spieker 0.0.1
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/LICENSE.txt +22 -0
- data/README.md +0 -0
- data/Rakefile +1 -0
- data/bin/spieker +5 -0
- data/lib/spieker/crawler.rb +64 -0
- data/lib/spieker/link_scraper.rb +77 -0
- data/lib/spieker/version.rb +3 -0
- data/lib/spieker.rb +3 -0
- data/spieker.gemspec +27 -0
- data/test/link_scraper_test.rb +36 -0
- data/test/spieker_test.rb +17 -0
- metadata +130 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 5b4522f86a2664e3028ed3193ba87f782dbdcb95
|
4
|
+
data.tar.gz: d110801ec5b674af967fe84a398176ce467b3a2b
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 87176bd62d604ac693772fb7dc761b0807c8776142470049e9ea729a8f1230cbee03010a40661d9e887f53f6ce8e2a3c21810c12e47e3aeb96298dc71334f324
|
7
|
+
data.tar.gz: c4f41f4346cba9e79ec7a6511f1dd3d7f6c7991668392d911a40a8b5f3570f6432bdb5c793f7123315c94b324a6511e61d0f7fd94a08b720fc71162a8a7fc333
|
data/.gitignore
ADDED
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2013 Timon Vonk
|
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
File without changes
|
data/Rakefile
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
require "bundler/gem_tasks"
|
data/bin/spieker
ADDED
@@ -0,0 +1,64 @@
|
|
1
|
+
module Spieker
|
2
|
+
class Crawler
|
3
|
+
def initialize(url, verbose: false)
|
4
|
+
@url = url
|
5
|
+
@tracked_links = []
|
6
|
+
@verbose = verbose
|
7
|
+
end
|
8
|
+
|
9
|
+
def crawl!
|
10
|
+
report "Starting to crawl on #{@url}"
|
11
|
+
|
12
|
+
scraper = LinkScraper.new(@url)
|
13
|
+
track_link(@url)
|
14
|
+
links = scraper.result
|
15
|
+
recursively_crawl(links)
|
16
|
+
|
17
|
+
print_results if @verbose
|
18
|
+
end
|
19
|
+
|
20
|
+
def current_path
|
21
|
+
URI.parse(@url).path
|
22
|
+
end
|
23
|
+
|
24
|
+
private
|
25
|
+
def recursively_crawl(links)
|
26
|
+
new_links_threaded = {}
|
27
|
+
links.each do |link|
|
28
|
+
report "Crawling page #{link}"
|
29
|
+
|
30
|
+
scraper = LinkScraper.new(link)
|
31
|
+
new_links_threaded[link] = scraper.result
|
32
|
+
track_link(link)
|
33
|
+
|
34
|
+
report "Finished page #{link}, #{new_links_threaded[link].length} links found"
|
35
|
+
end
|
36
|
+
new_links = select_untracked_links(new_links_threaded.values.flatten.uniq)
|
37
|
+
report "Recursively crawling #{new_links.length} links ..."
|
38
|
+
report "NEW LINKS FOUND: \n#{new_links.join("\n")}"
|
39
|
+
report "TRACKED LINKS: \n#{@tracked_links.join("\n")}"
|
40
|
+
|
41
|
+
recursively_crawl(new_links) if new_links.any?
