This gist is just for demo purpose for a talk I gave at Italian RubyDay in Milan, June 15 2012

.gitignore

*.swp

crawl.rb

#!/usr/bin/env ruby

require 'anemone'
require 'httpclient'
require 'getoptlong'

# Yes, I was buit just for RubyDay 2012 talk demo
# https://gist.github.com/2935464

module RubyDayIt
  module Crawling
    class Demo
      def self.test_1(url)
        Anemone.crawl(url) do |anemone|
          anemone.on_every_page do |page|
            puts page.url
          end
        end
      end

      def self.test_2(url)


        h=HTTPClient.new()
        Anemone.crawl(url) do |anemone|
          anemone.on_every_page do |page|
            response = h.get(page.url)
            puts "Original: #{page.url}: #{response.code}"
            response = h.get(page.url.to_s.split(";")[0].concat(".bak"))
            puts "BAK: #{page.url.to_s.split(";")[0].concat(".bak")}: #{response.code}"
            response = h.get(page.url.to_s.split(";")[0].concat(".old"))
            puts "OLD: #{page.url.to_s.split(";")[0].concat(".old")}: #{response.code}"
            response = h.get(page.url.to_s.split(";")[0].concat("~"))
            puts "~: #{page.url.to_s.split(";")[0].concat("~")}: #{response.code}"
          end
        end
      end


    end
  end
end


opts = GetoptLong.new(
  [ '--test-1', '-1', GetoptLong::NO_ARGUMENT ],
  [ '--test-2', '-2', GetoptLong::NO_ARGUMENT ]
)

opts.each do |opt, arg|
  case opt
  when '--test-1'
    RubyDayIt::Crawling::Demo.test_1(ARGV[0])
  when '--test-2'
    RubyDayIt::Crawling::Demo.test_2(ARGV[0])
  end
end


# http://localhost:8080/HacmeBooks