From d44e70ba7fcc6b071fdcded06cfc14943cb26e44 Mon Sep 17 00:00:00 2001
From: emijrp <emijrp@gmail.com>
Date: Wed, 6 Apr 2011 12:26:13 +0000
Subject: [PATCH] git-svn-id: https://wikiteam.googlecode.com/svn/trunk@10
 31edc4fc-5e31-b4c4-d58b-c8bc928bcb95

---
 dumpgenerator.py | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/dumpgenerator.py b/dumpgenerator.py
index f93e76a..fb9e893 100644
--- a/dumpgenerator.py
+++ b/dumpgenerator.py
@@ -118,12 +118,12 @@ def getHeader(domain=''):
 
 def getXML(domain='', title='', curonly=False):
     #http://www.mediawiki.org/wiki/Manual_talk:Parameters_to_Special:Export#Parameters_no_longer_in_use.3F
-    limit = 1000
+    limit = 100
     truncated = False
     title_ = re.sub(' ', '_', title)
     print title
     headers = {'User-Agent': 'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-GB; rv:1.8.0.4) Gecko/20060508 Firefox/1.5.0.4'}
-    params = {'title': 'Special:Export', 'pages': title, 'action': 'submit', }
+    params = {'title': 'Special:Export', 'pages': title_, 'action': 'submit', }
     if curonly:
         params['curonly'] = 1
     else:
@@ -153,6 +153,7 @@ def getXML(domain='', title='', curonly=False):
                 else:
                     #offset is OK in this wiki, merge with the previous chunk of this page history and continue
                     xml = xml.split('</page>')[0]+xml2.split('<page>\n')[1]
+                    print 'merging'
             else:
                 params['offset'] = '' #no more edits in this page history
             print title, len(re.findall(r_timestamp, xml)), 'edits'
@@ -167,17 +168,18 @@ if __name__ == '__main__':
     #domain = 'http://archiveteam.org/index.php'
     #domain = 'http://wikanda.cadizpedia.eu/w/index.php'
     domain = 'http://en.citizendium.org/index.php'
+    domain = 'http://en.wikipedia.org/w/index.php'
     curonly = False
     namespaces = [0]
     
     if re.findall(r'(wikipedia|wikisource|wiktionary|wikibooks|wikiversity|wikimedia|wikispecies|wikiquote|wikinews)\.org', domain):
         print 'DO NOT USE THIS SCRIPT TO DOWNLOAD WIKIMEDIA PROJECTS!\nDownload the dumps from http://download.wikimedia.org\nThanks!'
-        sys.exit()
+        #sys.exit()
     
     #get titles
     print 'Loading page titles from namespaces =', ','.join([str(i) for i in namespaces])
     #titles = getAllPageTitles(domain=domain, namespaces=namespaces)
-    titles = ['Life']
+    titles = ['Bay of Cádiz']
     #print '\n'.join(titles)
     print '%d page titles loaded' % (len(titles))