|
42
|
+
end
|
43
|
+
|
44
|
+
def select_untracked_links(links)
|
45
|
+
links.select { |l| !@tracked_links.include?(l) }
|
46
|
+
end
|
47
|
+
|
48
|
+
def track_link(link)
|
49
|
+
@tracked_links = @tracked_links.push(link)
|
50
|
+
end
|
51
|
+
|
52
|
+
def report(text)
|
53
|
+
if @verbose
|
54
|
+
puts text
|
55
|
+
end
|
56
|
+
end
|
57
|
+
|
58
|
+
def print_results
|
59
|
+
report "\n\n:::RESULTS:::\n\n"
|
60
|
+
report "Pages found #{@tracked_links.uniq.compact.length}\n\n"
|
61
|
+
report "All links found:\n\n #{@tracked_links.compact.join("\n")}"
|
62
|
+
end
|
63
|
+
end
|
64
|
+
end
|
@@ -0,0 +1,77 @@
|
|
1
|
+
require 'capybara'
|
2
|
+
require 'capybara/poltergeist'
|
3
|
+
|
4
|
+
module Spieker
|
5
|
+
class LinkScraper
|
6
|
+
LOCAL_LINK_REGEX = /^(?!(http(s)?\:|\/\/)|data\:).*/
|
7
|
+
|
8
|
+
include Capybara::DSL
|
9
|
+
attr_writer :links
|
10
|
+
|
11
|
+
def initialize(url)
|
12
|
+
@url = URI.parse(url)
|
13
|
+
Capybara.app_host = app_host
|
14
|
+
|
15
|
+
Capybara.register_driver :poltergeist do |app|
|
16
|
+
Capybara::Poltergeist::Driver.new(app, phantomjs_logger: NullStream.new )
|
17
|
+
end
|
18
|
+
|
19
|
+
Capybara.current_driver = :selenium
|
20
|
+
end
|
21
|
+
|
22
|
+
def result
|
23
|
+
cleaned_up_links(found_links)
|
24
|
+
end
|
25
|
+
|
26
|
+
def app_host
|
27
|
+
"#{@url.scheme}://#{@url.hostname}"
|
28
|
+
end
|
29
|
+
|
30
|
+
private
|
31
|
+
|
32
|
+
def found_links
|
33
|
+
@links ||= drive_page_for_links
|
34
|
+
end
|
35
|
+
|
36
|
+
def drive_page_for_links
|
37
|
+
begin
|
38
|
+
visit @url.path
|
39
|
+
page.all('a').map { |el| el[:href]}
|
40
|
+
rescue
|
41
|
+
puts "Error parsing #{@url.to_s}"
|
42
|
+
[]
|
43
|
+
end
|
44
|
+
end
|
45
|
+
|
46
|
+
def cleaned_up_links(links)
|
47
|
+
links.select { |link|
|
48
|
+
is_local?(link) && !is_email?(link)
|
49
|
+
}.map(&method(:filter_hash)).compact.uniq
|
50
|
+
end
|
51
|
+
|
52
|
+
def is_local?(link)
|
53
|
+
link =~ LOCAL_LINK_REGEX ||
|
54
|
+
begin
|
55
|
+
URI.parse(link).hostname == @url.hostname
|
56
|
+
rescue
|
57
|
+
false
|
58
|
+
end
|
59
|
+
end
|
60
|
+
|
61
|
+
def filter_hash(link)
|
62
|
+
if match = link.match(/(.*)#(.*)$/)
|
63
|
+
match[1]
|
64
|
+
else
|
65
|
+
link
|
66
|
+
end
|
67
|
+
end
|
68
|
+
|
69
|
+
def is_email? link
|
70
|
+
link =~ /mailto/
|
71
|
+
end
|
72
|
+
end
|
73
|
+
end
|
74
|
+
|
75
|
+
class NullStream
|
76
|
+
def puts; end
|
77
|
+
end
|
data/lib/spieker.rb
ADDED
data/spieker.gemspec
ADDED
@@ -0,0 +1,27 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'spieker/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "spieker"
|
8
|
+
spec.version = Spieker::VERSION
|
9
|
+
spec.authors = ["Timon Vonk"]
|
10
|
+
spec.email = ["timonv@gmail.com"]
|
11
|
+
spec.description = %q{Easilly crawl a website}
|
12
|
+
spec.summary = %q{Easilly crawl a website}
|
13
|
+
spec.homepage = ""
|
14
|
+
spec.license = "MIT"
|
15
|
+
|
16
|
+
spec.files = `git ls-files`.split($/)
|
17
|
+
spec.executables = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
|
18
|
+
spec.test_files = spec.files.grep(%r{^(test|spec|features)/})
|
19
|
+
spec.require_paths = ["lib"]
|
20
|
+
|
21
|
+
spec.add_development_dependency "bundler", "~> 1.3"
|
22
|
+
spec.add_development_dependency "rake"
|
23
|
+
|
24
|
+
spec.add_dependency "capybara"
|
25
|
+
spec.add_dependency "poltergeist"
|
26
|
+
spec.add_dependency "selenium-webdriver"
|
27
|
+
end
|
@@ -0,0 +1,36 @@
|
|
1
|
+
require 'test/unit'
|
2
|
+
require 'spieker.rb'
|
3
|
+
|
4
|
+
class TestLinkScraper < Test::Unit::TestCase
|
5
|
+
def setup
|
6
|
+
@scraper = Spieker::LinkScraper.new('http://www.google.com')
|
7
|
+
end
|
8
|
+
|
9
|
+
def test_apphost
|
10
|
+
assert_equal 'http://www.google.com', @scraper.app_host
|
11
|
+
end
|
12
|
+
|
13
|
+
def test_result
|
14
|
+
return
|
15
|
+
assert @scraper.result.any?
