Scrapes top 100 greatest movie characters with Ruby and Nokogiri

top_100_greatest_movie_characters_scraper.rb

# = Top 100 Greatest Movie Characters Scraper
# This program just scrapes the empire online 100 
# greatest movie characters web site (http://www.empireonline.com/100-greatest-movie-characters/)
# and generates a simple page to display all the 
# characters on one page so you don't have to go 
# clicking through 100 pages
#
# This was just built b/c I'd rather learn something new
# during the time it took me to view all 100 characters
# and still get to see who they are.  I'm too lazy to click
# through all of them


# Author::    Jason Amster  (mailto:[email protected])
# Copyright:: Copyright (c) 2008 Jason Amster
# License::   Distributes under the same terms as Ruby
      
require 'rubygems'
require 'nokogiri'
require 'open-uri'

#This class just scrapes the the pages and collects
# the relelvent information.  Then it can generate HTML
# based upon that.
class Top100
  
  BASE_URL="http://www.empireonline.com/100-greatest-movie-characters/default.asp?c="
  def initialize
      @top100 = []
      @html = ""
  end

  # Iterates 100 times and just scrapes each page collecting the position (redundant), 
  # name of the character, and the image
  def scrape
    (1..100).each do |num|
      doc = Nokogiri::HTML(open(BASE_URL+num.to_s))
      elements = doc.xpath('//head/title').first.inner_html.split("|")[1].split(". ")
      pos = elements.delete_at(0)
      name = elements.join(". ") # For the few names that have a period in it... lazy hack 
      @top100 << {
        :pos=>pos,
        :name=>name.to_a.join(". "),
        :image=>"http://www.empireonline.com/images/features/100greatestcharacters/photos/#{num}.jpg"
      }
    end
    @top100
  end
  
  # Checs to see if the *@top100* array has been set.  If so, it returns it.  If not, 
  # it runs the *scrape* method
  def top100
    @top100.empty? ? scrape : @top100
  end
  
  # Genreates simple HTML to for display of the scraped data
  def generate
    top100.each do |entry|
      @html << <<-EOS

      <div class="entry">
      <h1>#{entry[:pos]}. #{entry[:name]}</h1>
      <div class="image">
        <img src="#{entry[:image]}" />
      </div>
      </div>

      EOS
    end
    @html
  end

end

top100 = Top100.new
puts top100.generate