vorkers_list_repeat.rb

pagelist.txt

http://www.vorkers.com/field.php?ind_code=0003&f_code=0025
http://www.vorkers.com/field.php?next_page=2&ind_code=0003&f_code=0025
http://www.vorkers.com/field.php?next_page=3&ind_code=0003&f_code=0025

vorkers_list_repeat.rb

require 'open-uri'
require 'nokogiri'

def getList(gyokai_url)
  charset = nil
  html = open(gyokai_url) do |f|
    charset = f.charset # 文字種別を取得
    f.read # htmlを読み込んで変数htmlに渡す
  end

  # htmlをパース(解析)してオブジェクトを作成
  doc = Nokogiri::HTML.parse(html, nil, charset)

  doc.xpath('//tr').each_with_index do |node,index|
    if index == 0
      next
    end

    puts [
      node.xpath('.//td[@class="comp_name"]').text,
      node.xpath('.//td[@class="comp_name"]/a').attribute('href').value,
      node.xpath('.//td[@class="num_answer"]').text,
      node.xpath('.//td[@class="total_score"]/span[@class="score_up"]').text
    ].join(',')
  end
end

open('pagelist.txt').each do |line|
  p line.chomp!
  getList(line)
end