Created
March 9, 2012 18:57
-
-
Save deeeki/2008059 to your computer and use it in GitHub Desktop.
hituji_tokyo_emptyrooms
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 'mechanize' | |
SITE_URL = 'http://www.hituji.jp' | |
INFO_URL = "#{SITE_URL}/comret/info" | |
a = Mechanize.new | |
links = a.get(INFO_URL).search('.searchAreaElement').at('td').search('a').map do |city| | |
city['href'] | |
end | |
rows = [%w(name type low high status line owner cond comment id url).join(',')] | |
links.each do |l| | |
a.get(l).search('.propertyList').search('h3, .propertySummary').each do |elm| | |
break if elm.name == 'h3' | |
/(?<type>[^\d]+)¥(?<low>[\d]+) \- (?<high>[\d]+).*/ =~ elm.at('.emptyInfo').child.text.strip | |
cols = [ | |
elm.at('.houseName > a').text.strip, | |
type, | |
low, | |
high, | |
elm.at('.emptyStatusLabel > a').text.strip, | |
elm.at('.lineInfo').child.text.strip, | |
elm.at('.ownerName > a').text.strip, | |
elm.at('.ownerName').next.text.strip, | |
elm.at('.comment').text.strip, | |
elm.at('.propertyId').text.strip, | |
SITE_URL + elm.at('.houseName > a')['href'], | |
] | |
rows << ('"' << cols.map{|c| c.to_s.gsub(/"/, '""')}.join('","') << '"') | |
end | |
end | |
puts rows.join("\n") |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment