http://d.hatena.ne.jp/UDONCHAN/20100503/1272888368

tf.rb

#!/usr/bin/env ruby
# -*- coding: utf-8 -*-
require 'rubygems'
require 'MeCab'
require 'net/http'
require 'uri'
require 'extractcontent.rb'
$KCODE='u'
Net::HTTP.version_1_2

class TF

  @tagger = nil
  @extract_content = nil

  def initialize
    @tagger = MeCab::Tagger.new('-O wakati')
    @extract_content = ExtractContent::Extractor.new({:decay_factor=>0.75})
  end

  def fetch(uri_str, limit = 10)
    uri = URI.parse(URI.encode(uri_str))
    raise ArgumentError, 'http redirect too deep' if limit == 0
    response = nil
    Net::HTTP.new(uri.host).start do |http|
      response = http.get(uri.request_uri, {'user-agent' => 'Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10.6; en-US; rv:1.9.2.4) Gecko/20100413 Firefox/3.6.4'})
    end
    case response
    when Net::HTTPSuccess     then response
    when Net::HTTPRedirection then fetch(response['Location'], limit - 1)
    else
      response.error!
    end
  end
  protected :fetch

  def mecab_node(context)
    @tagger.parseToNode(context)
  end
  protected :mecab_node
  
  def tf(html)
    tf = Hash::new
    n = mecab_node(@extract_content.analyse(fetch(html).body).first)
    while n do
      if /^名詞/ =~ n.feature
        if tf.key?(n.surface)
          tf[n.surface] = tf[n.surface] + 1
        else
          tf[n.surface] = 1
        end
      end
      n = n.next
    end
    tf
  end

end

TF::new.tf('http://ja.wikipedia.org/wiki/沢城みゆき').each do |k, v|
  puts "#{k} : #{v}"
end