shelob 0.1.0.beta1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +17 -0
- data/Gemfile +4 -0
- data/Guardfile +7 -0
- data/LICENSE.txt +22 -0
- data/README.md +29 -0
- data/Rakefile +8 -0
- data/bin/shelob +38 -0
- data/lib/extractor.rb +23 -0
- data/lib/link_result.rb +13 -0
- data/lib/resolver.rb +16 -0
- data/lib/shelob/version.rb +3 -0
- data/lib/shelob.rb +64 -0
- data/shelob.gemspec +28 -0
- data/test/test_extractor.rb +37 -0
- data/test/test_link_result.rb +29 -0
- data/test/test_resolver.rb +31 -0
- data/test/test_shelob.rb +97 -0
- metadata +165 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 4fd39cfeaa059a074821a0d60ee93b464ff48819
|
4
|
+
data.tar.gz: fc04fd19c13c1a970abfed9c126854da9ad6eaeb
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 72b0645723887dfb1942108c93e5cfda5f50de550d5a240f5da0119763fbd02745fdce0f88038b42849b863e54a81cf214db6285badab74eed6dbb082debd8ab
|
7
|
+
data.tar.gz: e53ddc74da61a78b19acde7d9e87859c9682dc48bd044f736f51942d1ee51d79b573b868ee5c72e3c87e9ab1e4e922f6c3760357947a2497492f1b1ce9ecd693
|
data/.gitignore
ADDED
data/Gemfile
ADDED
data/Guardfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2013 Benjamin Nicholas
|
2
|
+
|
3
|
+
MIT License
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
6
|
+
a copy of this software and associated documentation files (the
|
7
|
+
"Software"), to deal in the Software without restriction, including
|
8
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
9
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
10
|
+
permit persons to whom the Software is furnished to do so, subject to
|
11
|
+
the following conditions:
|
12
|
+
|
13
|
+
The above copyright notice and this permission notice shall be
|
14
|
+
included in all copies or substantial portions of the Software.
|
15
|
+
|
16
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
17
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
18
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
19
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
20
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
21
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
22
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,29 @@
|
|
1
|
+
# LinkChecker
|
2
|
+
|
3
|
+
TODO: Write a gem description
|
4
|
+
|
5
|
+
## Installation
|
6
|
+
|
7
|
+
Add this line to your application's Gemfile:
|
8
|
+
|
9
|
+
gem 'link_checker'
|
10
|
+
|
11
|
+
And then execute:
|
12
|
+
|
13
|
+
$ bundle
|
14
|
+
|
15
|
+
Or install it yourself as:
|
16
|
+
|
17
|
+
$ gem install link_checker
|
18
|
+
|
19
|
+
## Usage
|
20
|
+
|
21
|
+
TODO: Write usage instructions here
|
22
|
+
|
23
|
+
## Contributing
|
24
|
+
|
25
|
+
1. Fork it
|
26
|
+
2. Create your feature branch (`git checkout -b my-new-feature`)
|
27
|
+
3. Commit your changes (`git commit -am 'Add some feature'`)
|
28
|
+
4. Push to the branch (`git push origin my-new-feature`)
|
29
|
+
5. Create new Pull Request
|
data/Rakefile
ADDED
data/bin/shelob
ADDED
@@ -0,0 +1,38 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require 'optparse'
|
4
|
+
require 'shelob'
|
5
|
+
|
6
|
+
def main args
|
7
|
+
puts Shelob::Spider.new(args[0], verbose: options[:verbose]).check
|
8
|
+
end
|
9
|
+
|
10
|
+
options = {verbose: 0}
|
11
|
+
optparse = OptionParser.new do |opts|
|
12
|
+
opts.banner = "Usage: shelob [options] root_url"
|
13
|
+
|
14
|
+
opts.on('-v', "--[no-]verbose", "Print simple information(overrides -r)") do
|
15
|
+
options[:verbose] = 1
|
16
|
+
end
|
17
|
+
|
18
|
+
opts.on('-r', '--[no-]really-verbose', "Print lots of information(overrides -v)") do
|
19
|
+
options[:verbose] = 2
|
20
|
+
end
|
21
|
+
|
22
|
+
opts.on_tail('-h', '--help', 'Show this message') do
|
23
|
+
puts opts
|
24
|
+
exit
|
25
|
+
end
|
26
|
+
end.parse!
