rack_detect_robots 0.0.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- data/lib/rack_detect_robots.rb +60 -0
- metadata +146 -0
@@ -0,0 +1,60 @@
|
|
1
|
+
module Rack
|
2
|
+
class DetectRobotsResult
|
3
|
+
def self.no_robot
|
4
|
+
new(nil)
|
5
|
+
end
|
6
|
+
def initialize(robot_name)
|
7
|
+
@robot_name=robot_name
|
8
|
+
@is_robot = !!robot_name #no name no robot
|
9
|
+
end
|
10
|
+
attr_reader :robot_name
|
11
|
+
def robot?
|
12
|
+
@is_robot
|
13
|
+
end
|
14
|
+
end
|
15
|
+
class DetectRobots
|
16
|
+
#this is fast for upto ca. 200 crawlers then use something different (trie...)
|
17
|
+
KNOWN_CRAWLERS = [
|
18
|
+
'yahoo! slurp',
|
19
|
+
'yahoo! de slurp',
|
20
|
+
'googlebot',
|
21
|
+
'ask jeeves',
|
22
|
+
'yanga worldsearch bot',
|
23
|
+
'gigaboti',
|
24
|
+
'ichiro',
|
25
|
+
'msnbot',
|
26
|
+
'crawler',
|
27
|
+
'ia_archiver',
|
28
|
+
'jobverifier',
|
29
|
+
'twiceler',
|
30
|
+
'eurobot',
|
31
|
+
'adsbot-google',
|
32
|
+
'speedy spider',
|
33
|
+
'yacybot',
|
34
|
+
'wget',
|
35
|
+
'findlinks',
|
36
|
+
'feedhub metadatafetcher',
|
37
|
+
'jobrobot.de',
|
38
|
+
'baiduspider']
|
39
|
+
|
40
|
+
def initialize(app, crawler_regexp=nil)
|
41
|
+
@app=app
|
42
|
+
@crawler_regexp = (crawler_regexp || Regexp.new(KNOWN_CRAWLERS.map{|bot| Regexp.escape(bot)}.join('|'),"i"))
|
43
|
+
end
|
44
|
+
|
45
|
+
def call(env)
|
46
|
+
env[:rack_detect_robots]=test_for_robots(env)
|
47
|
+
@app.call(env)
|
48
|
+
end
|
49
|
+
private
|
50
|
+
|
51
|
+
def test_for_robots(env)
|
52
|
+
user_agent=env["HTTP_USER_AGENT"]
|
53
|
+
return DetectRobotsResult.no_robot if user_agent.nil? || user_agent.empty?
|
54
|
+
match=@crawler_regexp.match( user_agent )
|
55
|
+
return DetectRobotsResult.no_robot unless match
|
56
|
+
DetectRobotsResult.new(match[0])
|
57
|
+
end
|
58
|
+
|
59
|
+
end
|
60
|
+
end
|
metadata
ADDED
@@ -0,0 +1,146 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: rack_detect_robots
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
prerelease:
|
6
|
+
platform: ruby
|
7
|
+
authors:
|
8
|
+
- Peter Schrammel
|
9
|
+
autorequire:
|
10
|
+
bindir: bin
|
11
|
+
cert_chain: []
|
12
|
+
date: 2011-09-05 00:00:00.000000000 +02:00
|
13
|
+
default_executable:
|
14
|
+
dependencies:
|
15
|
+
- !ruby/object:Gem::Dependency
|
16
|
+
name: rake
|
17
|
+
requirement: &75639470 !ruby/object:Gem::Requirement
|
18
|
+
none: false
|
19
|
+
requirements:
|
20
|
+
- - ! '>='
|
21
|
+
- !ruby/object:Gem::Version
|
22
|
+
version: '0'
|
23
|
+
type: :development
|
24
|
+
prerelease: false
|
25
|
+
version_requirements: *75639470
|
26
|
+
- !ruby/object:Gem::Dependency
|
27
|
+
name: rake
|
28
|
+
requirement: &75638730 !ruby/object:Gem::Requirement
|
29
|
+
none: false
|
30
|
+
requirements:
|
31
|
+
- - ! '>='
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '0'
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: *75638730
|
37
|
+
- !ruby/object:Gem::Dependency
|
38
|
+
name: rake
|
39
|
+
requirement: &75637980 !ruby/object:Gem::Requirement
|
40
|
+
none: false
|
41
|
+
requirements:
|
42
|
+
- - ! '>='
|
43
|
+
- !ruby/object:Gem::Version
|
44
|
+
version: '0'
