Created
December 23, 2014 13:51
-
-
Save shirayuca/d3c0d4b9619e8860e689 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
require 'open-uri' | |
require 'nokogiri' | |
url = 'http://www.vorkers.com/field.php?ind_code=0003&f_code=0025' | |
charset = nil | |
html = open(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 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment