dq-readability 1.0.4 → 1.0.5
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +8 -8
- data/README.md +8 -5
- data/dq-readability.gemspec +1 -1
- data/lib/dq-readability.rb +18 -2
- metadata +3 -3
checksums.yaml
CHANGED
@@ -1,15 +1,15 @@
|
|
1
1
|
---
|
2
2
|
!binary "U0hBMQ==":
|
3
3
|
metadata.gz: !binary |-
|
4
|
-
|
4
|
+
YWVkZDMxNmZmZWIxMDk5MjI5N2Q1MTZkNDBlZGYyZDFmOTE2NzNhMw==
|
5
5
|
data.tar.gz: !binary |-
|
6
|
-
|
6
|
+
YmQ0NTkzYzE1ZmRmNjQ3NzRkMDE2MmFjNDg3Y2VkMjY5ZDJiZDc4YQ==
|
7
7
|
SHA512:
|
8
8
|
metadata.gz: !binary |-
|
9
|
-
|
10
|
-
|
11
|
-
|
9
|
+
M2M5ZjRmODcyMzU0MWM3MGVlZGZlYmE4MjVmNmI5YmQ0ODRjZmY0OTM1MGRl
|
10
|
+
M2FiODJlZjU4YTUwYjgxNDI3Yjk4YjQ1ZjE3MTFmOTAzZmRhODdmOGNhZTRi
|
11
|
+
NmMyZDAxYzkxMTI1NWRlODg5ZjJjNWI1OTg3ZTBmNmU1YjU0ODc=
|
12
12
|
data.tar.gz: !binary |-
|
13
|
-
|
14
|
-
|
15
|
-
|
13
|
+
OTc0YTZjOTc3Nzg1OTI4ZmE3Yzg1YmRjOGVkYzgwZjU4MmNjYWUyY2I3NTkz
|
14
|
+
Zjc3ZTFiM2U3N2M2OTNiZmRkMGZlMDM2N2ZiODQxYjI4OGZiOTg5YjU1ZGM5
|
15
|
+
OTM3NTkyYjA4MDdiMGEwZmUzOTFlZDdlODcyMTY3ZTVjNDdkMzQ=
|
data/README.md
CHANGED
@@ -1,3 +1,10 @@
|
|
1
|
+
Version
|
2
|
+
-------
|
3
|
+
1.0.4 released. Check out https://rubygems.org/gems/dq-readability
|
4
|
+
|
5
|
+
* competing structure for fighting invalid characters
|
6
|
+
* Wikipedia image case resolved
|
7
|
+
|
1
8
|
Install
|
2
9
|
-------
|
3
10
|
Command line:
|
@@ -12,8 +19,4 @@ Example
|
|
12
19
|
require 'rubygems'
|
13
20
|
require 'dq-readability'
|
14
21
|
source = "http://www.personal.kent.edu/~rmuhamma/Algorithms/MyAlgorithms/Sorting/radixSort.htm"
|
15
|
-
puts DQReadability::Document.new(source,:tags=>%w[div pre p h1 h2 h3 h4 td table tr b a img br li ul ol center br hr blockquote em strong sub sup font tbody span],:attributes=>%w[href src align width color height]).content
|
16
|
-
|
17
|
-
|
18
|
-
|
19
|
-
|
22
|
+
puts DQReadability::Document.new(source,:tags=>%w[div pre p h1 h2 h3 h4 td table tr b a img br li ul ol center br hr blockquote em strong sub sup font tbody tt span dl dd t code figure fieldset legend dir noscript],:attributes=>%w[href src align width color height]).content
|
data/dq-readability.gemspec
CHANGED
@@ -3,7 +3,7 @@ $:.push File.expand_path("../lib", __FILE__)
|
|
3
3
|
|
4
4
|
Gem::Specification.new do |s|
|
5
5
|
s.name = "dq-readability"
|
6
|
-
s.version = '1.0.
|
6
|
+
s.version = '1.0.5'
|
7
7
|
s.authors = ["Prateek Papriwal"]
|
8
8
|
s.email = ["papriwalprateek@gmail.com"]
|
9
9
|
s.homepage = "http://github.com/DaQwest/dq-readability"
|
data/lib/dq-readability.rb
CHANGED
@@ -17,7 +17,8 @@ module DQReadability
|
|
17
17
|
:remove_empty_nodes => true,
|
18
18
|
:min_image_width => 130,
|
19
19
|
:min_image_height => 80,
|
20
|
-
:ignore_image_format => []
|
20
|
+
:ignore_image_format => [],
|
21
|
+
:bypass => false
|
21
22
|
}.freeze
|
22
23
|
|
23
24
|
REGEXES = {
|
@@ -51,6 +52,7 @@ module DQReadability
|
|
51
52
|
@weight_classes = @options[:weight_classes]
|
52
53
|
@clean_conditionally = @options[:clean_conditionally]
|
53
54
|
@best_candidate_has_image = true
|
55
|
+
@bypass = @options[:bypass]
|
54
56
|
make_html
|
55
57
|
end
|
56
58
|
|
@@ -144,10 +146,16 @@ module DQReadability
|
|
144
146
|
end
|
145
147
|
end
|
146
148
|
rescue
|
147
|
-
elem['href'] = ""
|
148
149
|
end
|
149
150
|
end
|
150
151
|
|
152
|
+
# removing edit spans
|
153
|
+
|
154
|
+
@html.css('span').each do |elem|
|
155
|
+
if elem.text.downcase == "[edit]"
|
156
|
+
elem.remove
|
157
|
+
end
|
158
|
+
end
|
151
159
|
|
152
160
|
end
|
153
161
|
|
@@ -296,6 +304,7 @@ module DQReadability
|
|
296
304
|
end
|
297
305
|
|
298
306
|
def content(remove_unlikely_candidates = :default)
|
307
|
+
if @bypass == false
|
299
308
|
@remove_unlikely_candidates = false if remove_unlikely_candidates == false
|
300
309
|
|
301
310
|
prepare_candidates
|
@@ -319,6 +328,13 @@ module DQReadability
|
|
319
328
|
else
|
320
329
|
cleaned_article
|
321
330
|
end
|
331
|
+
else
|
332
|
+
make_html
|
333
|
+
s = Nokogiri::XML::Node::SaveOptions
|
334
|
+
save_opts = s::NO_DECLARATION | s::NO_EMPTY_TAGS | s::AS_XHTML
|
335
|
+
html = @html.serialize(:save_with => save_opts)
|
336
|
+
return html
|
337
|
+
end
|
322
338
|
end
|
323
339
|
|
324
340
|
def get_article(candidates, best_candidate)
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: dq-readability
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 1.0.
|
4
|
+
version: 1.0.5
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Prateek Papriwal
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2014-
|
11
|
+
date: 2014-03-31 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: rspec
|
@@ -135,7 +135,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
135
135
|
version: '0'
|
136
136
|
requirements: []
|
137
137
|
rubyforge_project: dq-readability
|
138
|
-
rubygems_version: 2.
|
138
|
+
rubygems_version: 2.2.2
|
139
139
|
signing_key:
|
140
140
|
specification_version: 4
|
141
141
|
summary: Port of arc90's readability project to ruby
|