rack-evil_robot 0.1.0
Sign up to get free protection for your applications and to get access to all the features.
- data/.gitignore +1 -0
- data/README.rdoc +31 -0
- data/Rakefile +44 -0
- data/VERSION +1 -0
- data/lib/rack/evil_robot.rb +34 -0
- data/rake-evil_robot.gemspec +49 -0
- data/spec/rack/evil_robot_spec.rb +52 -0
- data/spec/spec_helper.rb +11 -0
- metadata +88 -0
data/.gitignore
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
pkg
|
data/README.rdoc
ADDED
@@ -0,0 +1,31 @@
|
|
1
|
+
= Rack::EvilRobot
|
2
|
+
|
3
|
+
== INSTALL
|
4
|
+
|
5
|
+
sudo gem install rack-evil_robot
|
6
|
+
|
7
|
+
== SETUP
|
8
|
+
|
9
|
+
require 'rack/evil_robot'
|
10
|
+
use Rack::EvilRobot
|
11
|
+
|
12
|
+
or
|
13
|
+
|
14
|
+
use Rack::EvilRobot, :redirect_path => "http://www.whatever-you-want.com"
|
15
|
+
|
16
|
+
== SET THE TRAP
|
17
|
+
|
18
|
+
Update your robots.txt to contain these lines
|
19
|
+
|
20
|
+
User-agent: *
|
21
|
+
Disallow: /honey_pot/index.html
|
22
|
+
|
23
|
+
Include this link tag on your page(s)
|
24
|
+
<a href="/honey_pot/index.html"><img src="images/pixel.gif" border="0" alt=" " width="1" height="1"></a>
|
25
|
+
|
26
|
+
After you have this set up for a few days check your access logs and look at the user agents that have been accessing /honey_pot/index.html.
|
27
|
+
Hopefully there is nothing there, but if there is, and they are misbehaving, add them to the regex defined in the 'evil_robots' method.
|
28
|
+
This will prevent this user agent from accessing any pages on your site anymore.
|
29
|
+
|
30
|
+
== Win
|
31
|
+
Now you don't have to worry about getting crawled by bots you don't care to be hit by (mp3 bots, torrent bots, bots that are slamming your servers, etc...)
|
data/Rakefile
ADDED
@@ -0,0 +1,44 @@
|
|
1
|
+
require 'rubygems'
|
2
|
+
require 'rake'
|
3
|
+
|
4
|
+
begin
|
5
|
+
require 'jeweler'
|
6
|
+
Jeweler::Tasks.new do |gem|
|
7
|
+
gem.name = "rack-evil_robot"
|
8
|
+
gem.summary = "Detect robots that are ignoring your robots.txt file and give them the middle finger"
|
9
|
+
gem.description = "Detect robots that are ignoring your robots.txt file and give them the middle finger"
|
10
|
+
gem.email = "shanewolf@gmail.com"
|
11
|
+
gem.homepage = "http://github.com/gizm0duck/rack-evil_robot"
|
12
|
+
gem.authors = ["Shane Wolf"]
|
13
|
+
gem.add_dependency "rack"
|
14
|
+
end
|
15
|
+
Jeweler::GemcutterTasks.new
|
16
|
+
rescue LoadError
|
17
|
+
puts "Jeweler (or a dependency) not available. Install it with: gem install jeweler"
|
18
|
+
end
|
19
|
+
|
20
|
+
require 'spec/rake/spectask'
|
21
|
+
Spec::Rake::SpecTask.new(:spec) do |spec|
|
22
|
+
spec.libs << 'lib' << 'spec'
|
23
|
+
spec.spec_files = FileList['spec/**/*_spec.rb']
|
24
|
+
end
|
25
|
+
|
26
|
+
Spec::Rake::SpecTask.new(:rcov) do |spec|
|
27
|
+
spec.libs << 'lib' << 'spec'
|
28
|
+
spec.pattern = 'spec/**/*_spec.rb'
|
29
|
+
spec.rcov = true
|
30
|
+
end
|
31
|
+
|
32
|
+
task :spec => :check_dependencies
|
33
|
+
|
34
|
+
task :default => :spec
|
35
|
+
|
36
|
+
require 'rake/rdoctask'
|
37
|
+
Rake::RDocTask.new do |rdoc|
|
38
|
+
version = File.exist?('VERSION') ? File.read('VERSION') : ""
|
39
|
+
|
40
|
+
rdoc.rdoc_dir = 'rdoc'
|
41
|
+
rdoc.title = "rack-evil_robot #{version}"
|
42
|
+
rdoc.rdoc_files.include('README*')
|
43
|
+
rdoc.rdoc_files.include('lib/**/*.rb')
|
44
|
+
end
|
data/VERSION
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
0.1.0
|
@@ -0,0 +1,34 @@
|
|
1
|
+
module Rack
|
2
|
+
class EvilRobot
|
3
|
+
def initialize(app, options = {})
|
4
|
+
@app = app
|
5
|
+
@redirect_path = options[:redirect_path] || 'http://www.example.com/'
|
6
|
+
end
|
7
|
+
|
8
|
+
def call(env)
|
9
|
+
if evil_robot?(env)
|
10
|
+
goodbye
|
11
|
+
else
|
12
|
+
if env['PATH_INFO'] =~ /honey_pot/
|
13
|
+
[200, {'Content-Type' => 'text/html'}, ['Mmmm Honey...']]
