microdata 0.0.1
Sign up to get free protection for your applications and to get access to all the features.
- data/.gitignore +17 -0
- data/Gemfile +4 -0
- data/LICENSE.txt +22 -0
- data/README.md +41 -0
- data/Rakefile +10 -0
- data/bin/microdata.rb +8 -0
- data/lib/microdata.rb +42 -0
- data/lib/microdata/document.rb +22 -0
- data/lib/microdata/item.rb +65 -0
- data/lib/microdata/itemprop.rb +91 -0
- data/lib/microdata/version.rb +3 -0
- data/microdata.gemspec +25 -0
- data/test/data/example.html +22 -0
- data/test/test_helper.rb +2 -0
- data/test/test_parse.rb +36 -0
- metadata +114 -0
data/.gitignore
ADDED
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2013 Jason Ronallo
|
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 +1,41 @@
|
|
1
|
+
# Microdata
|
2
|
+
|
3
|
+
Ruby library for extracting HTML5 Microdata
|
4
|
+
|
5
|
+
## Story
|
6
|
+
|
7
|
+
Most of the code here was extracted from [Mida](https://github.com/LawrenceWoodman/mida) by Lawrence Woodman. This was done in order to have a simpler, more generic Microdata parser without all the vocabulary awareness and other features. This gem is also tested under Ruby 1.9.3 and Ruby 2.0.0, though it could be better tested.
|
8
|
+
|
9
|
+
## Installation
|
10
|
+
|
11
|
+
This library has not been released to RubyGems.org yet, but when it is the intention is to have it install with the following.
|
12
|
+
|
13
|
+
Add this line to your application's Gemfile:
|
14
|
+
|
15
|
+
gem 'microdata'
|
16
|
+
|
17
|
+
And then execute:
|
18
|
+
|
19
|
+
$ bundle
|
20
|
+
|
21
|
+
Or install it yourself as:
|
22
|
+
|
23
|
+
$ gem install microdata
|
24
|
+
|
25
|
+
## Usage
|
26
|
+
|
27
|
+
The commandline tool microdata.rb can be run like the following:
|
28
|
+
|
29
|
+
```
|
30
|
+
microdata.rb http://d.lib.ncsu.edu/collections/catalog/mc00383-001-ff0006-001-001_0038
|
31
|
+
```
|
32
|
+
|
33
|
+
Output is in pretty JSON format.
|
34
|
+
|
35
|
+
## Contributing
|
36
|
+
|
37
|
+
1. Fork it
|
38
|
+
2. Create your feature branch (`git checkout -b my-new-feature`)
|
39
|
+
3. Commit your changes (`git commit -am 'Add some feature'`)
|
40
|
+
4. Push to the branch (`git push origin my-new-feature`)
|
41
|
+
5. Create new Pull Request
|
data/Rakefile
ADDED
data/bin/microdata.rb
ADDED
data/lib/microdata.rb
ADDED
@@ -0,0 +1,42 @@
|
|
1
|
+
require "microdata/version"
|
2
|
+
require "nokogiri"
|
3
|
+
require "microdata/item"
|
4
|
+
require "microdata/document"
|
5
|
+
require "microdata/itemprop"
|
6
|
+
require 'open-uri'
|
7
|
+
require 'json'
|
8
|
+
require 'uri'
|
9
|
+
|
10
|
+
module Microdata
|
11
|
+
|
12
|
+
# PROPERTY_VALUES = {
|
13
|
+
# meta: 'content',
|
14
|
+
# audio: 'src',
|
15
|
+
# embed: 'src',
|
16
|
+
# iframe: 'src',
|
17
|
+
# img: 'src',
|
18
|
+
# source: 'src',
|
19
|
+
# video: 'src',
|
20
|
+
# a: 'href',
|
21
|
+
# area: 'href',
|
22
|
+
# link: 'href',
|
23
|
+
# object: 'data',
|
24
|
+
# time: 'datetime'
|
25
|
+
# }
|
26
|
+
|
27
|
+
def self.get_items(location)
|
28
|
+
content = open(location)
|
29
|
+
page_url = location
|
30
|
+
Microdata::Document.new(content, page_url).extract_items
|
31
|
+
end
|
32
|
+
|
33
|
+
def self.to_json(location)
|
34
