legitbot 1.0.0 → 1.0.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/README.md +5 -0
- data/lib/legitbot/legitbot.rb +2 -0
- data/lib/legitbot/validators/ip_ranges.rb +11 -7
- data/lib/legitbot/version.rb +1 -1
- data/test/legitbot/validators/ip_ranges_test.rb +9 -0
- metadata +2 -2
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 1596ed8c3809fc3c3068f14d8bbbcf84232286fd7157fe724ba9515d195259cd
|
4
|
+
data.tar.gz: f0078d0404d752550adeeaa9c64954cbcec57fef3d0b37c98bc50d765c29bc1f
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 5640ae1e351bbd697325cd0bed0bdac45c3726e7b31923b7b5c8f51859ed025d4eb368d937a2b3bf9ef6c150d83418f8e019304dec3bc1b010572a4e1598c661
|
7
|
+
data.tar.gz: bf326da52d3adf1b2cfa3693b51cc763daef54c9b175cfb91b437b213722a0f578565db553f1240b6d6ee47d159bb418fdcc1db1f95cb14696b2bfb52e50b75d
|
data/README.md
CHANGED
@@ -67,3 +67,8 @@ Apache 2.0
|
|
67
67
|
detects bots by `User-Agent`
|
68
68
|
* [crawler_detect](https://github.com/loadkpi/crawler_detect) is a Ruby gem and Rack
|
69
69
|
middleware to detect crawlers by few different request headers, including `User-Agent`
|
70
|
+
* Project Honeypot's
|
71
|
+
[http:BL](https://www.projecthoneypot.org/httpbl_api.php) can not only
|
72
|
+
classify IP as a search engine, but also label them as suspicious and
|
73
|
+
reports the number of days since the last activity. My implementation of
|
74
|
+
the protocol in Scala is [here](https://github.com/osinka/httpbl).
|
data/lib/legitbot/legitbot.rb
CHANGED
@@ -18,6 +18,7 @@ module Legitbot
|
|
18
18
|
# otherwise.
|
19
19
|
# :yields: a found bot
|
20
20
|
#
|
21
|
+
# rubocop:disable Metrics/CyclomaticComplexity
|
21
22
|
def self.bot(user_agent, ip)
|
22
23
|
bots = @rules
|
23
24
|
.select { |rule| rule[:fragments].any? { |f| user_agent.index f } }
|
@@ -32,6 +33,7 @@ module Legitbot
|
|
32
33
|
selected
|
33
34
|
end
|
34
35
|
end
|
36
|
+
# rubocop:enable Metrics/CyclomaticComplexity
|
35
37
|
|
36
38
|
def self.rule(clazz, fragments)
|
37
39
|
@rules << { class: clazz, fragments: fragments }
|
@@ -59,22 +59,26 @@ module Legitbot
|
|
59
59
|
partition_ips(@ip_ranges_loader.call)
|
60
60
|
end
|
61
61
|
|
62
|
-
# rubocop:disable Metrics/AbcSize, Metrics/MethodLength
|
63
62
|
def partition_ips(ips)
|
64
|
-
return []
|
63
|
+
return [] unless ips&.any?
|
65
64
|
|
66
65
|
ips
|
67
66
|
.map { |cidr| IPAddr.new(cidr) }
|
68
67
|
.partition(&:ipv4?)
|
69
68
|
.each_with_index
|
70
69
|
.map do |list, index|
|
71
|
-
|
72
|
-
(r.begin.to_i..r.end.to_i)
|
73
|
-
end
|
74
|
-
[FAMILIES[index], IntervalTree::Tree.new(ranges)]
|
70
|
+
[FAMILIES[index], build_interval_tree(list)]
|
75
71
|
end.to_h
|
76
72
|
end
|
77
|
-
|
73
|
+
|
74
|
+
private
|
75
|
+
|
76
|
+
def build_interval_tree(list)
|
77
|
+
ranges = list.map(&:to_range).map do |r|
|
78
|
+
(r.begin.to_i..r.end.to_i)
|
79
|
+
end
|
80
|
+
IntervalTree::Tree.new(ranges)
|
81
|
+
end
|
78
82
|
end
|
79
83
|
end
|
80
84
|
end
|
data/lib/legitbot/version.rb
CHANGED
@@ -46,6 +46,11 @@ module Legitbot
|
|
46
46
|
end
|
47
47
|
end
|
48
48
|
|
49
|
+
class NilRanges
|
50
|
+
include IpRanges
|
51
|
+
ip_ranges { nil }
|
52
|
+
end
|
53
|
+
|
49
54
|
class IpRangesTest < Minitest::Test
|
50
55
|
def test_partition_method
|
51
56
|
empty = NoRanges.partition_ips([])
|
@@ -108,6 +113,10 @@ module Legitbot
|
|
108
113
|
assert_equal 2, LoadRanges.counter
|
109
114
|
end
|
110
115
|
# rubocop:enable Metrics/AbcSize
|
116
|
+
|
117
|
+
def test_nil_ranges
|
118
|
+
assert NilRanges.valid_ip?('127.0.0.1')
|
119
|
+
end
|
111
120
|
end
|
112
121
|
end
|
113
122
|
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: 1.0.1
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Alexander Azarov
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2020-
|
11
|
+
date: 2020-07-28 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: augmented_interval_tree
|