legitbot 1.0.2 → 1.4.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/.editorconfig +17 -0
- data/.github/workflows/build.yml +7 -3
- data/.rubocop.yml +7 -0
- data/.ruby-version +1 -1
- data/README.md +1 -1
- data/legitbot.gemspec +3 -3
- data/lib/legitbot/apple.rb +0 -8
- data/lib/legitbot/validators/ip_ranges.rb +1 -1
- data/lib/legitbot/version.rb +1 -1
- data/test/legitbot/validators/ip_ranges_test.rb +9 -0
- data/test/pinterest_test.rb +2 -2
- metadata +15 -16
- data/test/apple_as_google_test.rb +0 -27
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 783bc47b1bc8f80e5d4818f150663a2cb6fb90e5dd2378bae456eb2fb1d78823
|
4
|
+
data.tar.gz: 0e274e1eaa295ffa0e00a8d6e2884194ed53108da9ecb75c3ef2ef4746048c9e
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: ec7c2f2cb78cc8a586a35bea72e39b12835679089f4b4d5cba754aa0caccee0c9e8c1c94461a7fd8fcb1cf4f8195f196346ea4abe7bd96a080c5c831f9d68c7a
|
7
|
+
data.tar.gz: a92ea8ff049127871988e8dbad7cb76b3c53f13dde97a157509e9013898c1da2cc3e573ae695d9af2e82372bf478348aeca6ec77a673798b52ac1e3ab623e214
|
data/.editorconfig
ADDED
@@ -0,0 +1,17 @@
|
|
1
|
+
root = true
|
2
|
+
|
3
|
+
[*]
|
4
|
+
end_of_line = lf
|
5
|
+
insert_final_newline = true
|
6
|
+
trim_trailing_whitespace = true
|
7
|
+
charset = utf-8
|
8
|
+
|
9
|
+
indent_style = space
|
10
|
+
indent_size = 2
|
11
|
+
|
12
|
+
[*.md]
|
13
|
+
trim_trailing_whitespace = false
|
14
|
+
|
15
|
+
[*.yml]
|
16
|
+
indent_style = space
|
17
|
+
indent_size = 2
|
data/.github/workflows/build.yml
CHANGED
@@ -1,6 +1,10 @@
|
|
1
1
|
name: build
|
2
2
|
|
3
|
-
on:
|
3
|
+
on:
|
4
|
+
pull_request:
|
5
|
+
push:
|
6
|
+
schedule:
|
7
|
+
- cron: '29 6 * * 6'
|
4
8
|
|
5
9
|
jobs:
|
6
10
|
test:
|
@@ -9,7 +13,7 @@ jobs:
|
|
9
13
|
strategy:
|
10
14
|
fail-fast: false
|
11
15
|
matrix:
|
12
|
-
ruby: [ jruby, 2.6 ]
|
16
|
+
ruby: [ jruby, 2.5, 2.6, 2.7 ]
|
13
17
|
|
14
18
|
steps:
|
15
19
|
- uses: actions/checkout@v2
|
@@ -37,7 +41,7 @@ jobs:
|
|
37
41
|
|
38
42
|
strategy:
|
39
43
|
matrix:
|
40
|
-
ruby: [ 2.
|
44
|
+
ruby: [ 2.7 ]
|
41
45
|
|
42
46
|
steps:
|
43
47
|
- uses: actions/checkout@v2
|
data/.rubocop.yml
CHANGED
data/.ruby-version
CHANGED
@@ -1 +1 @@
|
|
1
|
-
2.
|
1
|
+
2.7.3
|
data/README.md
CHANGED
@@ -1,4 +1,4 @@
|
|
1
|
-
# Legitbot ![](https://github.com/alaz/legitbot/workflows/build/badge.svg)
|
1
|
+
# Legitbot ![](https://github.com/alaz/legitbot/workflows/build/badge.svg) ![](https://badge.fury.io/rb/legitbot.svg)
|
2
2
|
|
3
3
|
Ruby gem to check that an IP belongs to a bot, typically a search
|
4
4
|
engine. This can be of help in protecting a web site from fake search
|
data/legitbot.gemspec
CHANGED
@@ -14,13 +14,13 @@ Gem::Specification.new do |spec|
|
|
14
14
|
spec.summary = 'Validate requests from Web crawlers: impersonating or not?'
|
15
15
|
spec.description = 'Does Web request come from a real search engine or from an impersonating agent?'
|
16
16
|
|
17
|
-
spec.required_ruby_version = '>= 2.
