robotx 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 161a4310d0e1b28e499ce5dd6226125c6e345dd6
+  data.tar.gz: 2c33050af6edcdc516611e7eb8e1efc5a497ecf5
+SHA512:
+  metadata.gz: 6dc47d5c31e4629bb462ed353e31ec5e2b5b98fbf2a56363d87c8e9c9a8ed5a611341d88268f29b66b5b268acf4dce8e7766b7be0d6f189f1696544602d86d89
+  data.tar.gz: b939d2cf78e12054a92f8693ad35e5cc55efe75098df8b2e0c76c4347e3ad3763a15812a51968eba40c72b849c51b5373abddc9f0dfd92d49c3c2b1b85d59e84

data/.gitignore

@@ -0,0 +1,34 @@
+*.gem
+*.rbc
+/.config
+/coverage/
+/InstalledFiles
+/pkg/
+/spec/reports/
+/test/tmp/
+/test/version_tmp/
+/tmp/
+
+## Specific to RubyMotion:
+.dat*
+.repl_history
+build/
+
+## Documentation cache and generated files:
+/.yardoc/
+/_yardoc/
+/doc/
+/rdoc/
+
+## Environment normalisation:
+/.bundle/
+/lib/bundler/man/
+
+# for a library or gem, you might want to ignore these files since the code is
+# intended to run in multiple environments; otherwise, check them in:
+# Gemfile.lock
+# .ruby-version
+# .ruby-gemset
+
+# unless supporting rvm < 1.11.0 or doing something fancy, ignore this:
+.rvmrc

data/Gemfile

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

data/Gemfile.lock

@@ -0,0 +1,17 @@
+PATH
+  remote: .
+  specs:
+    robotx (0.1.0)
+
+GEM
+  remote: https://rubygems.org/
+  specs:
+    rake (10.3.2)
+
+PLATFORMS
+  ruby
+
+DEPENDENCIES
+  bundler (~> 1.6)
+  rake
+  robotx!

data/LICENSE

@@ -0,0 +1,21 @@
+The MIT License (MIT)
+
+Copyright (c) 2014 
+
+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 +1,72 @@
+# Robotx
+Robotx _(pronounced "robotex")_ is a simple but powerful parser for robots.txt files.
+It offers a bunch of features which allows you to check whether an URL is allowed/disallowed to be visited by a crawler.
+
+
+## Features
+
+- Maintains lists for allowed/disallowed URLs
+- Simple method to check whether an URL or just a path is allowed to be visited
+- Show all user agents covered by the robots.txt
+- Get the 'Crawl-Delay' for a website
+- Support for sitemap(s)
+
+## Installation
+### With Bundler
+Just add to your Gemfile
+~~~ruby
+gem 'robotx'
+~~~
+
+### Without Bundler
+If you're not using Bundler just execute on your commandline
+~~~bash
+$ gem install robotx
+~~~
+
+## Usage
+### Support for different user agents
+Robotx can be initialized with a special user agent. The default user agent is `*`.
+**Please note:** All method results depends on the user agent Robotx was initialized with.
+~~~ruby
+require 'robotx'
+
+# Initialize with the default user agent '*'
+robots_txt = Robotx.new('https://github.com')
+robots_txt.allowed  # => ["/humans.txt"]
+
+# Initialize with 'googlebot' as user agent
+robots_txt = Robotx.new('https://github.com', 'googlebot')
+robots_txt.allowed # => ["/*/*/tree/master", "/*/*/blob/master"]
+~~~
+
+### Check whether an URL is allowed to be indexed
+~~~ruby
+require 'robotx'
+
+robots_txt = Robotx.new('https://github.com')
+robots_txt.allowed?('/humans.txt')  # => true
+robots_txt.allowed?('/')  # => false
+~~~
+
+### Get all allowed/disallowed URLs
+~~~ruby
+require 'robotx'
+
+robots_txt = Robotx.new('https://github.com')
+robots_txt.allowed  # => ["/humans.txt"]
+robots_txt.disallowed  # => ["/"]
+~~~
+
+### Get additional information
+~~~ruby
+require 'robotx'
+
+robots_txt = Robotx.new('https://github.com')
+robots_txt.sitemap  # => []
+robots_txt.crawl_delay  # => 0
+robots_txt.user_agents  # => ["googlebot", "baiduspider", ...]
+~~~
+
+## Todo
+- Add tests

