gistfile1.rb

require 'open-uri'

namespace :tax_rates_scraper do
  namespace :california do
    # Order to run the rake tasks:
    # rake tax_rates_scraper:california:tax_rates
    # rake tax_rates_scraper:california:zip_codes 
    
    task :zip_codes => [:environment] do
      url  = "http://www.melissadata.com/lookups/CountyZip.asp?State=CA06California"
      file = open(url)
      page = file.read
    
      page.scan(/<option value="(06[0-9]+)">([a-z\s]+)<\/option>/i).each do |match|
        url_end = match[0]
        county  = match[1]
      
        # Download each County file to db/CA/#{county}.html
        county_url = "http://www.melissadata.com/lookups/CountyZip.asp?fips=" + url_end
        save_loc  = Rails.root.join("db/zip_codes/CA/#{county}.html")
      
        download_url(county_url, save_loc)
        puts "Saved #{save_loc}"
      end
    end
  
    def download_url(from, to)
      open(to, 'wb') { |file| file << open(from).read }
    end
  end
end