|
17
|
+
spec.required_ruby_version = '>= 2.5.0'
|
18
18
|
spec.add_dependency 'augmented_interval_tree', '~> 0.1', '>= 0.1.1'
|
19
19
|
spec.add_dependency 'irrc', '~> 0.2', '>= 0.2.1'
|
20
20
|
spec.add_development_dependency 'bump', '~> 0.8', '>= 0.8.0'
|
21
21
|
spec.add_development_dependency 'minitest', '~> 5.1', '>= 5.1.0'
|
22
|
-
spec.add_development_dependency 'rake', '~>
|
23
|
-
spec.add_development_dependency 'rubocop', '~> 0
|
22
|
+
spec.add_development_dependency 'rake', '~> 13.0', '>= 13.0.0'
|
23
|
+
spec.add_development_dependency 'rubocop', '~> 1.15.0', '>= 1.15.0'
|
24
24
|
|
25
25
|
spec.files = `git ls-files`.split($INPUT_RECORD_SEPARATOR)
|
26
26
|
spec.rdoc_options = ['--charset=UTF-8']
|
data/lib/legitbot/apple.rb
CHANGED
@@ -8,13 +8,5 @@ module Legitbot # :nodoc:
|
|
8
8
|
ip_ranges '17.0.0.0/8'
|
9
9
|
end
|
10
10
|
|
11
|
-
# https://support.apple.com/en-us/HT204683
|
12
|
-
# rubocop:disable Naming/ClassAndModuleCamelCase
|
13
|
-
class Apple_as_Google < BotMatch
|
14
|
-
ip_ranges '17.0.0.0/8'
|
15
|
-
end
|
16
|
-
# rubocop:enable Naming/ClassAndModuleCamelCase
|
17
|
-
|
18
11
|
rule Legitbot::Apple, %w[Applebot]
|
19
|
-
rule Legitbot::Apple_as_Google, %w[Googlebot]
|
20
12
|
end
|
data/lib/legitbot/version.rb
CHANGED
@@ -51,6 +51,11 @@ module Legitbot
|
|
51
51
|
ip_ranges { nil }
|
52
52
|
end
|
53
53
|
|
54
|
+
class Ipv4Ranges
|
55
|
+
include IpRanges
|
56
|
+
ip_ranges { ['66.220.144.0/21'] }
|
57
|
+
end
|
58
|
+
|
54
59
|
class IpRangesTest < Minitest::Test
|
55
60
|
def test_partition_method
|
56
61
|
empty = NoRanges.partition_ips([])
|
@@ -117,6 +122,10 @@ module Legitbot
|
|
117
122
|
def test_nil_ranges
|
118
123
|
assert NilRanges.valid_ip?('127.0.0.1')
|
119
124
|
end
|
125
|
+
|
126
|
+
def test_ipv4_only_ranges
|
127
|
+
refute Ipv4Ranges.valid_ip?('2a03:2880:f234:0:0:0:0:1')
|
128
|
+
end
|
120
129
|
end
|
121
130
|
end
|
122
131
|
end
|
data/test/pinterest_test.rb
CHANGED
@@ -34,7 +34,7 @@ class PinterestTest < Minitest::Test
|
|
34
34
|
assert bot.valid?, msg: 'Valid Pinterest'
|
35
35
|
end
|
36
36
|
|
37
|
-
# rubocop:disable
|
37
|
+
# rubocop:disable Layout/LineLength
|
38
38
|
def test_android_not_bot
|
39
39
|
bot = Legitbot.bot(
|
40
40
|
'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
|
|
42
42
|
)
|
43
43
|
assert_nil bot
|
44
44
|
end
|
45
|
-
# rubocop:enable
|
45
|
+
# rubocop:enable Layout/LineLength
|
46
46
|
|
47
47
|
def test_engine_name
|
48
48
|
bot = Legitbot.bot(
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: legitbot
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 1.0
|
4
|
+
version: 1.4.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Alexander Azarov
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date:
|
11
|
+
date: 2021-05-28 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: augmented_interval_tree
|
@@ -96,40 +96,40 @@ dependencies:
|
|
96
96
|
requirements:
|
97
97
|
- - "~>"
|
98
98
|
- !ruby/object:Gem::Version
|
99
|
-
version: '
|
99
|
+
version: '13.0'
|
100
100
|
- - ">="
|
101
101
|
- !ruby/object:Gem::Version
|
102
|
-
version:
|
102
|
+
version: 13.0.0
|
103
103
|
type: :development
|
104
104
|
prerelease: false
|
105
105
|
version_requirements: !ruby/object:Gem::Requirement
|
106
106
|
requirements:
|
107
107
|
- - "~>"
|
108
108
|
- !ruby/object:Gem::Version
|
109
|
-
version: '
|
109
|
+
version: '13.0'
|
110
110
|
- - ">="
|
111
111
|
- !ruby/object:Gem::Version
|
112
|
-
version:
|
112
|
+
version: 13.0.0
|
113
113
|
- !ruby/object:Gem::Dependency
|
114
114
|
name: rubocop
|
115
115
|
requirement: !ruby/object:Gem::Requirement
|
116
116
|
requirements:
|
117
117
|
- - "~>"
|
118
118
|
- !ruby/object:Gem::Version
|
119
|
-
version:
|
120
|
-
- - "
|
119
|
+
version: 1.15.0
|
120
|
+
- - ">="
|
121
121
|
- !ruby/object:Gem::Version
|
122
|
-
version:
|
122
|
+
version: 1.15.0
|
123
123
|
type: :development
|
124
124
|
prerelease: false
|
125
125
|
version_requirements: !ruby/object:Gem::Requirement
|
126
126
|
requirements:
|
127
127
|
- - "~>"
|
128
128
|
- !ruby/object:Gem::Version
|
129
|
-
version:
|
130
|
-
- - "
|
129
|
+
version: 1.15.0
|
130
|
+
- - ">="
|
131
131
|
- !ruby/object:Gem::Version
|
132
|
-
version:
|
132
|
+
version: 1.15.0
|
133
133
|
description: Does Web request come from a real search engine or from an impersonating
|
134
134
|
agent?
