woot 0.0.0
Sign up to get free protection for your applications and to get access to all the features.
- data/.gitignore +7 -0
- data/MIT-LICENSE +20 -0
- data/README.rdoc +40 -0
- data/Rakefile +57 -0
- data/VERSION +1 -0
- data/init.rb +1 -0
- data/lib/woot.rb +33 -0
- data/test/test_helper.rb +25 -0
- data/test/woot_test.rb +24 -0
- metadata +83 -0
data/.gitignore
ADDED
data/MIT-LICENSE
ADDED
@@ -0,0 +1,20 @@
|
|
1
|
+
Copyright (c) 2009 Sean Huber (shuber@huberry.com)
|
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 +1,40 @@
|
|
1
|
+
= woot
|
2
|
+
|
3
|
+
Scapes woot.com sites with ruby
|
4
|
+
|
5
|
+
== Installation
|
6
|
+
|
7
|
+
gem install woot --source http://gemcutter.org
|
8
|
+
|
9
|
+
== Usage
|
10
|
+
|
11
|
+
Simply call <tt>Woot.scrape</tt> and optionally specify the woot subdomain (e.g. www, shirt, kids, wine, etc).
|
12
|
+
Defaults to www.
|
13
|
+
|
14
|
+
data = Woot.scrape
|
15
|
+
puts data.title
|
16
|
+
puts data.price
|
17
|
+
|
18
|
+
data = Woot.scrape(:shirt)
|
19
|
+
puts data.title
|
20
|
+
|
21
|
+
== Note on Patches/Pull Requests
|
22
|
+
|
23
|
+
* Fork the project.
|
24
|
+
* Make your feature addition or bug fix.
|
25
|
+
* Add tests for it. This is important so I don't break it in a
|
26
|
+
future version unintentionally.
|
27
|
+
* Commit, do not mess with rakefile, version, or history.
|
28
|
+
(if you want to have your own version, that is fine but
|
29
|
+
bump version in a commit by itself I can ignore when I pull)
|
30
|
+
* Send me a pull request. Bonus points for topic branches.
|
31
|
+
|
32
|
+
== Todo
|
33
|
+
|
34
|
+
* sellout.woot.com support
|
35
|
+
* woot-off quantities
|
36
|
+
* build gem
|
37
|
+
|
38
|
+
== Copyright
|
39
|
+
|
40
|
+
Copyright (c) 2009 Sean Huber. See MIT-LICENSE for details.
|
data/Rakefile
ADDED
@@ -0,0 +1,57 @@
|
|
1
|
+
require 'rubygems'
|
2
|
+
require 'rake'
|
3
|
+
|
4
|
+
begin
|
5
|
+
require 'jeweler'
|
6
|
+
Jeweler::Tasks.new do |gem|
|
7
|
+
gem.name = 'woot'
|
8
|
+
gem.summary = 'Scapes woot.com sites'
|
9
|
+
gem.description = 'Scapes woot.com sites'
|
10
|
+
gem.email = 'shuber@huberry.com'
|
11
|
+
gem.homepage = 'http://github.com/shuber/woot'
|
12
|
+
gem.authors = ['Sean Huber']
|
13
|
+
gem.add_dependency 'scrapi'
|
14
|
+
gem.add_development_dependency 'shoulda'
|
15
|
+
# gem is a Gem::Specification... see http://www.rubygems.org/read/chapter/20 for additional settings
|
16
|
+
end
|
17
|
+
rescue LoadError
|
18
|
+
puts 'Jeweler (or a dependency) not available. Install it with: sudo gem install jeweler'
|
19
|
+
end
|
20
|
+
|
21
|
+
require 'rake/testtask'
|
22
|
+
Rake::TestTask.new(:test) do |test|
|
23
|
+
test.libs << 'lib' << 'test'
|
24
|
+
test.pattern = 'test/**/*_test.rb'
|
25
|
+
test.verbose = true
|
26
|
+
end
|
27
|
+
|
28
|
+
begin
|
29
|
+
require 'rcov/rcovtask'
|
30
|
+
Rcov::RcovTask.new do |test|
|
31
|
+
test.libs << 'test'
|
32
|
+
test.pattern = 'test/**/*_test.rb'
|
33
|
+
test.verbose = true
|
34
|
+
end
|
35
|
+
rescue LoadError
|
36
|
+
task :rcov do
|
37
|
+
abort 'RCov is not available. In order to run rcov, you must: sudo gem install spicycode-rcov'
|
38
|
+
end
|
39
|
+
end
|
40
|
+
|
41
|
+
task :test => :check_dependencies
|
42
|
+
|
43
|
+
task :default => :test
|
44
|
+
|
45
|
+
require 'rake/rdoctask'
|
46
|
+
Rake::RDocTask.new do |rdoc|
|
47
|
+
if File.exist?('VERSION')
|
48
|
+
version = File.read('VERSION')
|
49
|
+
else
|
50
