Archives/wikiteam
2
0
Fork 0
mirror of https://github.com/WikiTeam/wikiteam synced 2024-11-04 12:00:28 +00:00
Code Issues Projects Releases Wiki Activity

another case of subpages in allpages

Browse Source 
git-svn-id: https://wikiteam.googlecode.com/svn/trunk@42 31edc4fc-5e31-b4c4-d58b-c8bc928bcb95
This commit is contained in:
emijrp 2011-04-08 23:50:24 +00:00
parent fe94af27c7
commit 3e67420d92
1 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
dumpgenerator.py
View File

@ -118,11 +118,12 @@ def getPageTitles(config={}, start='!'):
name = '%s-%s' % (fr, to)
url = '%s?title=Special:Allpages&namespace=%s&from=%s&to=%s' % (config['domain'], namespace, fr, to) #do not put urllib.quote in fr or to
elif r_suballpages == r_suballpages2:
fr = fr.split('&namespace=')[0] #clean &namespace=\d, sometimes happens
name = fr
url = '%s?title=Special:Allpages/%s&namespace=%s' % (config['domain'], name, namespace)
if not name in checked_suballpages:
checked_suballpages.append(name)
checked_suballpages.append(name) #to avoid reload dupe subpages links
raw2 = urllib.urlopen(url).read()
raw2 = cleanHTML(raw2)
rawacum += raw2 #merge it after removed junk