bad_bot 0.9
Sign up to get free protection for your applications and to get access to all the features.
- data/MIT-LICENSE +20 -0
- data/README.rdoc +53 -0
- data/Rakefile +27 -0
- data/lib/bad_bot.rb +4 -0
- data/lib/bad_bot/bots.rb +39 -0
- data/lib/bad_bot/detector.rb +48 -0
- data/lib/bad_bot/version.rb +3 -0
- data/lib/tasks/bad_bot_tasks.rake +4 -0
- metadata +137 -0
data/MIT-LICENSE
ADDED
@@ -0,0 +1,20 @@
|
|
1
|
+
Copyright 2012 Tiago Scolari
|
2
|
+
|
3
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
4
|
+
a copy of this software and associated documentation files (the
|
5
|
+
"Software"), to deal in the Software without restriction, including
|
6
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
7
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
8
|
+
permit persons to whom the Software is furnished to do so, subject to
|
9
|
+
the following conditions:
|
10
|
+
|
11
|
+
The above copyright notice and this permission notice shall be
|
12
|
+
included in all copies or substantial portions of the Software.
|
13
|
+
|
14
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
15
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
16
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
17
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
18
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
19
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
20
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.rdoc
ADDED
@@ -0,0 +1,53 @@
|
|
1
|
+
= BadBot
|
2
|
+
|
3
|
+
This gem simply gives you the ability to avoid certain pieces of your view from being indexed by search bots.
|
4
|
+
|
5
|
+
Even if this is generally not recommended, there are situations that you really don't want parts to be indexed. Instead of loading all this stuff from a javascript, BadBot simply gives you an option for doing this instead:
|
6
|
+
|
7
|
+
<%= no_bot do %>
|
8
|
+
stuff i dont wat to be indexed
|
9
|
+
<% end %>
|
10
|
+
|
11
|
+
in case of a search bot request, the content of the block won't be rendered.
|
12
|
+
|
13
|
+
|
14
|
+
== Configuration
|
15
|
+
|
16
|
+
Include the gem in your gemfile: `gem 'bad_bot'`. And load it in a controller, for example `ApplicationController`:
|
17
|
+
|
18
|
+
class ApplicationController < ActionController::Base
|
19
|
+
include BadBot::Detector
|
20
|
+
end
|
21
|
+
|
22
|
+
== Usage
|
23
|
+
|
24
|
+
Once your controller is configured, you can call on you views/controller the `no_bot` and `is_bot?` methods:
|
25
|
+
|
26
|
+
Stories
|
27
|
+
<% no_bot do %>
|
28
|
+
1 of 10 pages
|
29
|
+
<% end %>
|
30
|
+
...
|
31
|
+
|
32
|
+
|
33
|
+
Stories
|
34
|
+
<% unless is_bot? %>
|
35
|
+
1 of 10 pages
|
36
|
+
<% end %>
|
37
|
+
|
38
|
+
== Customization
|
39
|
+
|
40
|
+
By default it will only trigger for Google, Yahoo and Bing.
|
41
|
+
|
42
|
+
You can add new user-agents to the robots list by using the `BadBot::Bots.setup` method.
|
43
|
+
|
44
|
+
# some_initializer.rb
|
45
|
+
BadBot::Bots.instance.setup do |robots|
|
46
|
+
robots << 'otherbot'
|
47
|
+
robots << 'otherbot2'
|
48
|
+
end
|
49
|
+
|
50
|
+
== Caution
|
51
|
+
|
52
|
+
How you will use this is entirely up to you. You can get punished by search engines if you make bad use of it.
|
53
|
+
My intent on creating this was to remove some useless words that kept showing as the highest keywords in webmasters tool.
