet's 'server' variable. --- youtube_dl/extractor/spiegel.py | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/spiegel.py b/youtube_dl/extractor/spiegel.py index 94346daf6..87f1ee694 100644 --- a/youtube_dl/extractor/spiegel.py +++ b/youtube_dl/extractor/spiegel.py @@ -33,7 +33,13 @@ def _real_extract(self, url): video_title = self._html_search_regex( r'
(.*?)
', 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( xml_url, video_id, note='Downloading XML', errnote='Failed to download XML from "{0}"'.format(xml_url))