|
+
items = get_items(location)
|
35
|
+
hash = {}
|
36
|
+
hash[:items] = items.map do |item|
|
37
|
+
item.to_hash
|
38
|
+
end
|
39
|
+
JSON.pretty_generate hash
|
40
|
+
end
|
41
|
+
|
42
|
+
end
|
@@ -0,0 +1,22 @@
|
|
1
|
+
module Microdata
|
2
|
+
class Document
|
3
|
+
|
4
|
+
attr_reader :items
|
5
|
+
|
6
|
+
def initialize(content, page_url=nil)
|
7
|
+
@doc = Nokogiri::HTML(content)
|
8
|
+
@page_url = page_url
|
9
|
+
@items = extract_items
|
10
|
+
end
|
11
|
+
|
12
|
+
def extract_items
|
13
|
+
itemscopes = @doc.search('//*[@itemscope and not(@itemprop)]')
|
14
|
+
return nil unless itemscopes
|
15
|
+
|
16
|
+
itemscopes.collect do |itemscope|
|
17
|
+
Item.new(itemscope, @page_url)
|
18
|
+
end
|
19
|
+
end
|
20
|
+
|
21
|
+
end
|
22
|
+
end
|
@@ -0,0 +1,65 @@
|
|
1
|
+
module Microdata
|
2
|
+
class Item
|
3
|
+
attr_reader :type, :properties, :id
|
4
|
+
|
5
|
+
def initialize(top_node, page_url)
|
6
|
+
@top_node = top_node
|
7
|
+
@type = extract_itemtype
|
8
|
+
@id = extract_itemid
|
9
|
+
@properties = {}
|
10
|
+
@page_url = page_url
|
11
|
+
parse_elements(extract_elements(@top_node))
|
12
|
+
end
|
13
|
+
|
14
|
+
def to_hash
|
15
|
+
hash = {}
|
16
|
+
hash[:id] = id if id
|
17
|
+
hash[:type] = type
|
18
|
+
hash[:properties] = {}
|
19
|
+
properties.each do |name, values|
|
20
|
+
final_values = values.map do |value|
|
21
|
+
if value.is_a?(Item)
|
22
|
+
value.to_hash
|
23
|
+
else
|
24
|
+
value
|
25
|
+
end
|
26
|
+
end
|
27
|
+
hash[:properties][name] = final_values
|
28
|
+
end
|
29
|
+
hash
|
30
|
+
end
|
31
|
+
|
32
|
+
private
|
33
|
+
|
34
|
+
def extract_elements(node)
|
35
|
+
node.search('./*')
|
36
|
+
end
|
37
|
+
|
38
|
+
def extract_itemid
|
39
|
+
(value = @top_node.attribute('itemid')) ? value.value : nil
|
40
|
+
end
|
41
|
+
|
42
|
+
def extract_itemtype
|
43
|
+
(value = @top_node.attribute('itemtype')) ? value.value.split(' ') : nil
|
44
|
+
end
|
45
|
+
|
46
|
+
def parse_elements(elements)
|
47
|
+
elements.each {|element| parse_element(element)}
|
48
|
+
end
|
49
|
+
|
50
|
+
def parse_element(element)
|
51
|
+
itemscope = element.attribute('itemscope')
|
52
|
+
itemprop = element.attribute('itemprop')
|
53
|
+
internal_elements = extract_elements(element)
|
54
|
+
add_itemprop(element) if itemscope || itemprop
|
55
|
+
parse_elements(internal_elements) if internal_elements && !itemscope
|
56
|
+
end
|
57
|
+
|
58
|
+
# Add an 'itemprop' to the properties
|
59
|
+
def add_itemprop(itemprop)
|
60
|
+
properties = Itemprop.parse(itemprop, @page_url)
|
61
|
+
properties.each { |name, value| (@properties[name] ||= []) << value }
|
62
|
+
end
|
63
|
+
|
64
|
+
end
|
65
|
+
end
|
@@ -0,0 +1,91 @@
|
|
1
|
+
module Microdata
|
2
|
+
# Class that parses itemprop elements
|
3
|
+
class Itemprop
|
4
|
+
|
5
|
+
NON_TEXTCONTENT_ELEMENTS = {
|
6
|
+
'a' => 'href', 'area' => 'href',
|
7
|
+
'audio' => 'src', 'embed' => 'src',
|
8
|
+
'iframe' => 'src', 'img' => 'src',
|
9
|
+
'link' => 'href', 'meta' => 'content',
|
10
|
+
'object' => 'data', 'source' => 'src',
|
11
|
+
'time' => 'datetime', 'track' => 'src',
|
12
|
+
'video' => 'src'
|
13
|
+
}
|
14
|
+
|
15
|
+
URL_ATTRIBUTES = ['data', 'href', 'src']