|
+
version = ""
|
51
|
+
end
|
52
|
+
|
53
|
+
rdoc.rdoc_dir = 'rdoc'
|
54
|
+
rdoc.title = "woot #{version}"
|
55
|
+
rdoc.rdoc_files.include('README*')
|
56
|
+
rdoc.rdoc_files.include('lib/**/*.rb')
|
57
|
+
end
|
data/VERSION
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
0.0.0
|
data/init.rb
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
require 'woot'
|
data/lib/woot.rb
ADDED
@@ -0,0 +1,33 @@
|
|
1
|
+
class Woot
|
2
|
+
DOMAIN = 'woot.com'
|
3
|
+
|
4
|
+
def self.scrape(subdomain = :www)
|
5
|
+
selectors = self.selectors(subdomain)
|
6
|
+
Scraper.define do
|
7
|
+
result *(selectors.inject([]) do |array, (pattern, results)|
|
8
|
+
process pattern, results
|
9
|
+
array += results.keys
|
10
|
+
end)
|
11
|
+
end.scrape(URI.parse("http://#{subdomain}.#{DOMAIN}/"))
|
12
|
+
end
|
13
|
+
|
14
|
+
def self.selectors(subdomain = :www)
|
15
|
+
@selectors = {
|
16
|
+
'h2.fn' => { :title => :text },
|
17
|
+
'span.amount' => { :price => :text },
|
18
|
+
'ul#shippingOptions' => { :shipping => :text },
|
19
|
+
'img.photo' => { :image => '@src' },
|
20
|
+
'div.hproduct>a' => { :alternate_image => proc { |element| $1 if element.attributes['href'] =~ /\('([^']+)'\);/ } },
|
21
|
+
'a.url' => { :url => '@href' },
|
22
|
+
'li.comments>a' => { :comments_url => '@href', :comments_count => proc { |element| element.children[0].content.gsub(/\D/, '') } },
|
23
|
+
'div.story>h2' => { :header => :text },
|
24
|
+
'div.story>h3' => { :sub_header => :text },
|
25
|
+
'div.writeUp' => { :writeup => :text },
|
26
|
+
'div.specs' => { :specs => :text },
|
27
|
+
'div.productDescription>dl' => { :details => :text },
|
28
|
+
'a#ctl00_ctl00_ContentPlaceHolderLeadIn_ContentPlaceHolderLeadIn_SaleControl_HyperLinkWantOne' => { :purchase_url => proc do |element|
|
29
|
+
"http://#{subdomain}.#{DOMAIN}#{element.attributes['href'].gsub(/^https?:\/\/[^\/]+/, '')}" if element.attributes.has_key?('href')
|
30
|
+
end }
|
31
|
+
}
|
32
|
+
end
|
33
|
+
end
|
data/test/test_helper.rb
ADDED
@@ -0,0 +1,25 @@
|
|
1
|
+
require 'rubygems'
|
2
|
+
require 'test/unit'
|
3
|
+
require 'shoulda'
|
4
|
+
require 'scrapi'
|
5
|
+
Tidy.path = ENV['TIDY_PATH'] if ENV['TIDY_PATH']
|
6
|
+
|
7
|
+
$LOAD_PATH.unshift(File.join(File.dirname(__FILE__), '..', 'lib'))
|
8
|
+
$LOAD_PATH.unshift(File.dirname(__FILE__))
|
9
|
+
require 'woot'
|
10
|
+
|
11
|
+
class Test::Unit::TestCase
|
12
|
+
|
13
|
+
def self.attributes
|
14
|
+
@attributes ||= Woot.selectors.map { |selector, results| results.keys }.flatten
|
15
|
+
end
|
16
|
+
|
17
|
+
def self.possible_blank_attributes
|
18
|
+
@possible_blank_attributes ||= [:purchase_url]
|
19
|
+
end
|
20
|
+
|
21
|
+
def self.subdomains
|
22
|
+
@subdomains ||= [:www, :wine, :shirt, :kids] # TODO: sellout
|
23
|
+
end
|
24
|
+
|
25
|
+
end
|
data/test/woot_test.rb
ADDED
@@ -0,0 +1,24 @@
|
|
1
|
+
require 'test_helper'
|
2
|
+
|
3
|
+
class WootTest < Test::Unit::TestCase
|
4
|
+
|
5
|
+
subdomains.each do |subdomain|
|
6
|
+
context "When parsing http://#{subdomain}.#{Woot::DOMAIN}/ it" do
|
7
|
+
setup { @woot = Woot.scrape(subdomain) }
|
8
|
+
|
9
|
+
attributes.each do |attribute|
|
10
|
+
should "have a key for #{attribute}" do
|
11
|
+
assert @woot.members.include?(attribute.to_s)
|
12
|
+
end
|
13
|
+
|
14
|
+
unless possible_blank_attributes.include?(attribute)
|
15
|
+
should "have a value for #{attribute}" do
|
16
|
+
assert !@woot.send(attribute).nil?
