legitbot 1.3.0 → 1.4.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: d709839505242be7ed07c5f6413e607bd8eb127a011765b9f45c1a3e0bba2fbb
-  data.tar.gz: 53a19413068473299ce78887756a2ef50f59859e54d652e4314755178a30028c
+  metadata.gz: 395c6363b221d300574d3a0bd0d324f882589ca44afc8db86f9f39e42c61a44c
+  data.tar.gz: 58f7c5205cdc0e0cd138b00d244bca133c16424f1b16f7a99263c121d02ae5f9
 SHA512:
-  metadata.gz: daaf7bbde5fae2ab3937b5e4f4cd936a61f54b80d5ec87eaca8db473977f633c993f267f6aeb101b94404119e58835878ee1433683cf613b476c6fc7f27b34b3
-  data.tar.gz: 1e51fe4ee02eb14bb0a95230e2ca3d4716a56cee199a40f3cfcd4d0999158526f151fa7915a9a3f0a21a9054ebc3862353e1a68a89057c2cf8bbcac4d082afb8
+  metadata.gz: df1f576284899afa5386cdea651a1cc811f9ddbf6cb683fdf85af71a829fedeae91995858e2453ed4743bd86105b3796a87cc2269f420e144f59faa5f982b646
+  data.tar.gz: 7f06269a4c24d08f957e47551a85338986e004f817a2d68ddacbc0354919fdcaef2106478ed2fce32133665343628b0b8ba922d0958485ee20ca98808ca3dbff

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) ![](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
@@ -52,10 +50,10 @@ end
 * [Facebook crawler](https://developers.facebook.com/docs/sharing/webmasters/crawler)
 * [Google crawlers](https://support.google.com/webmasters/answer/1061943)
 * [Oracle Data Cloud Crawler](https://www.oracle.com/corporate/acquisitions/grapeshot/crawler.html)
+* [Petal search engine](http://aspiegel.com/petalbot)
 * [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 robots (Huawei search)](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', '~> 1.20.0', '>= 1.20.0'
 
   spec.files = `git ls-files`.split($INPUT_RECORD_SEPARATOR)
   spec.rdoc_options = ['--charset=UTF-8']

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/oracle.rb

@@ -3,7 +3,31 @@
 module Legitbot # :nodoc:
   # https://www.oracle.com/corporate/acquisitions/grapeshot/crawler.html
   class Oracle < BotMatch
-    ip_ranges '148.64.56.0/24'
+    ip_ranges %w[
+      132.145.9.5
+      132.145.11.125
+      132.145.14.70
+      132.145.15.209
+      132.145.64.33
+      132.145.66.116
+      132.145.66.156
+      132.145.67.248
+      140.238.81.78
+      140.238.83.181
+      140.238.94.137
+      140.238.95.47
+      140.238.95.199
+      152.67.128.219
+      152.67.137.35
+      152.67.138.180
+
+      148.64.56.64/28
+      148.64.56.79
+      148.64.56.80
+      148.64.56.112/28
+      148.64.56.127
+      148.64.56.128
+    ]
   end
 
   rule Legitbot::Oracle, %w[GrapeshotCrawler]

data/lib/legitbot/petalbot.rb

@@ -2,8 +2,9 @@
 
 module Legitbot # :nodoc:
   # http://aspiegel.com/petalbot
+  # https://webmaster.petalsearch.com/site/petalbot
   class Petalbot < BotMatch
-    domains 'aspiegel.com.'
+    domains 'petalsearch.com.'
   end
 
   rule Legitbot::Petalbot, %w[PetalBot]

data/lib/legitbot/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Legitbot
-  VERSION = '1.3.0'
+  VERSION = '1.4.3'
 end

data/test/petalbot_test.rb

@@ -11,7 +11,7 @@ class PetalbotTest < Minitest::Test
   end
 
   def test_valid_ip
-    ip = '114.119.153.50'
+    ip = '114.119.128.10'
     match = Legitbot::Petalbot.new ip
     assert match.valid?, msg: "#{ip} is a valid Petalbot IP"
   end
@@ -28,7 +28,7 @@ class PetalbotTest < Minitest::Test
   def test_valid_ua
     bot = Legitbot.bot(
       'Mozilla/5.0 (compatible;PetalBot; +https://aspiegel.com/petalbot)',
-      '114.119.153.50'
+      '114.119.128.10'
     )
     assert bot, msg: 'Petalbot detected from User-Agent'
     assert bot.valid?, msg: 'Valid Petalbot'

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: 1.3.0
+  version: 1.4.3
 platform: ruby
 authors:
 - Alexander Azarov
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2020-12-16 00:00:00.000000000 Z
+date: 2021-09-10 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: 1.20.0
     - - ">="
       - !ruby/object:Gem::Version
-        version: 0.92.0
+        version: 1.20.0
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 0.92.0
+        version: 1.20.0
     - - ">="
       - !ruby/object:Gem::Version
-        version: 0.92.0
+        version: 1.20.0
 description: Does Web request come from a real search engine or from an impersonating
   agent?
 email: self@alaz.me
@@ -193,14 +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: 3.1.4
+rubygems_version: 3.1.6
 signing_key:
 specification_version: 4
 summary: 'Validate requests from Web crawlers: impersonating or not?'