wikipedia 0.1

data/lib/wikipedia.rb

@@ -0,0 +1,34 @@
+# encoding: utf-8
+
+require 'rubygems'
+require 'bundler/setup'
+
+require 'open-uri'
+require 'htmlentities'
+require 'hpricot'
+
+module Wikipedia
+
+	URL = "http://%LANG%.wikipedia.org/w/api.php?action=parse&page="
+
+	def self.article( n, lang = :es )
+
+		texts = []
+
+		raw_data = open( URL.gsub("%LANG%", lang.to_s)+n ).read()
+		#raw_data = File.read('pareidolia').gsub("\n", "")
+
+		he = HTMLEntities.new()
+
+		# characters = { Regexp.new("\\[(.*)\\]") => '' }
+
+ 		raw_data = he.decode( he.decode( raw_data ) ).gsub("\n", "") # >:D
+
+		Hpricot(raw_data).search('p').each do |ph|
+			texts << ph.inner_text
+		end
+
+		return texts
+
+	end
+end

metadata

@@ -0,0 +1,45 @@
+--- !ruby/object:Gem::Specification
+name: wikipedia
+version: !ruby/object:Gem::Version
+  version: '0.1'
+  prerelease: 
+platform: ruby
+authors:
+- Matias Insaurralde
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2013-05-03 00:00:00.000000000 Z
+dependencies: []
+description: tool for extracting plain text from wikipedia articles
+email: matiasbaruchinsaurralde@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- lib/wikipedia.rb
+homepage: http://lomitologia.blogspot.com/2013/05/030513.html
+licenses: []
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 1.8.23
+signing_key: 
+specification_version: 3
+summary: tool for extracting plain text from wikipedia articles
+test_files: []