Ruby based Spell Check Bot

spellCheck.rb

#!/usr/bin/env ruby 

require 'rubygems' 
require 'spider' 
require 'raspell' 
require 'hpricot' 

#The URL below will be used by the crawler.
#The bot will take this URL and run a spell check on the page that it leads to. 
#It will also perform the spell check on sub-pages emanating from the URL. 
domain = 'http://192.168.56.90/index.php/en/admissions'

#Here we can choose which dictionary we want to run the spell check against
#speller = Aspell.new('en_GB') 
speller = Aspell.new('en_US')
#speller = Aspell.new('en')

Spider.start_at(domain) do |s| 

  s.add_url_check do |a_url| 
    a_url.match("^#{domain}") 
  end 

  s.on :success do |a_url, resp, prior_url| 
    unless resp['content-type'].match('text/html') 
      puts "Skipping #{a_url}" 
      next 
    end 
    puts "On page #{a_url}" 
     
    document = Hpricot(resp.body) 
#   (document/"#middle-column").inner_html
    document.search('head').remove 
    document.search('script').remove 
    document.search('link').remove 
    document.search('meta').remove 
    document.search('style').remove 

#Hpricot is an XML parser.
#We are using it here to tell the bot which section of the document we want it to spell check.
#The site that I want to run the spell check on has a div titled "middle-column" that contains
#text that I want spell checked. I am giving that instruction to the bot here...
#    words = document.inner_text.gsub(/\s+/, ' ').strip.split(/\s/) 
    words = (document/"#middle-column").inner_text.gsub(/\s+/, ' ').strip.split(/\s/)
     
    speller.list_misspelled(words).each do |mistake| 
      puts " * Found mistake \"#{mistake}\" perhaps you meant \"#{speller.suggest(mistake).first}\"" 
    end 
  end 

end