product_spy 0.0.1
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/.gitignore +17 -0
- data/.rspec +2 -0
- data/.travis.yml +4 -0
- data/Gemfile +6 -0
- data/LICENSE.txt +22 -0
- data/README.md +58 -0
- data/Rakefile +8 -0
- data/lib/product_spy/configuration.rb +28 -0
- data/lib/product_spy/host.rb +62 -0
- data/lib/product_spy/version.rb +3 -0
- data/lib/product_spy.rb +54 -0
- data/product_spy.gemspec +21 -0
- data/spec/amazon_spec.rb +54 -0
- data/spec/spec_helper.rb +8 -0
- metadata +81 -0
data/.gitignore
ADDED
data/.rspec
ADDED
data/.travis.yml
ADDED
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2013 Paul Spieker
|
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 +1,58 @@
|
|
1
|
+
[](https://travis-ci.org/spieker/product_spy)
|
2
|
+
|
3
|
+
# ProductSpy
|
4
|
+
|
5
|
+
ProductSpy is made for parsing product URLs, i.e. Amazon-URLs, to get
|
6
|
+
the product keys and creating product URLs based on these keys. This can
|
7
|
+
be used to identify products based on the url or just to clean up
|
8
|
+
product URLs.
|
9
|
+
|
10
|
+
## Installation
|
11
|
+
|
12
|
+
Add this line to your application's Gemfile:
|
13
|
+
|
14
|
+
gem 'product_spy'
|
15
|
+
|
16
|
+
And then execute:
|
17
|
+
|
18
|
+
$ bundle
|
19
|
+
|
20
|
+
Or install it yourself as:
|
21
|
+
|
22
|
+
$ gem install product_spy
|
23
|
+
|
24
|
+
## Usage
|
25
|
+
|
26
|
+
```ruby
|
27
|
+
# Parsing URLs
|
28
|
+
ProductSpy.parse('https://www.amazon.de/dp/B004O9DF6O') => ['www.amazon.de', ['B004O9DF6O']]
|
29
|
+
|
30
|
+
# Building URLs
|
31
|
+
ProductSpy.build('amazon.de', ['B004O9DF6O']) # => https://www.amazon.de/dp/B004O9DF6O
|
32
|
+
|
33
|
+
# defining patterns
|
34
|
+
ProductSpy.setup do |config|
|
35
|
+
config.host 'www.amazon.de', :aliases => ['amazon.de'] do |host|
|
36
|
+
# ** Mobile
|
37
|
+
# http://www.amazon.de/gp/aw/d/B004O9DF7I/ref=aw_d_var_2nd_sports_img?vs=1
|
38
|
+
# http://www.amazon.de/gp/aw/B000K7BELW/ref=aw_imgblk_0?h=356&ie=UTF8&selIdx=0&tag=viddleit-21&w=320
|
39
|
+
host.parse /^http[s]{0,1}:\/\/(www\.|)amazon.de\/gp\/aw(\/d|)\/([A-Z0-9]{10})(\/.*|)$/, [3]
|
40
|
+
|
41
|
+
# ** Desktop
|
42
|
+
# http://www.amazon.de/Hauck-662984-Hochstuhl-Alpha-natur/dp/B000K7BELW/ref=sr_1_2?s=baby&ie=UTF8&qid=1360979509&sr=1-2
|
43
|
+
# http://www.amazon.de/dp/B000K7BELW/
|
44
|
+
host.parse /^http[s]{0,1}:\/\/(www\.|)amazon.de(\/.*?|)\/dp\/([A-Z0-9]{10})(\/.*|)$/, [3]
|
45
|
+
|
46
|
+
