Web ページの本文から【相変わらず女の子からも人気の定番アイテム！】みたいな prefix を抜き出すやつ

extract_prefix.rb

# coding: utf-8
#!/usr/bin/env ruby
require 'open-uri'
require 'nokogiri'

# Usage: ruby extract_prefix.rb http://shop.menz-style.com/
#        ruby extract_prefix.rb http://hayabusa.2ch.net/news4vip/subback.html

def get_prefix_list(url)
  list = []
  doc = Nokogiri::HTML.parse(open(url).read)
  doc.text.scan(/【.+?】/u).each do |text|
   list << text
  end
  list.uniq
end

puts get_prefix_list(ARGV[0])