legitbot 0.2.1 → 0.2.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 43121c17f4de712a7c1b33797c0075b31762ff31a1461a871efa486461acf0e2
-  data.tar.gz: b6d015e3889a421b3dbce8189489239894bbdf87f8a5677e0d612ece4655f973
+  metadata.gz: d526ed7ca64658503c66d7c291c8a24f5a9f8fdecb47899eca06d4135ccf4165
+  data.tar.gz: 9ba9bc7cebe5137e5a018366ccc63f869864f264b8a4988e4f971b0399d6bf39
 SHA512:
-  metadata.gz: 44dec432e5ba97bb28cefd59e6f800d363342360d10ae72cf69419124836ffcc115b780882e797ea2879e41217402c53b6bd8472a449343814f007d1ea9b6996
-  data.tar.gz: '091b35b6eccc08b4e4b083e8498084e3726534a7560e8626b47e0e9dbcaa5a469568b477429804b47a3c16848d506c856823e8809ee88fc70df0d10723507a9d'
+  metadata.gz: dc2814147aa8a02dc14ca39831b62ce5dab4d6506e4c7868d9b1938747858c09dd303e3ff955183dff853fdbb4d2f5e7469e6b433af71191ffb519c9cce403a9
+  data.tar.gz: 9b523df0e7d980cc4002197e63d9b76c95b7ed06504a431b2a7dcc3a61a0d126a786996e7e4031727aec92fbba726ff7e507d4d99e8e121780ce822c12706d99

data/.travis.yml

@@ -2,4 +2,4 @@ sudo: false
 language: ruby
 cache: bundler
 rvm:
-  - 2.2
+  - 2.3

data/README.md

@@ -1,8 +1,8 @@
 # Legitbot [![Build Status](https://secure.travis-ci.org/alaz/legitbot.png?branch=master)](http://travis-ci.org/alaz/legitbot) [![Gem Version](https://badge.fury.io/rb/legitbot.svg)](https://badge.fury.io/rb/legitbot)
 
-Ruby gem to check if an IP really belongs to some bot, typically a search
-engine. This can of much help if one wants to protect his/her web site from
-malicious scanners who pretend to be e.g. a Googlebot.
+Ruby gem to check that an IP belongs to a bot, typically a search
+engine. This can be of help in protecting a web site from fake search
+engines.
 
 ## Usage
 
@@ -14,7 +14,7 @@ bot = Legitbot.bot(userAgent, ip)
 ```
 
 `bot` will be `nil` if no bot signature was found in the `User-Agent`. Otherwise,
-it will be an instance with methods
+it will be an object with methods
 
 ```ruby
 bot.detected_as # => :google
@@ -22,7 +22,7 @@ bot.valid? # => true
 bot.fake? # => false
 ```
 
-Sometimes you already know what search engine to expect. For example, you may
+Sometimes you already know what search engine to expect. For example, you might
 be using [rack-attack](https://github.com/kickstarter/rack-attack):
 