host.build :default, 'https://www.amazon.de/dp/:1'
|
47
|
+
host.build :mobile, 'https://www.amazon.de/gp/aw/d/:1'
|
48
|
+
end
|
49
|
+
end
|
50
|
+
```
|
51
|
+
|
52
|
+
## Contributing
|
53
|
+
|
54
|
+
1. Fork it
|
55
|
+
2. Create your feature branch (`git checkout -b my-new-feature`)
|
56
|
+
3. Commit your changes (`git commit -am 'Add some feature'`)
|
57
|
+
4. Push to the branch (`git push origin my-new-feature`)
|
58
|
+
5. Create new Pull Request
|
data/Rakefile
ADDED
@@ -0,0 +1,28 @@
|
|
1
|
+
module ProductSpy
|
2
|
+
class Configuration
|
3
|
+
include Singleton
|
4
|
+
|
5
|
+
attr_reader :hosts
|
6
|
+
|
7
|
+
def initialize
|
8
|
+
@hosts = {}
|
9
|
+
end
|
10
|
+
|
11
|
+
def host(host, options = {}, &block)
|
12
|
+
host_inst = Host.new(host)
|
13
|
+
yield host_inst
|
14
|
+
@hosts[host.to_sym] = host_inst
|
15
|
+
|
16
|
+
options = {
|
17
|
+
:aliases => []
|
18
|
+
}.merge(options)
|
19
|
+
|
20
|
+
options[:aliases].each do |host|
|
21
|
+
@hosts[host.to_sym] = host_inst
|
22
|
+
end
|
23
|
+
end
|
24
|
+
end
|
25
|
+
def self.setup(&block)
|
26
|
+
yield Configuration.instance
|
27
|
+
end
|
28
|
+
end
|
@@ -0,0 +1,62 @@
|
|
1
|
+
module ProductSpy
|
2
|
+
class Host
|
3
|
+
class Parser
|
4
|
+
def initialize(regexp, pk_keys)
|
5
|
+
@regexp = regexp
|
6
|
+
@pk_keys = pk_keys
|
7
|
+
end
|
8
|
+
|
9
|
+
def get_pk(url)
|
10
|
+
if m = @regexp.match(url)
|
11
|
+
return @pk_keys.map do |i|
|
12
|
+
m[i]
|
13
|
+
end
|
14
|
+
else
|
15
|
+
return nil
|
16
|
+
end
|
17
|
+
end
|
18
|
+
end
|
19
|
+
|
20
|
+
class Builder
|
21
|
+
def initialize(pattern)
|
22
|
+
@pattern = pattern
|
23
|
+
end
|
24
|
+
|
25
|
+
def get_url(pk)
|
26
|
+
@pattern.gsub /:(\d+)/ do |i|
|
27
|
+
pk[i.to_i]
|
28
|
+
end
|
29
|
+
end
|
30
|
+
end
|
31
|
+
|
32
|
+
attr_reader :host_name
|
33
|
+
|
34
|
+
def initialize(host_name)
|
35
|
+
@host_name = host_name
|
36
|
+
@parser = []
|
37
|
+
@builder = {}
|
38
|
+
end
|
39
|
+
|
40
|
+
def parse(regex, pk_keys)
|
41
|
+
@parser << Parser.new(regex, pk_keys)
|
42
|
+
end
|
43
|
+
|
44
|
+
def build(type, pattern)
|
45
|
+
@builder[type.to_sym] = Builder.new(pattern)
|
46
|
+
end
|
47
|
+
|
48
|
+
def make_url(pk, options)
|
49
|
+
builder = @builder[options[:type].to_sym]
|
50
|
+
builder.get_url(pk)
|
51
|
+
end
|
52
|
+
|
53
|
+
def make_pk(url)
|
54
|
+
@parser.each do |parser|
|
55
|
+
result = parser.get_pk(url)
|
56
|
+
return result unless result.nil?