|
135
135
|
email: self@alaz.me
|
@@ -137,6 +137,7 @@ executables: []
|
|
137
137
|
extensions: []
|
138
138
|
extra_rdoc_files: []
|
139
139
|
files:
|
140
|
+
- ".editorconfig"
|
140
141
|
- ".github/workflows/build.yml"
|
141
142
|
- ".gitignore"
|
142
143
|
- ".rubocop.yml"
|
@@ -167,7 +168,6 @@ files:
|
|
167
168
|
- lib/legitbot/yandex.rb
|
168
169
|
- test/ahrefs_test.rb
|
169
170
|
- test/alexa_test.rb
|
170
|
-
- test/apple_as_google_test.rb
|
171
171
|
- test/apple_test.rb
|
172
172
|
- test/botmatch_test.rb
|
173
173
|
- test/facebook_test.rb
|
@@ -191,14 +191,14 @@ required_ruby_version: !ruby/object:Gem::Requirement
|
|
191
191
|
requirements:
|
192
192
|
- - ">="
|
193
193
|
- !ruby/object:Gem::Version
|
194
|
-
version: 2.
|
194
|
+
version: 2.5.0
|
195
195
|
required_rubygems_version: !ruby/object:Gem::Requirement
|
196
196
|
requirements:
|
197
197
|
- - ">="
|
198
198
|
- !ruby/object:Gem::Version
|
199
199
|
version: '0'
|
200
200
|
requirements: []
|
201
|
-
rubygems_version: 3.1.
|
201
|
+
rubygems_version: 3.1.6
|
202
202
|
signing_key:
|
203
203
|
specification_version: 4
|
204
204
|
summary: 'Validate requests from Web crawlers: impersonating or not?'
|
@@ -210,7 +210,6 @@ test_files:
|
|
210
210
|
- test/alexa_test.rb
|
211
211
|
- test/ahrefs_test.rb
|
212
212
|
- test/apple_test.rb
|
213
|
-
- test/apple_as_google_test.rb
|
214
213
|
- test/oracle_test.rb
|
215
214
|
- test/google_test.rb
|
216
215
|
- test/botmatch_test.rb
|
@@ -1,27 +0,0 @@
|
|
1
|
-
# frozen_string_literal: true
|
2
|
-
|
3
|
-
require 'minitest/autorun'
|
4
|
-
require 'legitbot'
|
5
|
-
|
6
|
-
class AppleAsGoogleTest < Minitest::Test
|
7
|
-
def test_valid_ip
|
8
|
-
ip = '17.58.98.60'
|
9
|
-
match = Legitbot::Apple_as_Google.new(ip)
|
10
|
-
assert match.valid?, msg: "#{ip} is a valid Applebot IP"
|
11
|
-
end
|
12
|
-
|
13
|
-
def test_invalid_ip
|
14
|
-
ip = '127.0.0.1'
|
15
|
-
match = Legitbot::Apple_as_Google.new(ip)
|
16
|
-
assert match.fake?, msg: "#{ip} is a fake Applebot IP"
|
17
|
-
end
|
18
|
-
|
19
|
-
def test_user_agent
|
20
|
-
bot = Legitbot.bot(
|
21
|
-
'Mozilla/5.0 (compatible; Googlebot/2.1; +http://www.google.com/bot.html)',
|
22
|
-
'17.58.98.60'
|
23
|
-
)
|
24
|
-
assert_equal :apple_as_google, bot.detected_as
|
25
|
-
assert bot.valid?, msg: 'A valid Applebot User-agent and IP'
|
26
|
-
end
|
27
|
-
end
|