|
27
|
+
|
28
|
+
if ARGV.empty?
|
29
|
+
puts optparse
|
30
|
+
exit 1
|
31
|
+
end
|
32
|
+
|
33
|
+
begin
|
34
|
+
exit main(ARGV)
|
35
|
+
rescue => ex
|
36
|
+
STDERR.puts ex.message
|
37
|
+
end
|
38
|
+
|
data/lib/extractor.rb
ADDED
@@ -0,0 +1,23 @@
|
|
1
|
+
require 'rubygems'
|
2
|
+
require 'nokogiri'
|
3
|
+
|
4
|
+
module Shelob
|
5
|
+
class Extractor
|
6
|
+
def initialize fetched
|
7
|
+
@fetched = fetched
|
8
|
+
end
|
9
|
+
|
10
|
+
def extract
|
11
|
+
content = Nokogiri::HTML(@fetched.body)
|
12
|
+
raw = content.css('a').map { |anchor| anchor['href'] }
|
13
|
+
raw.map do |link|
|
14
|
+
if link.start_with? '/'
|
15
|
+
u = URI(@fetched.url)
|
16
|
+
"#{u.scheme}://#{u.host}#{link}"
|
17
|
+
else
|
18
|
+
link
|
19
|
+
end
|
20
|
+
end
|
21
|
+
end
|
22
|
+
end
|
23
|
+
end
|
data/lib/link_result.rb
ADDED
data/lib/resolver.rb
ADDED
@@ -0,0 +1,16 @@
|
|
1
|
+
require 'link_result'
|
2
|
+
require 'net/http'
|
3
|
+
|
4
|
+
module Shelob
|
5
|
+
class Resolver
|
6
|
+
def initialize url
|
7
|
+
@uri = URI(url)
|
8
|
+
end
|
9
|
+
|
10
|
+
def resolve
|
11
|
+
resp = Net::HTTP.get_response(@uri)
|
12
|
+
|
13
|
+
LinkResult.new @uri.to_s, resp.code.to_i, resp.body
|
14
|
+
end
|
15
|
+
end
|
16
|
+
end
|
data/lib/shelob.rb
ADDED
@@ -0,0 +1,64 @@
|
|
1
|
+
require "shelob/version"
|
2
|
+
require "resolver"
|
3
|
+
require "extractor"
|
4
|
+
require "set"
|
5
|
+
|
6
|
+
module Shelob
|
7
|
+
class Spider
|
8
|
+
attr_accessor :hostname
|
9
|
+
|
10
|
+
def initialize hostname, options = {}
|
11
|
+
@hostname = hostname
|
12
|
+
@queue = [ hostname ]
|
13
|
+
@urls = Set.new @queue
|
14
|
+
@failures = []
|
15
|
+
@verbose = options[:verbose] == 1 ? true : false
|
16
|
+
@chatty = options[:verbose] == 2 ? true : false
|
17
|
+
end
|
18
|
+
|
19
|
+
def check
|
20
|
+
while not @queue.empty?
|
21
|
+
url = @queue.shift
|
22
|
+
@urls << url
|
23
|
+
|
24
|
+
if @verbose
|
25
|
+
print '.'
|
26
|
+
end
|
27
|
+
|
28
|
+
if @chatty
|
29
|
+
print "#{url}... "
|
30
|
+
end
|
31
|
+
|
32
|
+
fetch = Resolver.new(url).resolve
|
33
|
+
|
34
|
+
@failures << fetch if fetch.status >= 400
|
35
|
+
|
36
|
+
links = Extractor.new(fetch).extract
|
37
|
+
|
38
|
+
filtered = links.select do |link|
|
39
|
+
link.start_with? @hostname and !@urls.include? link
|
40
|
+
end
|
41
|
+
|
42
|
+
if @chatty
|
43
|
+
puts "checked!"