|
57
|
+
end
|
58
|
+
return nil
|
59
|
+
end
|
60
|
+
end
|
61
|
+
end
|
62
|
+
|
data/lib/product_spy.rb
ADDED
@@ -0,0 +1,54 @@
|
|
1
|
+
require 'singleton'
|
2
|
+
require 'addressable/uri'
|
3
|
+
require 'product_spy/version'
|
4
|
+
require 'product_spy/configuration'
|
5
|
+
require 'product_spy/host'
|
6
|
+
|
7
|
+
module ProductSpy
|
8
|
+
setup do |config|
|
9
|
+
config.host 'www.amazon.de', :aliases => ['amazon.de'] do |host|
|
10
|
+
# ** Mobile
|
11
|
+
# http://www.amazon.de/gp/aw/d/B004O9DF7I/ref=aw_d_var_2nd_sports_img?vs=1
|
12
|
+
# http://www.amazon.de/gp/aw/B000K7BELW/ref=aw_imgblk_0?h=356&ie=UTF8&selIdx=0&tag=viddleit-21&w=320
|
13
|
+
host.parse /^http[s]{0,1}:\/\/(www\.|)amazon.de\/gp\/aw(\/d|)\/([A-Z0-9]{10})(\/.*|)$/, [3]
|
14
|
+
|
15
|
+
# ** Desktop
|
16
|
+
# http://www.amazon.de/Hauck-662984-Hochstuhl-Alpha-natur/dp/B000K7BELW/ref=sr_1_2?s=baby&ie=UTF8&qid=1360979509&sr=1-2
|
17
|
+
# http://www.amazon.de/dp/B000K7BELW/
|
18
|
+
host.parse /^http[s]{0,1}:\/\/(www\.|)amazon.de(\/.*?|)\/dp\/([A-Z0-9]{10})(\/.*|)$/, [3]
|
19
|
+
|
20
|
+
host.build :default, 'https://www.amazon.de/dp/:1'
|
21
|
+
host.build :mobile, 'https://www.amazon.de/gp/aw/d/:1'
|
22
|
+
end
|
23
|
+
end
|
24
|
+
|
25
|
+
# Build the url for a given host and primary key
|
26
|
+
#
|
27
|
+
# Example
|
28
|
+
# =======
|
29
|
+
#
|
30
|
+
# ProductSpy.build('amazon.de', ['B004O9DF6O']) # => https://www.amazon.de/dp/B004O9DF6O
|
31
|
+
#
|
32
|
+
def self.build(host, pk, options = {})
|
33
|
+
options = {
|
34
|
+
:type => :default
|
35
|
+
}.merge(options)
|
36
|
+
|
37
|
+
host = Configuration.instance.hosts[host.to_sym]
|
38
|
+
host.make_url(pk, options)
|
39
|
+
end
|
40
|
+
|
41
|
+
# Get the primary key of a given url
|
42
|
+
#
|
43
|
+
# Example
|
44
|
+
# =======
|
45
|
+
#
|
46
|
+
# ProductSpy.parse('https://www.amazon.de/dp/B004O9DF6O') => ['www.amazon.de', ['B004O9DF6O']]
|
47
|
+
#
|
48
|
+
def self.parse(url)
|
49
|
+
uri = Addressable::URI.parse(url)
|
50
|
+
host = Configuration.instance.hosts[uri.host.downcase.to_sym]
|
51
|
+
return nil if host.nil?
|
52
|
+
[host.host_name.downcase, host.make_pk(url)]
|
53
|
+
end
|
54
|
+
end
|
data/product_spy.gemspec
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
# -*- encoding: utf-8 -*-
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'product_spy/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |gem|
|
7
|
+
gem.name = "product_spy"
|
8
|
+
gem.version = ProductSpy::VERSION
|
9
|
+
gem.authors = ["Paul Spieker"]
|
10
|
+
gem.email = ["p.spieker@duenos.de"]
|
11
|
+
gem.description = %q{ProductSpy is made for parsing product URLs, i.e. Amazon-URLs, to get the product keys and creating product URLs based on these keys. This can be used to identify products based on the url or just to clean up product URLs.}
|
12
|
+
