special_agent 0.1.3

data/lib/tasks/bot_agent_test.rake

@@ -0,0 +1,86 @@
+require "special_agent"
+require 'rexml/document'
+
+task :test_bots do
+	success = 0
+	fail = 0
+	
+	# tests for successful bot detection
+	bot_user_agent_strings = [
+		"ia_archiver (+http://www.alexa.com/site/help/webmasters; crawler@alexa.com)",
+		"Mozilla/5.0 (compatible; Googlebot/2.1; +http://www.google.com/bot.html)"
+		]
+	browser_user_agent_strings = [
+		"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_5_5; sv-se) AppleWebKit/525.26.2 (KHTML, like Gecko) Version/3.2 Safari/525.26.12",
+	  "Mozilla/5.0 (iPhone; U; Linux i686; pt-br) AppleWebKit/532+ (KHTML, like Gecko) Version/3.0 Mobile/1A538b Safari/419.3 Midori/0.2.0",
+	  "Mozilla/5.0 (iPhone; U; CPU iPhone OS 4_3_1 like Mac OS X; zh-tw) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8G4 Safari/6533.18.5",
+	  "Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_8; de-at) AppleWebKit/533.21.1 (KHTML, like Gecko) Version/5.0.5 Safari/533.21.1",
+	  "Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_5_8; en-us) AppleWebKit/533.21.1 (KHTML, like Gecko) Version/5.0.5 Safari/533.21.1",
+	  "Mozilla/5.0 (Windows; U; Windows NT 6.1; tr-TR) AppleWebKit/533.20.25 (KHTML, like Gecko) Version/5.0.4 Safari/533.20.27",
+	  "Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.1; Trident/6.0)",
+	  "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; Zune 4.0; InfoPath.3; MS-RTC LM 8; .NET4.0C; .NET4.0E)",
+	  "Mozilla/5.0 (Windows NT 6.1; rv:6.0) Gecko/20110814 Firefox/6.0",
+	  "Mozilla/5.0 (X11; U; Linux i586; de; rv:5.0) Gecko/20100101 Firefox/5.0",
+	  "Opera/9.80 (Windows NT 6.1; U; es-ES) Presto/2.9.181 Version/12.00",
+	  "Opera/9.80 (X11; Linux i686; U; ru) Presto/2.8.131 Version/11.11"
+		]
+	puts
+	puts "parsing the user-agents.org list..."
+	doc = REXML::Document.new(File.open("lib/tasks/allagents.xml"))
+	doc.elements.each("user-agents/user-agent") do |ua|
+		bot = false
+		browser = false
+		ua.elements.each("Type") do |item|
+			if item.text == "R" || item.text == "S"
+				bot = true
+			elsif item.text == "B"
+				browser = true
+			end
+			
+		end
+		if bot
+			ua.elements.each("String") do |item|
+				bot_user_agent_strings << item.text
+			end
+		end
+		if browser
+                        ua.elements.each("String") do |item|
+                                browser_user_agent_strings << item.text
+                        end
+                end
+	end
+	puts "testing..."
+	bot_user_agent_strings.each do |ua_str|
+		ua = SpecialAgent::UserAgent.new(ua_str)
+		if ua.is_bot?
+			#puts "SUCCESS:: " + ua_str
+			success += 1
+		else
+			#puts "FAIL:: " + ua_str
+			fail += 1
+		end
+	end
+
+	puts "BOT DETECTION"
+	puts success.to_s + " succeed. BENCHMARK: 376"
+	puts fail.to_s + " fail. BENCHMARK: 1083"
+	
+	success = 0
+	fail = 0 
+
+        browser_user_agent_strings.each do |ua_str|
+                ua = SpecialAgent::UserAgent.new(ua_str)
+                if !ua.is_bot?
+                        #puts "SUCCESS:: " + ua_str
+                        success += 1
+                else
+                        #puts "FAIL:: " + ua_str
+                        fail += 1
+                end
+        end
+
+	puts "FALSE POSITIVES CHECK"
+	puts success.to_s + " succeed. BENCHMARK: 326"
+	puts fail.to_s + " fail. BENCHMARK: 4"
+
+end

data/spec/spec_helper.rb

@@ -0,0 +1,16 @@
+require 'rubygems'
+require 'bundler'
+begin
+  Bundler.setup(:default, :development)
+rescue Bundler::BundlerError => e
+  $stderr.puts e.message
+  $stderr.puts "Run `bundle install` to install missing gems"
+  exit e.status_code
+end
+
+require File.join(File.dirname(__FILE__), "user_agent_matcher")
+
+
+$LOAD_PATH.unshift(File.join(File.dirname(__FILE__), '..', 'lib'))
+$LOAD_PATH.unshift(File.dirname(__FILE__))
+require 'special_agent'