data/Rakefile

@@ -0,0 +1,2 @@
+require "bundler/gem_tasks"
+

data/lib/robotx.rb

@@ -0,0 +1,114 @@
+require 'timeout'
+require 'stringio'
+require 'open-uri'
+require 'uri'
+require 'set'
+
+class Robotx
+
+  TIMEOUT = 30 # seconds
+
+  def initialize(uri, user_agent='*')
+    @uri = URI.parse(URI.encode(uri))
+    raise URI::InvalidURIError.new('scheme or host missing') unless @uri.scheme and @uri.host
+
+    @user_agent  = user_agent.downcase
+    @robots_data = parse_robots_txt
+  end
+
+  def allowed
+    return disallowed.empty? ? ['/'] : @robots_data.fetch(@user_agent, {}).fetch('allow', ['/'])
+  end
+
+  def disallowed
+    return @robots_data.fetch(@user_agent, {}).fetch('disallow', [])
+  end
+
+  def allowed?(data)
+    if data.is_a?(Array) or data.is_a?(Set)
+      return {}.tap do |hash|
+        data.each do |uri|
+          hash[uri] = check_permission(uri)
+        end
+      end
+    end
+
+    return check_permission(data)
+  end
+
+  def sitemap
+    return @robots_data.fetch('sitemap', [])
+  end
+
+  def crawl_delay
+    return [@robots_data.fetch(@user_agent, {}).fetch('crawl-delay', 0), 0].max
+  end
+
+  def user_agents
+    return @robots_data.keys.delete_if { |agent| agent == 'sitemap' }
+  end
+
+private
+
+  def load_robots_txt
+    Timeout::timeout(Robotx::TIMEOUT) do
+      if robots_txt_io = URI.join(@uri, 'robots.txt').open('User-Agent' => @user_agent) and robots_txt_io.content_type.downcase == 'text/plain' and robots_txt_io.status == ['200', 'OK']
+        return robots_txt_io
+      end
+      raise OpenURI::HTTPError
+    end
+  rescue
+    return StringIO.new("User-agent: *\nAllow: /\n")
+  end
+
+  def parse_robots_txt
+    agent  = '*'
+    {}.tap do |hash|
+      load_robots_txt.each do |line|
+        next if line =~ /^\s*(#.*|$)/
+
+        data  = line.split(/:/).map(&:strip)
+        key   = data.shift
+        value = data.join
+
+        case key.downcase
+        when 'user-agent'
+          agent = value.downcase
+          hash[agent] ||= {}
+        when 'allow'
+          hash[agent]['allow'] ||= []
+          hash[agent]['allow'] << value.sub(/(\/){2,}$/, '')
+        when 'disallow'
+          # Disallow: '' means Allow: '/'
+          if value.empty?
+            hash[agent]['allow'] ||= []
+            hash[agent]['allow'] << '/'
+          else
+            hash[agent]['disallow'] ||= []
+            hash[agent]['disallow'] << value.sub(/(\/){2,}$/, '')
+          end
+        when 'crawl-delay'
+          hash[agent]['crawl-delay'] = value.to_i
+        when 'sitemap'
+          hash['sitemap'] ||= []
+          hash['sitemap'] << value.sub(/(\/){2,}$/, '')
+        else
+          hash[key] ||= []
+          hash[key] << value.sub(/(\/){2,}$/, '')
+        end
+      end
+    end
+  rescue
+    {}
+  end
+
+  def check_permission(uri)
+    uri = URI.parse(URI.encode(uri))
+    return true unless (@robots_data or @robots_data.any?) or (uri.scheme and uri.host)
+
+    uri_path = uri.path.sub(/(\/){2,}$/, '')
+    pattern  = Regexp.compile("(^#{Regexp.escape(uri_path)}[\/]*$)|(^/$)")
+    return (@robots_data.fetch(@user_agent, {}).fetch('disallow', []).grep(pattern).empty? or @robots_data.fetch(@user_agent, {}).fetch('allow', []).grep(pattern).any?)
+  end
+
+end

data/robotx.gemspec

@@ -0,0 +1,22 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+
+Gem::Specification.new do |spec|
+  spec.name          = "robotx"
+  spec.version       = "0.1.0"
+  spec.authors       = ["Matthias Kalb"]
+  spec.email         = ["matthias.kalb@railsmechanic.de"]
+  spec.summary       = %q{A parser for the robots.txt file}
+  spec.description   = %q{A simple to use parser for the robots.txt file.}
+  spec.homepage      = "https://github.com/railsmechanic/robotx"
+  spec.license       = "MIT"
+
+  spec.files         = `git ls-files -z`.split("\x0")
+  spec.executables   = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
+  spec.test_files    = spec.files.grep(%r{^(test|spec|features)/})
+  spec.require_paths = ["lib"]
+
+  spec.add_development_dependency "bundler", "~> 1.6"
+  spec.add_development_dependency "rake"
+end

metadata

@@ -0,0 +1,80 @@
+--- !ruby/object:Gem::Specification
+name: robotx
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Matthias Kalb
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2014-07-04 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.6'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.6'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+description: A simple to use parser for the robots.txt file.
+email:
+- matthias.kalb@railsmechanic.de
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- .gitignore
+- Gemfile
+- Gemfile.lock
+- LICENSE
+- README.md
+- Rakefile
+- lib/robotx.rb
+- robotx.gemspec
+homepage: https://github.com/railsmechanic/robotx
+licenses:
+- MIT
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.2.2
+signing_key: 
+specification_version: 4
+summary: A parser for the robots.txt file
+test_files: []