|
16
|
+
|
17
|
+
# A Hash representing the properties.
|
18
|
+
# Hash is of the form {'property name' => 'value'}
|
19
|
+
attr_reader :properties
|
20
|
+
|
21
|
+
# Create a new Itemprop object
|
22
|
+
# [element] The itemprop element to be parsed
|
23
|
+
# [page_url] The url of the page, including filename, used to form
|
24
|
+
# absolute urls
|
25
|
+
def initialize(element, page_url=nil)
|
26
|
+
@element, @page_url = element, page_url
|
27
|
+
@properties = extract_properties
|
28
|
+
end
|
29
|
+
|
30
|
+
# Parse the element and return a hash representing the properties.
|
31
|
+
# Hash is of the form {'property name' => 'value'}
|
32
|
+
# [element] The itemprop element to be parsed
|
33
|
+
# [page_url] The url of the page, including filename, used to form
|
34
|
+
# absolute urls
|
35
|
+
def self.parse(element, page_url=nil)
|
36
|
+
self.new(element, page_url).properties
|
37
|
+
end
|
38
|
+
|
39
|
+
private
|
40
|
+
def extract_properties
|
41
|
+
prop_names = extract_property_names
|
42
|
+
prop_names.each_with_object({}) do |name, memo|
|
43
|
+
memo[name] = extract_property
|
44
|
+
end
|
45
|
+
end
|
46
|
+
|
47
|
+
# This returns an empty string if can't form a valid
|
48
|
+
# absolute url as per the Microdata spec.
|
49
|
+
def make_absolute_url(url)
|
50
|
+
return url unless URI.parse(url).relative?
|
51
|
+
begin
|
52
|
+
URI.parse(@page_url).merge(url).to_s
|
53
|
+
rescue URI::Error
|
54
|
+
url
|
55
|
+
end
|
56
|
+
end
|
57
|
+
|
58
|
+
def non_textcontent_element?(element)
|
59
|
+
NON_TEXTCONTENT_ELEMENTS.has_key?(element)
|
60
|
+
end
|
61
|
+
|
62
|
+
def url_attribute?(attribute)
|
63
|
+
URL_ATTRIBUTES.include?(attribute)
|
64
|
+
end
|
65
|
+
|
66
|
+
def extract_property_names
|
67
|
+
itemprop_attr = @element.attribute('itemprop')
|
68
|
+
itemprop_attr ? itemprop_attr.value.split() : []
|
69
|
+
end
|
70
|
+
|
71
|
+
def extract_property_value
|
72
|
+
element = @element.name
|
73
|
+
if non_textcontent_element?(element)
|
74
|
+
attribute = NON_TEXTCONTENT_ELEMENTS[element]
|
75
|
+
value = @element.attribute(attribute).value
|
76
|
+
url_attribute?(attribute) ? make_absolute_url(value) : value
|
77
|
+
else
|
78
|
+
@element.inner_text.strip
|
79
|
+
end
|
80
|
+
end
|
81
|
+
|
82
|
+
def extract_property
|
83
|
+
if @element.attribute('itemscope')
|
84
|
+
Item.new(@element, @page_url)
|
85
|
+
else
|
86
|
+
extract_property_value
|
87
|
+
end
|
88
|
+
end
|
89
|
+
|
90
|
+
end
|
91
|
+
end
|
data/microdata.gemspec
ADDED
@@ -0,0 +1,25 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'microdata/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "microdata"
|
8
|
+
spec.version = Microdata::VERSION
|
9
|
+
spec.authors = ["Jason Ronallo"]
|
10
|
+
spec.email = ["jronallo@gmail.com"]
