spiderz 0.1.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- data/History.txt +2 -0
- data/Manifest.txt +7 -0
- data/README.txt +60 -0
- data/Rakefile +14 -0
- data/bin/spiderz +0 -0
- data/lib/spiderz.rb +98 -0
- data/test/test_spiderz.rb +0 -0
- metadata +72 -0
data/History.txt
ADDED
data/Manifest.txt
ADDED
data/README.txt
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
1
|
+
= spiderz
|
|
2
|
+
|
|
3
|
+
http://parkerfox.co.uk/labs/spiderz
|
|
4
|
+
|
|
5
|
+
== DESCRIPTION:
|
|
6
|
+
|
|
7
|
+
Scarily easy spidering
|
|
8
|
+
|
|
9
|
+
== FEATURES/PROBLEMS:
|
|
10
|
+
|
|
11
|
+
* Very simple spidering using Hpricot
|
|
12
|
+
|
|
13
|
+
== SYNOPSIS:
|
|
14
|
+
|
|
15
|
+
Create a site map.
|
|
16
|
+
|
|
17
|
+
# create the class
|
|
18
|
+
spider = Spiderz.new "http://mysite.com"
|
|
19
|
+
|
|
20
|
+
# setup a custom
|
|
21
|
+
spider.success do |url, doc|
|
|
22
|
+
title = (doc / "title").text.strip
|
|
23
|
+
puts "<a href='#{url}' >#{title}</a>"
|
|
24
|
+
end
|
|
25
|
+
|
|
26
|
+
# set it going
|
|
27
|
+
spider.crawl
|
|
28
|
+
|
|
29
|
+
== REQUIREMENTS:
|
|
30
|
+
|
|
31
|
+
* Hpricot
|
|
32
|
+
|
|
33
|
+
== INSTALL:
|
|
34
|
+
|
|
35
|
+
sudo gem install spiderz
|
|
36
|
+
|
|
37
|
+
== LICENSE:
|
|
38
|
+
|
|
39
|
+
(The MIT License)
|
|
40
|
+
|
|
41
|
+
Copyright (c) 2008 FIX
|
|
42
|
+
|
|
43
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
|
44
|
+
a copy of this software and associated documentation files (the
|
|
45
|
+
'Software'), to deal in the Software without restriction, including
|
|
46
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
|
47
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
|
48
|
+
permit persons to whom the Software is furnished to do so, subject to
|
|
49
|
+
the following conditions:
|
|
50
|
+
|
|
51
|
+
The above copyright notice and this permission notice shall be
|
|
52
|
+
included in all copies or substantial portions of the Software.
|
|
53
|
+
|
|
54
|
+
THE SOFTWARE IS PROVIDED 'AS IS', WITHOUT WARRANTY OF ANY KIND,
|
|
55
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
|
56
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
|
|
57
|
+
IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
|
|
58
|
+
CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
|
|
59
|
+
TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
|
|
60
|
+
SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/Rakefile
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
1
|
+
# -*- ruby -*-
|
|
2
|
+
|
|
3
|
+
require 'rubygems'
|
|
4
|
+
require 'hoe'
|
|
5
|
+
require './lib/spiderz.rb'
|
|
6
|
+
|
|
7
|
+
Hoe.new('spiderz', Spiderz::VERSION) do |p|
|
|
8
|
+
# p.rubyforge_name = 'spiderzx' # if different than lowercase project name
|
|
9
|
+
p.developer('Jonah Fox', 'jonah@parkefox.co.uk')
|
|
10
|
+
p.remote_rdoc_dir = '' # Release to root
|
|
11
|
+
|
|
12
|
+
end
|
|
13
|
+
|
|
14
|
+
# vim: syntax=Ruby
|
data/bin/spiderz
ADDED
|
File without changes
|
data/lib/spiderz.rb
ADDED
|
@@ -0,0 +1,98 @@
|
|
|
1
|
+
require 'rubygems'
|
|
2
|
+
require 'hpricot'
|
|
3
|
+
require 'open-uri'
|
|
4
|
+
|
|
5
|
+
class Spiderz
|
|
6
|
+
|
|
7
|
+
VERSION = "0.1.0"
|
|
8
|
+
|
|
9
|
+
#root should be like http://www.google.com (i.e. with http://)
|
|
10
|
+
def initialize(root)
|
|
11
|
+
@crawled = {}
|
|
12
|
+
@root = root
|
|
13
|
+
|
|
14
|
+
@success = Proc.new { |url, doc| puts "Successfully read url: #{url}" }
|
|
15
|
+
@failure = Proc.new { |url| puts "failure to read/parse url: #{url}" }
|
|
16
|
+
@started = Proc.new { |url| puts "Started crawling from url: #{url}" }
|
|
17
|
+
@completed = Proc.new { |url| puts "Crawling complete" }
|
|
18
|
+
|
|
19
|
+
@skip = Proc.new do |href|
|
|
20
|
+
!href || (external?(href) || mail?(href) || bookmark?(href))
|
|
21
|
+
end
|
