From 4820339d10fc500245c712d61dde7f64528b01bd Mon Sep 17 00:00:00 2001
From: nemobis <federicoleva@tiscali.it>
Date: Tue, 5 Nov 2013 17:10:44 +0000
Subject: [PATCH] Fix r842, patch by balrog; Schbirid reported python error in
 CleanHTML

git-svn-id: https://wikiteam.googlecode.com/svn/trunk@854 31edc4fc-5e31-b4c4-d58b-c8bc928bcb95
---
 dumpgenerator.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/dumpgenerator.py b/dumpgenerator.py
index 8e49c23..f1111d7 100644
--- a/dumpgenerator.py
+++ b/dumpgenerator.py
@@ -181,7 +181,7 @@ def getPageTitlesScraper(config={}):
         print '    Retrieving titles in the namespace', namespace
         url = '%s?title=Special:Allpages&namespace=%s' % (config['index'], namespace)
         req = urllib2.Request(url=url, headers={'User-Agent': getUserAgent()})
-        raw = urllib2.urlopen(req)
+        raw = urllib2.urlopen(req).read()
         raw = cleanHTML(raw)
         
         r_title = r'title="(?P<title>[^>]+)">'
@@ -217,7 +217,7 @@ def getPageTitlesScraper(config={}):
                 if not name in checked_suballpages:
                     checked_suballpages.append(name) #to avoid reload dupe subpages links
                     req2 = urllib2.Request(url=url, headers={'User-Agent': getUserAgent()})
-                    raw2 = urllib2.urlopen(req)
+                    raw2 = urllib2.urlopen(req).read()
                     raw2 = cleanHTML(raw2)
                     rawacum += raw2 #merge it after removed junk
                     print '    Reading', name, len(raw2), 'bytes', len(re.findall(r_suballpages, raw2)), 'subpages', len(re.findall(r_title, raw2)), 'pages'