博客下载脚本

geekonomics_crawl

#觉得http://www.geekonomics10000.com/的内容都很不错，写了个脚本分类把文章抓起来做成txt,可以放到手机当电子书看
require "rubygems"
require "open-uri"
require 'hpricot' 

blog = File.new("blog.txt","w")
%w{self_develop books movies china conventional_wisdom politics science 
   joking us microtrends pop_science social_atom tech critics}.each do |category| 
   puts "downloading category #{category}"
   blog.puts category
   page = 1
   begin        
        target_url = "http://www.geekonomics10000.com/category/#{category}/page/#{page}"  
        doc = Hpricot(open(target_url))         
        doc.search("h3.post-title/a").each do |link|
            puts "downloding #{link.inner_html}"
            blog.puts link.inner_html
            post = Hpricot(open(link.attributes["href"]))
            post.search("div.post-content/p").each do |content|
                blog.puts content.inner_html
            end                  
        end      
        page += 1      
  end  while doc.search("div.alignleft").inner_html != ""
  10.times {puts ""}
end
blog.close