Google sitemap generator scripts

README

These files describes how to configure automatic google sitemap 
generation.

1. In your models you should define class method which will be generate 
   array or urls with last modified timestamp.
2. In 'lib/tasks/google_sitemap.rb' you should update 'sources' and 
   'host' variables for your site.
3. You should configure cron tasks to periodically regenerate sitemap 
   and ping google. You could use nice gem whenever and sample schedule 
   in 'config/schedule.rb'
4. This task will generate sitemap index and several sitemaps (one for 
   each models, because google limited items in one sitemap to 50k). It 
   places sitemaps to 'public/sitemaps'. It also gzips all sitemaps to 
   save traffic.
5. Install sitemap in google webmaster's tools using such URL 
   'http://yoursite.com/sitemaps/index.xml.gz'

That's all

google_sitemap.rb

require 'net/http'
require 'uri'
 
# A class specific to the application which generates a google sitemap from the contents of the database.
# Author: Alastair Brunton
# Modified: Harry Love 2008-06-09
class GoogleSitemapGenerator
 
  def initialize(base_url, sources)
    @base_url = base_url
    @sources = sources
  end
 
  # 1. Iterate through each model's #get_paths method
  # 2. Create sitemap file for each model
  # 3. Create sitemap index file
  # 4. Ping Google
  def generate
    path_ar = []
    sitemaps = []
    @sources.each do |source|
      # initialize the class and call the get_paths method on it.
      path_ar = eval("#{source}.get_paths")
      xml = generate_sitemap(path_ar)
      save_file(source, xml)
    end
    index = generate_sitemap_index(@sources)
    save_file('index', index)
    update_google
  end
 
  # Create a sitemap document for a model
  def generate_sitemap(path_ar)
    xml_str = ""
    xml = Builder::XmlMarkup.new(:target => xml_str)
    xml.instruct!
    xml.urlset(:xmlns => 'http://www.sitemaps.org/schemas/sitemap/0.9') {
      path_ar.each do |path|
        xml.url {
      	  xml.loc(@base_url + path[:url])
      	  xml.lastmod(path[:last_mod])
      	  xml.changefreq('weekly')
        }
      end
    }
    xml_str
  end
 
  # Create a sitemap index document
  def generate_sitemap_index(sitemaps)
    xml_str = ""
    xml = Builder::XmlMarkup.new(:target => xml_str)
    xml.instruct!
    xml.sitemapindex(:xmlns => 'http://www.sitemaps.org/schemas/sitemap/0.9') {
      sitemaps.each do |site|
        xml.sitemap {
      	  xml.loc(@base_url + "/sitemaps/sitemap_#{site.underscore}.xml.gz")
      	  xml.lastmod(Time.now.strftime('%Y-%m-%d'))
   	}
      end
    }
    xml_str
  end
 
  # Save the xml file (gzipped) to disk
  def save_file(source, xml)
    FileUtils.mkdir_p(RAILS_ROOT + "/public/sitemaps/")
    File.open(RAILS_ROOT + "/public/sitemaps/sitemap_#{source.underscore}.xml.gz", 'w+') do |f|
      gz = Zlib::GzipWriter.new(f)
      gz.write xml
      gz.close
    end
  end
 
  # Notify Google of the new sitemap index file
  def update_google
    sitemap_uri = @base_url + '/sitemaps/sitemap_index.xml.gz'
    escaped_sitemap_uri = URI.escape(sitemap_uri)
    puts 'www.google.com/webmasters/tools/ping?sitemap=' + escaped_sitemap_uri
    puts Net::HTTP.get('www.google.com', '/webmasters/tools/ping?sitemap=' + escaped_sitemap_uri)
  end
end

page.rb

class Page < ActiveRecord::Base

  def self.get_paths
    urls = []
    Page.all.each do |page|
      urls << { :url => "/pages/#{page.to_param}", :last_mod => page.updated_at.strftime('%Y-%m-%d')}
    end
    urls
  end

end

post.rb

class Post < ActiveRecord::Base

  def self.get_paths
    urls = []
    Post.all.each do |post|
      urls << { :url => "/posts/#{post.to_param}", :last_mod => post.updated_at.strftime('%Y-%m-%d')}
    end
    urls
  end

end

schedule.rb

set :output, "#{RAILS_ROOT}/log/cron.log"

every 1.day do
  rake "google_sitemap:generate"
end

sitemap.rake

require 'google_sitemap'
namespace :google_sitemap do
  desc "Generate a Google sitemap from the models"
  task(:generate => :environment) do
    # Generate sitemaps for each of the models listed in the array
    sources = %w(Post Page)
    host = ENV['HOST'] || 'http://mysite.com'
    sitemap = GoogleSitemapGenerator.new(host, sources)
    sitemap.generate
  end
end