legitbot 1.2.0 → 1.4.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 6cc8cb39a7c005fd9c8e97d095f482c98db48ebbb570408feb81782e03ce4e88
-  data.tar.gz: 200b76238f1cbd2239233bc82347e5d0f4c00b3856754a87beea7ecc3e80e54e
+  metadata.gz: 48fa3cd6d810e32c24c3027b57879438c658b64bdf2dfae3fbbcfd5ac67fb790
+  data.tar.gz: f8b77b3571978137339b06e633c9725ee8d1f4f6793bcdae8321a16cb9b37dfd
 SHA512:
-  metadata.gz: 7f3fe97a9e42feaf5233ae5733428fa7d87f1f5e545860240a1990dcef30a5785adeb349858817dc39a494978a910686778b3bb601f6928890ea1078d488b194
-  data.tar.gz: d4af0fced1c8fc0d629b49bab5da65ecdb945905ce2e2b76f0c78a3ed2aa7c71aa978d048bc11b591bb3f73c4a7981f23f1b52b5a98531e626ec611f6d436aaa
+  metadata.gz: ff62eb5208ee4e565504ada36c3d94129171f2487c5cf61e3cfbc5388a189ab5e5645537d311a01376e16abd486d69c465d148d6a4ebf35f5cf5d4c51a212bd8
+  data.tar.gz: c3a9d54b1add735629ac5caaf744c8bb75d2d9fa88fe5e793bd351e860cf00ef39cb084eb3bb048fe34b1ab9d95dec66eb08b075b9ee0bd7657e0160873f24bb

data/.github/workflows/build.yml

@@ -1,6 +1,10 @@
 name: build
 
-on: [pull_request, push]
+on:
+  pull_request:
+  push:
+  schedule:
+  - cron: '29 6 * * 6'
 
 jobs:
   test:
@@ -9,7 +13,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        ruby: [ jruby, 2.6 ]
+        ruby: [ jruby, 2.5, 2.6, 2.7 ]
 
     steps:
     - uses: actions/checkout@v2
@@ -37,7 +41,7 @@ jobs:
 
     strategy:
       matrix:
-        ruby: [ 2.6 ]
+        ruby: [ 2.7 ]
 
     steps:
     - uses: actions/checkout@v2

data/.rubocop.yml

@@ -1,3 +1,10 @@
 AllCops:
   CacheRootDirectory: 'vendor'
   NewCops: enable
+  SuggestExtensions: false
+
+Gemspec/RequiredRubyVersion:
+  Enabled: false
+
+Naming/MemoizedInstanceVariableName:
+  Enabled: false

data/.ruby-version

@@ -1 +1 @@
-2.4
+2.7.3

data/README.md

@@ -1,13 +1,11 @@
-# Legitbot ![](https://github.com/alaz/legitbot/workflows/build/badge.svg) [![Gem Version](https://badge.fury.io/rb/legitbot.svg)](https://badge.fury.io/rb/legitbot)
+# Legitbot ![](https://github.com/alaz/legitbot/workflows/build/badge.svg) ![](https://badge.fury.io/rb/legitbot.svg)
 
-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.
+Ruby gem to make sure that an IP really belongs to a bot, typically a search
+engine.
 
 ## Usage
 
-Suppose you have a Web request and you'd like to make sure it's not from a fake
-search engine:
+Suppose you have a Web request and you would like to check it is not diguised:
 
 ```ruby
 bot = Legitbot.bot(userAgent, ip)
@@ -22,7 +20,7 @@ bot.valid? # => true
 bot.fake? # => false
 ```
 
-Sometimes you already know what search engine to expect. For example, you might
+Sometimes you already know which search engine to expect. For example, you might
 be using [rack-attack](https://github.com/kickstarter/rack-attack):
 
 ```ruby
@@ -31,8 +29,8 @@ 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,
+Or if you do not like all those ghoulish crawlers stealing your
+content, evaluating it and getting ready to invade your site with spammers,
 then block them all:
 
