killsite 0.1.0

Sign up to get free protection for your applications and to get access to all the features.
data/.document ADDED
@@ -0,0 +1,5 @@
1
+ lib/**/*.rb
2
+ bin/*
3
+ -
4
+ features/**/*.feature
5
+ LICENSE.txt
data/Gemfile ADDED
@@ -0,0 +1,11 @@
1
+ source :rubygems
2
+
3
+ gem "em-http-request"
4
+ gem "nokogiri"
5
+
6
+ group :development do
7
+ gem "shoulda", ">= 0"
8
+ gem "bundler", "~> 1.0.0"
9
+ gem "jeweler", "~> 1.6.4"
10
+ gem "rcov", ">= 0"
11
+ end
data/Gemfile.lock ADDED
@@ -0,0 +1,30 @@
1
+ GEM
2
+ remote: http://rubygems.org/
3
+ specs:
4
+ addressable (2.2.6)
5
+ em-http-request (0.3.0)
6
+ addressable (>= 2.0.0)
7
+ escape_utils
8
+ eventmachine (>= 0.12.9)
9
+ escape_utils (0.2.3)
10
+ eventmachine (0.12.10)
11
+ git (1.2.5)
12
+ jeweler (1.6.4)
13
+ bundler (~> 1.0)
14
+ git (>= 1.2.5)
15
+ rake
16
+ nokogiri (1.5.0)
17
+ rake (0.9.2)
18
+ rcov (0.9.9)
19
+ shoulda (2.11.3)
20
+
21
+ PLATFORMS
22
+ ruby
23
+
24
+ DEPENDENCIES
25
+ bundler (~> 1.0.0)
26
+ em-http-request
27
+ jeweler (~> 1.6.4)
28
+ nokogiri
29
+ rcov
30
+ shoulda
data/LICENSE.txt ADDED
@@ -0,0 +1,20 @@
1
+ Copyright (c) 2011 Andrew Liu
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 +1,19 @@
1
+ = killsite
2
+
3
+ Description goes here.
4
+
5
+ == Contributing to killsite
6
+
7
+ * Check out the latest master to make sure the feature hasn't been implemented or the bug hasn't been fixed yet
8
+ * Check out the issue tracker to make sure someone already hasn't requested it and/or contributed it
9
+ * Fork the project
10
+ * Start a feature/bugfix branch
11
+ * Commit and push until you are happy with your contribution
12
+ * Make sure to add tests for it. This is important so I don't break it in a future version unintentionally.
13
+ * Please try not to mess with the Rakefile, version, or history. If you want to have your own version, or is otherwise necessary, that is fine, but please isolate to its own commit so I can cherry-pick around it.
14
+
15
+ == Copyright
16
+
17
+ Copyright (c) 2011 Andrew Liu. See LICENSE.txt for
18
+ further details.
