ruby-readability 0.1.0
Sign up to get free protection for your applications and to get access to all the features.
- data/.document +5 -0
- data/.gitignore +21 -0
- data/README +9 -0
- data/Rakefile +45 -0
- data/VERSION +1 -0
- data/bin/readability +13 -0
- data/lib/readability.rb +295 -0
- data/lib/readability_old.rb +74 -0
- data/spec/fixtures/cant_read.html +426 -0
- data/spec/fixtures/sample.html +1198 -0
- data/spec/fixtures/samples/channel4-1-fragments.rb +14 -0
- data/spec/fixtures/samples/channel4-1.html +1330 -0
- data/spec/fixtures/samples/globemail-ottawa-cuts-fragments.rb +31 -0
- data/spec/fixtures/samples/globemail-ottawa-cuts.html +2410 -0
- data/spec/fixtures/should_not_truncate.txt +1077 -0
- data/spec/readability_spec.rb +180 -0
- data/spec/spec_helper.rb +10 -0
- metadata +94 -0
@@ -0,0 +1,180 @@
|
|
1
|
+
require File.expand_path(File.join(File.dirname(__FILE__), "spec_helper"))
|
2
|
+
|
3
|
+
describe Readability do
|
4
|
+
before do
|
5
|
+
@simple_html_fixture = <<-HTML
|
6
|
+
<html>
|
7
|
+
<head>
|
8
|
+
<title>title!</title>
|
9
|
+
</head>
|
10
|
+
<body class='comment'>
|
11
|
+
<div>
|
12
|
+
<p class='comment'>a comment</p>
|
13
|
+
<div class='comment' id='body'>real content</div>
|
14
|
+
<div id="contains_blockquote"><blockquote>something in a table</blockquote></div>
|
15
|
+
</div>
|
16
|
+
</body>
|
17
|
+
</html>
|
18
|
+
HTML
|
19
|
+
end
|
20
|
+
|
21
|
+
describe "transformMisusedDivsIntoParagraphs" do
|
22
|
+
before do
|
23
|
+
@doc = Readability::Document.new(@simple_html_fixture)
|
24
|
+
@doc.transform_misused_divs_into_paragraphs!
|
25
|
+
end
|
26
|
+
|
27
|
+
it "should transform divs containing no block elements into <p>s" do
|
28
|
+
@doc.html.css("#body").first.name.should == "p"
|
29
|
+
end
|
30
|
+
|
31
|
+
it "should not transform divs that contain block elements" do
|
32
|
+
@doc.html.css("#contains_blockquote").first.name.should == "div"
|
33
|
+
end
|
34
|
+
end
|
35
|
+
|
36
|
+
describe "score_node" do
|
37
|
+
before do
|
38
|
+
@doc = Readability::Document.new(<<-HTML)
|
39
|
+
<html>
|
40
|
+
<body>
|
41
|
+
<div id='elem1'>
|
42
|
+
<p>some content</p>
|
43
|
+
</div>
|
44
|
+
<th id='elem2'>
|
45
|
+
<p>some other content</p>
|
46
|
+
</th>
|
47
|
+
</body>
|
48
|
+
</html>
|
49
|
+
HTML
|
50
|
+
@elem1 = @doc.html.css("#elem1").first
|
51
|
+
@elem2 = @doc.html.css("#elem2").first
|
52
|
+
end
|
53
|
+
|
54
|
+
it "should like <div>s more than <th>s" do
|
55
|
+
@doc.score_node(@elem1)[:content_score].should > @doc.score_node(@elem2)[:content_score]
|
56
|
+
end
|
57
|
+
|
58
|
+
it "should like classes like text more than classes like comment" do
|
59
|
+
@elem2.name = "div"
|
60
|
+
@doc.score_node(@elem1)[:content_score].should == @doc.score_node(@elem2)[:content_score]
|
61
|
+
@elem1['class'] = "text"
|
62
|
+
@elem2['class'] = "comment"
|
63
|
+
@doc.score_node(@elem1)[:content_score].should > @doc.score_node(@elem2)[:content_score]
|
64
|
+
end
|
65
|
+
end
|
66
|
+
|
67
|
+
describe "remove_unlikely_candidates!" do
|
68
|
+
before do
|
69
|
+
@doc = Readability::Document.new(@simple_html_fixture)
|
70
|
+
@doc.remove_unlikely_candidates!
