ipython_all_pages.py

#!/usr/bin/env python

import re
import requests

html = requests.get('http://wiki.ipython.org/Special:AllPages')
all_pages_table = re.search('<table class="mw-allpages-table-chunk">(.*)</table>',
                            html.content, re.DOTALL).group()

titles = re.findall(r'title="([^"]*?)"', all_pages_table)
hrefs = re.findall(r'href="([^"]*?)"', all_pages_table)

print("Go to http://wiki.ipython.org/Special:Export and export the following:")
print('\n'.join(titles))

mw-to-gollum.rb

#!/usr/bin/env ruby
require 'rubygems'
require 'hpricot'
require 'gollum'

wiki = Gollum::Wiki.new('openaustralia.wiki')

file = File.open("OpenAustralia-20110309232515.xml", "r")
 
doc = Hpricot(file)

doc.search('/mediawiki/page').each do |el|
  title = el.at('title').inner_text
  content = el.at('text').inner_text
  commit = { :message => "Import MediaWiki page #{title} into Gollum",
             :name => 'Henare Degan',
             :email => '[email protected]' }
  begin
    puts "Writing page #{title}"
    wiki.write_page(title, :mediawiki, content, commit)
  rescue Gollum::DuplicatePageError => e
    p "Duplicate #{title}"
  end
end

file.close