killsite 0.1.0 → 0.2.0
Sign up to get free protection for your applications and to get access to all the features.
- data/README.rdoc +12 -11
- data/VERSION +1 -1
- data/bin/killsite +2 -2
- data/killsite.gemspec +3 -4
- data/lib/killsite.rb +27 -25
- metadata +15 -16
- data/test/test_killsite.rb +0 -7
data/README.rdoc
CHANGED
@@ -1,16 +1,17 @@
|
|
1
1
|
= killsite
|
2
2
|
|
3
|
-
|
4
|
-
|
5
|
-
|
6
|
-
|
7
|
-
|
8
|
-
|
9
|
-
|
10
|
-
|
11
|
-
|
12
|
-
|
13
|
-
|
3
|
+
Recursively GET all the pages of a given site through hyperlinks.
|
4
|
+
The tool is for the usage of testing and profiling.
|
5
|
+
|
6
|
+
== Installation
|
7
|
+
|
8
|
+
Simply `gem install killsite`.
|
9
|
+
|
10
|
+
== Usage
|
11
|
+
|
12
|
+
killsite [website] [# of GET for each pages]
|
13
|
+
|
14
|
+
The second argument can be omitted.
|
14
15
|
|
15
16
|
== Copyright
|
16
17
|
|
data/VERSION
CHANGED
@@ -1 +1 @@
|
|
1
|
-
0.
|
1
|
+
0.2.0
|
data/bin/killsite
CHANGED
data/killsite.gemspec
CHANGED
@@ -5,11 +5,11 @@
|
|
5
5
|
|
6
6
|
Gem::Specification.new do |s|
|
7
7
|
s.name = %q{killsite}
|
8
|
-
s.version = "0.
|
8
|
+
s.version = "0.2.0"
|
9
9
|
|
10
10
|
s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
|
11
11
|
s.authors = ["Andrew Liu"]
|
12
|
-
s.date = %q{2011-07-
|
12
|
+
s.date = %q{2011-07-16}
|
13
13
|
s.default_executable = %q{killsite}
|
14
14
|
s.description = %q{Recursively GET the site by links, try to kill the site}
|
15
15
|
s.email = %q{andrewliu33@gmail.com}
|
@@ -29,8 +29,7 @@ Gem::Specification.new do |s|
|
|
29
29
|
"bin/killsite",
|
30
30
|
"killsite.gemspec",
|
31
31
|
"lib/killsite.rb",
|
32
|
-
"test/helper.rb"
|
33
|
-
"test/test_killsite.rb"
|
32
|
+
"test/helper.rb"
|
34
33
|
]
|
35
34
|
s.homepage = %q{http://github.com/eggegg/killsite}
|
36
35
|
s.licenses = ["MIT"]
|
data/lib/killsite.rb
CHANGED
@@ -2,46 +2,48 @@ require 'bundler'
|
|
2
2
|
require 'uri'
|
3
3
|
Bundler.require
|
4
4
|
|
5
|
-
class
|
5
|
+
class SiteKiller
|
6
6
|
def initialize(prefix, limit = 1, verbose = false)
|
7
7
|
@count = 1
|
8
|
-
@prefix = prefix
|
9
|
-
@visited =
|
10
|
-
@queue = [prefix]
|
8
|
+
@prefix = URI.parse(prefix)
|
9
|
+
@visited = { @prefix => 0 }
|
11
10
|
@verbose = verbose
|
12
11
|
@limit = limit
|
13
12
|
end
|
14
13
|
|
15
|
-
def run
|
16
|
-
|
17
|
-
return if @queue.empty?
|
18
|
-
|
19
|
-
url = @queue.shift
|
14
|
+
def run url = nil
|
15
|
+
url ||= @prefix
|
20
16
|
|
21
17
|
http = EventMachine::HttpRequest.new(url).get
|
22
18
|
http.callback do
|
23
|
-
|
24
|
-
|
25
|
-
|
26
|
-
|
27
|
-
|
28
|
-
|
19
|
+
if @visited[url] == 0
|
20
|
+
puts "Processing '#{url}'" if @verbose
|
21
|
+
Nokogiri::HTML.parse(http.response).xpath("//a[@href]").each do |link|
|
22
|
+
next_url = process_url link['href']
|
23
|
+
if next_url and !@visited.include?(next_url)
|
24
|
+
puts " Queueing '#{next_url}'" if @verbose
|
29
25
|
|
30
|
-
|
31
|
-
|
32
|
-
|
33
|
-
|
26
|
+
@visited[next_url] = 0
|
27
|
+
@count += @limit
|
28
|
+
@limit.times { run next_url }
|
29
|
+
end
|
30
|
+
end
|
31
|
+
print " Progress " if @verbose
|
32
|
+
else
|
33
|
+
print '*' if @verbose
|
34
34
|
end
|
35
|
+
|
36
|
+
@visited[url] += 1
|
37
|
+
puts if @verbose and @visited[url] == @limit
|
35
38
|
@count -= 1
|
36
|
-
EM.
