legitbot 0.4.0 → 0.4.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/.rubocop.yml +1 -0
- data/README.md +1 -0
- data/legitbot.gemspec +19 -18
- data/lib/legitbot.rb +1 -0
- data/lib/legitbot/twitter.rb +14 -0
- data/lib/legitbot/version.rb +1 -1
- data/test/facebook_test.rb +1 -1
- data/test/twitter_test.rb +36 -0
- metadata +56 -17
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 86eb19b33835daaf208e4603d289ceb47c7ab68700a3bd08de99f60792d49798
|
4
|
+
data.tar.gz: 620efdf47110dfd96c07e1ffe148666b65d8121c639330f20b0b27f26b1a91d0
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 53fe5ac9f2fbcdbd229fe8dc32b2dade2671ecdb1b03d61a17c0d49139c0137790dbb97735987d4a9957cb0ae0563e6893ed8292c98dadec309ebc88f2013bfe
|
7
|
+
data.tar.gz: e1adf66298503e14032b13f8f16fe86fe5ed3a8fe1a3021bb165de7b2037a7051ba49ddd4ddc5aa396a34a627ef42e3c2239de1cb220eb8f07171718a0207a99
|
data/.rubocop.yml
CHANGED
data/README.md
CHANGED
@@ -51,6 +51,7 @@ end
|
|
51
51
|
* [Facebook crawler](https://developers.facebook.com/docs/sharing/webmasters/crawler)
|
52
52
|
* [Google crawlers](https://support.google.com/webmasters/answer/1061943)
|
53
53
|
* [Pinterest](https://help.pinterest.com/en/articles/about-pinterest-crawler-0)
|
54
|
+
* [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)
|
54
55
|
* [Yandex robots](https://yandex.com/support/webmaster/robot-workings/check-yandex-robots.xml)
|
55
56
|
|
56
57
|
## License
|
data/legitbot.gemspec
CHANGED
@@ -1,28 +1,29 @@
|
|
1
|
-
#
|
2
|
-
|
3
|
-
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
$LOAD_PATH.push File.expand_path('lib', __dir__)
|
4
|
+
require 'legitbot/version'
|
4
5
|
|
5
6
|
Gem::Specification.new do |spec|
|
6
7
|
spec.name = 'legitbot'
|
7
8
|
spec.version = Legitbot::VERSION
|
8
9
|
spec.license = 'Apache-2.0'
|
9
10
|
|
10
|
-
spec.author =
|
11
|
-
spec.email =
|
12
|
-
spec.homepage =
|
13
|
-
spec.summary =
|
14
|
-
spec.description =
|
15
|
-
|
11
|
+
spec.author = 'Alexander Azarov'
|
12
|
+
spec.email = 'self@alaz.me'
|
13
|
+
spec.homepage = 'https://github.com/alaz/legitbot'
|
14
|
+
spec.summary = 'Validate requests from Web crawlers: impersonating or not?'
|
15
|
+
spec.description = 'A library to make sure a Web request has been '\
|
16
|
+
'made by a real search engine, not a malicious agent'
|
16
17
|
|
17
18
|
spec.required_ruby_version = '>= 2.3.0'
|
18
|
-
spec.add_dependency
|
19
|
-
spec.add_dependency
|
20
|
-
spec.add_development_dependency
|
21
|
-
spec.add_development_dependency
|
22
|
-
spec.add_development_dependency
|
23
|
-
spec.add_development_dependency
|
19
|
+
spec.add_dependency 'augmented_interval_tree', '~> 0.1', '>= 0.1.1'
|
20
|
+
spec.add_dependency 'irrc', '~> 0.2', '>= 0.2.1'
|
21
|
+
spec.add_development_dependency 'bump', '~> 0.8', '>= 0.8.0'
|
22
|
+
spec.add_development_dependency 'minitest', '~> 5.1', '>= 5.1.0'
|
23
|
+
spec.add_development_dependency 'rake', '~> 12.3', '>= 12.3.0'
|
24
|
+
spec.add_development_dependency 'rubocop', '~> 0.74', '>= 0.74.0'
|
24
25
|
|
25
|
-
spec.files = `git ls-files`.split(
|
26
|
-
spec.rdoc_options = [
|
27
|
-
spec.test_files = Dir.glob(
|
26
|
+
spec.files = `git ls-files`.split($INPUT_RECORD_SEPARATOR)
|
27
|
+
spec.rdoc_options = ['--charset=UTF-8']
|
28
|
+
spec.test_files = Dir.glob('test/**/*')
|
28
29
|
end
|
data/lib/legitbot.rb
CHANGED
@@ -0,0 +1,14 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
module Legitbot # :nodoc:
|
4
|
+
# https://developer.twitter.com/en/docs/tweets/optimize-with-cards/guides/getting-started
|
