boilerpipe 0.0.1

data/README.textile

@@ -0,0 +1,21 @@
+This gem is a ruby wrapper for the Boilerpipe API.
+Boilerpipe definition:
+
+bq. The boilerpipe library provides algorithms to detect and remove the surplus "clutter" (boilerplate, templates) around the main textual content of a web page.
+
+For more information: http://code.google.com/p/boilerpipe/
+
+h1. Explication
+
+The Boilerpipe module has only one method which is extract. Extract takes 2 parameters, first the url and second a hash.
+The hash can have 3 options:
+* output => :html, :htmlFragment, :text, :json, :debug
+* extractor => :ArticleExtractor, :DefaultExtractor, :LargestContentExtractor, :KeepEverythingExtractor, :CanolaExtractor
+* api: => The api url
+
+None of these options are mandatory. To find out more about these options checkout the Boilerpipe API http://boilerpipe-web.appspot.com/
+
+h1. Example
+
+>> require "boilerpipe"
+>> Boilerpipe.extract("http://techcrunch.com/2011/05/12/karma-is-a-bitch/", {:output => :json})

data/boilerpipe.gemspec

@@ -0,0 +1,20 @@
+Gem::Specification.new do |s|
+  s.name = "boilerpipe"
+  s.version = "0.0.1"
+  s.date = "2010-05-13"
+  s.summary = "Ruby wrapper of the Boilerpipe API"
+  s.email = "g.marcilhacy@gmail.com"
+  s.homepage = "https://github.com/gregorym/boilerpipe"
+  s.description = "Ruby wrapper of the Boilerpipe API"
+  s.has_rdoc = false
+  s.authors = ["Grégory Marcilhacy"]
+
+  s.require_paths = %w[lib]
+
+  s.files = %w[
+    boilerpipe.gemspec
+    README.textile
+    Rakefile
+    lib/boilerpipe.rb
+    ]
+end

data/lib/boilerpipe.rb

@@ -0,0 +1,26 @@
+require 'open-uri'
+
+class Object
+  def blank?
+    respond_to?(:empty?) ? empty? : !self
+  end
+  
+  def present?
+    !blank?
+  end
+end
+
+module Boilerpipe
+  DEFAULT_API_URL = 'http://boilerpipe-web.appspot.com/extract'
+  EXTRACTORS = [ :ArticleExtractor, :DefaultExtractor, :LargestContentExtractor, :KeepEverythingExtractor, :CanolaExtractor ]
+  OUTPUT_FORMATS =  [ :html, :htmlFragment, :text, :json, :debug ]
+  
+  def self.extract(extract_url, opts = {})
+    @output    = opts[:output].present?     ? opts[:output]     : OUTPUT_FORMATS.first
+    @extractor = opts[:extractor].present?  ? opts[:extractor]  : EXTRACTORS.first 
+    @api       = opts[:api].present?        ? opts[:api]        : DEFAULT_API_URL
+    
+    url = [@api, "?url=#{extract_url}", "&extractor=#{@extractor}","&output=#{@output}"].join
+    open(url).read
+  end
+end

metadata

@@ -0,0 +1,70 @@
+--- !ruby/object:Gem::Specification 
+name: boilerpipe
+version: !ruby/object:Gem::Version 
+  hash: 29
+  prerelease: 
+  segments: 
+  - 0
+  - 0
+  - 1
+  version: 0.0.1
+platform: ruby
+authors: 
+- "Gr\xC3\xA9gory Marcilhacy"
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2010-05-13 00:00:00 +02:00
+default_executable: 
+dependencies: []
+
+description: Ruby wrapper of the Boilerpipe API
+email: g.marcilhacy@gmail.com
+executables: []
+
+extensions: []
+
+extra_rdoc_files: []
+
+files: 
+- boilerpipe.gemspec
+- README.textile
+- Rakefile
+- lib/boilerpipe.rb
+has_rdoc: true
+homepage: https://github.com/gregorym/boilerpipe
+licenses: []
+
+post_install_message: 
+rdoc_options: []
+
+require_paths: 
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement 
+  none: false
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      hash: 3
+      segments: 
+      - 0
+      version: "0"
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  none: false
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      hash: 3
+      segments: 
+      - 0
+      version: "0"
+requirements: []
+
+rubyforge_project: 
+rubygems_version: 1.6.2
+signing_key: 
+specification_version: 3
+summary: Ruby wrapper of the Boilerpipe API
+test_files: []
+