a simple script to fetch url schemes from http://handleopenurl.com/scheme.

handleopenurl_parser.rb

# coding: utf-8
require "rubygems"
require "nokogiri"
require 'open-uri'

SITE_URL = "http://handleopenurl.com/scheme?page="

page = 0
last = false
result = {}

loop do
  page += 1
  doc = Nokogiri::HTML(open(SITE_URL + page.to_s))
  
  if(doc && !last)
    doc.css("#schemeIndex .scheme").each do |node|
      appname = node.css("h1").first.text
      schemes = []

      if(!appname.empty? && node.css(".code").count > 0)
        schemes = node.css(".code").first.text.split(" ")

        # end if stop paging
        if(result.has_key?(appname))
          last = true
          break
        end

        puts "#{appname}: #{schemes.to_s}"
        result[appname] = schemes
      end
    end
  else
    break
  end

  # DO NOT ATTACK
  sleep 1
end