legitbot 1.0.1 → 1.0.2
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/.github/workflows/build.yml +1 -1
- data/.rubocop.yml +1 -0
- data/README.md +1 -0
- data/legitbot.gemspec +1 -1
- data/lib/legitbot.rb +1 -0
- data/lib/legitbot/alexa.rb +17 -0
- data/lib/legitbot/legitbot.rb +2 -2
- data/lib/legitbot/version.rb +1 -1
- data/test/alexa_test.rb +36 -0
- data/test/facebook_test.rb +2 -2
- metadata +11 -8
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: c0b43dcf4386a8427415729bf9ba5edfe3c0efc24a002bb4301ff98d43c4ee0d
|
4
|
+
data.tar.gz: 9f18f03e613473a97cda23e8663d44da10cfd32b3fd271e1ffd5ee20cfdef48d
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 73ad2e000c4513880bc5558c7fe5f7c7c04d01b1a820ef7b12541c8c9d6cc5dddd20c785d67ef489d5b00664632c6b88a805c3bb1e2a060517126c7d7292d661
|
7
|
+
data.tar.gz: a578a30a512495523e906ec1d6a650f4f472a58856caa542714d3e57a0b99f764ee015f11624c4a20cae79a3975eb41eaf8ced106977dd994981d71c288b5653
|
data/.github/workflows/build.yml
CHANGED
data/.rubocop.yml
CHANGED
data/README.md
CHANGED
@@ -44,6 +44,7 @@ end
|
|
44
44
|
## Supported
|
45
45
|
|
46
46
|
* [Ahrefs](https://ahrefs.com/robot)
|
47
|
+
* [Alexa](https://support.alexa.com/hc/en-us/articles/360046707834-What-are-the-IP-addresses-for-Alexa-s-Certify-and-Site-Audit-crawlers-)
|
47
48
|
* [Applebot](https://support.apple.com/en-us/HT204683)
|
48
49
|
* [Baidu spider](http://help.baidu.com/question?prod_en=master&class=498&id=1000973)
|
49
50
|
* [Bingbot](https://blogs.bing.com/webmaster/2012/08/31/how-to-verify-that-bingbot-is-bingbot/)
|
data/legitbot.gemspec
CHANGED
@@ -20,7 +20,7 @@ Gem::Specification.new do |spec|
|
|
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
22
|
spec.add_development_dependency 'rake', '~> 12.3', '>= 12.3.0'
|
23
|
-
spec.add_development_dependency 'rubocop', '~> 0.
|
23
|
+
spec.add_development_dependency 'rubocop', '~> 0.90', '< 0.91'
|
24
24
|
|
25
25
|
spec.files = `git ls-files`.split($INPUT_RECORD_SEPARATOR)
|
26
26
|
spec.rdoc_options = ['--charset=UTF-8']
|
data/lib/legitbot.rb
CHANGED
@@ -0,0 +1,17 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
module Legitbot # :nodoc:
|
4
|
+
# https://support.alexa.com/hc/en-us/articles/360046707834-What-are-the-IP-addresses-for-Alexa-s-Certify-and-Site-Audit-crawlers-
|
5
|
+
# https://support.alexa.com/hc/en-us/articles/200462340
|
6
|
+
# https://support.alexa.com/hc/en-us/articles/200450194
|
7
|
+
class Alexa < BotMatch
|
8
|
+
ip_ranges %w[
|
9
|
+
52.86.176.3
|
10
|
+
52.4.48.181
|
11
|
+
52.2.182.169
|
12
|
+
52.86.185.29
|
13
|
+
]
|
14
|
+
end
|
15
|
+
|
16
|
+
rule Legitbot::Alexa, %w[Alexabot ia_archiver]