|
44
|
+
end
|
45
|
+
|
46
|
+
@queue.push(*filtered)
|
47
|
+
end
|
48
|
+
|
49
|
+
@failures
|
50
|
+
end
|
51
|
+
|
52
|
+
def remaining
|
53
|
+
return @queue.count
|
54
|
+
end
|
55
|
+
|
56
|
+
def requests
|
57
|
+
return @urls.count
|
58
|
+
end
|
59
|
+
|
60
|
+
def fetched
|
61
|
+
return @urls
|
62
|
+
end
|
63
|
+
end
|
64
|
+
end
|
data/shelob.gemspec
ADDED
@@ -0,0 +1,28 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'shelob/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "shelob"
|
8
|
+
spec.version = Shelob::VERSION
|
9
|
+
spec.authors = ["Benjamin Nicholas"]
|
10
|
+
spec.email = ["bnicholas@brandnetworksinc.com"]
|
11
|
+
spec.description = %q{A giant spider that starts on a given page, finds all links on the page, ensure they resolve, and recurses if the link is underneath the starting url}
|
12
|
+
spec.summary = %q{Spider a site and check links}
|
13
|
+
spec.license = "MIT"
|
14
|
+
|
15
|
+
spec.files = `git ls-files`.split($/)
|
16
|
+
spec.executables = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
|
17
|
+
spec.test_files = spec.files.grep(%r{^(test|spec|features)/})
|
18
|
+
spec.require_paths = ["lib"]
|
19
|
+
|
20
|
+
spec.add_development_dependency "bundler", "~> 1.3"
|
21
|
+
spec.add_development_dependency "rake"
|
22
|
+
spec.add_development_dependency "minitest"
|
23
|
+
spec.add_development_dependency "webmock"
|
24
|
+
spec.add_development_dependency "guard"
|
25
|
+
spec.add_development_dependency "guard-minitest"
|
26
|
+
|
27
|
+
spec.add_runtime_dependency "nokogiri"
|
28
|
+
end
|
@@ -0,0 +1,37 @@
|
|
1
|
+
require 'minitest/autorun'
|
2
|
+
require 'extractor'
|
3
|
+
require 'link_result'
|
4
|
+
|
5
|
+
describe Shelob::Extractor, "Link extracting module" do
|
6
|
+
|
7
|
+
describe "when created" do
|
8
|
+
it "should be created with a LinkResult" do
|
9
|
+
le = LinkResult.new("http://google.com", 200, '<html><head><title>resume</title></head><body><a href="http://bmnick.com">home</a><a href="http://bmnick.com/resume/resume.pdf">pdf</a></body></html>')
|
10
|
+
le.wont_be_nil
|
11
|
+
end
|
12
|
+
end
|
13
|
+
|
14
|
+
describe "when used" do
|
15
|
+
before do
|
16
|
+
@result = LinkResult.new("http://google.com", 200, '<html><head><title>hi</title></head><body><a href="http://bing.com">bing</a><a href="http://yahoo.com">yahoo</a></body></html>')
|
17
|
+
@result2 = LinkResult.new("http://google.com/something", 200, '<html><head><title>hi</title></head><body><a href="/about">about</a></body></html>')
|
18
|
+
@le = Shelob::Extractor.new(@result)
|
19
|
+
@le2 = Shelob::Extractor.new(@result2)
|
20
|
+
end
|
21
|
+
|
22
|
+
it "should return a list of the links in the page" do
|
23
|
+
extracts = @le.extract
|
24
|
+
extracts.must_be_kind_of Array
|
25
|
+
extracts.must_equal ["http://bing.com", "http://yahoo.com"]
|
26
|
+
end
|
27
|
+
|
28
|
+
it "should transform relative links to absolute" do
|
29
|
+
extracts = @le2.extract
|
30
|
+
extracts.must_be_kind_of Array
|
31
|
+
extracts.must_equal ["http://google.com/about"]
|
32
|
+
end
|
33
|
+
|
34
|
+
end # describe
|
35
|
+
|
36
|
+
end # describe
|
37
|
+
|
@@ -0,0 +1,29 @@
|
|
1
|
+
require 'minitest/autorun'
|
2
|
+
require 'link_result'
|
3
|
+
|
4
|
+
describe LinkResult, "Link fetch result" do
|
5
|
+
before do
|
6
|
+
@result = LinkResult.new("http://google.com", 200, '<html><head><title>hi</title></head><body><a href="http://bing.com">bing</a><a href="http://yahoo.com">yahoo</a></body></html>')
|
7
|
+
end
|
8
|
+
|
9
|
+
describe "when created" do
|
10
|
+
it "should take three arguments" do
|
11
|
+
@result.wont_be_nil
|
12
|
+
end
|
13
|
+
|
14
|
+
it "should save arguments" do
|
15
|
+
@result.url.must_equal "http://google.com"
|
16
|
+
@result.status.must_equal 200
|
17
|
+
@result.body.must_equal '<html><head><title>hi</title></head><body><a href="http://bing.com">bing</a><a href="http://yahoo.com">yahoo</a></body></html>'
|
18
|
+
end
|
19
|
+
|
20
|
+
it "should be immutable" do
|
21
|
+
proc { @result.status = 404 }.must_raise NoMethodError
|
22
|
+
end
|
23
|
+
|
24
|
+
it "should have a clean string rep" do
|
25
|
+
@result.to_s.must_equal "200: http://google.com"
|
26
|
+
end
|
27
|
+
end
|
28
|
+
end
|
29
|
+
|
@@ -0,0 +1,31 @@
|
|
1
|
+
require 'minitest/autorun'
|
2
|
+
require 'webmock/minitest'
|
3
|
+
require 'resolver'
|
4
|
+
require 'link_result'
|
5
|
+
|
6
|
+
WebMock.allow_net_connect!