5
|
+
# https://developer.twitter.com/en/docs/tweets/optimize-with-cards/guides/troubleshooting-cards
|
6
|
+
class Twitter < BotMatch
|
7
|
+
ip_ranges %w[
|
8
|
+
199.16.156.0/22
|
9
|
+
199.59.148.0/22
|
10
|
+
]
|
11
|
+
end
|
12
|
+
|
13
|
+
rule Legitbot::Twitter, %w[Twitterbot]
|
14
|
+
end
|
data/lib/legitbot/version.rb
CHANGED
data/test/facebook_test.rb
CHANGED
@@ -55,7 +55,7 @@ class FacebookTest < Minitest::Test
|
|
55
55
|
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_1) AppleWebKit/601.2.4 (KHTML, like Gecko) Version/9.0.1 Safari/601.2.4 facebookexternalhit/1.1 Facebot Twitterbot/1.0',
|
56
56
|
'92.243.181.7'
|
57
57
|
) do |bot|
|
58
|
-
|
58
|
+
assert %i[facebook twitter].include?(bot.detected_as)
|
59
59
|
assert bot.fake?, msg: 'fake Facebook'
|
60
60
|
end
|
61
61
|
end
|
@@ -0,0 +1,36 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require 'minitest/autorun'
|
4
|
+
require 'legitbot'
|
5
|
+
|
6
|
+
class TwitterTest < Minitest::Test
|
7
|
+
def test_malicious_ip
|
8
|
+
ip = '149.210.164.47'
|
9
|
+
match = Legitbot::Twitter.new ip
|
10
|
+
assert !match.valid?, msg: "#{ip} is not a real Twitter IP"
|
11
|
+
end
|
12
|
+
|
13
|
+
def test_valid_ip
|
14
|
+
ip = '199.16.156.125'
|
15
|
+
match = Legitbot::Twitter.new ip
|
16
|
+
assert match.valid?, msg: "#{ip} is a valid Twitter IP"
|
17
|
+
end
|
18
|
+
|
19
|
+
def test_malicious_ua
|
20
|
+
bot = Legitbot.bot(
|
21
|
+
'Twitterbot/1.0',
|
22
|
+
'149.210.164.47'
|
23
|
+
)
|
24
|
+
assert bot, msg: 'Twitter detected from User-Agent'
|
25
|
+
assert !bot.valid?, msg: 'Not a valid Twitter'
|
26
|
+
end
|
27
|
+
|
28
|
+
def test_valid_ua
|
29
|
+
bot = Legitbot.bot(
|
30
|
+
'Twitterbot/1.0',
|
31
|
+
'199.16.156.125'
|
32
|
+
)
|
33
|
+
assert bot, msg: 'Twitter detected from User-Agent'
|
34
|
+
assert bot.valid?, msg: 'Valid Twitter'
|
35
|
+
end
|
36
|
+
end
|
metadata
CHANGED
@@ -1,47 +1,62 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: legitbot
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.4.
|
4
|
+
version: 0.4.1
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Alexander Azarov
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2019-
|
11
|
+
date: 2019-10-21 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
|
-
name:
|
14
|
+
name: augmented_interval_tree
|
15
15
|
requirement: !ruby/object:Gem::Requirement
|
16
16
|
requirements:
|
17
|
+
- - "~>"
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '0.1'
|
17
20
|
- - ">="
|
18
21
|
- !ruby/object:Gem::Version
|
19
|
-
version: 0.
|
22
|
+
version: 0.1.1
|
20
23
|
type: :runtime
|
21
24
|
prerelease: false
|
22
25
|
version_requirements: !ruby/object:Gem::Requirement
|
23
26
|
requirements:
|
27
|
+
- - "~>"
|
28
|
+
- !ruby/object:Gem::Version
|
29
|
+
version: '0.1'
|
24
30
|
- - ">="
|
25
31
|
- !ruby/object:Gem::Version
|
26
|
-
version: 0.
|
32
|
+
version: 0.1.1
|
27
33
|
- !ruby/object:Gem::Dependency
|
28
|
-
name:
|
34
|
+
name: irrc
|
29
35
|
requirement: !ruby/object:Gem::Requirement
|
30
36
|
requirements:
|
37
|
+
- - "~>"
|
38
|
+
- !ruby/object:Gem::Version
|
39
|
+
version: '0.2'
|
31
40
|
- - ">="
|
32
41
|
- !ruby/object:Gem::Version
|
33
|
-
version: 0.
|
42
|
+
version: 0.2.1
|
34
43
|
type: :runtime
|
35
44
|
prerelease: false
|
36
45
|
version_requirements: !ruby/object:Gem::Requirement
|
37
46
|
requirements:
|
47
|
+
- - "~>"
|
48
|
+
- !ruby/object:Gem::Version
|
49
|
+
version: '0.2'
|
38
50
|
- - ">="
|
39
51
|
- !ruby/object:Gem::Version
|
40
|
-
version: 0.