data/spec/user_agent_matcher.rb

@@ -0,0 +1,16 @@
+class RSpec::Core::ExampleGroup
+
+  class << self
+
+    def detect(user_agent, &block)
+      klass = self.describes
+      subject = klass.new(user_agent)
+      it(user_agent) do
+        yield subject
+      end
+    end
+
+  end
+end
+
+

data/spec/user_agent_spec.rb

@@ -0,0 +1,85 @@
+require File.dirname(__FILE__) + '/spec_helper'
+
+describe SpecialAgent::UserAgent do
+
+  describe "Safari" do
+    detect "Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_8; de-at) AppleWebKit/533.21.1 (KHTML, like Gecko) Version/5.0.5 Safari/533.21.1" do |ua|
+      ua.device.type.should == :computer
+      ua.device.name.should == "Computer"
+      ua.device.version.should == nil
+
+      ua.device.operating_system.name.should == "Mac OS X"
+      ua.device.operating_system.version.to_s.should == "10.6.8"
+
+      ua.device.platform.name.should == "Macintosh"
+      ua.device.platform.version.should == nil
+
+      ua.device.engine.name.should == "AppleWebKit"
+      ua.device.engine.version.to_s.should == "533.21.1"
+
+      ua.device.engine.browser.name.should == "Safari"
+      ua.device.engine.browser.version.to_s.should == "533.21.1"
+    end
+
+    detect "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_1) AppleWebKit/535.5 (KHTML, like Gecko) Chrome/16.0.891.1 Safari/535.5" do |ua|
+      ua.device.type.should == :computer
+      ua.device.name.should == "Computer"
+      ua.device.version.should == nil
+
+      ua.device.operating_system.name.should == "Mac OS X"
+      ua.device.operating_system.version.to_s.should == "10.7.1"
+
+      ua.device.platform.name.should == "Macintosh"
+      ua.device.platform.version.should == nil
+
+      ua.device.engine.name.should == "AppleWebKit"
+      ua.device.engine.version.to_s.should == "535.5"
+
+      ua.device.engine.browser.name.should == "Safari"
+      ua.device.engine.browser.version.to_s.should == "535.5"
+    end
+  end
+
+  describe "Firefox" do
+    detect "Mozilla/5.0 (X11; Linux i686; rv:6.0) Gecko/20100101 Firefox/6.0" do |ua|
+      ua.device.type.should == :computer
+      ua.device.name.should == "Computer"
+      ua.device.version.should == nil
+
+      ua.device.operating_system.name.should == "Linux"
+      ua.device.operating_system.version.to_s.should == "i686"
+
+      ua.device.platform.name.should == "PC"
+      ua.device.platform.version.should == nil
+
+      ua.device.engine.name.should == "Gecko"
+      ua.device.engine.version.to_s.should == "20100101"
+
+      # TODO should be Chrome.
+      ua.device.engine.browser.name.should == "Firefox"
+      ua.device.engine.browser.version.to_s.should == "6.0"
+    end
+  end
+
+  describe "Chrome" do
+    detect "Mozilla/5.0 (Windows NT 5.1) AppleWebKit/535.2 (KHTML, like Gecko) Chrome/15.0.872.0 Safari/535.2" do |ua|
+      ua.device.type.should == :computer
+      ua.device.name.should == "Computer"
+      ua.device.version.should == nil
+
+      ua.device.operating_system.name.should == "Windows"
+      ua.device.operating_system.version.to_s.should == "5.1"
+
+      ua.device.platform.name.should == "PC"
+      ua.device.platform.version.should == nil
+
+      ua.device.engine.name.should == "AppleWebKit"
+      ua.device.engine.version.to_s.should == "535.2"
+
+      # TODO should be Chrome.
+      ua.device.engine.browser.name.should == "Safari"
+      ua.device.engine.browser.version.to_s.should == "535.2"
+    end
+  end
+
+end

data/special_agent.gemspec

@@ -0,0 +1,23 @@
+# -*- encoding: utf-8 -*-
+require 'rake'
+$:.push File.expand_path("../lib", __FILE__)
+require "special_agent/version"
+
+Gem::Specification.new do |s|
+  s.name        = "special_agent"
+  s.version     = SpecialAgent::VERSION
+  s.authors     = ["Zeke Sikelianos"]
+  s.email       = ["zeke@sikelianos.com"]
+  s.homepage    = "http://github.com/zeke/special_agent"
+  s.summary     = %q{Parse and process User Agents like a secret one}
+  s.description = %q{Parse and process User Agents like a secret one}
+
+  s.add_development_dependency "rake"
+  s.add_development_dependency "rspec"
+  s.add_development_dependency "bundler"
+
+  s.files         = `git ls-files`.split("\n")
+  s.test_files    = `git ls-files -- {test,spec,features}/*`.split("\n")
+  s.executables   = `git ls-files -- bin/*`.split("\n").map{ |f| File.basename(f) }
+  s.require_paths = ["lib"]
+end

