microformat 0.0.2 → 0.0.3
Sign up to get free protection for your applications and to get access to all the features.
- data/README.md +8 -35
- data/lib/microformat/parser.rb +7 -1
- data/lib/microformat/version.rb +1 -1
- data/spec/microformat/parser_spec.rb +38 -0
- metadata +9 -3
data/README.md
CHANGED
|
@@ -2,6 +2,13 @@
|
|
|
2
2
|
|
|
3
3
|
Reads Microformats from HTML documents
|
|
4
4
|
|
|
5
|
+
[![Build Status][2]][1] [![Code Climate][3]][4]
|
|
6
|
+
|
|
7
|
+
[1]: http://travis-ci.org/platformq/microformat
|
|
8
|
+
[2]: https://secure.travis-ci.org/platformq/microformat.png?branch=master
|
|
9
|
+
[3]: https://codeclimate.com/badge.png
|
|
10
|
+
[4]: https://codeclimate.com/github/platformq/microformat
|
|
11
|
+
|
|
5
12
|
## Installation
|
|
6
13
|
|
|
7
14
|
Add this line to your application's Gemfile:
|
|
@@ -34,45 +41,11 @@ require "nokogiri"
|
|
|
34
41
|
|
|
35
42
|
html = "<html>...</html>"
|
|
36
43
|
doc = Nokogiri::HTML(html)
|
|
37
|
-
element = doc.css("
|
|
44
|
+
element = doc.css("body")
|
|
38
45
|
Microformat.parse(element)
|
|
39
46
|
# => Microformat::Collection
|
|
40
47
|
```
|
|
41
48
|
|
|
42
|
-
Collections act as standard Ruby arrays, however they provide additional filtering methods:
|
|
43
|
-
|
|
44
|
-
```ruby
|
|
45
|
-
collection = Microformat.parse(element)
|
|
46
|
-
# => Microformat::Collection (of all microformat objects)
|
|
47
|
-
collection.filter(Microformat::Review, Microformat::ReviewAggregate)
|
|
48
|
-
# => Microformat::Collection (of only hreviews and hreview-aggregates)
|
|
49
|
-
```
|
|
50
|
-
|
|
51
|
-
You can also improve performance by passing a set of formats to the initial parse:
|
|
52
|
-
|
|
53
|
-
```ruby
|
|
54
|
-
formats = [Microformat::Review, Microformat::Card]
|
|
55
|
-
Microformat.parse(element, filter: formats)
|
|
56
|
-
# => Microformat::Collection (of only hreviews and hcards)
|
|
57
|
-
```
|
|
58
|
-
|
|
59
|
-
You can specify a limit (should you only want the first or a few objects)
|
|
60
|
-
|
|
61
|
-
```ruby
|
|
62
|
-
Microformat.parse(element, limit: 3)
|
|
63
|
-
# => Microformat::Collection (of max size 3)
|
|
64
|
-
```
|
|
65
|
-
|
|
66
|
-
You can also parse a Nokogiri element to return an object of the first found exact Microformat:
|
|
67
|
-
|
|
68
|
-
```ruby
|
|
69
|
-
html = "<html>...</html>"
|
|
70
|
-
doc = Nokogiri::HTML(html)
|
|
71
|
-
element = doc.css(".hcard")
|
|
72
|
-
Microformat::Card.parse(element)
|
|
73
|
-
# => Microformat::Card instance
|
|
74
|
-
```
|
|
75
|
-
|
|
76
49
|
## Contributing
|
|
77
50
|
|
|
78
51
|
1. Fork it
|
data/lib/microformat/parser.rb
CHANGED
|
@@ -42,7 +42,13 @@ module Microformat
|
|
|
42
42
|
|
|
43
43
|
private
|
|
44
44
|
def elements
|
|
45
|
-
@elements ||=
|
|
45
|
+
@elements ||= [].tap do |elements|
|
|
46
|
+
while doc.css(selectors.join(", ")).length > 0
|
|
47
|
+
node = doc.css(selectors.join(", ")).first
|
|
48
|
+
node.remove
|
|
49
|
+
elements.push node
|
|
50
|
+
end
