patento 0.2.0

data/.document

@@ -0,0 +1,5 @@
+lib/**/*.rb
+bin/*
+- 
+features/**/*.feature
+LICENSE.txt

data/.rspec

@@ -0,0 +1 @@
+--color

data/Gemfile

@@ -0,0 +1,18 @@
+source 'http://rubygems.org'
+
+gem 'nokogiri'
+
+group :development do
+  gem 'rspec'
+  gem 'rdoc'
+  gem 'bundler'
+  gem 'jeweler'
+end
+
+gem 'rspec', group: ['test', 'development']
+
+group :test do
+  gem 'ruby_gntp'
+  gem 'guard-rspec'
+  gem 'spork'
+end

data/Gemfile.lock

@@ -0,0 +1,54 @@
+GEM
+  remote: http://rubygems.org/
+  specs:
+    diff-lcs (1.1.3)
+    ffi (1.0.11)
+    git (1.2.5)
+    guard (1.2.3)
+      listen (>= 0.4.2)
+      thor (>= 0.14.6)
+    guard-rspec (1.2.0)
+      guard (>= 1.1)
+    jeweler (1.8.4)
+      bundler (~> 1.0)
+      git (>= 1.2.5)
+      rake
+      rdoc
+    json (1.7.3)
+    listen (0.4.7)
+      rb-fchange (~> 0.0.5)
+      rb-fsevent (~> 0.9.1)
+      rb-inotify (~> 0.8.8)
+    nokogiri (1.5.5)
+    rake (0.9.2.2)
+    rb-fchange (0.0.5)
+      ffi
+    rb-fsevent (0.9.1)
+    rb-inotify (0.8.8)
+      ffi (>= 0.5.0)
+    rdoc (3.12)
+      json (~> 1.4)
+    rspec (2.11.0)
+      rspec-core (~> 2.11.0)
+      rspec-expectations (~> 2.11.0)
+      rspec-mocks (~> 2.11.0)
+    rspec-core (2.11.0)
+    rspec-expectations (2.11.1)
+      diff-lcs (~> 1.1.3)
+    rspec-mocks (2.11.1)
+    ruby_gntp (0.3.4)
+    spork (0.9.2)
+    thor (0.15.4)
+
+PLATFORMS
+  ruby
+
+DEPENDENCIES
+  bundler
+  guard-rspec
+  jeweler
+  nokogiri
+  rdoc
+  rspec
+  ruby_gntp
+  spork

data/Guardfile

@@ -0,0 +1,9 @@
+# A sample Guardfile
+# More info at https://github.com/guard/guard#readme
+
+guard 'rspec', :cli => '--tag ~slow --format nested', :version => 2 do
+  watch(%r{^spec/.+_spec\.rb$})
+  watch(%r{^lib/patento/(.+)\.rb$})     { |m| "spec/#{m[1]}_spec.rb" }
+  watch('spec/spec_helper.rb')  { "spec" }
+end
+

data/LICENSE.txt

@@ -0,0 +1,20 @@
+Copyright (c) 2012 George Zalepa
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/README.mdown

@@ -0,0 +1,78 @@
+# Patento
+
+Patento is a simple gem for scraping Google Patents and formatting the visible data into objects and hashes.
+
+## Usage
+
+Patento has two models of operation: local and remote. In local mode, you pass in the .html file saved from Google patents. In remote mode, you simply supply a patent number and Patento will pull the HTML from Google.
+
+Note that pulling remote data will result in one HTTP request per patent requested. Thus, if doing large amounts of downloading, please consider respecting Google's server load. For your convenience, Google's terms of service can be found here: [http://www.google.com/intl/en/policies/terms/](http://www.google.com/intl/en/policies/terms/).
+
+### Examples:
+  
+    Patent.new(6000000) # Retreives patent details remotely
+    
+    Patent.new(6000000, local_path: "US6000000.html") # Parses  ./US6000000.html and returns the same data as above
+
+### Data Retreived
+
+Patento retrieves the following data:
+
+1. Patent Number (`String`): `patent.number`
+2. Title (`String`): `patent.title`
+3. Abstract (`String`): `patent.abstract`
+4. Inventors (`Array` of `String` objects): `patent.inventors`
+5. Assignee (`String`): `patent.assignee`
+6. U.S. Classifications (`Array` of `String` objects): `patent.us_classifications`
+7. International Classification (`String`): `patent.intl_classifications`
+8. Filing Date (`Date`): `patent.filing_date`
+9. Issue Date (`Date`): `patent.issue_date`
+  * ***Note***: Patento does not retrieve the publication date of published applications due to this data not being available at Google
+10. Claims (`Array` of `Claim` objects (see below)): `patent.claims`
+11. Forward Citations (`Array` of `Hash` objects): `patent.forward_citations`
+12. Backward Citations (`Array` of `Hash` objects): `patent.backward_citations`
+
+## Citations
+Forward and backward citations are just `Hash` objects with the following keys: `number`, `filing`, `issue`, `assignee`, and `title`.
+
+## Claim Objects
+Patento stores claim data in separate `Claim` objects. Claim objects have a `number`, a `type` (independent or dependent), a `preamble`, and a `body`. All attributes are public.
+
+All claims are guaranteed to have a `preamble`. Shorter claims (one liners) may *only* have a preamble. 
+
+The `body` element is a nested array of elements corresponding to the indenting of the original claim. For example, the claim:
+
+    Preamble
+    Element 1
+        Sub-element 1
+        Sub-element 2
+    Element 2
+
+will have a `body` represented as a nested array like so:
+
+    [
+        [
+            "Element 1",
+            
+            [
+                "Sub-element 1",
+                "Sub-element 2"
+            ]
+        ],
+        
+        "Element 2"
+    ]
+
+## Contributing to patento
+ 
+* Check out the latest master to make sure the feature hasn't been implemented or the bug hasn't been fixed yet.
+* Check out the issue tracker to make sure someone already hasn't requested it and/or contributed it.
+* Fork the project.
+* Start a feature/bugfix branch.
+* Commit and push until you are happy with your contribution.
+* Make sure to add tests for it. This is important so I don't break it in a future version unintentionally.
+* Please try not to mess with the Rakefile, version, or history. If you want to have your own version, or is otherwise necessary, that is fine, but please isolate to its own commit so I can cherry-pick around it.
+
+## Copyright
+
+Copyright (c) 2012 George Zalepa. See LICENSE.txt for further details.