|
14
|
+
else
|
15
|
+
@app.call(env)
|
16
|
+
end
|
17
|
+
end
|
18
|
+
end
|
19
|
+
|
20
|
+
private
|
21
|
+
def evil_robot?(env)
|
22
|
+
env['HTTP_USER_AGENT'] && env['HTTP_USER_AGENT'] =~ evil_robots
|
23
|
+
end
|
24
|
+
|
25
|
+
def goodbye
|
26
|
+
[301, {'Location' => @redirect_path}, ['No thank you.']]
|
27
|
+
end
|
28
|
+
|
29
|
+
def evil_robots
|
30
|
+
# add your evil-bots here... these are just for examples sake
|
31
|
+
/badBot|reallyBadBot/i
|
32
|
+
end
|
33
|
+
end
|
34
|
+
end
|
@@ -0,0 +1,49 @@
|
|
1
|
+
# Generated by jeweler
|
2
|
+
# DO NOT EDIT THIS FILE DIRECTLY
|
3
|
+
# Instead, edit Jeweler::Tasks in Rakefile, and run the gemspec command
|
4
|
+
# -*- encoding: utf-8 -*-
|
5
|
+
|
6
|
+
Gem::Specification.new do |s|
|
7
|
+
s.name = %q{rake-evil_robot}
|
8
|
+
s.version = "0.1.0"
|
9
|
+
|
10
|
+
s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
|
11
|
+
s.authors = ["Shane Wolf"]
|
12
|
+
s.date = %q{2010-08-06}
|
13
|
+
s.description = %q{Detect robots that are ignoring your robots.txt file and give them the middle finger}
|
14
|
+
s.email = %q{shanewolf@gmail.com}
|
15
|
+
s.extra_rdoc_files = [
|
16
|
+
"README"
|
17
|
+
]
|
18
|
+
s.files = [
|
19
|
+
"README",
|
20
|
+
"Rakefile",
|
21
|
+
"VERSION",
|
22
|
+
"lib/rack/evil_robot.rb",
|
23
|
+
"spec/rack/evil_robot_spec.rb",
|
24
|
+
"spec/spec_helper.rb"
|
25
|
+
]
|
26
|
+
s.homepage = %q{http://github.com/gizm0duck/rack-evil_robot}
|
27
|
+
s.rdoc_options = ["--charset=UTF-8"]
|
28
|
+
s.require_paths = ["lib"]
|
29
|
+
s.rubygems_version = %q{1.3.7}
|
30
|
+
s.summary = %q{Detect robots that are ignoring your robots.txt file and give them the middle finger}
|
31
|
+
s.test_files = [
|
32
|
+
"spec/rack/evil_robot_spec.rb",
|
33
|
+
"spec/spec_helper.rb"
|
34
|
+
]
|
35
|
+
|
36
|
+
if s.respond_to? :specification_version then
|
37
|
+
current_version = Gem::Specification::CURRENT_SPECIFICATION_VERSION
|
38
|
+
s.specification_version = 3
|
39
|
+
|
40
|
+
if Gem::Version.new(Gem::VERSION) >= Gem::Version.new('1.2.0') then
|
41
|
+
s.add_runtime_dependency(%q<rack>, [">= 0"])
|
42
|
+
else
|
43
|
+
s.add_dependency(%q<rack>, [">= 0"])
|
44
|
+
end
|
45
|
+
else
|
46
|
+
s.add_dependency(%q<rack>, [">= 0"])
|
47
|
+
end
|
48
|
+
end
|
49
|
+
|
@@ -0,0 +1,52 @@
|
|
1
|
+
require 'spec_helper'
|
2
|
+
|
3
|
+
describe Rack::EvilRobot do
|
4
|
+
|
5
|
+
describe "call" do
|
6
|
+
attr_reader :app
|
7
|
+
before do
|
8
|
+
@app = lambda { |env| [200, {'Content-Type' => 'text/plain'}, ['This is my body']] }
|
9
|
+
end
|
10
|
+
|
11
|
+
context "when the user agent is in the evil robots list" do
|
12
|
+
describe "when passing in custom redirect_path" do
|
13
|
+
it "redirects to the custom path" do
|
14
|
+
request = Rack::MockRequest.env_for('/real_path', {'HTTP_USER_AGENT' => 'badBot'})
|
15
|
+
response = Rack::EvilRobot.new(app, {:redirect_path => "http://www.google.com"}).call(request)
|
16
|
+
response[0].should == 301
|
17
|
+
response[1]["Location"].should == "http://www.google.com"
|
18
|
+
response[2].should == ["No thank you."]
