ruby-readability 0.2.1 → 0.2.2
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/README +19 -0
- data/VERSION +1 -1
- data/lib/readability.rb +5 -5
- data/ruby-readability.gemspec +2 -2
- metadata +4 -4
data/README
CHANGED
@@ -1,3 +1,22 @@
|
|
1
|
+
Ruby Readability
|
2
|
+
|
3
|
+
Command line:
|
4
|
+
(sudo) gem install ruby-readability
|
5
|
+
|
6
|
+
Bundler:
|
7
|
+
gem "ruby-readability", :require => 'readability'
|
8
|
+
|
9
|
+
Example:
|
10
|
+
|
11
|
+
require 'rubygems'
|
12
|
+
require 'readability'
|
13
|
+
require 'open-uri'
|
14
|
+
|
15
|
+
source = open('http://lab.arc90.com/experiments/readability/').read
|
16
|
+
puts Readability::Document.new(source).content
|
17
|
+
|
18
|
+
===
|
19
|
+
|
1
20
|
This code is under the Apache License 2.0. http://www.apache.org/licenses/LICENSE-2.0
|
2
21
|
|
3
22
|
This is a ruby port of arc90's readability project
|
data/VERSION
CHANGED
@@ -1 +1 @@
|
|
1
|
-
0.2.
|
1
|
+
0.2.2
|
data/lib/readability.rb
CHANGED
@@ -183,13 +183,13 @@ module Readability
|
|
183
183
|
def score_node(elem)
|
184
184
|
content_score = class_weight(elem)
|
185
185
|
case elem.name.downcase
|
186
|
-
when "div"
|
186
|
+
when "div"
|
187
187
|
content_score += 5
|
188
|
-
when "blockquote"
|
188
|
+
when "blockquote"
|
189
189
|
content_score += 3
|
190
|
-
when "form"
|
190
|
+
when "form"
|
191
191
|
content_score -= 3
|
192
|
-
when "th"
|
192
|
+
when "th"
|
193
193
|
content_score -= 5
|
194
194
|
end
|
195
195
|
{ :content_score => content_score, :elem => elem }
|
@@ -277,7 +277,7 @@ module Readability
|
|
277
277
|
end
|
278
278
|
|
279
279
|
# Get rid of duplicate whitespace
|
280
|
-
node.to_html.gsub(/[\r\n\f]+/, "\n" ).gsub(/[\t
|
280
|
+
node.to_html.gsub(/[\r\n\f]+/, "\n" ).gsub(/[\t ]+/, " ")
|
281
281
|
end
|
282
282
|
|
283
283
|
def clean_conditionally(node, candidates, selector)
|
data/ruby-readability.gemspec
CHANGED
@@ -5,11 +5,11 @@
|
|
5
5
|
|
6
6
|
Gem::Specification.new do |s|
|
7
7
|
s.name = %q{ruby-readability}
|
8
|
-
s.version = "0.2.
|
8
|
+
s.version = "0.2.2"
|
9
9
|
|
10
10
|
s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
|
11
11
|
s.authors = ["Andrew Cantino", "starrhorne", "libc", "Kyle Maxwell"]
|
12
|
-
s.date = %q{2010-11-
|
12
|
+
s.date = %q{2010-11-08}
|
13
13
|
s.default_executable = %q{readability}
|
14
14
|
s.description = %q{Port of arc90's readability project to ruby}
|
15
15
|
s.email = %q{andrew@iterationlabs.com}
|
metadata
CHANGED
@@ -1,13 +1,13 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: ruby-readability
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
hash:
|
4
|
+
hash: 19
|
5
5
|
prerelease: false
|
6
6
|
segments:
|
7
7
|
- 0
|
8
8
|
- 2
|
9
|
-
-
|
10
|
-
version: 0.2.
|
9
|
+
- 2
|
10
|
+
version: 0.2.2
|
11
11
|
platform: ruby
|
12
12
|
authors:
|
13
13
|
- Andrew Cantino
|
@@ -18,7 +18,7 @@ autorequire:
|
|
18
18
|
bindir: bin
|
19
19
|
cert_chain: []
|
20
20
|
|
21
|
-
date: 2010-11-
|
21
|
+
date: 2010-11-08 00:00:00 -08:00
|
22
22
|
default_executable: readability
|
23
23
|
dependencies:
|
24
24
|
- !ruby/object:Gem::Dependency
|