|
39
|
+
EM.stop if @count == 0
|
37
40
|
end
|
38
41
|
end
|
39
42
|
|
40
|
-
private
|
43
|
+
private
|
41
44
|
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
|
-
|
45
|
-
URI.join @prefix, url
|
45
|
+
return nil if url =~ /^http/ and URI.parse(@prefix.to_s).host != URI.parse(url).host
|
46
|
+
return nil if url =~ /^javascript/ or url =~ /^#/
|
47
|
+
URI.join @prefix.to_s, url
|
46
48
|
end
|
47
49
|
end
|
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: killsite
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.
|
4
|
+
version: 0.2.0
|
5
5
|
prerelease:
|
6
6
|
platform: ruby
|
7
7
|
authors:
|
@@ -9,12 +9,12 @@ authors:
|
|
9
9
|
autorequire:
|
10
10
|
bindir: bin
|
11
11
|
cert_chain: []
|
12
|
-
date: 2011-07-
|
12
|
+
date: 2011-07-16 00:00:00.000000000 +08:00
|
13
13
|
default_executable: killsite
|
14
14
|
dependencies:
|
15
15
|
- !ruby/object:Gem::Dependency
|
16
16
|
name: em-http-request
|
17
|
-
requirement: &
|
17
|
+
requirement: &2157593620 !ruby/object:Gem::Requirement
|
18
18
|
none: false
|
19
19
|
requirements:
|
20
20
|
- - ! '>='
|
@@ -22,10 +22,10 @@ dependencies:
|
|
22
22
|
version: '0'
|
23
23
|
type: :runtime
|
24
24
|
prerelease: false
|
25
|
-
version_requirements: *
|
25
|
+
version_requirements: *2157593620
|
26
26
|
- !ruby/object:Gem::Dependency
|
27
27
|
name: nokogiri
|
28
|
-
requirement: &
|
28
|
+
requirement: &2157593140 !ruby/object:Gem::Requirement
|
29
29
|
none: false
|
30
30
|
requirements:
|
31
31
|
- - ! '>='
|
@@ -33,10 +33,10 @@ dependencies:
|
|
33
33
|
version: '0'
|
34
34
|
type: :runtime
|
35
35
|
prerelease: false
|
36
|
-
version_requirements: *
|
36
|
+
version_requirements: *2157593140
|
37
37
|
- !ruby/object:Gem::Dependency
|
38
38
|
name: shoulda
|
39
|
-
requirement: &
|
39
|
+
requirement: &2157592660 !ruby/object:Gem::Requirement
|
40
40
|
none: false
|
41
41
|
requirements:
|
42
42
|
- - ! '>='
|
@@ -44,10 +44,10 @@ dependencies:
|
|
44
44
|
version: '0'
|
45
45
|
type: :development
|
46
46
|
prerelease: false
|
47
|
-
version_requirements: *
|
47
|
+
version_requirements: *2157592660
|
48
48
|
- !ruby/object:Gem::Dependency
|
49
49
|
name: bundler
|
50
|
-
requirement: &
|
50
|
+
requirement: &2157592180 !ruby/object:Gem::Requirement
|
51
51
|
none: false
|
52
52
|
requirements:
|
53
53
|
- - ~>
|
@@ -55,10 +55,10 @@ dependencies:
|
|
55
55
|
version: 1.0.0
|
56
56
|
type: :development
|
57
57
|
prerelease: false
|
58
|
-
version_requirements: *
|
58
|
+
version_requirements: *2157592180
|
59
59
|
- !ruby/object:Gem::Dependency
|
60
60
|
name: jeweler
|
61
|
-
requirement: &
|
61
|
+
requirement: &2157591700 !ruby/object:Gem::Requirement
|
62
62
|
none: false
|
63
63
|
requirements:
|
64
64
|
- - ~>
|
@@ -66,10 +66,10 @@ dependencies:
|
|
66
66
|
version: 1.6.4
|
67
67
|
type: :development
|
68
68
|
prerelease: false
|
69
|
-
version_requirements: *
|
69
|
+
version_requirements: *2157591700
|
70
70
|
- !ruby/object:Gem::Dependency
|
71
71
|
name: rcov
|
72
|
-
requirement: &
|
72
|
+
requirement: &2157591220 !ruby/object:Gem::Requirement
|
73
73
|
none: false
|
74
74
|
requirements:
|
75
75
|
- - ! '>='
|
@@ -77,7 +77,7 @@ dependencies:
|
|
77
77
|
version: '0'
|
78
78
|
type: :development
|
79
79
|
prerelease: false
|
80
|
-
version_requirements: *
|
80
|
+
version_requirements: *2157591220
|
81
81
|
description: Recursively GET the site by links, try to kill the site
|
82
82
|
email: andrewliu33@gmail.com
|
83
83
|
executables:
|
@@ -98,7 +98,6 @@ files:
|
|
98
98
|
- killsite.gemspec
|
99
99
|
- lib/killsite.rb
|
100
100
|
- test/helper.rb
|
101
|
-
- test/test_killsite.rb
|
102
101
|
has_rdoc: true
|
103
102
|
homepage: http://github.com/eggegg/killsite
|
104
103
|
licenses:
|
@@ -115,7 +114,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
|
|
115
114
|
version: '0'
|
116
115
|
segments:
|
117
116
|
- 0
|
118
|
-
hash:
|
117
|
+
hash: -2909793090681244207
|
119
118
|
required_rubygems_version: !ruby/object:Gem::Requirement
|
120
119
|
none: false
|
121
120
|
requirements:
|