gem.summary = %q{ProductSpy is made for parsing product URLs, i.e. Amazon-URLs, to get the product keys and creating product URLs based on these keys}
|
13
|
+
gem.homepage = "https://github.com/spieker/product_spy"
|
14
|
+
|
15
|
+
gem.files = `git ls-files`.split($/)
|
16
|
+
gem.executables = gem.files.grep(%r{^bin/}).map{ |f| File.basename(f) }
|
17
|
+
gem.test_files = gem.files.grep(%r{^(test|spec|features)/})
|
18
|
+
gem.require_paths = ["lib"]
|
19
|
+
|
20
|
+
gem.add_dependency 'addressable'
|
21
|
+
end
|
data/spec/amazon_spec.rb
ADDED
@@ -0,0 +1,54 @@
|
|
1
|
+
require 'spec_helper'
|
2
|
+
describe ProductSpy, 'amazon' do
|
3
|
+
context 'parse url' do
|
4
|
+
it 'parses: https://www.amazon.de/dp/B000K7BELW' do
|
5
|
+
host, pk = ProductSpy.parse('https://www.amazon.de/dp/B000K7BELW')
|
6
|
+
host.should == 'www.amazon.de'
|
7
|
+
pk.should == ['B000K7BELW']
|
8
|
+
end
|
9
|
+
|
10
|
+
it 'parses: https://www.amazon.de/dp/B000K7BELW/' do
|
11
|
+
host, pk = ProductSpy.parse('https://www.amazon.de/dp/B000K7BELW/')
|
12
|
+
host.should == 'www.amazon.de'
|
13
|
+
pk.should == ['B000K7BELW']
|
14
|
+
end
|
15
|
+
|
16
|
+
it 'parses: http://www.amazon.de/gp/aw/d/B004O9DF6O/ref=s9_simh_awgw_d1_g200_i0/279-4049004-9468652?aid=aw_gw&apid=317822427&arc=1201&arid=13W5CTR69XS38DGRS4HQ&asn=center-6&pf_rd_i=aw_gw&pf_rd_m=A3JWKAKR8XB7XF&pf_rd_p=317822427&pf_rd_r=13W5CTR69XS38DGRS4HQ&pf_rd_s=center-6&pf_rd_t=1201' do
|
17
|
+
host, pk = ProductSpy.parse('http://www.amazon.de/gp/aw/d/B004O9DF6O/ref=s9_simh_awgw_d1_g200_i0/279-4049004-9468652?aid=aw_gw&apid=317822427&arc=1201&arid=13W5CTR69XS38DGRS4HQ&asn=center-6&pf_rd_i=aw_gw&pf_rd_m=A3JWKAKR8XB7XF&pf_rd_p=317822427&pf_rd_r=13W5CTR69XS38DGRS4HQ&pf_rd_s=center-6&pf_rd_t=1201')
|
18
|
+
host.should == 'www.amazon.de'
|
19
|
+
pk.should == ['B004O9DF6O']
|
20
|
+
end
|
21
|
+
|
22
|
+
it 'parses: http://www.amazon.de/Hauck-662984-Hochstuhl-Alpha-natur/dp/B000K7BELW/ref=sr_1_2?s=baby&ie=UTF8&qid=1360983324&sr=1-2' do
|
23
|
+
host, pk = ProductSpy.parse('http://www.amazon.de/Hauck-662984-Hochstuhl-Alpha-natur/dp/B000K7BELW/ref=sr_1_2?s=baby&ie=UTF8&qid=1360983324&sr=1-2')
|
24
|
+
host.should == 'www.amazon.de'
|
25
|
+
pk.should == ['B000K7BELW']
|
26
|
+
end
|
27
|
+
end
|
28
|
+
|
29
|
+
context 'build url' do
|
30
|
+
it 'returns: https://www.amazon.de/dp/B000K7BELW' do
|
31
|
+
ProductSpy.build('www.amazon.de', ['B000K7BELW']).should == 'https://www.amazon.de/dp/B000K7BELW'
|
32
|
+
end
|
33
|
+
|
34
|
+
it 'returns: https://www.amazon.de/gp/aw/d/B000K7BELW' do
|
35
|
+
ProductSpy.build('www.amazon.de', ['B000K7BELW'], :type => 'mobile').should == 'https://www.amazon.de/gp/aw/d/B000K7BELW'
|
36
|
+
end
|
37
|
+
end
|
38
|
+
|
39
|
+
context 'aliases' do
|
40
|
+
context 'parse url' do
|
41
|
+
it 'parses: https://amazon.de/dp/B000K7BELW' do
|
42
|
+
host, pk = ProductSpy.parse('https://www.amazon.de/dp/B000K7BELW')
|
43
|
+
host.should == 'www.amazon.de'
|
44
|
+
