rack-evil_robot 0.1.0

data/.gitignore

@@ -0,0 +1 @@
+pkg

data/README.rdoc

@@ -0,0 +1,31 @@
+= Rack::EvilRobot
+
+== INSTALL
+
+sudo gem install rack-evil_robot
+
+== SETUP
+
+  require 'rack/evil_robot'
+  use Rack::EvilRobot
+  
+  or
+  
+  use Rack::EvilRobot, :redirect_path => "http://www.whatever-you-want.com"
+
+== SET THE TRAP
+
+Update your robots.txt to contain these lines
+
+  User-agent: *
+  Disallow: /honey_pot/index.html
+
+Include this link tag on your page(s)
+  <a href="/honey_pot/index.html"><img src="images/pixel.gif" border="0" alt=" " width="1" height="1"></a>
+
+After you have this set up for a few days check your access logs and look at the user agents that have been accessing /honey_pot/index.html.
+Hopefully there is nothing there, but if there is, and they are misbehaving, add them to the regex defined in the 'evil_robots' method.
+This will prevent this user agent from accessing any pages on your site anymore.
+
+== Win
+Now you don't have to worry about getting crawled by bots you don't care to be hit by (mp3 bots, torrent bots, bots that are slamming your servers, etc...)

data/Rakefile

@@ -0,0 +1,44 @@
+require 'rubygems'
+require 'rake'
+
+begin
+  require 'jeweler'
+  Jeweler::Tasks.new do |gem|
+    gem.name = "rack-evil_robot"
+    gem.summary = "Detect robots that are ignoring your robots.txt file and give them the middle finger"
+    gem.description = "Detect robots that are ignoring your robots.txt file and give them the middle finger"
+    gem.email = "shanewolf@gmail.com"
+    gem.homepage = "http://github.com/gizm0duck/rack-evil_robot"
+    gem.authors = ["Shane Wolf"]
+    gem.add_dependency "rack"
+  end
+  Jeweler::GemcutterTasks.new
+rescue LoadError
+  puts "Jeweler (or a dependency) not available. Install it with: gem install jeweler"
+end
+
+require 'spec/rake/spectask'
+Spec::Rake::SpecTask.new(:spec) do |spec|
+  spec.libs << 'lib' << 'spec'
+  spec.spec_files = FileList['spec/**/*_spec.rb']
+end
+
+Spec::Rake::SpecTask.new(:rcov) do |spec|
+  spec.libs << 'lib' << 'spec'
+  spec.pattern = 'spec/**/*_spec.rb'
+  spec.rcov = true
+end
+
+task :spec => :check_dependencies
+
+task :default => :spec
+
+require 'rake/rdoctask'
+Rake::RDocTask.new do |rdoc|
+  version = File.exist?('VERSION') ? File.read('VERSION') : ""
+
+  rdoc.rdoc_dir = 'rdoc'
+  rdoc.title = "rack-evil_robot #{version}"
+  rdoc.rdoc_files.include('README*')
+  rdoc.rdoc_files.include('lib/**/*.rb')
+end

data/VERSION

@@ -0,0 +1 @@
+0.1.0

data/lib/rack/evil_robot.rb

@@ -0,0 +1,34 @@
+module Rack
+  class EvilRobot
+    def initialize(app, options = {})
+      @app = app
+      @redirect_path = options[:redirect_path] || 'http://www.example.com/'
+    end
+
+    def call(env)
+      if evil_robot?(env)
+        goodbye
+      else
+        if env['PATH_INFO'] =~ /honey_pot/
+          [200, {'Content-Type' => 'text/html'}, ['Mmmm Honey...']]
+        else
+          @app.call(env)
+        end
+      end
+    end
+
+    private
+    def evil_robot?(env)
+      env['HTTP_USER_AGENT'] && env['HTTP_USER_AGENT'] =~ evil_robots
+    end
+
+    def goodbye
+      [301, {'Location' => @redirect_path}, ['No thank you.']]
+    end
+    
+    def evil_robots
+      # add your evil-bots here... these are just for examples sake
+      /badBot|reallyBadBot/i
+    end
+  end
+end

data/rake-evil_robot.gemspec

@@ -0,0 +1,49 @@
+# Generated by jeweler
+# DO NOT EDIT THIS FILE DIRECTLY
+# Instead, edit Jeweler::Tasks in Rakefile, and run the gemspec command
+# -*- encoding: utf-8 -*-
+
+Gem::Specification.new do |s|
+  s.name = %q{rake-evil_robot}
+  s.version = "0.1.0"
+
+  s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
+  s.authors = ["Shane Wolf"]
+  s.date = %q{2010-08-06}
+  s.description = %q{Detect robots that are ignoring your robots.txt file and give them the middle finger}
+  s.email = %q{shanewolf@gmail.com}
+  s.extra_rdoc_files = [
+    "README"
+  ]
+  s.files = [
+    "README",
+     "Rakefile",
+     "VERSION",
+     "lib/rack/evil_robot.rb",
+     "spec/rack/evil_robot_spec.rb",
+     "spec/spec_helper.rb"
+  ]
+  s.homepage = %q{http://github.com/gizm0duck/rack-evil_robot}
+  s.rdoc_options = ["--charset=UTF-8"]
+  s.require_paths = ["lib"]
+  s.rubygems_version = %q{1.3.7}
+  s.summary = %q{Detect robots that are ignoring your robots.txt file and give them the middle finger}
+  s.test_files = [
+    "spec/rack/evil_robot_spec.rb",
+     "spec/spec_helper.rb"
+  ]
+
+  if s.respond_to? :specification_version then
+    current_version = Gem::Specification::CURRENT_SPECIFICATION_VERSION
+    s.specification_version = 3
+
+    if Gem::Version.new(Gem::VERSION) >= Gem::Version.new('1.2.0') then
+      s.add_runtime_dependency(%q<rack>, [">= 0"])
+    else
+      s.add_dependency(%q<rack>, [">= 0"])
+    end
+  else
+    s.add_dependency(%q<rack>, [">= 0"])
+  end
+end
+

