ターンエーのセリフ抽出

turn_a_word.rb

#!/usr/local/bin/ruby

require 'rubygems'
require 'hpricot'
require 'open-uri'
require 'uri'
require 'kconv'

def getWord(page)
   html = Hpricot(open(URI.parse(@uri) + page))
   html.search("tr"){ |tr|

     td = tr.search("td")
     if td[0].inner_html.toutf8 =~ /#{@char}/
       puts $1 if !td[1].nil? && td[1].inner_text.toutf8 =~ /^(.+?)$/
     end
   }
end

@uri = ARGV[0] || "http://www.geocities.co.jp/AnimeComic-Pastel/3829/portal_TurnA.html"
@char = ARGV[1] || "ロラン"
html = Hpricot(open(@uri))
html.search("a"){ |a|
  getWord $1 if a.attributes['href'] =~ /^(words.+?)$/
}