|
22
|
+
end
|
|
23
|
+
|
|
24
|
+
def crawl(url)
|
|
25
|
+
@started.call(url)
|
|
26
|
+
|
|
27
|
+
@to_crawl = [url]
|
|
28
|
+
|
|
29
|
+
while(@to_crawl.length > 0)
|
|
30
|
+
@to_crawl += page_links(@to_crawl.shift)
|
|
31
|
+
end
|
|
32
|
+
|
|
33
|
+
@completed.call(url)
|
|
34
|
+
end
|
|
35
|
+
|
|
36
|
+
def external? href
|
|
37
|
+
href.match("[a-z]+://") && !href.match(@root)
|
|
38
|
+
end
|
|
39
|
+
|
|
40
|
+
def bookmark? href
|
|
41
|
+
href.match(/^#/)
|
|
42
|
+
end
|
|
43
|
+
|
|
44
|
+
def mail? href
|
|
45
|
+
href.match("mailto")
|
|
46
|
+
end
|
|
47
|
+
|
|
48
|
+
def started &action
|
|
49
|
+
@started = action
|
|
50
|
+
end
|
|
51
|
+
|
|
52
|
+
def completed &action
|
|
53
|
+
@completed = action
|
|
54
|
+
end
|
|
55
|
+
|
|
56
|
+
def failure &action
|
|
57
|
+
@failure = action
|
|
58
|
+
end
|
|
59
|
+
|
|
60
|
+
def success &action
|
|
61
|
+
@success = action
|
|
62
|
+
end
|
|
63
|
+
|
|
64
|
+
def skip &action
|
|
65
|
+
@skip = action
|
|
66
|
+
end
|
|
67
|
+
|
|
68
|
+
def page_links url
|
|
69
|
+
#puts url
|
|
70
|
+
return [] if @crawled[url]
|
|
71
|
+
|
|
72
|
+
@crawled[url] = true
|
|
73
|
+
|
|
74
|
+
begin
|
|
75
|
+
doc = Hpricot(open(@root+url))
|
|
76
|
+
rescue
|
|
77
|
+
@failure.call(url)
|
|
78
|
+
return []
|
|
79
|
+
end
|
|
80
|
+
|
|
81
|
+
@success.call(url, doc)
|
|
82
|
+
|
|
83
|
+
links = doc/"a" #find links
|
|
84
|
+
|
|
85
|
+
urls = links.map do |a|
|
|
86
|
+
a.attributes["href"]
|
|
87
|
+
end
|
|
88
|
+
|
|
89
|
+
urls.delete_if do |url|
|
|
90
|
+
@crawled[url] || @skip.call(url)
|
|
91
|
+
end
|
|
92
|
+
|
|
93
|
+
urls
|
|
94
|
+
end
|
|
95
|
+
|
|
96
|
+
end
|
|
97
|
+
|
|
98
|
+
|
|
File without changes
|
metadata
ADDED
|
@@ -0,0 +1,72 @@
|
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
|
2
|
+
name: spiderz
|
|
3
|
+
version: !ruby/object:Gem::Version
|
|
4
|
+
version: 0.1.0
|
|
5
|
+
platform: ruby
|
|
6
|
+
authors:
|
|
7
|
+
- Jonah Fox
|
|
8
|
+
autorequire:
|
|
9
|
+
bindir: bin
|
|
10
|
+
cert_chain: []
|
|
11
|
+
|
|
12
|
+
date: 2008-11-30 00:00:00 +00:00
|
|
13
|
+
default_executable:
|
|
14
|
+
dependencies:
|
|
15
|
+
- !ruby/object:Gem::Dependency
|
|
16
|
+
name: hoe
|
|
17
|
+
type: :development
|
|
18
|
+
version_requirement:
|
|
19
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
20
|
+
requirements:
|
|
21
|
+
- - ">="
|
|
22
|
+
- !ruby/object:Gem::Version
|
|
23
|
+
version: 1.8.2
|
|
24
|
+
version:
|
|
25
|
+
description: Scarily easy spidering
|
|
26
|
+
email:
|
|
27
|
+
- jonah@parkefox.co.uk
|
|
28
|
+
executables:
|
|
29
|
+
- spiderz
|
|
30
|
+
extensions: []
|
|
31
|
+
|
|
32
|
+
extra_rdoc_files:
|
|
33
|
+
- History.txt
|
|
34
|
+
- Manifest.txt
|
|
35
|
+
- README.txt
|
|
36
|
+
files:
|
|
37
|
+
- History.txt
|
|
38
|
+
- Manifest.txt
|
|
39
|
+
- README.txt
|
|
40
|
+
- Rakefile
|
|
41
|
+
- bin/spiderz
|
|
42
|
+
- lib/spiderz.rb
|
|
43
|
+
- test/test_spiderz.rb
|
|
44
|
+
has_rdoc: true
|
|
45
|
+
homepage: http://parkerfox.co.uk/labs/spiderz
|
|
46
|
+
post_install_message:
|
|
47
|
+
rdoc_options:
|
|
48
|
+
- --main
|
|
49
|
+
- README.txt
|
|
50
|
+
require_paths:
|
|
51
|
+
- lib
|
|
52
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
|
53
|
+
requirements:
|
|
54
|
+
- - ">="
|
|
55
|
+
- !ruby/object:Gem::Version
|
|
56
|
+
version: "0"
|
|
57
|
+
version:
|
|
58
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
|
59
|
+
requirements:
|
|
60
|
+
- - ">="
|
|
61
|
+
- !ruby/object:Gem::Version
|
|
62
|
+
version: "0"
|
|
63
|
+
version:
|
|
64
|
+
requirements: []
|
|
65
|
+
|
|
66
|
+
rubyforge_project: spiderz
|
|
67
|
+
rubygems_version: 1.3.1
|
|
68
|
+
signing_key:
|
|
69
|
+
specification_version: 2
|
|
70
|
+
summary: Scarily easy spidering
|
|
71
|
+
test_files:
|
|
72
|
+
- test/test_spiderz.rb
|