|
45
|
+
type: :development
|
46
|
+
prerelease: false
|
47
|
+
version_requirements: *75637980
|
48
|
+
- !ruby/object:Gem::Dependency
|
49
|
+
name: jeweler
|
50
|
+
requirement: &75637530 !ruby/object:Gem::Requirement
|
51
|
+
none: false
|
52
|
+
requirements:
|
53
|
+
- - ~>
|
54
|
+
- !ruby/object:Gem::Version
|
55
|
+
version: '1.6'
|
56
|
+
type: :development
|
57
|
+
prerelease: false
|
58
|
+
version_requirements: *75637530
|
59
|
+
- !ruby/object:Gem::Dependency
|
60
|
+
name: rspec
|
61
|
+
requirement: &75637010 !ruby/object:Gem::Requirement
|
62
|
+
none: false
|
63
|
+
requirements:
|
64
|
+
- - ~>
|
65
|
+
- !ruby/object:Gem::Version
|
66
|
+
version: '2.6'
|
67
|
+
type: :development
|
68
|
+
prerelease: false
|
69
|
+
version_requirements: *75637010
|
70
|
+
- !ruby/object:Gem::Dependency
|
71
|
+
name: rake
|
72
|
+
requirement: &75636540 !ruby/object:Gem::Requirement
|
73
|
+
none: false
|
74
|
+
requirements:
|
75
|
+
- - ! '>='
|
76
|
+
- !ruby/object:Gem::Version
|
77
|
+
version: '0'
|
78
|
+
type: :development
|
79
|
+
prerelease: false
|
80
|
+
version_requirements: *75636540
|
81
|
+
- !ruby/object:Gem::Dependency
|
82
|
+
name: jeweler
|
83
|
+
requirement: &75636050 !ruby/object:Gem::Requirement
|
84
|
+
none: false
|
85
|
+
requirements:
|
86
|
+
- - ~>
|
87
|
+
- !ruby/object:Gem::Version
|
88
|
+
version: '1.6'
|
89
|
+
type: :development
|
90
|
+
prerelease: false
|
91
|
+
version_requirements: *75636050
|
92
|
+
- !ruby/object:Gem::Dependency
|
93
|
+
name: rspec
|
94
|
+
requirement: &75635640 !ruby/object:Gem::Requirement
|
95
|
+
none: false
|
96
|
+
requirements:
|
97
|
+
- - ~>
|
98
|
+
- !ruby/object:Gem::Version
|
99
|
+
version: '2.6'
|
100
|
+
type: :development
|
101
|
+
prerelease: false
|
102
|
+
version_requirements: *75635640
|
103
|
+
- !ruby/object:Gem::Dependency
|
104
|
+
name: rack
|
105
|
+
requirement: &75635220 !ruby/object:Gem::Requirement
|
106
|
+
none: false
|
107
|
+
requirements:
|
108
|
+
- - ! '>='
|
109
|
+
- !ruby/object:Gem::Version
|
110
|
+
version: 0.9.1
|
111
|
+
type: :runtime
|
112
|
+
prerelease: false
|
113
|
+
version_requirements: *75635220
|
114
|
+
description:
|
115
|
+
email:
|
116
|
+
executables: []
|
117
|
+
extensions: []
|
118
|
+
extra_rdoc_files: []
|
119
|
+
files:
|
120
|
+
- lib/rack_detect_robots.rb
|
121
|
+
has_rdoc: true
|
122
|
+
homepage: http://github.com/experteer/rack_detect_robots
|
123
|
+
licenses: []
|
124
|
+
post_install_message:
|
125
|
+
rdoc_options: []
|
126
|
+
require_paths:
|
127
|
+
- lib
|
128
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
129
|
+
none: false
|
130
|
+
requirements:
|
131
|
+
- - ! '>='
|
132
|
+
- !ruby/object:Gem::Version
|
133
|
+
version: '0'
|
134
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
135
|
+
none: false
|
136
|
+
requirements:
|
137
|
+
- - ! '>='
|
138
|
+
- !ruby/object:Gem::Version
|
139
|
+
version: '0'
|
140
|
+
requirements: []
|
141
|
+
rubyforge_project:
|
142
|
+
rubygems_version: 1.6.2
|
143
|
+
signing_key:
|
144
|
+
specification_version: 3
|
145
|
+
summary: Rack Middleware for detecting robots
|
146
|
+
test_files: []
|