 ```ruby
@@ -55,6 +53,7 @@ end
 * [Pinterest](https://help.pinterest.com/en/articles/about-pinterest-crawler-0)
 * [Twitterbot](https://developer.twitter.com/en/docs/tweets/optimize-with-cards/guides/getting-started), the list of IPs is in the [Troubleshooting page](https://developer.twitter.com/en/docs/tweets/optimize-with-cards/guides/troubleshooting-cards)
 * [Yandex robots](https://yandex.com/support/webmaster/robot-workings/check-yandex-robots.xml)
+* [Petal search engine](http://aspiegel.com/petalbot)
 
 ## License
 

data/legitbot.gemspec

@@ -14,13 +14,13 @@ Gem::Specification.new do |spec|
   spec.summary = 'Validate requests from Web crawlers: impersonating or not?'
   spec.description = 'Does Web request come from a real search engine or from an impersonating agent?'
 
-  spec.required_ruby_version = '>= 2.4.0'
+  spec.required_ruby_version = '>= 2.5.0'
   spec.add_dependency 'augmented_interval_tree', '~> 0.1', '>= 0.1.1'
   spec.add_dependency 'irrc', '~> 0.2', '>= 0.2.1'
   spec.add_development_dependency 'bump', '~> 0.8', '>= 0.8.0'
   spec.add_development_dependency 'minitest', '~> 5.1', '>= 5.1.0'
   spec.add_development_dependency 'rake', '~> 13.0', '>= 13.0.0'
-  spec.add_development_dependency 'rubocop', '~> 0.92.0', '>= 0.92.0'
+  spec.add_development_dependency 'rubocop', '~> 1.18.0', '>= 1.18.0'
 
   spec.files = `git ls-files`.split($INPUT_RECORD_SEPARATOR)
   spec.rdoc_options = ['--charset=UTF-8']

data/lib/legitbot.rb

@@ -15,3 +15,4 @@ require_relative 'legitbot/oracle'
 require_relative 'legitbot/pinterest'
 require_relative 'legitbot/twitter'
 require_relative 'legitbot/yandex'
+require_relative 'legitbot/petalbot'

data/lib/legitbot/duckduckgo.rb

@@ -4,14 +4,15 @@ module Legitbot # :nodoc:
   # https://duckduckgo.com/duckduckbot
   class DuckDuckGo < BotMatch
     ip_ranges %w[
+      20.191.45.212
       23.21.227.69
       40.88.21.235
       50.16.241.113
       50.16.241.114
       50.16.241.117
       50.16.247.234
-      52.204.97.54
       52.5.190.19
+      52.204.97.54
       54.197.234.188
       54.208.100.253
       54.208.102.37

data/lib/legitbot/petalbot.rb

@@ -0,0 +1,11 @@
+# frozen_string_literal: true
+
+module Legitbot # :nodoc:
+  # http://aspiegel.com/petalbot
+  # https://webmaster.petalsearch.com/site/petalbot
+  class Petalbot < BotMatch
+    domains 'petalsearch.com.'
+  end
+
+  rule Legitbot::Petalbot, %w[PetalBot]
+end

data/lib/legitbot/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Legitbot
-  VERSION = '1.2.0'
+  VERSION = '1.4.2'
 end