|
52
|
+
version: 0.2.1
|
41
53
|
- !ruby/object:Gem::Dependency
|
42
54
|
name: bump
|
43
55
|
requirement: !ruby/object:Gem::Requirement
|
44
56
|
requirements:
|
57
|
+
- - "~>"
|
58
|
+
- !ruby/object:Gem::Version
|
59
|
+
version: '0.8'
|
45
60
|
- - ">="
|
46
61
|
- !ruby/object:Gem::Version
|
47
62
|
version: 0.8.0
|
@@ -49,51 +64,72 @@ dependencies:
|
|
49
64
|
prerelease: false
|
50
65
|
version_requirements: !ruby/object:Gem::Requirement
|
51
66
|
requirements:
|
67
|
+
- - "~>"
|
68
|
+
- !ruby/object:Gem::Version
|
69
|
+
version: '0.8'
|
52
70
|
- - ">="
|
53
71
|
- !ruby/object:Gem::Version
|
54
72
|
version: 0.8.0
|
55
73
|
- !ruby/object:Gem::Dependency
|
56
|
-
name:
|
74
|
+
name: minitest
|
57
75
|
requirement: !ruby/object:Gem::Requirement
|
58
76
|
requirements:
|
77
|
+
- - "~>"
|
78
|
+
- !ruby/object:Gem::Version
|
79
|
+
version: '5.1'
|
59
80
|
- - ">="
|
60
81
|
- !ruby/object:Gem::Version
|
61
|
-
version:
|
82
|
+
version: 5.1.0
|
62
83
|
type: :development
|
63
84
|
prerelease: false
|
64
85
|
version_requirements: !ruby/object:Gem::Requirement
|
65
86
|
requirements:
|
87
|
+
- - "~>"
|
88
|
+
- !ruby/object:Gem::Version
|
89
|
+
version: '5.1'
|
66
90
|
- - ">="
|
67
91
|
- !ruby/object:Gem::Version
|
68
|
-
version:
|
92
|
+
version: 5.1.0
|
69
93
|
- !ruby/object:Gem::Dependency
|
70
|
-
name:
|
94
|
+
name: rake
|
71
95
|
requirement: !ruby/object:Gem::Requirement
|
72
96
|
requirements:
|
97
|
+
- - "~>"
|
98
|
+
- !ruby/object:Gem::Version
|
99
|
+
version: '12.3'
|
73
100
|
- - ">="
|
74
101
|
- !ruby/object:Gem::Version
|
75
|
-
version:
|
102
|
+
version: 12.3.0
|
76
103
|
type: :development
|
77
104
|
prerelease: false
|
78
105
|
version_requirements: !ruby/object:Gem::Requirement
|
79
106
|
requirements:
|
107
|
+
- - "~>"
|
108
|
+
- !ruby/object:Gem::Version
|
109
|
+
version: '12.3'
|
80
110
|
- - ">="
|
81
111
|
- !ruby/object:Gem::Version
|
82
|
-
version:
|
112
|
+
version: 12.3.0
|
83
113
|
- !ruby/object:Gem::Dependency
|
84
|
-
name:
|
114
|
+
name: rubocop
|
85
115
|
requirement: !ruby/object:Gem::Requirement
|
86
116
|
requirements:
|
117
|
+
- - "~>"
|
118
|
+
- !ruby/object:Gem::Version
|
119
|
+
version: '0.74'
|
87
120
|
- - ">="
|
88
121
|
- !ruby/object:Gem::Version
|
89
|
-
version:
|
122
|
+
version: 0.74.0
|
90
123
|
type: :development
|
91
124
|
prerelease: false
|
92
125
|
version_requirements: !ruby/object:Gem::Requirement
|
93
126
|
requirements:
|
127
|
+
- - "~>"
|
128
|
+
- !ruby/object:Gem::Version
|
129
|
+
version: '0.74'
|
94
130
|
- - ">="
|
95
131
|
- !ruby/object:Gem::Version
|
96
|
-
version:
|
132
|
+
version: 0.74.0
|
97
133
|
description: A library to make sure a Web request has been made by a real search engine,
|
98
134
|
not a malicious agent
|
99
135
|
email: self@alaz.me
|
@@ -121,6 +157,7 @@ files:
|
|
121
157
|
- lib/legitbot/google.rb
|
122
158
|
- lib/legitbot/legitbot.rb
|
123
159
|
- lib/legitbot/pinterest.rb
|
160
|
+
- lib/legitbot/twitter.rb
|
124
161
|
- lib/legitbot/validators/domains.rb
|
125
162
|
- lib/legitbot/validators/ip_ranges.rb
|
126
163
|
- lib/legitbot/version.rb
|
@@ -135,6 +172,7 @@ files:
|
|
135
172
|
- test/legitbot/validators/ip_ranges_test.rb
|
136
173
|
- test/legitbot_test.rb
|
137
174
|
- test/pinterest_test.rb
|
175
|
+
- test/twitter_test.rb
|
138
176
|
homepage: https://github.com/alaz/legitbot
|
139
177
|
licenses:
|
140
178
|
- Apache-2.0
|
@@ -171,3 +209,4 @@ test_files:
|
|
171
209
|
- test/google_test.rb
|
172
210
|
- test/botmatch_test.rb
|
173
211
|
- test/facebook_test.rb
|
212
|
+
- test/twitter_test.rb
|