Wikipedia mirroring in 10 lines

wikipedia.rb

# we are going to intentionally use the vanilla mongo driver
require 'mongo'
require 'nokogiri'
require 'open-uri'
require 'active_support/core_ext' # from rails

include Mongo
pages = Connection.new('localhost', 27017).db('loadtest').collection('pages')

wikipedia_page = "http://en.wikipedia.org/wiki/Special:Export/Ford_Motor"

# no blanks is magic here?  had problems without it
doc = Nokogiri::XML(open(wikipedia_page)) { |config| config.noblanks }
page = Hash.from_xml(doc.to_s)    # here's the magical method from rails
pages.insert page["mediawiki"]["page"]

# content includes hierarchy and complete structure of the original XML document