|
71
|
+
end
|
72
|
+
|
73
|
+
it "should remove things that have class comment" do
|
74
|
+
@doc.html.inner_html.should_not =~ /a comment/
|
75
|
+
end
|
76
|
+
|
77
|
+
it "should not remove body tags" do
|
78
|
+
@doc.html.inner_html.should =~ /<\/body>/
|
79
|
+
end
|
80
|
+
|
81
|
+
it "should not remove things with class comment and id body" do
|
82
|
+
@doc.html.inner_html.should =~ /real content/
|
83
|
+
end
|
84
|
+
end
|
85
|
+
|
86
|
+
describe "score_paragraphs" do
|
87
|
+
before(:each) do
|
88
|
+
@doc = Readability::Document.new(<<-HTML)
|
89
|
+
<html>
|
90
|
+
<head>
|
91
|
+
<title>title!</title>
|
92
|
+
</head>
|
93
|
+
<body id="body">
|
94
|
+
<div id="div1">
|
95
|
+
<div id="div2>
|
96
|
+
<p id="some_comment">a comment</p>
|
97
|
+
</div>
|
98
|
+
<p id="some_text">some text</p>
|
99
|
+
</div>
|
100
|
+
<div id="div3">
|
101
|
+
<p id="some_text2">some more text</p>
|
102
|
+
</div>
|
103
|
+
</body>
|
104
|
+
</html>
|
105
|
+
HTML
|
106
|
+
@candidates = @doc.score_paragraphs(0)
|
107
|
+
end
|
108
|
+
|
109
|
+
it "should score elements in the document" do
|
110
|
+
@candidates.values.length.should == 3
|
111
|
+
end
|
112
|
+
|
113
|
+
it "should prefer the body in this particular example" do
|
114
|
+
@candidates.values.sort { |a, b|
|
115
|
+
b[:content_score] <=> a[:content_score]
|
116
|
+
}.first[:elem][:id].should == "body"
|
117
|
+
end
|
118
|
+
end
|
119
|
+
|
120
|
+
describe "the cant_read.html fixture" do
|
121
|
+
it "should work on the cant_read.html fixture with some allowed tags" do
|
122
|
+
allowed_tags = %w[div span table tr td p i strong u h1 h2 h3 h4 pre code br a]
|
123
|
+
allowed_attributes = %w[href]
|
124
|
+
html = File.read(File.dirname(__FILE__) + "/fixtures/cant_read.html")
|
125
|
+
Readability::Document.new(html, :tags => allowed_tags, :attributes => allowed_attributes).content.should match(/Can you talk a little about how you developed the looks for the/)
|
126
|
+
end
|
127
|
+
end
|
128
|
+
|
129
|
+
describe "general functionality" do
|
130
|
+
before do
|
131
|
+
@doc = Readability::Document.new("<html><head><title>title!</title></head><body><div><p>Some content</p></div></body>",
|
132
|
+
:min_text_length => 0, :retry_length => 1)
|
133
|
+
end
|
134
|
+
|
135
|
+
it "should return the main page content" do
|
136
|
+
@doc.content.should match("Some content")
|
137
|
+
end
|
138
|
+
end
|
139
|
+
|
140
|
+
describe "ignoring sidebars" do
|
141
|
+
before do
|
142
|
+
@doc = Readability::Document.new("<html><head><title>title!</title></head><body><div><p>Some content</p></div><div class='sidebar'><p>sidebar<p></div></body>",
|
143
|
+
:min_text_length => 0, :retry_length => 1)
|
144
|
+
end
|
145
|
+
|
146
|
+
it "should not return the sidebar" do
|
147
|
+
@doc.content.should_not match("sidebar")
|
148
|
+
end
|
149
|
+
end
|
150
|
+
|
151
|
+
describe "outputs good stuff for known documents" do
|
152
|
+
before do
|
153
|
+
@html_files = Dir.glob(File.dirname(__FILE__) + "/fixtures/samples/*.html")
|
154
|
+
@samples = @html_files.map {|filename| File.basename(filename, '.html') }
|
155
|
+
end
|
156
|
+
|
157
|
+
it "should output expected fragments of text" do
|
158
|
+
|
159
|
+
checks = 0
|
160
|
+
@samples.each do |sample|
|
161
|
+
html = File.read(File.dirname(__FILE__) + "/fixtures/samples/#{sample}.html")
|
162
|
+
doc = Readability::Document.new(html).content
|
163
|
+
|
164
|
+
load "fixtures/samples/#{sample}-fragments.rb"
|
165
|
+
puts "testing #{sample}..."