19
+
data/Rakefile ADDED
@@ -0,0 +1,54 @@
1
+ # encoding: utf-8
2
+
3
+ require 'rubygems'
4
+ require 'bundler'
5
+ begin
6
+ Bundler.setup(:default, :development)
7
+ rescue Bundler::BundlerError => e
8
+ $stderr.puts e.message
9
+ $stderr.puts "Run `bundle install` to install missing gems"
10
+ exit e.status_code
11
+ end
12
+ require 'rake'
13
+
14
+ require 'jeweler'
15
+ Jeweler::Tasks.new do |gem|
16
+ # gem is a Gem::Specification... see http://docs.rubygems.org/read/chapter/20 for more options
17
+ gem.name = "killsite"
18
+ gem.homepage = "http://github.com/eggegg/killsite"
19
+ gem.executables = %w[killsite]
20
+ gem.license = "MIT"
21
+ gem.summary = %Q{Recursively GET the site by links}
22
+ gem.description = %Q{Recursively GET the site by links, try to kill the site}
23
+ gem.email = "andrewliu33@gmail.com"
24
+ gem.authors = ["Andrew Liu"]
25
+ # dependencies defined in Gemfile
26
+ end
27
+ Jeweler::RubygemsDotOrgTasks.new
28
+
29
+ require 'rake/testtask'
30
+ Rake::TestTask.new(:test) do |test|
31
+ test.libs << 'lib' << 'test'
32
+ test.pattern = 'test/**/test_*.rb'
33
+ test.verbose = true
34
+ end
35
+
36
+ require 'rcov/rcovtask'
37
+ Rcov::RcovTask.new do |test|
38
+ test.libs << 'test'
39
+ test.pattern = 'test/**/test_*.rb'
40
+ test.verbose = true
41
+ test.rcov_opts << '--exclude "gems/*"'
42
+ end
43
+
44
+ task :default => :test
45
+
46
+ require 'rake/rdoctask'
47
+ Rake::RDocTask.new do |rdoc|
48
+ version = File.exist?('VERSION') ? File.read('VERSION') : ""
49
+
50
+ rdoc.rdoc_dir = 'rdoc'
51
+ rdoc.title = "killsite #{version}"
52
+ rdoc.rdoc_files.include('README*')
53
+ rdoc.rdoc_files.include('lib/**/*.rb')
54
+ end
data/VERSION ADDED
@@ -0,0 +1 @@
1
+ 0.1.0
data/bin/killsite ADDED
@@ -0,0 +1,15 @@
1
+ #!/usr/bin/env ruby
2
+
3
+ require 'killsite'
4
+
5
+ if ARGV.size == 0
6
+ puts "USAGE: killsite [site] [limit]"
7
+ exit
8
+ end
9
+
10
+ prefix = ARGV[0]
11
+ limit = (ARGV[1] || 1).to_i
12
+
13
+ ks = KillSite.new(prefix, limit, true)
14
+
15
+ EM.run { ks.run }
data/killsite.gemspec ADDED
@@ -0,0 +1,68 @@
1
+ # Generated by jeweler
2
+ # DO NOT EDIT THIS FILE DIRECTLY
3
+ # Instead, edit Jeweler::Tasks in Rakefile, and run 'rake gemspec'
4
+ # -*- encoding: utf-8 -*-
5
+
6
+ Gem::Specification.new do |s|
7
+ s.name = %q{killsite}
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 = ["Andrew Liu"]
12
+ s.date = %q{2011-07-15}
13
+ s.default_executable = %q{killsite}
14
+ s.description = %q{Recursively GET the site by links, try to kill the site}
15
+ s.email = %q{andrewliu33@gmail.com}
16
+ s.executables = ["killsite"]
17
+ s.extra_rdoc_files = [
18
+ "LICENSE.txt",
19
+ "README.rdoc"
20
+ ]
21
+ s.files = [
22
+ ".document",
23
+ "Gemfile",
24
+ "Gemfile.lock",
25
+ "LICENSE.txt",
26
+ "README.rdoc",
27
+ "Rakefile",
28
+ "VERSION",
29
+ "bin/killsite",
30
+ "killsite.gemspec",
31
+ "lib/killsite.rb",
32
+ "test/helper.rb",
33
+ "test/test_killsite.rb"
34
+ ]
35
+ s.homepage = %q{http://github.com/eggegg/killsite}
36
+ s.licenses = ["MIT"]
37
+ s.require_paths = ["lib"]
38
+ s.rubygems_version = %q{1.6.2}
39
+ s.summary = %q{Recursively GET the site by links}