data/test/petalbot_test.rb

@@ -0,0 +1,52 @@
+# frozen_string_literal: true
+
+require 'minitest/autorun'
+require 'legitbot'
+
+class PetalbotTest < Minitest::Test
+  def test_malicious_ip
+    ip = '149.210.164.47'
+    match = Legitbot::Petalbot.new ip
+    assert !match.valid?, msg: "#{ip} is not a real Petalbot IP"
+  end
+
+  def test_valid_ip
+    ip = '114.119.128.10'
+    match = Legitbot::Petalbot.new ip
+    assert match.valid?, msg: "#{ip} is a valid Petalbot IP"
+  end
+
+  def test_malicious_ua
+    bot = Legitbot.bot(
+      'Mozilla/5.0 (compatible;PetalBot; +https://aspiegel.com/petalbot)',
+      '149.210.164.47'
+    )
+    assert bot, msg: 'Petalbot detected from User-Agent'
+    assert !bot.valid?, msg: 'Not a valid Petalbot'
+  end
+
+  def test_valid_ua
+    bot = Legitbot.bot(
+      'Mozilla/5.0 (compatible;PetalBot; +https://aspiegel.com/petalbot)',
+      '114.119.128.10'
+    )
+    assert bot, msg: 'Petalbot detected from User-Agent'
+    assert bot.valid?, msg: 'Valid Petalbot'
+  end
+
+  def test_valid_name
+    bot = Legitbot.bot(
+      'Mozilla/5.0 (compatible;PetalBot; +https://aspiegel.com/petalbot)',
+      '66.249.64.141'
+    )
+    assert_equal :petalbot, bot.detected_as
+  end
+
+  def test_fake_name
+    bot = Legitbot.bot(
+      'Mozilla/5.0 (compatible; PetalBot/2.1; +http://www.google.com/bot.html)',
+      '81.1.172.108'
+    )
+    assert_equal :petalbot, bot.detected_as
+  end
+end

data/test/pinterest_test.rb

@@ -34,7 +34,7 @@ class PinterestTest < Minitest::Test
     assert bot.valid?, msg: 'Valid Pinterest'
   end
 
-  # rubocop:disable Metrics/LineLength
+  # rubocop:disable Layout/LineLength
   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]',
@@ -42,7 +42,7 @@ class PinterestTest < Minitest::Test
     )
     assert_nil bot
   end
-  # rubocop:enable Metrics/LineLength
+  # rubocop:enable Layout/LineLength
 
   def test_engine_name
     bot = Legitbot.bot(

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: legitbot
 version: !ruby/object:Gem::Version
-  version: 1.2.0
+  version: 1.4.2
 platform: ruby
 authors:
 - Alexander Azarov
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2020-09-27 00:00:00.000000000 Z
+date: 2021-08-10 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: augmented_interval_tree
@@ -116,20 +116,20 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 0.92.0
+        version: 1.18.0
     - - ">="
       - !ruby/object:Gem::Version
-        version: 0.92.0
+        version: 1.18.0
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 0.92.0
+        version: 1.18.0
     - - ">="
       - !ruby/object:Gem::Version
-        version: 0.92.0
+        version: 1.18.0
 description: Does Web request come from a real search engine or from an impersonating
   agent?
 email: self@alaz.me
@@ -160,6 +160,7 @@ files:
 - lib/legitbot/google.rb
 - lib/legitbot/legitbot.rb
 - lib/legitbot/oracle.rb
+- lib/legitbot/petalbot.rb
 - lib/legitbot/pinterest.rb
 - lib/legitbot/twitter.rb
 - lib/legitbot/validators/domains.rb
@@ -176,6 +177,7 @@ files:
 - test/legitbot/validators/ip_ranges_test.rb
 - test/legitbot_test.rb
 - test/oracle_test.rb
+- test/petalbot_test.rb
 - test/pinterest_test.rb
 - test/twitter_test.rb
 homepage: https://github.com/alaz/legitbot
@@ -191,14 +193,14 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: 2.4.0
+      version: 2.5.0
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.1.2
+rubygems_version: 3.1.6
 signing_key:
 specification_version: 4
 summary: 'Validate requests from Web crawlers: impersonating or not?'
@@ -212,6 +214,7 @@ test_files:
 - test/apple_test.rb
 - test/oracle_test.rb
 - test/google_test.rb
+- test/petalbot_test.rb
 - test/botmatch_test.rb
 - test/facebook_test.rb
 - test/twitter_test.rb