|
data/Rakefile
ADDED
@@ -0,0 +1,27 @@
|
|
1
|
+
#!/usr/bin/env rake
|
2
|
+
begin
|
3
|
+
require 'bundler/setup'
|
4
|
+
rescue LoadError
|
5
|
+
puts 'You must `gem install bundler` and `bundle install` to run rake tasks'
|
6
|
+
end
|
7
|
+
begin
|
8
|
+
require 'rdoc/task'
|
9
|
+
rescue LoadError
|
10
|
+
require 'rdoc/rdoc'
|
11
|
+
require 'rake/rdoctask'
|
12
|
+
RDoc::Task = Rake::RDocTask
|
13
|
+
end
|
14
|
+
|
15
|
+
RDoc::Task.new(:rdoc) do |rdoc|
|
16
|
+
rdoc.rdoc_dir = 'rdoc'
|
17
|
+
rdoc.title = 'BadBot'
|
18
|
+
rdoc.options << '--line-numbers'
|
19
|
+
rdoc.rdoc_files.include('README.rdoc')
|
20
|
+
rdoc.rdoc_files.include('lib/**/*.rb')
|
21
|
+
end
|
22
|
+
|
23
|
+
|
24
|
+
|
25
|
+
|
26
|
+
Bundler::GemHelper.install_tasks
|
27
|
+
|
data/lib/bad_bot.rb
ADDED
data/lib/bad_bot/bots.rb
ADDED
@@ -0,0 +1,39 @@
|
|
1
|
+
module BadBot
|
2
|
+
require 'singleton'
|
3
|
+
|
4
|
+
# Bots list
|
5
|
+
#
|
6
|
+
#
|
7
|
+
class Bots
|
8
|
+
include Singleton
|
9
|
+
|
10
|
+
def initialize
|
11
|
+
@bots = ['msnbot', 'googlebot', 'slurp', 'yahoo']
|
12
|
+
end
|
13
|
+
|
14
|
+
# Public: Configures the search robots array:
|
15
|
+
# Example
|
16
|
+
# BadBot.Bot.insance.setup do |bots|
|
17
|
+
# bots << 'googlebot'
|
18
|
+
# bots << 'yahoo'
|
19
|
+
# bots << 'custom stuff'
|
20
|
+
# end
|
21
|
+
#
|
22
|
+
def setup
|
23
|
+
yield(@bots)
|
24
|
+
end
|
25
|
+
|
26
|
+
# Public: Returns the array of bots
|
27
|
+
#
|
28
|
+
def bots
|
29
|
+
@bots
|
30
|
+
end
|
31
|
+
|
32
|
+
# Public: Convert the array of bots into a regular
|
33
|
+
# expression for searching
|
34
|
+
def bots_to_regexp
|
35
|
+
Regexp.union(bots)
|
36
|
+
end
|
37
|
+
|
38
|
+
end
|
39
|
+
end
|
@@ -0,0 +1,48 @@
|
|
1
|
+
module BadBot
|
2
|
+
# Detector
|
3
|
+
# Gives the controller the ability to detect and behave
|
4
|
+
# different for requests that come from search bots.
|
5
|
+
#
|
6
|
+
# Example:
|
7
|
+
# class ApplicationController < ...
|
8
|
+
# include BadBot::Detector
|
9
|
+
# end
|
10
|
+
# ...
|
11
|
+
# <div>
|
12
|
+
# <% no_bot do %>
|
13
|
+
# stuff that is not worth to crawl
|
14
|
+
# <% end %>
|
15
|
+
# </div>
|
16
|
+
#
|
17
|
+
#
|
18
|
+
module Detector
|
19
|
+
extend ActiveSupport::Concern
|
20
|
+
|
21
|
+
included do
|
22
|
+
before_filter :detect_search_bots
|
23
|
+
helper_method :no_bot, :is_bot?
|
24
|
+
end
|
25
|
+
|
26
|
+
# Public: Helper that only executes the block in case
|
27
|
+
# this is not a request made by a search bot
|
28
|
+
#
|
29
|
+
def no_bot(&block)
|
30
|
+
block.call unless(is_bot?)
|
31
|
+
end
|
32
|
+
|
33
|
+
# Public: Helper that returns true or false, if the the
|
34
|
+
# request if from a search bot or not.
|
35
|
+
#
|
36
|
+
def is_bot?
|
37
|
+
@search_bot
|
38
|
+
end
|
39
|
+
|
40
|
+
private
|
41
|
+
|
42
|
+
# Private: Detects if the request comes from a search bot or not
|
43
|
+
#
|
44
|
+
def detect_search_bots
|
45
|
+
@search_bot ||= (request.user_agent =~ BadBot::Bots.instance.bots_to_regexp ? true : false)
|
46
|
+
end
|
47
|
+
end
|
48
|
+
end
|
metadata
ADDED
@@ -0,0 +1,137 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: bad_bot
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: '0.9'
|
5
|
+
prerelease:
|
6
|
+
platform: ruby
|
7
|
+
authors:
|
8
|
+
- Tiago Scolari
|
9
|
+
autorequire:
|
10
|
+
bindir: bin
|
11
|
+
cert_chain: []
|
12
|
+
date: 2012-05-01 00:00:00.000000000 Z
|
13
|
+
dependencies:
|
14
|
+
- !ruby/object:Gem::Dependency
|
15
|
+
name: rails
|
16
|
+
requirement: &70109398068500 !ruby/object:Gem::Requirement
|
17
|
+
none: false
|
18
|
+
requirements:
|
19
|
+
- - ~>
|
20
|
+
- !ruby/object:Gem::Version
|
21
|
+
