Scrape RailsConf 2009 presentations

scrape_presentations.rb

#!/usr/bin/env ruby
require 'rubygems'
require 'curb'
require 'webrat'

Webrat.configure { |config| config.mode = :mechanize }
session = Webrat.session_class.new
session.visit "http://en.oreilly.com/rails2009/public/schedule/proceedings"
session.dom.search(".en_session_downloads a").each do |link|
  url = URI.escape(link['href'])
  filename = "download/" + URI.unescape(url.split(/\//).last)
  unless File.exists?(filename)
    puts "Downloading #{url} to #{filename}"
    Curl::Easy.download(url, filename)
  end
end