|
166
|
+
|
167
|
+
$required_fragments.each do |required_text|
|
168
|
+
doc.should include(required_text)
|
169
|
+
checks += 1
|
170
|
+
end
|
171
|
+
|
172
|
+
$excluded_fragments.each do |text_to_avoid|
|
173
|
+
doc.should_not include(text_to_avoid)
|
174
|
+
checks += 1
|
175
|
+
end
|
176
|
+
end
|
177
|
+
puts "Performed #{checks} checks."
|
178
|
+
end
|
179
|
+
end
|
180
|
+
end
|
data/spec/spec_helper.rb
ADDED
metadata
ADDED
@@ -0,0 +1,94 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: ruby-readability
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
prerelease: false
|
5
|
+
segments:
|
6
|
+
- 0
|
7
|
+
- 1
|
8
|
+
- 0
|
9
|
+
version: 0.1.0
|
10
|
+
platform: ruby
|
11
|
+
authors:
|
12
|
+
- Kyle Maxwell
|
13
|
+
autorequire:
|
14
|
+
bindir: bin
|
15
|
+
cert_chain: []
|
16
|
+
|
17
|
+
date: 2010-08-30 00:00:00 -07:00
|
18
|
+
default_executable: readability
|
19
|
+
dependencies:
|
20
|
+
- !ruby/object:Gem::Dependency
|
21
|
+
name: rspec
|
22
|
+
prerelease: false
|
23
|
+
requirement: &id001 !ruby/object:Gem::Requirement
|
24
|
+
requirements:
|
25
|
+
- - ">="
|
26
|
+
- !ruby/object:Gem::Version
|
27
|
+
segments:
|
28
|
+
- 1
|
29
|
+
- 2
|
30
|
+
- 9
|
31
|
+
version: 1.2.9
|
32
|
+
type: :development
|
33
|
+
version_requirements: *id001
|
34
|
+
description: ruby-readability
|
35
|
+
email: kmaxwell@twitter.com
|
36
|
+
executables:
|
37
|
+
- readability
|
38
|
+
extensions: []
|
39
|
+
|
40
|
+
extra_rdoc_files:
|
41
|
+
- README
|
42
|
+
files:
|
43
|
+
- .document
|
44
|
+
- .gitignore
|
45
|
+
- README
|
46
|
+
- Rakefile
|
47
|
+
- VERSION
|
48
|
+
- bin/readability
|
49
|
+
- lib/readability.rb
|
50
|
+
- lib/readability_old.rb
|
51
|
+
- spec/fixtures/cant_read.html
|
52
|
+
- spec/fixtures/sample.html
|
53
|
+
- spec/fixtures/samples/channel4-1-fragments.rb
|
54
|
+
- spec/fixtures/samples/channel4-1.html
|
55
|
+
- spec/fixtures/samples/globemail-ottawa-cuts-fragments.rb
|
56
|
+
- spec/fixtures/samples/globemail-ottawa-cuts.html
|
57
|
+
- spec/fixtures/should_not_truncate.txt
|
58
|
+
- spec/readability_spec.rb
|
59
|
+
- spec/spec_helper.rb
|
60
|
+
has_rdoc: true
|
61
|
+
homepage: http://github.com/fizx/ruby-readability
|
62
|
+
licenses: []
|
63
|
+
|
64
|
+
post_install_message:
|
65
|
+
rdoc_options:
|
66
|
+
- --charset=UTF-8
|
67
|
+
require_paths:
|
68
|
+
- lib
|
69
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
70
|
+
requirements:
|
71
|
+
- - ">="
|
72
|
+
- !ruby/object:Gem::Version
|
73
|
+
segments:
|
74
|
+
- 0
|
75
|
+
version: "0"
|
76
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
77
|
+
requirements:
|
78
|
+
- - ">="
|
79
|
+
- !ruby/object:Gem::Version
|
80
|
+
segments:
|
81
|
+
- 0
|
82
|
+
version: "0"
|
83
|
+
requirements: []
|
84
|
+
|
85
|
+
rubyforge_project:
|
86
|
+
rubygems_version: 1.3.6
|
87
|
+
signing_key:
|
88
|
+
specification_version: 3
|
89
|
+
summary: ruby-readability
|
90
|
+
test_files:
|
91
|
+
- spec/fixtures/samples/channel4-1-fragments.rb
|
92
|
+
- spec/fixtures/samples/globemail-ottawa-cuts-fragments.rb
|
93
|
+
- spec/readability_spec.rb
|
94
|
+
- spec/spec_helper.rb
|