wikipedia 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/wikipedia.rb +34 -0
- metadata +45 -0
data/lib/wikipedia.rb
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
1
|
+
# encoding: utf-8
|
|
2
|
+
|
|
3
|
+
require 'rubygems'
|
|
4
|
+
require 'bundler/setup'
|
|
5
|
+
|
|
6
|
+
require 'open-uri'
|
|
7
|
+
require 'htmlentities'
|
|
8
|
+
require 'hpricot'
|
|
9
|
+
|
|
10
|
+
module Wikipedia
|
|
11
|
+
|
|
12
|
+
URL = "http://%LANG%.wikipedia.org/w/api.php?action=parse&page="
|
|
13
|
+
|
|
14
|
+
def self.article( n, lang = :es )
|
|
15
|
+
|
|
16
|
+
texts = []
|
|
17
|
+
|
|
18
|
+
raw_data = open( URL.gsub("%LANG%", lang.to_s)+n ).read()
|
|
19
|
+
#raw_data = File.read('pareidolia').gsub("\n", "")
|
|
20
|
+
|
|
21
|
+
he = HTMLEntities.new()
|
|
22
|
+
|
|
23
|
+
# characters = { Regexp.new("\\[(.*)\\]") => '' }
|
|
24
|
+
|
|
25
|
+
raw_data = he.decode( he.decode( raw_data ) ).gsub("\n", "") # >:D
|
|
26
|
+
|
|
27
|
+
Hpricot(raw_data).search('p').each do |ph|
|
|
28
|
+
texts << ph.inner_text
|
|
29
|
+
end
|
|
30
|
+
|
|
31
|
+
return texts
|
|
32
|
+
|
|
33
|
+
end
|
|
34
|
+
end
|
metadata
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
|
2
|
+
name: wikipedia
|
|
3
|
+
version: !ruby/object:Gem::Version
|
|
4
|
+
version: '0.1'
|
|
5
|
+
prerelease:
|
|
6
|
+
platform: ruby
|
|
7
|
+
authors:
|
|
8
|
+
- Matias Insaurralde
|
|
9
|
+
autorequire:
|
|
10
|
+
bindir: bin
|
|
11
|
+
cert_chain: []
|
|
12
|
+
date: 2013-05-03 00:00:00.000000000 Z
|
|
13
|
+
dependencies: []
|
|
14
|
+
description: tool for extracting plain text from wikipedia articles
|
|
15
|
+
email: matiasbaruchinsaurralde@gmail.com
|
|
16
|
+
executables: []
|
|
17
|
+
extensions: []
|
|
18
|
+
extra_rdoc_files: []
|
|
19
|
+
files:
|
|
20
|
+
- lib/wikipedia.rb
|
|
21
|
+
homepage: http://lomitologia.blogspot.com/2013/05/030513.html
|
|
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: 1.8.23
|
|
42
|
+
signing_key:
|
|
43
|
+
specification_version: 3
|
|
44
|
+
summary: tool for extracting plain text from wikipedia articles
|
|
45
|
+
test_files: []
|