valo

curl http://europe.wsj.com/home-page > wsj.html
curl --data-binary @wsj.html g.pdfgenapp.com > wsj.pdf

valo

require 'spec/expectations'
require 'webrat'

Webrat.configure do |config|
  config.mode = :mechanize
end

class MechanizeWorld < Webrat::MechanizeAdapter
end

valo

require 'rubygems'
require 'mechanize'
require 'tidied_html_page.rb'

a = WWW::Mechanize.new do |agent|
  agent.user_agent_alias = 'Mac Safari'
  agent.log = Logger.new(File.open('parser.log', 'w+'))
  agent.pluggable_parser.html = TidiedHTMLPage
  agent.pluggable_parser.xhtml = TidiedHTMLPage
end