|
19
|
+
end
|
20
|
+
end
|
21
|
+
|
22
|
+
describe "when no custom options are passed in" do
|
23
|
+
it "redirects the bot to example.com" do
|
24
|
+
request = Rack::MockRequest.env_for('/real_path', {'HTTP_USER_AGENT' => 'badBot'})
|
25
|
+
response = Rack::EvilRobot.new(app).call(request)
|
26
|
+
response[0].should == 301
|
27
|
+
response[1]["Location"].should == "http://www.example.com/"
|
28
|
+
response[2].should == ["No thank you."]
|
29
|
+
end
|
30
|
+
end
|
31
|
+
end
|
32
|
+
|
33
|
+
context "when the user agent is not in the evil robots list" do
|
34
|
+
context "when the request hits the honey pot" do
|
35
|
+
it "tells the robot it's been busted" do
|
36
|
+
request = Rack::MockRequest.env_for('/honey_pot/sticky.html', {'HTTP_USER_AGENT' => 'Mozilla/5.0'})
|
37
|
+
response = Rack::EvilRobot.new(app).call(request)
|
38
|
+
response.first.should == 200
|
39
|
+
response.last.should == ["Mmmm Honey..."]
|
40
|
+
end
|
41
|
+
end
|
42
|
+
|
43
|
+
context "when the request does not hit the honey pot" do
|
44
|
+
it "does nothing" do
|
45
|
+
request = Rack::MockRequest.env_for('/real_path', {'HTTP_USER_AGENT' => 'Mozilla/5.0'})
|
46
|
+
body = Rack::EvilRobot.new(app).call(request).last
|
47
|
+
body.should == ['This is my body']
|
48
|
+
end
|
49
|
+
end
|
50
|
+
end
|
51
|
+
end
|
52
|
+
end
|
data/spec/spec_helper.rb
ADDED
metadata
ADDED
@@ -0,0 +1,88 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: rack-evil_robot
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
hash: 27
|
5
|
+
prerelease: false
|
6
|
+
segments:
|
7
|
+
- 0
|
8
|
+
- 1
|
9
|
+
- 0
|
10
|
+
version: 0.1.0
|
11
|
+
platform: ruby
|
12
|
+
authors:
|
13
|
+
- Shane Wolf
|
14
|
+
autorequire:
|
15
|
+
bindir: bin
|
16
|
+
cert_chain: []
|
17
|
+
|
18
|
+
date: 2010-08-06 00:00:00 -07:00
|
19
|
+
default_executable:
|
20
|
+
dependencies:
|
21
|
+
- !ruby/object:Gem::Dependency
|
22
|
+
name: rack
|
23
|
+
prerelease: false
|
24
|
+
requirement: &id001 !ruby/object:Gem::Requirement
|
25
|
+
none: false
|
26
|
+
requirements:
|
27
|
+
- - ">="
|
28
|
+
- !ruby/object:Gem::Version
|
29
|
+
hash: 3
|
30
|
+
segments:
|
31
|
+
- 0
|
32
|
+
version: "0"
|
33
|
+
type: :runtime
|
34
|
+
version_requirements: *id001
|
35
|
+
description: Detect robots that are ignoring your robots.txt file and give them the middle finger
|
36
|
+
email: shanewolf@gmail.com
|
37
|
+
executables: []
|
38
|
+
|
39
|
+
extensions: []
|
40
|
+
|
41
|
+
extra_rdoc_files:
|
42
|
+
- README.rdoc
|
43
|
+
files:
|
44
|
+
- .gitignore
|
45
|
+
- README.rdoc
|
46
|
+
- Rakefile
|
47
|
+
- VERSION
|
48
|
+
- lib/rack/evil_robot.rb
|
49
|
+
- rake-evil_robot.gemspec
|
50
|
+
- spec/rack/evil_robot_spec.rb
|
51
|
+
- spec/spec_helper.rb
|
52
|
+
has_rdoc: true
|
53
|
+
homepage: http://github.com/gizm0duck/rack-evil_robot
|
54
|
+
licenses: []
|
55
|
+
|
56
|
+
post_install_message:
|
57
|
+
rdoc_options:
|
58
|
+
- --charset=UTF-8
|
59
|
+
require_paths:
|
60
|
+
- lib
|
61
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
62
|
+
none: false
|
63
|
+
requirements:
|
64
|
+
- - ">="
|
65
|
+
- !ruby/object:Gem::Version
|
66
|
+
hash: 3
|
67
|
+
segments:
|
68
|
+
- 0
|
69
|
+
version: "0"
|
70
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
71
|
+
none: false
|
72
|
+
requirements:
|
73
|
+
- - ">="
|
74
|
+
- !ruby/object:Gem::Version
|
75
|
+
hash: 3
|
76
|
+
segments:
|
77
|
+
- 0
|
78
|
+
version: "0"
|
79
|
+
requirements: []
|
80
|
+
|
81
|
+
rubyforge_project:
|
82
|
+
rubygems_version: 1.3.7
|
83
|
+
signing_key:
|
84
|
+
specification_version: 3
|
85
|
+
summary: Detect robots that are ignoring your robots.txt file and give them the middle finger
|
86
|
+
test_files:
|
87
|
+
- spec/rack/evil_robot_spec.rb
|
88
|
+
- spec/spec_helper.rb
|