Wiki_Category_Extractor 0.0.1
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/Wiki_Category_Extractor.rb +40 -0
- metadata +45 -0
|
@@ -0,0 +1,40 @@
|
|
|
1
|
+
class Wiki_Category_Extractor
|
|
2
|
+
def self.extract(a,pagelimit)
|
|
3
|
+
@pages = {}
|
|
4
|
+
@categories = []
|
|
5
|
+
@cat_links = []
|
|
6
|
+
|
|
7
|
+
@categories << a
|
|
8
|
+
@cat_links << "http://en.wikipedia.org/wiki/Category:" + a
|
|
9
|
+
|
|
10
|
+
while @categories != []
|
|
11
|
+
@doc = Nokogiri::HTML(open(@cat_links[0]))
|
|
12
|
+
@x = @doc.css("#mw-subcategories")
|
|
13
|
+
j = 0
|
|
14
|
+
while j < @x.css("a").length
|
|
15
|
+
@categories << @x.css("a")[j].text
|
|
16
|
+
@cat_links << "http://en.wikipedia.org" + @x.css("a")[j].attributes["href"].value
|
|
17
|
+
j = j + 1
|
|
18
|
+
end
|
|
19
|
+
|
|
20
|
+
@y = @doc.css("#mw-pages")
|
|
21
|
+
j = 0
|
|
22
|
+
while j < @y.css("a").length
|
|
23
|
+
if @y.css("a")[j].text != ""
|
|
24
|
+
@pages[@y.css("a")[j].text] = "http://en.wikipedia.org" + @y.css("a")[j].attributes["href"].value
|
|
25
|
+
end
|
|
26
|
+
j = j + 1
|
|
27
|
+
end
|
|
28
|
+
|
|
29
|
+
if @pages.length > pagelimit
|
|
30
|
+
break
|
|
31
|
+
end
|
|
32
|
+
|
|
33
|
+
puts @categories[0]
|
|
34
|
+
@categories.delete_at(0)
|
|
35
|
+
@cat_links.delete_at(0)
|
|
36
|
+
|
|
37
|
+
end
|
|
38
|
+
return @pages
|
|
39
|
+
end
|
|
40
|
+
end
|
metadata
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
|
2
|
+
name: Wiki_Category_Extractor
|
|
3
|
+
version: !ruby/object:Gem::Version
|
|
4
|
+
version: 0.0.1
|
|
5
|
+
prerelease:
|
|
6
|
+
platform: ruby
|
|
7
|
+
authors:
|
|
8
|
+
- Prateek Papriwal
|
|
9
|
+
autorequire:
|
|
10
|
+
bindir: bin
|
|
11
|
+
cert_chain: []
|
|
12
|
+
date: 2013-12-20 00:00:00.000000000 Z
|
|
13
|
+
dependencies: []
|
|
14
|
+
description: Category Extractor
|
|
15
|
+
email: papriwalprateek@gmail.com
|
|
16
|
+
executables: []
|
|
17
|
+
extensions: []
|
|
18
|
+
extra_rdoc_files: []
|
|
19
|
+
files:
|
|
20
|
+
- lib/Wiki_Category_Extractor.rb
|
|
21
|
+
homepage: http://rubygems.org/gems/Wiki_Category_Extractor
|
|
22
|
+
licenses: []
|
|
23
|
+
post_install_message:
|
|
24
|
+
rdoc_options: []
|
|
25
|
+
require_paths:
|
|
26
|
+
- lib
|
|
27
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
|
28
|
+
none: false
|
|
29
|
+
requirements:
|
|
30
|
+
- - ! '>='
|
|
31
|
+
- !ruby/object:Gem::Version
|
|
32
|
+
version: '0'
|
|
33
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
|
34
|
+
none: false
|
|
35
|
+
requirements:
|
|
36
|
+
- - ! '>='
|
|
37
|
+
- !ruby/object:Gem::Version
|
|
38
|
+
version: '0'
|
|
39
|
+
requirements: []
|
|
40
|
+
rubyforge_project:
|
|
41
|
+
rubygems_version: 1.8.11
|
|
42
|
+
signing_key:
|
|
43
|
+
specification_version: 3
|
|
44
|
+
summary: ! '!!!'
|
|
45
|
+
test_files: []
|