|
|
51
|
+
end
|
|
46
52
|
end
|
|
47
53
|
end
|
|
48
54
|
end
|
data/lib/microformat/version.rb
CHANGED
|
@@ -30,6 +30,18 @@ describe Microformat::Parser do
|
|
|
30
30
|
</body></html>)
|
|
31
31
|
end
|
|
32
32
|
|
|
33
|
+
let(:nested_review_html) do
|
|
34
|
+
%Q(<html><body>
|
|
35
|
+
<div class="hreview">
|
|
36
|
+
<div class="summary">It's good</div>
|
|
37
|
+
<div class="reviewer">
|
|
38
|
+
<p class="fn">Dave</p>
|
|
39
|
+
<div class="hreview"></div>
|
|
40
|
+
</div>
|
|
41
|
+
</div>
|
|
42
|
+
</body></html>)
|
|
43
|
+
end
|
|
44
|
+
|
|
33
45
|
context "given a HTML string" do
|
|
34
46
|
let(:doc) { html }
|
|
35
47
|
|
|
@@ -79,5 +91,31 @@ describe Microformat::Parser do
|
|
|
79
91
|
end
|
|
80
92
|
end
|
|
81
93
|
end
|
|
94
|
+
|
|
95
|
+
context "given a HTML document with nested microformats" do
|
|
96
|
+
let(:doc) { Nokogiri::HTML(nested_review_html) }
|
|
97
|
+
|
|
98
|
+
it "should return a collection with one object" do
|
|
99
|
+
expect(subject.size).to eq 1
|
|
100
|
+
end
|
|
101
|
+
|
|
102
|
+
describe "the returned Microformat object" do
|
|
103
|
+
subject do
|
|
104
|
+
Microformat::Parser.parse(doc).first
|
|
105
|
+
end
|
|
106
|
+
|
|
107
|
+
it "should be a Microformat::Review" do
|
|
108
|
+
expect(subject).to be_kind_of(Microformat::Review)
|
|
109
|
+
end
|
|
110
|
+
|
|
111
|
+
it "should return the summary" do
|
|
112
|
+
expect(subject.summary.value).to eq "It's good"
|
|
113
|
+
end
|
|
114
|
+
|
|
115
|
+
it "should return the reviewer's full name" do
|
|
116
|
+
expect(subject.reviewer.fn.value).to eq "Dave"
|
|
117
|
+
end
|
|
118
|
+
end
|
|
119
|
+
end
|
|
82
120
|
end
|
|
83
121
|
end
|
metadata
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: microformat
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.0.
|
|
4
|
+
version: 0.0.3
|
|
5
5
|
prerelease:
|
|
6
6
|
platform: ruby
|
|
7
7
|
authors:
|
|
@@ -9,7 +9,7 @@ authors:
|
|
|
9
9
|
autorequire:
|
|
10
10
|
bindir: bin
|
|
11
11
|
cert_chain: []
|
|
12
|
-
date: 2012-
|
|
12
|
+
date: 2012-11-29 00:00:00.000000000 Z
|
|
13
13
|
dependencies:
|
|
14
14
|
- !ruby/object:Gem::Dependency
|
|
15
15
|
name: nokogiri
|
|
@@ -122,15 +122,21 @@ required_ruby_version: !ruby/object:Gem::Requirement
|
|
|
122
122
|
- - ! '>='
|
|
123
123
|
- !ruby/object:Gem::Version
|
|
124
124
|
version: '0'
|
|
125
|
+
segments:
|
|
126
|
+
- 0
|
|
127
|
+
hash: -2467505088189709361
|
|
125
128
|
required_rubygems_version: !ruby/object:Gem::Requirement
|
|
126
129
|
none: false
|
|
127
130
|
requirements:
|
|
128
131
|
- - ! '>='
|
|
129
132
|
- !ruby/object:Gem::Version
|
|
130
133
|
version: '0'
|
|
134
|
+
segments:
|
|
135
|
+
- 0
|
|
136
|
+
hash: -2467505088189709361
|
|
131
137
|
requirements: []
|
|
132
138
|
rubyforge_project:
|
|
133
|
-
rubygems_version: 1.8.
|
|
139
|
+
rubygems_version: 1.8.24
|
|
134
140
|
signing_key:
|
|
135
141
|
specification_version: 3
|
|
136
142
|
summary: Reads Microformats from HTML documents
|