|
17
|
+
end
|
data/lib/legitbot/legitbot.rb
CHANGED
@@ -18,7 +18,7 @@ module Legitbot
|
|
18
18
|
# otherwise.
|
19
19
|
# :yields: a found bot
|
20
20
|
#
|
21
|
-
# rubocop:disable Metrics/CyclomaticComplexity
|
21
|
+
# rubocop:disable Metrics/AbcSize, Metrics/CyclomaticComplexity, Metrics/PerceivedComplexity
|
22
22
|
def self.bot(user_agent, ip)
|
23
23
|
bots = @rules
|
24
24
|
.select { |rule| rule[:fragments].any? { |f| user_agent.index f } }
|
@@ -33,7 +33,7 @@ module Legitbot
|
|
33
33
|
selected
|
34
34
|
end
|
35
35
|
end
|
36
|
-
# rubocop:enable Metrics/CyclomaticComplexity
|
36
|
+
# rubocop:enable Metrics/AbcSize, Metrics/CyclomaticComplexity, Metrics/PerceivedComplexity
|
37
37
|
|
38
38
|
def self.rule(clazz, fragments)
|
39
39
|
@rules << { class: clazz, fragments: fragments }
|
data/lib/legitbot/version.rb
CHANGED
data/test/alexa_test.rb
ADDED
@@ -0,0 +1,36 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require 'minitest/autorun'
|
4
|
+
require 'legitbot'
|
5
|
+
|
6
|
+
class AlexaTest < Minitest::Test
|
7
|
+
def test_malicious_ip
|
8
|
+
ip = '149.210.164.47'
|
9
|
+
match = Legitbot::Alexa.new ip
|
10
|
+
assert !match.valid?, msg: "#{ip} is not a real Alexa IP"
|
11
|
+
end
|
12
|
+
|
13
|
+
def test_valid_ip
|
14
|
+
ip = '52.86.176.3'
|
15
|
+
match = Legitbot::Alexa.new ip
|
16
|
+
assert match.valid?, msg: "#{ip} is a valid Alexa IP"
|
17
|
+
end
|
18
|
+
|
19
|
+
def test_malicious_ua
|
20
|
+
bot = Legitbot.bot(
|
21
|
+
'Mozilla/5.0 (compatible; Alexabot/1.0; +http://www.alexa.com/help/certifyscan; certifyscan@alexa.com)',
|
22
|
+
'149.210.164.47'
|
23
|
+
)
|
24
|
+
assert bot, msg: 'Alexa detected from User-Agent'
|
25
|
+
assert !bot.valid?, msg: 'Not a valid Alexa'
|
26
|
+
end
|
27
|
+
|
28
|
+
def test_valid_ua
|
29
|
+
bot = Legitbot.bot(
|
30
|
+
'Mozilla/5.0 (compatible; Alexabot/1.0; +http://www.alexa.com/help/certifyscan; certifyscan@alexa.com)',
|
31
|
+
'52.86.176.3'
|
32
|
+
)
|
33
|
+
assert bot, msg: 'Alexa detected from User-Agent'
|
34
|
+
assert bot.valid?, msg: 'Valid Alexa'
|
35
|
+
end
|
36
|
+
end
|
data/test/facebook_test.rb
CHANGED
@@ -33,7 +33,7 @@ class FacebookTest < Minitest::Test
|
|
33
33
|
assert match.fake?, msg: "#{ip} is a fake Facebook IP"
|
34
34
|
end
|
35
35
|
|
36
|
-
# rubocop:disable
|
36
|
+
# rubocop:disable Layout/LineLength, Metrics/MethodLength
|
37
37
|
def test_user_agent
|
38
38
|
Legitbot.bot(
|
39
39
|
'facebookexternalhit/1.1 (+http://www.facebook.com/externalhit_uatext.php)',
|
@@ -59,5 +59,5 @@ class FacebookTest < Minitest::Test
|
|
59
59
|
assert bot.fake?, msg: 'fake Facebook'
|
60
60
|
end
|
61
61
|
end
|
62
|
-
# rubocop:enable
|
62
|
+
# rubocop:enable Layout/LineLength, Metrics/MethodLength
|
63
63
|
end
|
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: 1.0.2
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Alexander Azarov
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2020-
|
11
|
+
date: 2020-09-03 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: augmented_interval_tree
|
@@ -116,20 +116,20 @@ dependencies:
|
|
116
116
|
requirements:
|
117
117
|
- - "~>"
|
118
118
|
- !ruby/object:Gem::Version
|
119
|
-
version: '0.
|
120
|
-
- - "
|
119
|
+
version: '0.90'
|
120
|
+
- - "<"
|
121
121
|
- !ruby/object:Gem::Version
|
122
|
-
version: 0.
|
122
|
+
version: '0.91'
|
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: '0.
|
130
|
-
- - "
|
129
|
+
version: '0.90'
|
130
|
+
- - "<"
|
131
131
|
- !ruby/object:Gem::Version
|
132
|
-
version: 0.
|
132
|
+
version: '0.91'
|
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
|
@@ -148,6 +148,7 @@ files:
|
|
148
148
|
- legitbot.gemspec
|
149
149
|
- lib/legitbot.rb
|
150
150
|
- lib/legitbot/ahrefs.rb
|
151
|
+
- lib/legitbot/alexa.rb
|
151
152
|
- lib/legitbot/apple.rb
|
152
153
|
- lib/legitbot/baidu.rb
|
153
154
|
- lib/legitbot/bing.rb
|
@@ -165,6 +166,7 @@ files:
|
|
165
166
|
- lib/legitbot/version.rb
|
166
167
|
- lib/legitbot/yandex.rb
|
167
168
|
- test/ahrefs_test.rb
|
169
|
+
- test/alexa_test.rb
|
168
170
|
- test/apple_as_google_test.rb
|
169
171
|
- test/apple_test.rb
|
170
172
|
- test/botmatch_test.rb
|
@@ -205,6 +207,7 @@ test_files:
|
|
205
207
|
- test/legitbot/validators/domains_test.rb
|
206
208
|
- test/legitbot/validators/ip_ranges_test.rb
|
207
209
|
- test/pinterest_test.rb
|
210
|
+
- test/alexa_test.rb
|
208
211
|
- test/ahrefs_test.rb
|
209
212
|
- test/apple_test.rb
|
210
213
|
- test/apple_as_google_test.rb
|