legitbot 1.4.1 → 1.4.5
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/README.md +7 -8
- data/legitbot.gemspec +1 -1
- data/lib/legitbot/facebook.rb +4 -1
- data/lib/legitbot/google.rb +9 -1
- data/lib/legitbot/oracle.rb +25 -1
- data/lib/legitbot/petalbot.rb +11 -0
- data/lib/legitbot/twitter.rb +1 -0
- data/lib/legitbot/version.rb +1 -1
- data/lib/legitbot.rb +1 -0
- data/test/petalbot_test.rb +52 -0
- metadata +9 -6
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 3eb1ad3043aa5d9c87f6417fa287121cc5ec37fe1fcb6b043f9e6ee9a88ec771
|
4
|
+
data.tar.gz: 01764d6f90fd4f72751d18ea17d4f6921103ba2e050fe8f179d13d889d920347
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: '0269f1dd308855bb4dd15e82601dba739b2f77bfb2777d802f4b813b0a73d31f052e3f75cbc26812589a3816aefe6d49c9b9ab20b59b229a346c4d8da27b46a5'
|
7
|
+
data.tar.gz: 1e2f8e9e5e7ae7812df3016e6f0c6e45af9f4b60d67512f9678be1437ccbc8dcf55ae1fbeb404274d03b80c32e6bc8e7678b22654c089900b11f2681fc090b73
|
data/README.md
CHANGED
@@ -1,13 +1,11 @@
|
|
1
1
|
# Legitbot ![](https://github.com/alaz/legitbot/workflows/build/badge.svg) ![](https://badge.fury.io/rb/legitbot.svg)
|
2
2
|
|
3
|
-
Ruby gem to
|
4
|
-
engine.
|
5
|
-
engines.
|
3
|
+
Ruby gem to make sure that an IP really belongs to a bot, typically a search
|
4
|
+
engine.
|
6
5
|
|
7
6
|
## Usage
|
8
7
|
|
9
|
-
Suppose you have a Web request and you
|
10
|
-
search engine:
|
8
|
+
Suppose you have a Web request and you would like to check it is not diguised:
|
11
9
|
|
12
10
|
```ruby
|
13
11
|
bot = Legitbot.bot(userAgent, ip)
|
@@ -22,7 +20,7 @@ bot.valid? # => true
|
|
22
20
|
bot.fake? # => false
|
23
21
|
```
|
24
22
|
|
25
|
-
Sometimes you already know
|
23
|
+
Sometimes you already know which search engine to expect. For example, you might
|
26
24
|
be using [rack-attack](https://github.com/kickstarter/rack-attack):
|
27
25
|
|
28
26
|
```ruby
|
@@ -31,8 +29,8 @@ Rack::Attack.blocklist("fake Googlebot") do |req|
|
|
31
29
|
end
|
32
30
|
```
|
33
31
|
|
34
|
-
Or if you do not like all
|
35
|
-
|
32
|
+
Or if you do not like all those ghoulish crawlers stealing your
|
33
|
+
content, evaluating it and getting ready to invade your site with spammers,
|
36
34
|
then block them all:
|
37
35
|
|
38
36
|
```ruby
|
@@ -52,6 +50,7 @@ end
|
|
52
50
|
* [Facebook crawler](https://developers.facebook.com/docs/sharing/webmasters/crawler)
|
53
51
|
* [Google crawlers](https://support.google.com/webmasters/answer/1061943)
|
54
52
|
* [Oracle Data Cloud Crawler](https://www.oracle.com/corporate/acquisitions/grapeshot/crawler.html)
|
53
|
+
* [Petal search engine](http://aspiegel.com/petalbot)
|
55
54
|
* [Pinterest](https://help.pinterest.com/en/articles/about-pinterest-crawler-0)
|
56
55
|
* [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)
|
57
56
|
* [Yandex robots](https://yandex.com/support/webmaster/robot-workings/check-yandex-robots.xml)
|
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', '~> 13.0', '>= 13.0.0'
|
23
|
-
spec.add_development_dependency 'rubocop', '~> 1.
|
23
|
+
spec.add_development_dependency 'rubocop', '~> 1.22.0', '>= 1.22.0'
|
24
24
|
|
25
25
|
spec.files = `git ls-files`.split($INPUT_RECORD_SEPARATOR)
|
26
26
|
spec.rdoc_options = ['--charset=UTF-8']
|
data/lib/legitbot/facebook.rb
CHANGED
data/lib/legitbot/google.rb
CHANGED
@@ -7,5 +7,13 @@ module Legitbot # :nodoc:
|
|
7
7
|
domains 'google.com.', 'googlebot.com.'