|
7
|
+
|
8
|
+
describe Shelob::Resolver, "Link fetching module" do
|
9
|
+
describe "when created" do
|
10
|
+
it "should be created with a url" do
|
11
|
+
Shelob::Resolver.new("http://bmnick.com/ruby-c-extensions")
|
12
|
+
end
|
13
|
+
end
|
14
|
+
|
15
|
+
describe "when used" do
|
16
|
+
before do
|
17
|
+
@resolver = Shelob::Resolver.new("http://bmnick.com/ruby-c-extensions")
|
18
|
+
@result = @resolver.resolve
|
19
|
+
end
|
20
|
+
|
21
|
+
it "should return a LinkResult" do
|
22
|
+
@result.must_be_kind_of LinkResult
|
23
|
+
end
|
24
|
+
|
25
|
+
it "should return live result" do
|
26
|
+
@result.body.must_match(/CExt/)
|
27
|
+
end
|
28
|
+
|
29
|
+
end
|
30
|
+
|
31
|
+
end
|
data/test/test_shelob.rb
ADDED
@@ -0,0 +1,97 @@
|
|
1
|
+
require 'minitest/autorun'
|
2
|
+
require 'webmock/minitest'
|
3
|
+
require 'shelob'
|
4
|
+
|
5
|
+
# Stub out requests
|
6
|
+
|
7
|
+
describe Shelob, "Link checking module" do
|
8
|
+
describe "when created" do
|
9
|
+
it "should exist" do
|
10
|
+
Shelob.wont_be_nil
|
11
|
+
end
|
12
|
+
end
|
13
|
+
end
|
14
|
+
|
15
|
+
describe Shelob::Spider, "Link checking spider" do
|
16
|
+
before do
|
17
|
+
stub_request(:any, 'http://bmnick.com/resume').to_return(body: '<html><head><title>resume</title></head><body><a href="http://bmnick.com">home</a><a href="http://bmnick.com/resume/resume.pdf">pdf</a><a href="http://bmnick.com/resume/secret"</body></html>')
|
18
|
+
stub_request(:any, 'http://bmnick.com/').to_return(status: 200, body: '<html><head><title>pdf</title></head><body><a href="http://bmnick.com/resume/">resume</a><a href="http://bmnick.com/">home</a><a href="http://bmnick.com/resume/secret">no touchy!</a></body></html>')
|
19
|
+
stub_request(:any, 'http://bmnick.com/resume/secret').to_return(body: '<html><head><title>secrets</title></head><body><a href="http://bmnick.com/resume/boring">boredom</a><a href="http://bmnick.com/resume">resume</a><a href="/resume/relative">relative</a></body></html>"')
|
20
|
+
stub_request(:any, 'http://bmnick.com/resume/resume.pdf').to_return(status: 404)
|
21
|
+
stub_request(:any, 'http://bmnick.com/resume/boring').to_return(status: 500)
|
22
|
+
stub_request(:any, 'http://bmnick.com/resume/relative').to_return(status: 204)
|
23
|
+
end
|
24
|
+
describe "when created" do
|
25
|
+
it "should exist" do
|
26
|
+
Shelob::Spider.wont_be_nil
|
27
|
+
end
|
28
|
+
it "should store the initial url" do
|
29
|
+
spider = Shelob::Spider.new("https://openforum.com")
|
30
|
+
spider.wont_be_nil
|
31
|
+
spider.hostname.must_equal "https://openforum.com"
|
32
|
+
end
|
33
|
+
end
|
34
|
+
describe "when checking links" do
|
35
|
+
before do
|
36
|
+
|
37
|
+
@spider = Shelob::Spider.new("http://bmnick.com/resume")
|
38
|
+
@results = @spider.check
|
39
|
+
end
|
40
|
+
|
41
|
+
it "should return an array from check" do
|
42
|
+
@results.must_be_kind_of Array
|
43
|
+
end
|
44
|
+
it "should return only error links" do
|
45
|
+
@results.select{|r| r.status == 200}.must_be_empty
|
46
|
+
end
|
47
|
+
it "should provide remaining counts" do
|
48
|
+
@spider.remaining.must_equal 0
|
49
|
+
end
|
50
|
+
it "should fetch the original url" do
|
51
|
+
@spider.fetched.must_include "http://bmnick.com/resume"
|
52
|
+
end
|
53
|
+