pk.should == ['B000K7BELW']
|
45
|
+
end
|
46
|
+
end
|
47
|
+
|
48
|
+
context 'build url' do
|
49
|
+
it 'returns: https://www.amazon.de/dp/B000K7BELW' do
|
50
|
+
ProductSpy.build('amazon.de', ['B000K7BELW']).should == 'https://www.amazon.de/dp/B000K7BELW'
|
51
|
+
end
|
52
|
+
end
|
53
|
+
end
|
54
|
+
end
|
data/spec/spec_helper.rb
ADDED
metadata
ADDED
@@ -0,0 +1,81 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: product_spy
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
prerelease:
|
6
|
+
platform: ruby
|
7
|
+
authors:
|
8
|
+
- Paul Spieker
|
9
|
+
autorequire:
|
10
|
+
bindir: bin
|
11
|
+
cert_chain: []
|
12
|
+
date: 2013-02-16 00:00:00.000000000 Z
|
13
|
+
dependencies:
|
14
|
+
- !ruby/object:Gem::Dependency
|
15
|
+
name: addressable
|
16
|
+
requirement: !ruby/object:Gem::Requirement
|
17
|
+
none: false
|
18
|
+
requirements:
|
19
|
+
- - ! '>='
|
20
|
+
- !ruby/object:Gem::Version
|
21
|
+
version: '0'
|
22
|
+
type: :runtime
|
23
|
+
prerelease: false
|
24
|
+
version_requirements: !ruby/object:Gem::Requirement
|
25
|
+
none: false
|
26
|
+
requirements:
|
27
|
+
- - ! '>='
|
28
|
+
- !ruby/object:Gem::Version
|
29
|
+
version: '0'
|
30
|
+
description: ProductSpy is made for parsing product URLs, i.e. Amazon-URLs, to get
|
31
|
+
the product keys and creating product URLs based on these keys. This can be used
|
32
|
+
to identify products based on the url or just to clean up product URLs.
|
33
|
+
email:
|
34
|
+
- p.spieker@duenos.de
|
35
|
+
executables: []
|
36
|
+
extensions: []
|
37
|
+
extra_rdoc_files: []
|
38
|
+
files:
|
39
|
+
- .gitignore
|
40
|
+
- .rspec
|
41
|
+
- .travis.yml
|
42
|
+
- Gemfile
|
43
|
+
- LICENSE.txt
|
44
|
+
- README.md
|
45
|
+
- Rakefile
|
46
|
+
- lib/product_spy.rb
|
47
|
+
- lib/product_spy/configuration.rb
|
48
|
+
- lib/product_spy/host.rb
|
49
|
+
- lib/product_spy/version.rb
|
50
|
+
- product_spy.gemspec
|
51
|
+
- spec/amazon_spec.rb
|
52
|
+
- spec/spec_helper.rb
|
53
|
+
homepage: https://github.com/spieker/product_spy
|
54
|
+
licenses: []
|
55
|
+
post_install_message:
|
56
|
+
rdoc_options: []
|
57
|
+
require_paths:
|
58
|
+
- lib
|
59
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
60
|
+
none: false
|
61
|
+
requirements:
|
62
|
+
- - ! '>='
|
63
|
+
- !ruby/object:Gem::Version
|
64
|
+
version: '0'
|
65
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
66
|
+
none: false
|
67
|
+
requirements:
|
68
|
+
- - ! '>='
|
69
|
+
- !ruby/object:Gem::Version
|
70
|
+
version: '0'
|
71
|
+
requirements: []
|
72
|
+
rubyforge_project:
|
73
|
+
rubygems_version: 1.8.24
|
74
|
+
signing_key:
|
75
|
+
specification_version: 3
|
76
|
+
summary: ProductSpy is made for parsing product URLs, i.e. Amazon-URLs, to get the
|
77
|
+
product keys and creating product URLs based on these keys
|
78
|
+
test_files:
|
79
|
+
- spec/amazon_spec.rb
|
80
|
+
- spec/spec_helper.rb
|
81
|
+
has_rdoc:
|