From 3210735c499e6a7d0b4df4b8120e17bd7ba8927b Mon Sep 17 00:00:00 2001
From: Philipp Hagemeister <phihag@phihag.de>
Date: Wed, 18 Jul 2012 21:17:51 +0200
Subject: [PATCH] Fix EscapistMagazine IE
---
youtube_dl/InfoExtractors.py | 6 ++++--
1 file changed, 4 insertions(+), 2 deletions(-)
diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py
index baf859ea8b..499d9b1aed 100644
--- a/youtube_dl/InfoExtractors.py
+++ b/youtube_dl/InfoExtractors.py
@@ -2193,12 +2193,14 @@ class EscapistIE(InfoExtractor):
self.report_extraction(showName)
try:
- webPageBytes = urllib2.urlopen(url).read()
+ webPage = urllib2.urlopen(url)
+ webPageBytes = webPage.read()
+ m = re.match(r'text/html; charset="?([^"]+)"?', webPage.headers['Content-Type'])
+ webPage = webPageBytes.decode(m.group(1) if m else 'utf-8')
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self._downloader.trouble(u'ERROR: unable to download webpage: ' + unicode(err))
return
- webPage = webPageBytes.decode('utf-8')
descMatch = re.search('<meta name="description" content="([^"]*)"', webPage)
description = unescapeHTML(descMatch.group(1))
imgMatch = re.search('<meta property="og:image" content="([^"]*)"', webPage)