jeremyf-robot_rules 0.9.1

data/.document

@@ -0,0 +1,5 @@
+README.rdoc
+lib/**/*.rb
+bin/*
+features/**/*.feature
+LICENSE

data/.gitignore

@@ -0,0 +1,5 @@
+*.sw?
+.DS_Store
+coverage
+rdoc
+pkg

data/LICENSE

@@ -0,0 +1,20 @@
+Copyright (c) 2009 James Edward Gray II and Jeremy Friesen
+
+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.markdown

@@ -0,0 +1,62 @@
+robot_rules
+===========
+
+A tool to determine if the robots.txt would prevent a given user agent 
+from making a request to a given URI.
+
+Example
+-------
+  
+  Given the following:
+    #!/usr/local/bin/ruby -w
+
+    require "robot_rules"
+    require "open-uri"
+
+    rules      = RobotRules.new("RubyQuizBrowser 1.0")
+    robots_url = "http://pragmaticprogrammer.com/robots.txt"
+
+    open(robots_url) do |url|
+       data = url.read
+
+       puts "/robots.txt:"
+       puts data
+       puts
+
+       rules.parse(robots_url, data)
+    end
+
+    puts "URL tests:"
+    %w{ http://pragmaticprogrammer.com/images/dave.jpg
+         http://pragmaticprogrammer.com/imagination }.each do |test|
+       puts "rules.allowed?( #{test.inspect} )"
+       puts rules.allowed?(test)
+    end
+
+    __END__
+
+  This script will print
+
+    /robots.txt:
+    User-agent:  *
+    Disallow:    images
+
+    URL tests:
+    rules.allowed?( "http://pragmaticprogrammer.com/images/dave.jpg" )
+    false
+    rules.allowed?( "http://pragmaticprogrammer.com/imagination" )
+    true
+  
+
+
+History
+-------
+
+RobotRules was created by James Edward Gray II as a response to "Port a 
+Library" Ruby Quiz #64.  A few years later, Jeremy Friesen wrapped the 
+library up into a gem and added some tests.
+
+Copyright
+---------
+
+Copyright (c) 2009 James Edward Gray II and Jeremy Friesen. See LICENSE for details.

data/Rakefile

@@ -0,0 +1,56 @@
+require 'rubygems'
+require 'rake'
+
+begin
+  require 'jeweler'
+  Jeweler::Tasks.new do |gem|
+    gem.name = "robot_rules"
+    gem.summary = %Q{A tool to determine if the robots.txt would prevent a given user agent from making a request to a given URI.}
+    gem.email = "jeremy.n.friesen@gmail.com"
+    gem.homepage = "http://github.com/jeremyf/robot_rules"
+    gem.authors = ["James Edward Gray II", "Jeremy Friesen"]
+    # gem is a Gem::Specification... see http://www.rubygems.org/read/chapter/20 for additional settings
+  end
+
+rescue LoadError
+  puts "Jeweler (or a dependency) not available. Install it with: sudo gem install jeweler"
+end
+
+require 'rake/testtask'
+Rake::TestTask.new(:test) do |test|
+  test.libs << 'lib' << 'test'
+  test.pattern = 'test/**/*_test.rb'
+  test.verbose = true
+end
+
+begin
+  require 'rcov/rcovtask'
+  Rcov::RcovTask.new do |test|
+    test.libs << 'test'
+    test.pattern = 'test/**/*_test.rb'
+    test.verbose = true
+  end
+rescue LoadError
+  task :rcov do
+    abort "RCov is not available. In order to run rcov, you must: sudo gem install spicycode-rcov"
+  end
+end
+
+
+task :default => :test
+
+require 'rake/rdoctask'
+Rake::RDocTask.new do |rdoc|
+  if File.exist?('VERSION.yml')
+    config = YAML.load(File.read('VERSION.yml'))
+    version = "#{config[:major]}.#{config[:minor]}.#{config[:patch]}"
+  else
+    version = ""
+  end
+
+  rdoc.rdoc_dir = 'rdoc'
+  rdoc.title = "robot_rules #{version}"
+  rdoc.rdoc_files.include('README*')
+  rdoc.rdoc_files.include('lib/**/*.rb')
+end
+