|
11
|
+
spec.description = %q{HTML5 Microdata extractor}
|
12
|
+
spec.summary = %q{Ruby library for extracting HTML5 Microdata}
|
13
|
+
spec.homepage = ""
|
14
|
+
spec.license = "MIT"
|
15
|
+
|
16
|
+
spec.files = `git ls-files`.split($/)
|
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_dependency "nokogiri"
|
22
|
+
|
23
|
+
spec.add_development_dependency "bundler", "~> 1.3"
|
24
|
+
spec.add_development_dependency "rake"
|
25
|
+
end
|
@@ -0,0 +1,22 @@
|
|
1
|
+
<!doctype html>
|
2
|
+
<html>
|
3
|
+
<!-- shameless -->
|
4
|
+
<head>
|
5
|
+
<title>Jason Ronallo</title>
|
6
|
+
</head>
|
7
|
+
|
8
|
+
<body>
|
9
|
+
<span itemscope itemtype="http://schema.org/Person"
|
10
|
+
itemid="http://ronallo.com#me">
|
11
|
+
<a itemprop="url" href="http://twitter.com/ronallo">
|
12
|
+
<span itemprop="name">Jason Ronallo</span>
|
13
|
+
</a> is the
|
14
|
+
<span itemprop="jobTitle">Associate Head of Digital Library Initiatives</span> at
|
15
|
+
<span itemprop="affiliation" itemscope itemtype="http://schema.org/Library" itemid="http://lib.ncsu.edu">
|
16
|
+
<span itemprop="name">
|
17
|
+
<a itemprop="url" href="http://www.lib.ncsu.edu">NCSU Libraries</a>
|
18
|
+
</span>
|
19
|
+
</span>.
|
20
|
+
</span>
|
21
|
+
</body>
|
22
|
+
</html>
|
data/test/test_helper.rb
ADDED
data/test/test_parse.rb
ADDED
@@ -0,0 +1,36 @@
|
|
1
|
+
require 'test_helper'
|
2
|
+
|
3
|
+
class TestParse < Test::Unit::TestCase
|
4
|
+
|
5
|
+
def setup
|
6
|
+
@items = Microdata.get_items('test/data/example.html')
|
7
|
+
end
|
8
|
+
|
9
|
+
def test_top_item_type
|
10
|
+
assert_equal ['http://schema.org/Person'], @items.first.type
|
11
|
+
end
|
12
|
+
|
13
|
+
def test_top_item_id
|
14
|
+
assert_equal "http://ronallo.com#me", @items.first.id
|
15
|
+
end
|
16
|
+
|
17
|
+
def test_top_item_properties
|
18
|
+
properties = @items.first.properties
|
19
|
+
assert_equal ["Jason Ronallo"], properties['name']
|
20
|
+
assert_equal ["http://twitter.com/ronallo"], properties['url']
|
21
|
+
assert_equal ["Associate Head of Digital Library Initiatives"], properties['jobTitle']
|
22
|
+
end
|
23
|
+
|
24
|
+
def test_nested_item
|
25
|
+
item = @items.first.properties['affiliation'][0]
|
26
|
+
assert_equal ['http://schema.org/Library'], item.type
|
27
|
+
assert_equal "http://lib.ncsu.edu", item.id
|
28
|
+
end
|
29
|
+
|
30
|
+
def test_nested_item_properties
|
31
|
+
properties = @items.first.properties['affiliation'][0].properties
|
32
|
+
assert_equal ['NCSU Libraries'], properties['name']
|
33
|
+
assert_equal ['http://www.lib.ncsu.edu'], properties['url']
|
34
|
+
end
|
35
|
+
|
36
|
+
end
|
metadata
ADDED
@@ -0,0 +1,114 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: microdata
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