|
17
|
+
assert !@woot.send(attribute).empty?
|
18
|
+
end
|
19
|
+
end
|
20
|
+
end
|
21
|
+
end
|
22
|
+
end
|
23
|
+
|
24
|
+
end
|
metadata
ADDED
@@ -0,0 +1,83 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: woot
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Sean Huber
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
|
12
|
+
date: 2009-10-30 00:00:00 -07:00
|
13
|
+
default_executable:
|
14
|
+
dependencies:
|
15
|
+
- !ruby/object:Gem::Dependency
|
16
|
+
name: scrapi
|
17
|
+
type: :runtime
|
18
|
+
version_requirement:
|
19
|
+
version_requirements: !ruby/object:Gem::Requirement
|
20
|
+
requirements:
|
21
|
+
- - ">="
|
22
|
+
- !ruby/object:Gem::Version
|
23
|
+
version: "0"
|
24
|
+
version:
|
25
|
+
- !ruby/object:Gem::Dependency
|
26
|
+
name: shoulda
|
27
|
+
type: :development
|
28
|
+
version_requirement:
|
29
|
+
version_requirements: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - ">="
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: "0"
|
34
|
+
version:
|
35
|
+
description: Scapes woot.com sites
|
36
|
+
email: shuber@huberry.com
|
37
|
+
executables: []
|
38
|
+
|
39
|
+
extensions: []
|
40
|
+
|
41
|
+
extra_rdoc_files:
|
42
|
+
- README.rdoc
|
43
|
+
files:
|
44
|
+
- .gitignore
|
45
|
+
- MIT-LICENSE
|
46
|
+
- README.rdoc
|
47
|
+
- Rakefile
|
48
|
+
- VERSION
|
49
|
+
- init.rb
|
50
|
+
- lib/woot.rb
|
51
|
+
- test/test_helper.rb
|
52
|
+
- test/woot_test.rb
|
53
|
+
has_rdoc: true
|
54
|
+
homepage: http://github.com/shuber/woot
|
55
|
+
licenses: []
|
56
|
+
|
57
|
+
post_install_message:
|
58
|
+
rdoc_options:
|
59
|
+
- --charset=UTF-8
|
60
|
+
require_paths:
|
61
|
+
- lib
|
62
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
63
|
+
requirements:
|
64
|
+
- - ">="
|
65
|
+
- !ruby/object:Gem::Version
|
66
|
+
version: "0"
|
67
|
+
version:
|
68
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
69
|
+
requirements:
|
70
|
+
- - ">="
|
71
|
+
- !ruby/object:Gem::Version
|
72
|
+
version: "0"
|
73
|
+
version:
|
74
|
+
requirements: []
|
75
|
+
|
76
|
+
rubyforge_project:
|
77
|
+
rubygems_version: 1.3.5
|
78
|
+
signing_key:
|
79
|
+
specification_version: 3
|
80
|
+
summary: Scapes woot.com sites
|
81
|
+
test_files:
|
82
|
+
- test/test_helper.rb
|
83
|
+
- test/woot_test.rb
|