busk-ruby-readability 1.0.5.1 → 1.0.5.2
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/lib/readability.rb +3 -2
- metadata +4 -4
data/lib/readability.rb
CHANGED
|
@@ -47,7 +47,8 @@ module Readability
|
|
|
47
47
|
}
|
|
48
48
|
|
|
49
49
|
def content(remove_unlikely_candidates = true)
|
|
50
|
-
@html.css("script, style").each {
|
|
50
|
+
@html.css("script, style").each {|el| el.remove }
|
|
51
|
+
@html.search('//comment()').each {|el| el.remove }
|
|
51
52
|
|
|
52
53
|
article = youtube if is_youtube? && remove_unlikely_candidates
|
|
53
54
|
article = vimeo if is_vimeo? && remove_unlikely_candidates
|
|
@@ -140,7 +141,7 @@ module Readability
|
|
|
140
141
|
|
|
141
142
|
sibling_score_threshold = [10, best_candidate[:content_score] * 0.2].max
|
|
142
143
|
output = Nokogiri::XML::Node.new('div', @html)
|
|
143
|
-
best_candidate[:elem].parent.children.each do |sibling|
|
|
144
|
+
best_candidate[:elem].parent.andand.children.each do |sibling|
|
|
144
145
|
append = false
|
|
145
146
|
append = true if sibling == best_candidate[:elem]
|
|
146
147
|
append = true if candidates[sibling] && candidates[sibling][:content_score] >= sibling_score_threshold
|
metadata
CHANGED
|
@@ -1,14 +1,14 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: busk-ruby-readability
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
hash:
|
|
4
|
+
hash: 79
|
|
5
5
|
prerelease: false
|
|
6
6
|
segments:
|
|
7
7
|
- 1
|
|
8
8
|
- 0
|
|
9
9
|
- 5
|
|
10
|
-
-
|
|
11
|
-
version: 1.0.5.
|
|
10
|
+
- 2
|
|
11
|
+
version: 1.0.5.2
|
|
12
12
|
platform: ruby
|
|
13
13
|
authors: []
|
|
14
14
|
|
|
@@ -16,7 +16,7 @@ autorequire:
|
|
|
16
16
|
bindir: bin
|
|
17
17
|
cert_chain: []
|
|
18
18
|
|
|
19
|
-
date: 2010-
|
|
19
|
+
date: 2010-10-05 00:00:00 -03:00
|
|
20
20
|
default_executable:
|
|
21
21
|
dependencies: []
|
|
22
22
|
|