prerelease:
|
6
|
+
platform: ruby
|
7
|
+
authors:
|
8
|
+
- Jason Ronallo
|
9
|
+
autorequire:
|
10
|
+
bindir: bin
|
11
|
+
cert_chain: []
|
12
|
+
date: 2013-03-16 00:00:00.000000000 Z
|
13
|
+
dependencies:
|
14
|
+
- !ruby/object:Gem::Dependency
|
15
|
+
name: nokogiri
|
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
|
+
- !ruby/object:Gem::Dependency
|
31
|
+
name: bundler
|
32
|
+
requirement: !ruby/object:Gem::Requirement
|
33
|
+
none: false
|
34
|
+
requirements:
|
35
|
+
- - ~>
|
36
|
+
- !ruby/object:Gem::Version
|
37
|
+
version: '1.3'
|
38
|
+
type: :development
|
39
|
+
prerelease: false
|
40
|
+
version_requirements: !ruby/object:Gem::Requirement
|
41
|
+
none: false
|
42
|
+
requirements:
|
43
|
+
- - ~>
|
44
|
+
- !ruby/object:Gem::Version
|
45
|
+
version: '1.3'
|
46
|
+
- !ruby/object:Gem::Dependency
|
47
|
+
name: rake
|
48
|
+
requirement: !ruby/object:Gem::Requirement
|
49
|
+
none: false
|
50
|
+
requirements:
|
51
|
+
- - ! '>='
|
52
|
+
- !ruby/object:Gem::Version
|
53
|
+
version: '0'
|
54
|
+
type: :development
|
55
|
+
prerelease: false
|
56
|
+
version_requirements: !ruby/object:Gem::Requirement
|
57
|
+
none: false
|
58
|
+
requirements:
|
59
|
+
- - ! '>='
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '0'
|
62
|
+
description: HTML5 Microdata extractor
|
63
|
+
email:
|
64
|
+
- jronallo@gmail.com
|
65
|
+
executables:
|
66
|
+
- microdata.rb
|
67
|
+
extensions: []
|
68
|
+
extra_rdoc_files: []
|
69
|
+
files:
|
70
|
+
- .gitignore
|
71
|
+
- Gemfile
|
72
|
+
- LICENSE.txt
|
73
|
+
- README.md
|
74
|
+
- Rakefile
|
75
|
+
- bin/microdata.rb
|
76
|
+
- lib/microdata.rb
|
77
|
+
- lib/microdata/document.rb
|
78
|
+
- lib/microdata/item.rb
|
79
|
+
- lib/microdata/itemprop.rb
|
80
|
+
- lib/microdata/version.rb
|
81
|
+
- microdata.gemspec
|
82
|
+
- test/data/example.html
|
83
|
+
- test/test_helper.rb
|
84
|
+
- test/test_parse.rb
|
85
|
+
homepage: ''
|
86
|
+
licenses:
|
87
|
+
- MIT
|
88
|
+
post_install_message:
|
89
|
+
rdoc_options: []
|
90
|
+
require_paths:
|
91
|
+
- lib
|
92
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
93
|
+
none: false
|
94
|
+
requirements:
|
95
|
+
- - ! '>='
|
96
|
+
- !ruby/object:Gem::Version
|
97
|
+
version: '0'
|
98
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
99
|
+
none: false
|
100
|
+
requirements:
|
101
|
+
- - ! '>='
|
102
|
+
- !ruby/object:Gem::Version
|
103
|
+
version: '0'
|
104
|
+
requirements: []
|
105
|
+
rubyforge_project:
|
106
|
+
rubygems_version: 1.8.25
|
107
|
+
signing_key:
|
108
|
+
specification_version: 3
|
109
|
+
summary: Ruby library for extracting HTML5 Microdata
|
110
|
+
test_files:
|
111
|
+
- test/data/example.html
|
112
|
+
- test/test_helper.rb
|
113
|
+
- test/test_parse.rb
|
114
|
+
has_rdoc:
|