|
16
|
+
end
|
17
|
+
|
18
|
+
def test_filter_local
|
19
|
+
found_links = [
|
20
|
+
'http://www.google.com/local',
|
21
|
+
'/local',
|
22
|
+
'/local#justahash',
|
23
|
+
'#justahash',
|
24
|
+
'http://www.remote.com',
|
25
|
+
'mailto:timonv@gmail.com'
|
26
|
+
]
|
27
|
+
expected_links = [
|
28
|
+
'http://www.google.com/local',
|
29
|
+
'/local',
|
30
|
+
''
|
31
|
+
]
|
32
|
+
|
33
|
+
@scraper.links = found_links
|
34
|
+
assert_equal expected_links, @scraper.result
|
35
|
+
end
|
36
|
+
end
|
@@ -0,0 +1,17 @@
|
|
1
|
+
require 'test/unit'
|
2
|
+
|
3
|
+
require 'spieker.rb'
|
4
|
+
|
5
|
+
class TestSpieker < Test::Unit::TestCase
|
6
|
+
def setup
|
7
|
+
@crawler = Spieker::Crawler.new('http://www.google.com/path')
|
8
|
+
end
|
9
|
+
|
10
|
+
def test_current_path
|
11
|
+
assert_equal '/path', @crawler.current_path
|
12
|
+
end
|
13
|
+
|
14
|
+
def test_all_links
|
15
|
+
assert_equal [], @crawler.current_links
|
16
|
+
end
|
17
|
+
end
|
metadata
ADDED
@@ -0,0 +1,130 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: spieker
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Timon Vonk
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2013-07-23 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: capybara
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - '>='
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '0'
|
48
|
+
type: :runtime
|
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: poltergeist
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - '>='
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '0'
|
62
|
+
type: :runtime
|
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: selenium-webdriver
|
71
|
+
requirement: !ruby/object:Gem::Requirement
|
72
|
+
requirements:
|
73
|
+
- - '>='
|
74
|
+
- !ruby/object:Gem::Version
|
75
|
+
version: '0'
|
76
|
+
type: :runtime
|
77
|
+
prerelease: false
|
78
|
+
version_requirements: !ruby/object:Gem::Requirement
|
79
|
+
requirements:
|
80
|
+
- - '>='
|
81
|
+
- !ruby/object:Gem::Version
|
82
|
+
version: '0'
|
83
|
+
description: Easilly crawl a website
|
84
|
+
email:
|
85
|
+
- timonv@gmail.com
|
86
|
+
executables:
|
87
|
+
- spieker
|
88
|
+
extensions: []
|
89
|
+
extra_rdoc_files: []
|
90
|
+
files:
|
91
|
+
- .gitignore
|
92
|
+
- Gemfile
|
93
|
+
- LICENSE.txt
|
94
|
+
- README.md
|
95
|
+
- Rakefile
|
96
|
+
- bin/spieker
|
97
|
+
- lib/spieker.rb
|
98
|
+
- lib/spieker/crawler.rb
|
99
|
+
- lib/spieker/link_scraper.rb
|
100
|
+
- lib/spieker/version.rb
|
101
|
+
- spieker.gemspec
|
102
|
+
- test/link_scraper_test.rb
|
103
|
+
- test/spieker_test.rb
|
104
|
+
homepage: ''
|
105
|
+
licenses:
|
106
|
+
- MIT
|
107
|
+
metadata: {}
|
108
|
+
post_install_message:
|
109
|
+
rdoc_options: []
|
110
|
+
require_paths:
|
111
|
+
- lib
|
112
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
113
|
+
requirements:
|
114
|
+
- - '>='
|
115
|
+
- !ruby/object:Gem::Version
|
116
|
+
version: '0'
|
117
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
118
|
+
requirements:
|
119
|
+
- - '>='
|
120
|
+
- !ruby/object:Gem::Version
|
121
|
+
version: '0'
|
122
|
+
requirements: []
|
123
|
+
rubyforge_project:
|
124
|
+
rubygems_version: 2.0.3
|
125
|
+
signing_key:
|
126
|
+
specification_version: 4
|
127
|
+
summary: Easilly crawl a website
|
128
|
+
test_files:
|
129
|
+
- test/link_scraper_test.rb
|
130
|
+
- test/spieker_test.rb
|