40
+
41
+ if s.respond_to? :specification_version then
42
+ s.specification_version = 3
43
+
44
+ if Gem::Version.new(Gem::VERSION) >= Gem::Version.new('1.2.0') then
45
+ s.add_runtime_dependency(%q<em-http-request>, [">= 0"])
46
+ s.add_runtime_dependency(%q<nokogiri>, [">= 0"])
47
+ s.add_development_dependency(%q<shoulda>, [">= 0"])
48
+ s.add_development_dependency(%q<bundler>, ["~> 1.0.0"])
49
+ s.add_development_dependency(%q<jeweler>, ["~> 1.6.4"])
50
+ s.add_development_dependency(%q<rcov>, [">= 0"])
51
+ else
52
+ s.add_dependency(%q<em-http-request>, [">= 0"])
53
+ s.add_dependency(%q<nokogiri>, [">= 0"])
54
+ s.add_dependency(%q<shoulda>, [">= 0"])
55
+ s.add_dependency(%q<bundler>, ["~> 1.0.0"])
56
+ s.add_dependency(%q<jeweler>, ["~> 1.6.4"])
57
+ s.add_dependency(%q<rcov>, [">= 0"])
58
+ end
59
+ else
60
+ s.add_dependency(%q<em-http-request>, [">= 0"])
61
+ s.add_dependency(%q<nokogiri>, [">= 0"])
62
+ s.add_dependency(%q<shoulda>, [">= 0"])
63
+ s.add_dependency(%q<bundler>, ["~> 1.0.0"])
64
+ s.add_dependency(%q<jeweler>, ["~> 1.6.4"])
65
+ s.add_dependency(%q<rcov>, [">= 0"])
66
+ end
67
+ end
68
+
data/lib/killsite.rb ADDED
@@ -0,0 +1,47 @@
1
+ require 'bundler'
2
+ require 'uri'
3
+ Bundler.require
4
+
5
+ class KillSite
6
+ def initialize(prefix, limit = 1, verbose = false)
7
+ @count = 1
8
+ @prefix = prefix
9
+ @visited = [prefix]
10
+ @queue = [prefix]
11
+ @verbose = verbose
12
+ @limit = limit
13
+ end
14
+
15
+ def run
16
+ EM.stop if @count == 0
17
+ return if @queue.empty?
18
+
19
+ url = @queue.shift
20
+
21
+ http = EventMachine::HttpRequest.new(url).get
22
+ http.callback do
23
+ puts "Processing '#{url}'" if @verbose
24
+
25
+ Nokogiri::HTML.parse(http.response).xpath("//a[@href]").each do |link|
26
+ next_url = process_url link['href']
27
+ if next_url and !@visited.include? next_url
28
+ puts " Queueing '#{next_url}'" if @verbose
29
+
30
+ @limit.times { @queue << next_url }
31
+ @visited << next_url
32
+ @count += @limit
33
+ end
34
+ end
35
+ @count -= 1
36
+ EM.next_tick { run }
37
+ end
38
+ end
39
+
40
+ private
41
+ def process_url url
42
+ return nil if url =~ /^http/ and URI.parse(@prefix).host != URI.parse(url).host
43
+ return nil if url =~ /^javascript/
44
+ return nil if url =~ /^#/
45
+ URI.join @prefix, url
46
+ end
47
+ end
data/test/helper.rb ADDED
@@ -0,0 +1,18 @@
1
+ require 'rubygems'
2
+ require 'bundler'
3
+ begin
4
+ Bundler.setup(:default, :development)
5
+ rescue Bundler::BundlerError => e
6
+ $stderr.puts e.message
7
+ $stderr.puts "Run `bundle install` to install missing gems"
8
+ exit e.status_code
9
+ end
10
+ require 'test/unit'
11
+ require 'shoulda'
12
+
13
+ $LOAD_PATH.unshift(File.join(File.dirname(__FILE__), '..', 'lib'))
14
+ $LOAD_PATH.unshift(File.dirname(__FILE__))
15
+ require 'killsite'
16
+
17
+ class Test::Unit::TestCase
18
+ end
@@ -0,0 +1,7 @@
1
+ require 'helper'
2
+
3
+ class TestKillsite < Test::Unit::TestCase
4
+ should "probably rename this file and start testing for real" do
5
+ flunk "hey buddy, you should probably rename this file and start testing for real"
6
+ end
7
+ end