data/spec/rack/evil_robot_spec.rb

@@ -0,0 +1,52 @@
+require 'spec_helper'
+
+describe Rack::EvilRobot do
+  
+  describe "call" do
+    attr_reader :app
+    before do
+      @app = lambda { |env| [200, {'Content-Type' => 'text/plain'}, ['This is my body']] }
+    end
+    
+    context "when the user agent is in the evil robots list" do
+      describe "when passing in custom redirect_path" do
+        it "redirects to the custom path" do
+          request = Rack::MockRequest.env_for('/real_path', {'HTTP_USER_AGENT' => 'badBot'})
+          response = Rack::EvilRobot.new(app, {:redirect_path => "http://www.google.com"}).call(request)
+          response[0].should == 301
+          response[1]["Location"].should == "http://www.google.com"
+          response[2].should == ["No thank you."]
+        end
+      end
+      
+      describe "when no custom options are passed in" do
+        it "redirects the bot to example.com" do
+          request = Rack::MockRequest.env_for('/real_path', {'HTTP_USER_AGENT' => 'badBot'})
+          response = Rack::EvilRobot.new(app).call(request)
+          response[0].should == 301
+          response[1]["Location"].should == "http://www.example.com/"
+          response[2].should == ["No thank you."]
+        end
+      end
+    end
+
+    context "when the user agent is not in the evil robots list" do
+      context "when the request hits the honey pot" do
+        it "tells the robot it's been busted" do
+          request = Rack::MockRequest.env_for('/honey_pot/sticky.html', {'HTTP_USER_AGENT' => 'Mozilla/5.0'})
+          response = Rack::EvilRobot.new(app).call(request)
+          response.first.should == 200
+          response.last.should == ["Mmmm Honey..."]
+        end
+      end
+      
+      context "when the request does not hit the honey pot" do
+        it "does nothing" do
+          request = Rack::MockRequest.env_for('/real_path', {'HTTP_USER_AGENT' => 'Mozilla/5.0'})
+          body = Rack::EvilRobot.new(app).call(request).last
+          body.should == ['This is my body']
+        end
+      end
+    end
+  end
+end

data/spec/spec_helper.rb

@@ -0,0 +1,11 @@
+$LOAD_PATH.unshift(File.dirname(__FILE__))
+$LOAD_PATH.unshift(File.join(File.dirname(__FILE__), '..', 'lib'))
+require 'rack/evil_robot'
+require 'spec'
+require 'spec/autorun'
+require 'rack'
+
+
+Spec::Runner.configure do |config|
+  
+end

metadata

@@ -0,0 +1,88 @@
+--- !ruby/object:Gem::Specification 
+name: rack-evil_robot
+version: !ruby/object:Gem::Version 
+  hash: 27
+  prerelease: false
+  segments: 
+  - 0
+  - 1
+  - 0
+  version: 0.1.0
+platform: ruby
+authors: 
+- Shane Wolf
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2010-08-06 00:00:00 -07:00
+default_executable: 
+dependencies: 
+- !ruby/object:Gem::Dependency 
+  name: rack
+  prerelease: false
+  requirement: &id001 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        hash: 3
+        segments: 
+        - 0
+        version: "0"
+  type: :runtime
+  version_requirements: *id001
+description: Detect robots that are ignoring your robots.txt file and give them the middle finger
+email: shanewolf@gmail.com
+executables: []
+
+extensions: []
+
+extra_rdoc_files: 
+- README.rdoc
+files: 
+- .gitignore
+- README.rdoc
+- Rakefile
+- VERSION
+- lib/rack/evil_robot.rb
+- rake-evil_robot.gemspec
+- spec/rack/evil_robot_spec.rb
+- spec/spec_helper.rb
+has_rdoc: true
+homepage: http://github.com/gizm0duck/rack-evil_robot
+licenses: []
+
+post_install_message: 
+rdoc_options: 
+- --charset=UTF-8
+require_paths: 
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement 
+  none: false
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      hash: 3
+      segments: 
+      - 0
+      version: "0"
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  none: false
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      hash: 3
+      segments: 
+      - 0
+      version: "0"
+requirements: []
+
+rubyforge_project: 
+rubygems_version: 1.3.7
+signing_key: 
+specification_version: 3
+summary: Detect robots that are ignoring your robots.txt file and give them the middle finger
+test_files: 
+- spec/rack/evil_robot_spec.rb
+- spec/spec_helper.rb