simple_pager.rb

require "rubygems"
require "nokogiri"
require "open-uri"
require "uri"

class SimplePager
  include Enumerable

  attr_reader :doc, :original_url, :current_url

  def initialize(original_url, next_link_xpath)
    @original_url    = original_url
    @current_url     = original_url
    @next_link_xpath = next_link_xpath

    @continue = true

    @doc = Nokogiri::HTML(open(original_url))
  end

  def stop
    @continue = false
  end

  def next
    next_link = @doc.xpath(@next_link_xpath).first["href"]
    next_link = URI.split(@original_url)[0] + "://" + URI.split(@original_url)[2] + next_link unless /^http/ =~ next_link

    @doc = Nokogiri::HTML(open(next_link))
    @current_url = next_link

    self
  end

  def each
    yield @doc

    if @continue
      self.next.each do |doc|
        yield doc
      end
    end
  end
end

simple_pager_sample.rb

pager = SimplePager.new("http://june29.jp/", "//a[@rel='next']")

pager.each do |doc|
  puts "------------------------"
  puts pager.current_url
  puts "------------------------"

  doc.xpath("//div[contains(concat(' ', normalize-space(@class), ' '), ' hentry ')]").each do |hentry|
    title = hentry.xpath("./h2[@class='entry-title']").text
    link  = hentry.xpath("./h2[@class='entry-title']/a").attr("href")

    if /2008\/10/ =~ link
      pager.stop
      break
    end

    puts "#{title}\n\t#{link}"
  end

  sleep 5
end