|
8
8
|
end
|
9
9
|
|
10
|
-
rule Legitbot::Google, %w[
|
10
|
+
rule Legitbot::Google, %w[
|
11
|
+
APIs-Google
|
12
|
+
AdsBot-Google-Mobile
|
13
|
+
AdsBot-Google
|
14
|
+
Googlebot
|
15
|
+
Mediapartners-Google
|
16
|
+
AdsBot-Google-Mobile-Apps
|
17
|
+
FeedFetcher-Google
|
18
|
+
]
|
11
19
|
end
|
data/lib/legitbot/oracle.rb
CHANGED
@@ -3,7 +3,31 @@
|
|
3
3
|
module Legitbot # :nodoc:
|
4
4
|
# https://www.oracle.com/corporate/acquisitions/grapeshot/crawler.html
|
5
5
|
class Oracle < BotMatch
|
6
|
-
ip_ranges
|
6
|
+
ip_ranges %w[
|
7
|
+
132.145.9.5
|
8
|
+
132.145.11.125
|
9
|
+
132.145.14.70
|
10
|
+
132.145.15.209
|
11
|
+
132.145.64.33
|
12
|
+
132.145.66.116
|
13
|
+
132.145.66.156
|
14
|
+
132.145.67.248
|
15
|
+
140.238.81.78
|
16
|
+
140.238.83.181
|
17
|
+
140.238.94.137
|
18
|
+
140.238.95.47
|
19
|
+
140.238.95.199
|
20
|
+
152.67.128.219
|
21
|
+
152.67.137.35
|
22
|
+
152.67.138.180
|
23
|
+
|
24
|
+
148.64.56.64/28
|
25
|
+
148.64.56.79
|
26
|
+
148.64.56.80
|
27
|
+
148.64.56.112/28
|
28
|
+
148.64.56.127
|
29
|
+
148.64.56.128
|
30
|
+
]
|
7
31
|
end
|
8
32
|
|
9
33
|
rule Legitbot::Oracle, %w[GrapeshotCrawler]
|
data/lib/legitbot/twitter.rb
CHANGED
data/lib/legitbot/version.rb
CHANGED
data/lib/legitbot.rb
CHANGED
@@ -0,0 +1,52 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require 'minitest/autorun'
|
4
|
+
require 'legitbot'
|
5
|
+
|
6
|
+
class PetalbotTest < Minitest::Test
|
7
|
+
def test_malicious_ip
|
8
|
+
ip = '149.210.164.47'
|
9
|
+
match = Legitbot::Petalbot.new ip
|
10
|
+
assert !match.valid?, msg: "#{ip} is not a real Petalbot IP"
|
11
|
+
end
|
12
|
+
|
13
|
+
def test_valid_ip
|
14
|
+
ip = '114.119.128.10'
|
15
|
+
match = Legitbot::Petalbot.new ip
|
16
|
+
assert match.valid?, msg: "#{ip} is a valid Petalbot IP"
|
17
|
+
end
|
18
|
+
|
19
|
+
def test_malicious_ua
|
20
|
+
bot = Legitbot.bot(
|
21
|
+
'Mozilla/5.0 (compatible;PetalBot; +https://aspiegel.com/petalbot)',
|
22
|
+
'149.210.164.47'
|
23
|
+
)
|
24
|
+
assert bot, msg: 'Petalbot detected from User-Agent'
|
25
|
+
assert !bot.valid?, msg: 'Not a valid Petalbot'
|
26
|
+
end
|
27
|
+
|
28
|
+
def test_valid_ua
|
29
|
+
bot = Legitbot.bot(
|
30
|
+
'Mozilla/5.0 (compatible;PetalBot; +https://aspiegel.com/petalbot)',
|
31
|
+
'114.119.128.10'
|
32
|
+
)
|
33
|
+
assert bot, msg: 'Petalbot detected from User-Agent'
|
34
|
+
assert bot.valid?, msg: 'Valid Petalbot'
|
35
|
+
end
|
36
|
+
|
37
|
+
def test_valid_name
|
38
|
+
bot = Legitbot.bot(
|
39
|
+
'Mozilla/5.0 (compatible;PetalBot; +https://aspiegel.com/petalbot)',
|
40
|
+
'66.249.64.141'
|
41
|
+
)
|
42
|
+
assert_equal :petalbot, bot.detected_as
|
43
|
+
end
|
44
|
+
|
45
|
+
def test_fake_name
|
46
|
+
bot = Legitbot.bot(
|
47
|
+
'Mozilla/5.0 (compatible; PetalBot/2.1; +http://www.google.com/bot.html)',
|
48
|
+
'81.1.172.108'
|
49
|
+
)
|
50
|
+
assert_equal :petalbot, bot.detected_as
|
51
|
+
end
|
52
|
+
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: 1.4.
|
4
|
+
version: 1.4.5
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Alexander Azarov
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2021-
|
11
|
+
date: 2021-10-01 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: 1.
|
119
|
+
version: 1.22.0
|
120
120
|
- - ">="
|
121
121
|
- !ruby/object:Gem::Version
|
122
|
-
version: 1.
|
122
|
+
version: 1.22.0
|
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: 1.
|
129
|
+
version: 1.22.0
|
130
130
|
- - ">="
|
131
131
|
- !ruby/object:Gem::Version
|
132
|
-
version: 1.
|
132
|
+
version: 1.22.0
|
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
|
@@ -160,6 +160,7 @@ files:
|
|
160
160
|
- lib/legitbot/google.rb
|
161
161
|
- lib/legitbot/legitbot.rb
|
162
162
|
- lib/legitbot/oracle.rb
|
163
|
+
- lib/legitbot/petalbot.rb
|
163
164
|
- lib/legitbot/pinterest.rb
|
164
165
|
- lib/legitbot/twitter.rb
|
165
166
|
- lib/legitbot/validators/domains.rb
|
@@ -176,6 +177,7 @@ files:
|
|
176
177
|
- test/legitbot/validators/ip_ranges_test.rb
|
177
178
|
- test/legitbot_test.rb
|
178
179
|
- test/oracle_test.rb
|
180
|
+
- test/petalbot_test.rb
|
179
181
|
- test/pinterest_test.rb
|
180
182
|
- test/twitter_test.rb
|
181
183
|
homepage: https://github.com/alaz/legitbot
|
@@ -212,6 +214,7 @@ test_files:
|
|
212
214
|
- test/apple_test.rb
|
213
215
|
- test/oracle_test.rb
|
214
216
|
- test/google_test.rb
|
217
|
+
- test/petalbot_test.rb
|
215
218
|
- test/botmatch_test.rb
|
216
219
|
- test/facebook_test.rb
|
217
220
|
- test/twitter_test.rb
|