Created
August 3, 2010 00:59
-
-
Save huacnlee/505618 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
# | |
# Ruby scrapi 采集口碑房源数据 | |
# Author: Huacnlee <huacnlee@gmail.com> | |
# Blog: http://huacnlee.com | |
# | |
# Gems install: | |
# sudo gem install scrapi | |
# | |
require 'rubygems' | |
require 'scrapi' | |
scraper = Scraper.define do | |
array :items | |
process "html>body>div.yui-d2f>div#bd.yui-cn-t2>div.yui-main>div.yui-b>table.infoList>tbody>tr", | |
:items => Scraper.define { | |
process "td:nth-child(2)>p.titleInfo>a:nth-child(1)", :title => :text, :link => "@href" | |
process "td:nth-child(3)>p.priceInfo>span.number", :price => :text | |
process "td:nth-child(3)>p.fitmentInfo", :fitment => :text | |
process "td:nth-child(4)>p.rentStyle", :style => :text | |
result :price,:title, :link, :style, :fitment | |
} | |
result :items | |
end | |
uri = URI.parse("http://chengdu.koubei.com/fang/li-rent-all.html") | |
scraper.scrape(uri).each do |house| | |
puts "标题:#{house.title}" | |
puts "价格:#{house.price} 元/月" | |
puts "类型:#{house.style}" | |
puts "装修:#{house.fitment }" | |
puts "连接:#{house.link}" | |
puts | |
end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment