Web page scrubbing util to pull content from a main non-Rails driven site and create a template from it.

template_grab.rb

#!/usr/bin/ruby

require 'rubygems'
require 'hpricot'
require 'yaml'
require 'open-uri'

site = "http://www2.hargray.com"
settings = YAML::load( File.open("template_options.yml") )

settings.each_key do |page|
   begin
      doc = open(site) {|f| Hpricot(f)}
   
      head = doc.search("//head")
      head.prepend(settings[page]["js"].to_s)
      head.append(settings[page]["css"].to_s)
      (head/"title").inner_html(settings[page]["title"])
      (head/"base").remove
      (head/"script").remove
      (head/"link[@rel='alternate']").remove

      (doc/"body script").remove
      doc.search("*[@href]") do |link|
         unless link.attributes['href'].index("http")
            link.attributes['href'] = site + link.attributes['href']
         end
      end
      
      page_content = doc.at("//table[@class='contentpaneopen']/tr/td")
      page_content.inner_html(settings[page]["body_html"].to_s)
   
      File.open("#{settings[page]["path"]}/signal.erb", "w+") { |f| f.write doc.to_html }
   
      puts "Template generated for #{page.to_s}"
   rescue Exception => exc
      puts "Failed to update templates: #{exc}"
      exit(0)
   end
end

template_options.yml

---   
trouble-ticket:
 path: /code/trouble-ticket/app/views/layouts
 title: Trouble Ticket
 js: <%= javascript_include_tag 'prototype', 'effects', 'application' %>
 css: " "
 body_html: <%= render :file => 'layouts/application' %>

serv-av: 
 path: /code/serv-av/app/views/layouts
 title: "Service Availability"
 js: <%= javascript_include_tag 'jquery', 'application' %>
 css: <%= stylesheet_link_tag 'default' %>
 body_html: <%= render :file => 'layouts/application' %>

online-billing:
 path: /code/online-billing/app/views/layouts
 title: Online Billpay
 js: <%= javascript_include_tag 'jquery', 'jquery-ui', 'jrails', 'application' %>
 css: <%= stylesheet_link_tag 'the_aftermath' %>
 body_html: <%= render :file => 'layouts/application' %>