取网站domain

local_file_c = File.open("/Usres/shuguo/directory/c.txt")

local_file_d = File.open("/Usres/shuguo/directory/d.txt")


local_file_c.each_line do|line|
  add_domain_whitelist(local_file_d, line)
end


local_file_d.close

def parse_macro(url)
      urls = url.scan(/{((\S*?):(.*?))}/).collect{|u|u[2]}
      urls << url.split(/http(s)?(%3A%2F%2F|:\/\/)/).select{|u| u.to_s != "://" and u.to_s != ""}
      return [url] if urls.empty?
      return urls.flatten.uniq
end


def add_domain_whitelist( local_file_d, display_url )
     host = nil
     domain = nil
     current_host = Addressable::URI.heuristic_parse(display_url).host
     current_domain = PublicSuffix.parse(current_host.downcase).domain
     host = Addressable::URI.heuristic_parse(url).host
     domain = PublicSuffix.parse(host.downcase).domain
     local_file_d << domain + "\n"
end

猜你喜欢

转载自schooltop.iteye.com/blog/2241632