 ```ruby
@@ -31,6 +31,16 @@ Rack::Attack.blocklist("fake Googlebot") do |req|
 end
 ```
 
+Or if you do not like all these nasty crawlers stealing your content or
+maybe evaluating it and getting ready to invade your site with spammers,
+then block them all:
+
+```ruby
+Rack::Attack.blocklist 'fake search engines' do |request|
+  Legitbot.bot(request.user_agent, request.ip)&.fake?
+end
+```
+
 ## Supported
 
 * [Applebot](https://support.apple.com/en-us/HT204683)
@@ -48,9 +58,7 @@ Apache 2.0
 
 ## References
 
-* I have initially created Play Framework version in Scala: [play-legitbot](https://github.com/osinka/play-legitbot)
+* Play Framework variant in Scala: [play-legitbot](https://github.com/osinka/play-legitbot)
 * Article [When (Fake) Googlebots Attack Your Rails App](http://jessewolgamott.com/blog/2015/11/17/when-fake-googlebots-attack-your-rails-app/)
-* [Voight-Kampff](https://github.com/biola/Voight-Kampff) is a Ruby gem which
+* [Voight-Kampff](https://github.com/biola/Voight-Kampff) is a Ruby gem that
   detects bots by `User-Agent`
-* [browser](https://github.com/fnando/browser) is a Ruby gem which may tell
-  you if the request comes from a search engine.

data/lib/legitbot/botmatch.rb

@@ -17,26 +17,32 @@ module Legitbot
     # the reverse name
     def reverse_domain
       @reverse_domain ||= @dns.getname(@ip)
+    rescue Resolv::ResolvError
+      @reverse_domain ||= nil
     end
 
     ##
     # Returns a String with the reverse name
     def reverse_name
-      reverse_domain.to_s
+      reverse_domain&.to_s
     end
 
     ##
     # Returns a String with IP created from the reverse name
     def reversed_ip
+      return nil if reverse_name.nil?
+
       @reverse_ip ||= @dns.getaddress(reverse_name)
       @reverse_ip.to_s
     end
 
     def reverse_resolves?
-      reversed_ip == @ip
+      @ip == reversed_ip
     end
 
     def subdomain_of?(*domains)
+      return false if reverse_name.nil?
+
       domains.any? { |d|
         reverse_domain.subdomain_of? Resolv::DNS::Name.create(d)
       }

data/lib/legitbot/legitbot.rb

@@ -18,13 +18,13 @@ module Legitbot
         rule[:class].new(ip, resolver_config)
       }
 
-    bot = bots.select { |bot| bot.valid? }.first if bots.size > 1
-    bot = bots.first if bot.nil?
+    selected = bots.select { |b| b.valid? }.first if bots.size > 1
+    selected = bots.first if selected.nil?
 
-    if bot && block_given?
-      yield bot
+    if selected && block_given?
+      yield selected
     else
-      bot
+      selected
     end
   end
 

data/lib/legitbot/pinterest.rb

@@ -9,5 +9,5 @@ module Legitbot
     end
   end
 
-  rule Legitbot::Pinterest, %w(Pinterestbot Pinterest)
+  rule Legitbot::Pinterest, %w(Pinterestbot Pinterest/0.2)
 end

data/lib/legitbot/version.rb

@@ -1,3 +1,3 @@
 module Legitbot
-  VERSION = '0.2.1'
+  VERSION = '0.2.2'
 end

data/test/botmatch_test.rb

@@ -17,6 +17,11 @@ class BotMatchTest < Minitest::Test
     assert_equal true, match.reverse_resolves?
   end
 
+  def test_reverse_doesnt_resolve
+    match = Legitbot::BotMatch.new "5.140.70.64"
+    assert !match.reverse_resolves?
+  end
+
   def test_valid_class_syntax
     assert Legitbot::Google.valid?("66.249.64.141"), msg: "Valid Googlebot"
     assert Legitbot::Google.fake?("149.210.164.47"), msg: "Fake Googlebot"

data/test/legitbot_test.rb

@@ -4,6 +4,7 @@ require 'legitbot'
 class LegitbotTest < Minitest::Test
   def test_rules
     assert !Legitbot.bot("Firefox", "127.0.0.1"), msg: "Not a bot"
+    assert Legitbot.bot("Googlebot", "5.140.70.64"), msg: "No reverse resolve, bot"
 
     Legitbot.bot("Firefox", "127.0.0.1") do |bot|
       flunk "No bot Firefox is possible"

data/test/pinterest_test.rb

@@ -30,6 +30,11 @@ class PinterestTest < Minitest::Test
     assert bot.valid?, msg: "Valid Pinterest"
   end
 
+  def test_android_not_bot
+    bot = Legitbot.bot("Mozilla/5.0 (Linux; Android 8.0.0; SM-G965F Build/R16NW; wv) AppleWebKit/537.36 (KHTML, like Gecko) Version/4.0 Chrome/70.0.3538.64 Mobile Safari/537.36 [Pinterest/Android]", "85.117.106.133")
+    assert_nil bot
+  end
+
   def test_engine_name
     bot = Legitbot.bot("Mozilla/5.0 (compatible; Pinterestbot/1.0; +https://www.pinterest.com/bot.html)", "54.236.1.11")
     assert_equal :pinterest, bot.detected_as

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: legitbot
 version: !ruby/object:Gem::Version
-  version: 0.2.1
+  version: 0.2.2
 platform: ruby
 authors:
 - Alexander Azarov
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2018-10-09 00:00:00.000000000 Z
+date: 2018-10-25 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: irrc