HpricotScraper.rb

require 'hpricot'
require 'open-uri'

module HpricotScraper
  def self.get_div_contents(url, div)
    doc = Hpricot(open(url))
    result = (doc/"##{div}")
    return result
  end

  def self.get_links(url)
    doc = Hpricot(open(url))
    links = (doc/"a")
    results = Array.new    
    links.each do |link|
      href = link[:href] 
      if (not href =~ /^http/ and not href =~ /\.pdf$/)
        results << href
      end	
    end
    return results
  end
end