is_crawler 0.0.1

data/.gitignore

@@ -0,0 +1,17 @@
+*.gem
+*.rbc
+.bundle
+.config
+.yardoc
+Gemfile.lock
+InstalledFiles
+_yardoc
+coverage
+doc/
+lib/bundler/man
+pkg
+rdoc
+spec/reports
+test/tmp
+test/version_tmp
+tmp

data/Gemfile

@@ -0,0 +1,4 @@
+source 'https://rubygems.org'
+
+# Specify your gem's dependencies in is_crawler.gemspec
+gemspec

data/LICENSE.txt

@@ -0,0 +1,22 @@
+Copyright (c) 2013 Chris Cashwell
+
+MIT License
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/README.md

@@ -0,0 +1,46 @@
+# IsCrawler
+
+is\_crawler does exactly what you might think it does: determine if the current request is coming from a crawler or bot.
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+    gem 'is_crawler'
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install is_crawler
+
+## Usage
+
+You can use the `is_any_crawler?` method to determine if the given string, as you might have guessed, matches *any* (noteworthy) crawler, like so:
+
+    class MyController < ActionController::Base
+      include IsCrawler
+      def index
+        if is_any_crawler? request.env["HTTP_USER_AGENT"]
+          render 'special_crawler_index'
+        else
+          render 'normal_boring_index'
+        end
+      end
+    end
+
+...or the `is_crawler?("Some User Agent/1.0", :facebook, :google)` methods to determine if you're dealing with one or more specific crawlers. That's it!
+
+## Contributing
+
+Missing out on a noteworthy crawler? Find a problem? Ideas for improvement?
+
+Raise an issue, or:
+
+1. Fork it
+2. Create your feature branch (`git checkout -b my-new-feature`)
+3. Commit your changes (`git commit -am 'Add some feature'`)
+4. Push to the branch (`git push origin my-new-feature`)
+5. Create new Pull Request

data/Rakefile

@@ -0,0 +1 @@
+require "bundler/gem_tasks"

data/is_crawler.gemspec

@@ -0,0 +1,21 @@
+# -*- encoding: utf-8 -*-
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'is_crawler'
+
+Gem::Specification.new do |gem|
+  gem.name          = "is_crawler"
+  gem.version       = IsCrawler::VERSION
+  gem.authors       = ["Chris Cashwell"]
+  gem.email         = ["ccashwell@gmail.com"]
+  gem.description   = %q{is_crawler does just what you might expect: detect whether the current request is from a crawler.}
+  gem.summary       = %q{Simple, effective crawler and bot detection.}
+  gem.homepage      = "http://github.com/ccashwell/is_crawler"
+
+  gem.files         = `git ls-files`.split($/)
+  gem.executables   = gem.files.grep(%r{^bin/}).map{ |f| File.basename(f) }
+  gem.test_files    = gem.files.grep(%r{^(test|spec|features)/})
+  gem.require_paths = ["lib"]
+
+  gem.add_development_dependency "rspec"
+end

data/lib/crawler.rb

@@ -0,0 +1,18 @@
+class Crawler < Struct.new(:name, :ua_string)
+  BING      = Crawler.new(:bing, "bingbot/2.0")
+  FACEBOOK  = Crawler.new(:facebook, "facebookexternalhit/1.1")
+  GOOGLE    = Crawler.new(:google, "Googlebot/2.1")
+  MSN       = Crawler.new(:msn, "MSNBot")
+  TWITTER   = Crawler.new(:twitter, "Twitterbot")
+  YAHOO     = Crawler.new(:yahoo, "Yahoo! Slurp")
+
+  ALL = [BING, FACEBOOK, GOOGLE, MSN, TWITTER, YAHOO]
+
+  def self.matches_any? user_agent
+    ALL.detect { |crawler| crawler.matches? user_agent } != nil
+  end
+
+  def matches? user_agent
+    user_agent.downcase.include? ua_string.downcase
+  end
+end

data/lib/is_crawler/version.rb

@@ -0,0 +1,3 @@
+module IsCrawler
+  VERSION = "0.0.1"
+end

data/lib/is_crawler.rb

@@ -0,0 +1,17 @@
+require './lib/is_crawler/version'
+require './lib/crawler'
+
+module IsCrawler
+  def is_any_crawler? requesting_user_agent
+    Crawler.matches_any? requesting_user_agent
+  end
+
+  def is_crawler? requesting_user_agent, *specific_crawlers
+    crawler = which_crawler(requesting_user_agent)
+    crawler && specific_crawlers.include?(crawler.name) ? true : false
+  end
+
+  def which_crawler requesting_user_agent
+    Crawler::ALL.detect {|crawler| crawler.matches? requesting_user_agent }
+  end
+end

data/spec/is_crawler_spec.rb

@@ -0,0 +1,12 @@
+describe IsCrawler do
+  describe '#is_any_crawler?' do
+    let(:user_agent) { "Commodo Vestibulum/1.0" }
+    subject { Test.new.is_any_crawler?(user_agent) }
+    it 'defers to Crawler#matches_any?' do
+      Crawler.should_receive(:matches_any?).with(user_agent)
+      subject
+    end
+  end
+end
+
+class Test; include IsCrawler; end

data/spec/lib/crawler_spec.rb

@@ -0,0 +1,33 @@
+describe Crawler do
+  describe '.matches_any?' do
+    let(:user_agent) { "Commodo Vestibulum/1.0" }
+    subject { Crawler.matches_any?(user_agent) }
+
+    context 'When an unknown user agent is encountered' do
+      it { should be_false }
+    end
+
+    context 'When a known user agent is encountered' do
+      Crawler::ALL.each do |crawler|
+        context "such as the #{crawler.name.to_s} bot" do
+          let(:user_agent) { "#{crawler.ua_string}" }
+          it { should be_true }
+        end
+      end
+    end
+  end
+
+  describe '#matches?' do
+    Crawler::ALL.each do |crawler|
+      describe "Comparing #{crawler.name.to_s}'s known UA string" do
+        it 'with a matching string' do
+          crawler.matches?(crawler.ua_string).should == true
+        end
+
+        it 'with a non-matching string' do
+          crawler.matches?('Commodo Vestibulum/1.0').should == false
+        end
+      end
+    end
+  end
+end

metadata

@@ -0,0 +1,75 @@
+--- !ruby/object:Gem::Specification
+name: is_crawler
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+  prerelease: 
+platform: ruby
+authors:
+- Chris Cashwell
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2013-02-27 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+description: ! 'is_crawler does just what you might expect: detect whether the current
+  request is from a crawler.'
+email:
+- ccashwell@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- .gitignore
+- Gemfile
+- LICENSE.txt
+- README.md
+- Rakefile
+- is_crawler.gemspec
+- lib/crawler.rb
+- lib/is_crawler.rb
+- lib/is_crawler/version.rb
+- spec/is_crawler_spec.rb
+- spec/lib/crawler_spec.rb
+homepage: http://github.com/ccashwell/is_crawler
+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: 1.8.24
+signing_key: 
+specification_version: 3
+summary: Simple, effective crawler and bot detection.
+test_files:
+- spec/is_crawler_spec.rb
+- spec/lib/crawler_spec.rb