data/special_agent_example

@@ -0,0 +1,39 @@
+#!/usr/bin/env ruby
+
+require "special_agent/user_agent"
+
+user_agent_strings = [
+  "Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_5_5; sv-se) AppleWebKit/525.26.2 (KHTML, like Gecko) Version/3.2 Safari/525.26.12",
+  "Mozilla/5.0 (iPhone; U; Linux i686; pt-br) AppleWebKit/532+ (KHTML, like Gecko) Version/3.0 Mobile/1A538b Safari/419.3 Midori/0.2.0",
+  "Mozilla/5.0 (iPhone; U; CPU iPhone OS 4_3_1 like Mac OS X; zh-tw) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8G4 Safari/6533.18.5",
+  "Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_8; de-at) AppleWebKit/533.21.1 (KHTML, like Gecko) Version/5.0.5 Safari/533.21.1",
+  "Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_5_8; en-us) AppleWebKit/533.21.1 (KHTML, like Gecko) Version/5.0.5 Safari/533.21.1",
+  "Mozilla/5.0 (Windows; U; Windows NT 6.1; tr-TR) AppleWebKit/533.20.25 (KHTML, like Gecko) Version/5.0.4 Safari/533.20.27",
+  "Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.1; Trident/6.0)",
+  "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; Zune 4.0; InfoPath.3; MS-RTC LM 8; .NET4.0C; .NET4.0E)",
+  "Mozilla/5.0 (Windows NT 6.1; rv:6.0) Gecko/20110814 Firefox/6.0",
+  "Mozilla/5.0 (X11; U; Linux i586; de; rv:5.0) Gecko/20100101 Firefox/5.0",
+  "Opera/9.80 (Windows NT 6.1; U; es-ES) Presto/2.9.181 Version/12.00",
+  "Opera/9.80 (X11; Linux i686; U; ru) Presto/2.8.131 Version/11.11",
+  "ia_archiver (+http://www.alexa.com/site/help/webmasters; crawler@alexa.com)",
+  "Mozilla/5.0 (compatible; Googlebot/2.1; +http://www.google.com/bot.html)"
+  ]
+
+def process_user_agent(ua_str)
+  puts
+  puts '='*120
+  puts "Original User Agent:"
+  puts "  #{ua_str}"
+  puts
+  ua = SpecialAgent::UserAgent.new(ua_str)
+  puts "Parsed Object String:"
+  puts "  #{ua}"
+  puts '='*120
+end
+
+SpecialAgent::DEBUG = true
+SpecialAgent::DEBUG_LEVEL = 2
+
+user_agent_strings.each do |ua_str|
+  process_user_agent(ua_str)
+end

metadata

@@ -0,0 +1,101 @@
+--- !ruby/object:Gem::Specification
+name: special_agent
+version: !ruby/object:Gem::Version
+  version: 0.1.3
+  prerelease: 
+platform: ruby
+authors:
+- Zeke Sikelianos
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2011-12-05 00:00:00.000000000Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: &70202056269220 !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: *70202056269220
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: &70202056268760 !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: *70202056268760
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: &70202056268320 !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: *70202056268320
+description: Parse and process User Agents like a secret one
+email:
+- zeke@sikelianos.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- .gitignore
+- Gemfile
+- README.md
+- Rakefile
+- lib/special_agent.rb
+- lib/special_agent/base.rb
+- lib/special_agent/browser.rb
+- lib/special_agent/device.rb
+- lib/special_agent/engine.rb
+- lib/special_agent/operating_system.rb
+- lib/special_agent/platform.rb
+- lib/special_agent/user_agent.rb
+- lib/special_agent/version.rb
+- lib/tasks/allagents.xml
+- lib/tasks/bot_agent_test.rake
+- spec/spec_helper.rb
+- spec/user_agent_matcher.rb
+- spec/user_agent_spec.rb
+- special_agent.gemspec
+- special_agent_example
+homepage: http://github.com/zeke/special_agent
+licenses: []
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 1.8.10
+signing_key: 
+specification_version: 3
+summary: Parse and process User Agents like a secret one
+test_files:
+- spec/spec_helper.rb
+- spec/user_agent_matcher.rb
+- spec/user_agent_spec.rb