dl.rb

# -*- coding: utf-8 -*-
#######################################
# 将棋の棋譜でーたべーすのidのリスト
# を使って棋譜をぶっこぬくスクリプト
#######################################
require 'open-uri'
require 'nkf'
require 'nokogiri'

File.open("./kid.list","r") do |f|
  `mkdir -p tmp-kifu`
  while (line = f.gets)
    kid = line.chomp
    puts kid
    url = "http://wiki.optus.nu/shogi/index.php?cmd=kif&cmds=displaytxt&kid=#{kid}"
    #page = NKF.nkf('-w', open(url).read)
    try_count = 0
    begin
      page = open(url,
                  "User-Agent" =>
                  "Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10.5; ja-JP-mac; rv:1.9.0.6) Gecko/2009011912 Firefox/3.0.6"
                  ).read
    rescue 
      if try_count < 10
        try_count += 1
        retry
      end
      raise "10回失敗"
    end
    if page.to_s == ""
      raise "取得できなかった"
    end
    doc  = Nokogiri::HTML(page)
    doc.search('textarea').each do |t|
      File.open("./tmp-kifu/#{kid}.kif","w") do |out|
        out.puts t.text
      end   
    end
    sleep 2
  end
end