it "should provide a number of urls fetched" do
|
54
|
+
# http://bmnick.com/resume
|
55
|
+
# http://bmnick.com/resume/resume.pdf
|
56
|
+
# http://bmnick.com/resume/secret
|
57
|
+
# http://bmnick.com/resume/boring
|
58
|
+
# http://bmnick.com/resume/relative
|
59
|
+
@spider.requests.must_equal 5
|
60
|
+
end
|
61
|
+
it "should make a web request for the original url" do
|
62
|
+
assert_requested :get, "http://bmnick.com/resume"
|
63
|
+
end
|
64
|
+
it "should make a web request for child urls" do
|
65
|
+
# 404
|
66
|
+
assert_requested :get, "http://bmnick.com/resume/resume.pdf"
|
67
|
+
@spider.fetched.must_include "http://bmnick.com/resume/resume.pdf"
|
68
|
+
|
69
|
+
# successful
|
70
|
+
assert_requested :get, "http://bmnick.com/resume/secret"
|
71
|
+
@spider.fetched.must_include "http://bmnick.com/resume/secret"
|
72
|
+
end
|
73
|
+
it "should return the failed request" do
|
74
|
+
# http://bmnick.com/resume/resume.pdf => 404
|
75
|
+
# http://bmnick.com/resume/boring => 500
|
76
|
+
@results.count.must_equal 2
|
77
|
+
end
|
78
|
+
it "shouldn't request pages without the prefix" do
|
79
|
+
assert_not_requested :get, "http://bmnick.com"
|
80
|
+
end
|
81
|
+
it "shouldn't request pages multiple times" do
|
82
|
+
assert_requested :get, "http://bmnick.com/resume", times: 1
|
83
|
+
end
|
84
|
+
it "should continue to spider down the page" do
|
85
|
+
assert_requested :get, "http://bmnick.com/resume/boring"
|
86
|
+
@spider.fetched.must_include "http://bmnick.com/resume/boring"
|
87
|
+
end
|
88
|
+
it "should support relative links" do
|
89
|
+
assert_requested :get, "http://bmnick.com/resume/relative"
|
90
|
+
@spider.fetched.must_include "http://bmnick.com/resume/relative"
|
91
|
+
end
|
92
|
+
it "should format a string cleanly" do
|
93
|
+
@results.map{|r|r.to_s}.join("\n").must_equal "404: http://bmnick.com/resume/resume.pdf
|
94
|
+
500: http://bmnick.com/resume/boring"
|
95
|
+
end
|
96
|
+
end
|
97
|
+
end
|
metadata
ADDED
@@ -0,0 +1,165 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: shelob
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0.beta1
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Benjamin Nicholas
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2013-12-30 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: bundler
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - ~>
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '1.3'
|
20
|
+
type: :development
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - ~>
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '1.3'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: rake
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - '>='
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '0'
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - '>='
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '0'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: minitest
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - '>='
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '0'
|
48
|
+
type: :development
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - '>='
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '0'
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: webmock