data/VERSION.yml

@@ -0,0 +1,4 @@
+--- 
+:major: 0
+:minor: 9
+:patch: 1

data/lib/robot_rules.rb

@@ -0,0 +1,76 @@
+ #!/usr/local/bin/ruby -w
+
+# robot_rules.rb
+#
+#  Created by James Edward Gray II on 2006-01-31.
+#  Copyright 2006 Gray Productions. All rights reserved.
+
+require "uri"
+
+# Based on Perl's WWW::RobotRules module, by Gisle Aas.
+class RobotRules
+   def initialize( user_agent )
+     @user_agent = user_agent.scan(/\S+/).first.sub(%r{/.*},  
+"").downcase
+     @rules      = Hash.new { |rules, rule| rules[rule] = Array.new }
+   end
+
+   def parse( text_uri, robots_data )
+     uri      = URI.parse(text_uri)
+     location = "#{uri.host}:#{uri.port}"
+     @rules.delete(location)
+
+     rules      = robots_data.split(/[\015\012]+/).map { |rule| rule.sub(/\s*#.*$/, "") }
+     anon_rules = Array.new
+     my_rules   = Array.new
+     current    = anon_rules
+     rules.each do |rule|
+       case rule
+       when /^\s*User-Agent\s*:\s*(.+?)\s*$/i
+         break unless my_rules.empty?
+
+         current = if $1 == "*"
+           anon_rules
+         elsif $1.downcase.index(@user_agent)
+           my_rules
+         else
+           nil
+         end
+       when /^\s*Disallow\s*:\s*(.*?)\s*$/i
+         next if current.nil?
+
+         if $1.empty?
+           current << nil
+         else
+           disallow = URI.parse($1)
+
+           next unless disallow.scheme.nil? or disallow.scheme == uri.scheme
+           next unless disallow.port.nil?   or disallow.port == uri.port
+           next unless disallow.host.nil?   or disallow.host.downcase == uri.host.downcase
+
+           disallow = disallow.path
+           disallow = "/" if disallow.empty?
+           disallow = "/#{disallow}" unless disallow[0] == ?/
+
+           current << disallow
+         end
+       end
+     end
+
+     @rules[location] = if my_rules.empty?
+       anon_rules.compact
+     else
+       my_rules.compact
+     end
+   end
+
+   def allowed?( text_uri )
+     uri      = URI.parse(text_uri)
+     location = "#{uri.host}:#{uri.port}"
+     path     = uri.path
+
+     return true unless %w{http https}.include?(uri.scheme)
+
+     not @rules[location].any? { |rule| path.index(rule) == 0 }
+   end
+end

data/robot_rules.gemspec

@@ -0,0 +1,46 @@
+# -*- encoding: utf-8 -*-
+
+Gem::Specification.new do |s|
+  s.name = %q{robot_rules}
+  s.version = "0.9.1"
+
+  s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
+  s.authors = ["James Edward Gray II", "Jeremy Friesen"]
+  s.date = %q{2009-07-28}
+  s.email = %q{jeremy.n.friesen@gmail.com}
+  s.extra_rdoc_files = [
+    "LICENSE",
+     "README.markdown"
+  ]
+  s.files = [
+    ".document",
+     ".gitignore",
+     "LICENSE",
+     "README.markdown",
+     "Rakefile",
+     "VERSION.yml",
+     "lib/robot_rules.rb",
+     "robot_rules.gemspec",
+     "test/robot_rules_test.rb",
+     "test/test_helper.rb"
+  ]
+  s.homepage = %q{http://github.com/jeremyf/robot_rules}
+  s.rdoc_options = ["--charset=UTF-8"]
+  s.require_paths = ["lib"]
+  s.rubygems_version = %q{1.3.4}
+  s.summary = %q{A tool to determine if the robots.txt would prevent a given user agent from making a request to a given URI.}
+  s.test_files = [
+    "test/robot_rules_test.rb",
+     "test/test_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::RubyGemsVersion) >= Gem::Version.new('1.2.0') then
+    else
+    end
+  else
+  end
+end