version: 3.2.3
|
22
|
+
type: :runtime
|
23
|
+
prerelease: false
|
24
|
+
version_requirements: *70109398068500
|
25
|
+
- !ruby/object:Gem::Dependency
|
26
|
+
name: sqlite3
|
27
|
+
requirement: &70109398067600 !ruby/object:Gem::Requirement
|
28
|
+
none: false
|
29
|
+
requirements:
|
30
|
+
- - ! '>='
|
31
|
+
- !ruby/object:Gem::Version
|
32
|
+
version: '0'
|
33
|
+
type: :development
|
34
|
+
prerelease: false
|
35
|
+
version_requirements: *70109398067600
|
36
|
+
- !ruby/object:Gem::Dependency
|
37
|
+
name: rspec-rails
|
38
|
+
requirement: &70109398066260 !ruby/object:Gem::Requirement
|
39
|
+
none: false
|
40
|
+
requirements:
|
41
|
+
- - ! '>='
|
42
|
+
- !ruby/object:Gem::Version
|
43
|
+
version: '0'
|
44
|
+
type: :development
|
45
|
+
prerelease: false
|
46
|
+
version_requirements: *70109398066260
|
47
|
+
- !ruby/object:Gem::Dependency
|
48
|
+
name: turnip
|
49
|
+
requirement: &70109398065160 !ruby/object:Gem::Requirement
|
50
|
+
none: false
|
51
|
+
requirements:
|
52
|
+
- - ! '>='
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '0'
|
55
|
+
type: :development
|
56
|
+
prerelease: false
|
57
|
+
version_requirements: *70109398065160
|
58
|
+
- !ruby/object:Gem::Dependency
|
59
|
+
name: capybara
|
60
|
+
requirement: &70109398063960 !ruby/object:Gem::Requirement
|
61
|
+
none: false
|
62
|
+
requirements:
|
63
|
+
- - ! '>='
|
64
|
+
- !ruby/object:Gem::Version
|
65
|
+
version: '0'
|
66
|
+
type: :development
|
67
|
+
prerelease: false
|
68
|
+
version_requirements: *70109398063960
|
69
|
+
- !ruby/object:Gem::Dependency
|
70
|
+
name: debugger
|
71
|
+
requirement: &70109398062880 !ruby/object:Gem::Requirement
|
72
|
+
none: false
|
73
|
+
requirements:
|
74
|
+
- - ! '>='
|
75
|
+
- !ruby/object:Gem::Version
|
76
|
+
version: '0'
|
77
|
+
type: :development
|
78
|
+
prerelease: false
|
79
|
+
version_requirements: *70109398062880
|
80
|
+
- !ruby/object:Gem::Dependency
|
81
|
+
name: simplecov
|
82
|
+
requirement: &70109398062380 !ruby/object:Gem::Requirement
|
83
|
+
none: false
|
84
|
+
requirements:
|
85
|
+
- - ! '>='
|
86
|
+
- !ruby/object:Gem::Version
|
87
|
+
version: '0'
|
88
|
+
type: :development
|
89
|
+
prerelease: false
|
90
|
+
version_requirements: *70109398062380
|
91
|
+
description: Avoid bad keywords from being indexed by google and other robots.
|
92
|
+
email:
|
93
|
+
- tscolari@gmail.com
|
94
|
+
executables: []
|
95
|
+
extensions: []
|
96
|
+
extra_rdoc_files: []
|
97
|
+
files:
|
98
|
+
- lib/bad_bot/bots.rb
|
99
|
+
- lib/bad_bot/detector.rb
|
100
|
+
- lib/bad_bot/version.rb
|
101
|
+
- lib/bad_bot.rb
|
102
|
+
- lib/tasks/bad_bot_tasks.rake
|
103
|
+
- MIT-LICENSE
|
104
|
+
- Rakefile
|
105
|
+
- README.rdoc
|
106
|
+
homepage: http://github.com/tscolari/bad_bot
|
107
|
+
licenses: []
|
108
|
+
post_install_message:
|
109
|
+
rdoc_options: []
|
110
|
+
require_paths:
|
111
|
+
- lib
|
112
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
113
|
+
none: false
|
114
|
+
requirements:
|
115
|
+
- - ! '>='
|
116
|
+
- !ruby/object:Gem::Version
|
117
|
+
version: '0'
|
118
|
+
segments:
|
119
|
+
- 0
|
120
|
+
hash: -496881733477053487
|
121
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
122
|
+
none: false
|
123
|
+
requirements:
|
124
|
+
- - ! '>='
|
125
|
+
- !ruby/object:Gem::Version
|
126
|
+
version: '0'
|
127
|
+
segments:
|
128
|
+
- 0
|
129
|
+
hash: -496881733477053487
|
130
|
+
requirements: []
|
131
|
+
rubyforge_project:
|
132
|
+
rubygems_version: 1.8.17
|
133
|
+
signing_key:
|
134
|
+
specification_version: 3
|
135
|
+
summary: Get better ranking on search engines, by preventing bad stuff from being
|
136
|
+
indexed.
|
137
|
+
test_files: []
|