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - '>='
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '0'
|
62
|
+
type: :development
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - '>='
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: '0'
|
69
|
+
- !ruby/object:Gem::Dependency
|
70
|
+
name: guard
|
71
|
+
requirement: !ruby/object:Gem::Requirement
|
72
|
+
requirements:
|
73
|
+
- - '>='
|
74
|
+
- !ruby/object:Gem::Version
|
75
|
+
version: '0'
|
76
|
+
type: :development
|
77
|
+
prerelease: false
|
78
|
+
version_requirements: !ruby/object:Gem::Requirement
|
79
|
+
requirements:
|
80
|
+
- - '>='
|
81
|
+
- !ruby/object:Gem::Version
|
82
|
+
version: '0'
|
83
|
+
- !ruby/object:Gem::Dependency
|
84
|
+
name: guard-minitest
|
85
|
+
requirement: !ruby/object:Gem::Requirement
|
86
|
+
requirements:
|
87
|
+
- - '>='
|
88
|
+
- !ruby/object:Gem::Version
|
89
|
+
version: '0'
|
90
|
+
type: :development
|
91
|
+
prerelease: false
|
92
|
+
version_requirements: !ruby/object:Gem::Requirement
|
93
|
+
requirements:
|
94
|
+
- - '>='
|
95
|
+
- !ruby/object:Gem::Version
|
96
|
+
version: '0'
|
97
|
+
- !ruby/object:Gem::Dependency
|
98
|
+
name: nokogiri
|
99
|
+
requirement: !ruby/object:Gem::Requirement
|
100
|
+
requirements:
|
101
|
+
- - '>='
|
102
|
+
- !ruby/object:Gem::Version
|
103
|
+
version: '0'
|
104
|
+
type: :runtime
|
105
|
+
prerelease: false
|
106
|
+
version_requirements: !ruby/object:Gem::Requirement
|
107
|
+
requirements:
|
108
|
+
- - '>='
|
109
|
+
- !ruby/object:Gem::Version
|
110
|
+
version: '0'
|
111
|
+
description: A giant spider that starts on a given page, finds all links on the page,
|
112
|
+
ensure they resolve, and recurses if the link is underneath the starting url
|
113
|
+
email:
|
114
|
+
- bnicholas@brandnetworksinc.com
|
115
|
+
executables:
|
116
|
+
- shelob
|
117
|
+
extensions: []
|
118
|
+
extra_rdoc_files: []
|
119
|
+
files:
|
120
|
+
- .gitignore
|
121
|
+
- Gemfile
|
122
|
+
- Guardfile
|
123
|
+
- LICENSE.txt
|
124
|
+
- README.md
|
125
|
+
- Rakefile
|
126
|
+
- bin/shelob
|
127
|
+
- lib/extractor.rb
|
128
|
+
- lib/link_result.rb
|
129
|
+
- lib/resolver.rb
|
130
|
+
- lib/shelob.rb
|
131
|
+
- lib/shelob/version.rb
|
132
|
+
- shelob.gemspec
|
133
|
+
- test/test_extractor.rb
|
134
|
+
- test/test_link_result.rb
|
135
|
+
- test/test_resolver.rb
|
136
|
+
- test/test_shelob.rb
|
137
|
+
homepage:
|
138
|
+
licenses:
|
139
|
+
- MIT
|
140
|
+
metadata: {}
|
141
|
+
post_install_message:
|
142
|
+
rdoc_options: []
|
143
|
+
require_paths:
|
144
|
+
- lib
|
145
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
146
|
+
requirements:
|
147
|
+
- - '>='
|
148
|
+
- !ruby/object:Gem::Version
|
149
|
+
version: '0'
|
150
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
151
|
+
requirements:
|
152
|
+
- - '>'
|
153
|
+
- !ruby/object:Gem::Version
|
154
|
+
version: 1.3.1
|
155
|
+
requirements: []
|
156
|
+
rubyforge_project:
|
157
|
+
rubygems_version: 2.0.3
|
158
|
+
signing_key:
|
159
|
+
specification_version: 4
|
160
|
+
summary: Spider a site and check links
|
161
|
+
test_files:
|
162
|
+
- test/test_extractor.rb
|
163
|
+
- test/test_link_result.rb
|
164
|
+
- test/test_resolver.rb
|
165
|
+
- test/test_shelob.rb
|