data/test/robot_rules_test.rb

@@ -0,0 +1,37 @@
+require 'test_helper'
+
+class RobotRulesTest < Test::Unit::TestCase
+  SITE_URL = "http://www.example.com"
+  def setup
+    @robot_rule = RobotRules.new('Ruby Spider 1.0')
+    @robot_rule.parse(File.join(SITE_URL,'robots.txt'), %(User-agent:  *\nDisallow:    images))
+  end
+  def test_should_allow_path_imagination
+    assert_equal true, @robot_rule.allowed?(File.join(SITE_URL, 'imagination/me.jpg'))
+  end
+  def test_should_disallow_path_images
+    assert_equal false, @robot_rule.allowed?(File.join(SITE_URL, 'images/me.jpg'))
+  end
+  def test_should_allow_path_images_for_other_site
+    assert_equal true, @robot_rule.allowed?(File.join("http://google.com", 'images/me.jpg'))
+  end
+  def test_should_disallow_path_images_for_other_site
+    assert_equal true, @robot_rule.allowed?(File.join("http://google.com", 'images/me.jpg'))
+  end
+
+  def test_should_abide_by_disallowed_user_agent
+    @robot_rule = RobotRules.new('Microsoft')
+    robots_txt = %(/robots.txt:\nUser-agent: Microsoft\nDisallow:  google\nUser-agent:  *\nDisallow:    images)
+    @robot_rule.parse(File.join(SITE_URL,'robots.txt'), robots_txt)
+    
+    assert_equal false, @robot_rule.allowed?(File.join(SITE_URL, 'google/hellow_world.txt'))
+  end
+
+  def test_should_allow_user_agent_to_specified_path
+    @robot_rule = RobotRules.new('Google')
+    robots_txt = %(/robots.txt:\nUser-agent: Microsoft\nDisallow:  google\nUser-agent:  *\nDisallow:    images)
+    @robot_rule.parse(File.join(SITE_URL,'robots.txt'), robots_txt)
+    
+    assert_equal true, @robot_rule.allowed?(File.join(SITE_URL, 'google/hellow_world.txt'))
+  end
+end

data/test/test_helper.rb

@@ -0,0 +1,9 @@
+require 'rubygems'
+require 'test/unit'
+
+$LOAD_PATH.unshift(File.dirname(__FILE__))
+$LOAD_PATH.unshift(File.join(File.dirname(__FILE__), '..', 'lib'))
+require 'robot_rules'
+
+class Test::Unit::TestCase
+end

metadata

@@ -0,0 +1,66 @@
+--- !ruby/object:Gem::Specification 
+name: jeremyf-robot_rules
+version: !ruby/object:Gem::Version 
+  version: 0.9.1
+platform: ruby
+authors: 
+- James Edward Gray II
+- Jeremy Friesen
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2009-07-28 00:00:00 -07:00
+default_executable: 
+dependencies: []
+
+description: 
+email: jeremy.n.friesen@gmail.com
+executables: []
+
+extensions: []
+
+extra_rdoc_files: 
+- LICENSE
+- README.markdown
+files: 
+- .document
+- .gitignore
+- LICENSE
+- README.markdown
+- Rakefile
+- VERSION.yml
+- lib/robot_rules.rb
+- robot_rules.gemspec
+- test/robot_rules_test.rb
+- test/test_helper.rb
+has_rdoc: false
+homepage: http://github.com/jeremyf/robot_rules
+licenses: 
+post_install_message: 
+rdoc_options: 
+- --charset=UTF-8
+require_paths: 
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      version: "0"
+  version: 
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      version: "0"
+  version: 
+requirements: []
+
+rubyforge_project: 
+rubygems_version: 1.3.5
+signing_key: 
+specification_version: 3
+summary: A tool to determine if the robots.txt would prevent a given user agent from making a request to a given URI.
+test_files: 
+- test/robot_rules_test.rb
+- test/test_helper.rb