metadata ADDED
@@ -0,0 +1,131 @@
1
+ --- !ruby/object:Gem::Specification
2
+ name: killsite
3
+ version: !ruby/object:Gem::Version
4
+ version: 0.1.0
5
+ prerelease:
6
+ platform: ruby
7
+ authors:
8
+ - Andrew Liu
9
+ autorequire:
10
+ bindir: bin
11
+ cert_chain: []
12
+ date: 2011-07-15 00:00:00.000000000 +08:00
13
+ default_executable: killsite
14
+ dependencies:
15
+ - !ruby/object:Gem::Dependency
16
+ name: em-http-request
17
+ requirement: &2154293760 !ruby/object:Gem::Requirement
18
+ none: false
19
+ requirements:
20
+ - - ! '>='
21
+ - !ruby/object:Gem::Version
22
+ version: '0'
23
+ type: :runtime
24
+ prerelease: false
25
+ version_requirements: *2154293760
26
+ - !ruby/object:Gem::Dependency
27
+ name: nokogiri
28
+ requirement: &2154293280 !ruby/object:Gem::Requirement
29
+ none: false
30
+ requirements:
31
+ - - ! '>='
32
+ - !ruby/object:Gem::Version
33
+ version: '0'
34
+ type: :runtime
35
+ prerelease: false
36
+ version_requirements: *2154293280
37
+ - !ruby/object:Gem::Dependency
38
+ name: shoulda
39
+ requirement: &2154292800 !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: *2154292800
48
+ - !ruby/object:Gem::Dependency
49
+ name: bundler
50
+ requirement: &2154292320 !ruby/object:Gem::Requirement
51
+ none: false
52
+ requirements:
53
+ - - ~>
54
+ - !ruby/object:Gem::Version
55
+ version: 1.0.0
56
+ type: :development
57
+ prerelease: false
58
+ version_requirements: *2154292320
59
+ - !ruby/object:Gem::Dependency
60
+ name: jeweler
61
+ requirement: &2154291840 !ruby/object:Gem::Requirement
62
+ none: false
63
+ requirements:
64
+ - - ~>
65
+ - !ruby/object:Gem::Version
66
+ version: 1.6.4
67
+ type: :development
68
+ prerelease: false
69
+ version_requirements: *2154291840
70
+ - !ruby/object:Gem::Dependency
71
+ name: rcov
72
+ requirement: &2154291360 !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: *2154291360
81
+ description: Recursively GET the site by links, try to kill the site
82
+ email: andrewliu33@gmail.com
83
+ executables:
84
+ - killsite
85
+ extensions: []
86
+ extra_rdoc_files:
87
+ - LICENSE.txt
88
+ - README.rdoc
89
+ files:
90
+ - .document
91
+ - Gemfile
92
+ - Gemfile.lock
93
+ - LICENSE.txt
94
+ - README.rdoc
95
+ - Rakefile
96
+ - VERSION
97
+ - bin/killsite
98
+ - killsite.gemspec
99
+ - lib/killsite.rb
100
+ - test/helper.rb
101
+ - test/test_killsite.rb
102
+ has_rdoc: true
103
+ homepage: http://github.com/eggegg/killsite
104
+ licenses:
105
+ - MIT
106
+ post_install_message:
107
+ rdoc_options: []
108
+ require_paths:
109
+ - lib
110
+ required_ruby_version: !ruby/object:Gem::Requirement
111
+ none: false
112
+ requirements:
113
+ - - ! '>='
114
+ - !ruby/object:Gem::Version
115
+ version: '0'
116
+ segments:
117
+ - 0
118
+ hash: 4297911674037475226
119
+ required_rubygems_version: !ruby/object:Gem::Requirement
120
+ none: false
121
+ requirements:
122
+ - - ! '>='
123
+ - !ruby/object:Gem::Version
124
+ version: '0'
125
+ requirements: []
126
+ rubyforge_project:
127
+ rubygems_version: 1.6.2
128
+ signing_key:
129
+ specification_version: 3
130
+ summary: Recursively GET the site by links
131
+ test_files: []