data/Rakefile

@@ -0,0 +1,49 @@
+# encoding: utf-8
+
+require 'rubygems'
+require 'bundler'
+begin
+  Bundler.setup(:default, :development)
+rescue Bundler::BundlerError => e
+  $stderr.puts e.message
+  $stderr.puts "Run `bundle install` to install missing gems"
+  exit e.status_code
+end
+require 'rake'
+
+require 'jeweler'
+Jeweler::Tasks.new do |gem|
+  # gem is a Gem::Specification... see http://docs.rubygems.org/read/chapter/20 for more options
+  gem.name = "patento"
+  gem.homepage = "http://github.com/aosik/patento"
+  gem.license = "MIT"
+  gem.summary = %Q{Patento is a simple gem for scraping Google Patents and formatting the visible data into objects and hashes.}
+  gem.description = %Q{Patento is a simple gem for scraping Google Patents and formatting the visible data into objects and hashes. See the README for more details}
+  gem.email = "george.zalepa@gmail.com"
+  gem.authors = ["George Zalepa"]
+  # dependencies defined in Gemfile
+end
+Jeweler::RubygemsDotOrgTasks.new
+
+require 'rspec/core'
+require 'rspec/core/rake_task'
+RSpec::Core::RakeTask.new(:spec) do |spec|
+  spec.pattern = FileList['spec/**/*_spec.rb']
+end
+
+RSpec::Core::RakeTask.new(:rcov) do |spec|
+  spec.pattern = 'spec/**/*_spec.rb'
+  spec.rcov = true
+end
+
+task :default => :spec
+
+require 'rdoc/task'
+Rake::RDocTask.new do |rdoc|
+  version = File.exist?('VERSION') ? File.read('VERSION') : ""
+
+  rdoc.rdoc_dir = 'rdoc'
+  rdoc.title = "patento #{version}"
+  rdoc.rdoc_files.include('README*')
+  rdoc.rdoc_files.include('lib/**/*.rb')
+end

data/VERSION

@@ -0,0 +1 @@
+0.2.0

data/lib/patento.rb

@@ -0,0 +1,30 @@
+require 'nokogiri'
+require 'net/http'
+require 'date'
+
+require 'patento/document'
+require 'patento/patent'
+require 'patento/publication'
+require 'patento/claim'
+
+module Patento
+#	class Downloader
+	  def self.download_html(number)
+	    Net::HTTP.get_response(URI.parse("http://www.google.com/patents/US#{number}")).body
+	  end
+#  end
+end
+
+# Some quick string regex helpers 
+class String
+	# identifies if the text contains "N. ..." where N is the claim number
+	def is_preamble?
+		self.match(/^\d*\.\s/) ? true : false
+	end	
+
+	# identifiers if the text has " claim N " in it
+	# note this is not foolproof since some claims aren't worded this way (few, but some)
+	def is_independent?
+		self.match(/\sclaim\s\d*\s/) ? true : false
+	end
+end

data/lib/patento/claim.rb

@@ -0,0 +1,93 @@
+require 'pp'
+
+module Patento
+	
+	class Claim
+		attr_accessor :number, :type, :preamble, :body
+		
+		# Class Methods
+		
+		def self.from_hash(hash)
+			
+			claim = Claim.new
+			
+			claim.number = hash[:number]
+			claim.type = hash[:type]
+			claim.preamble = hash[:preamble]
+			claim.body = hash[:body]
+			
+			return claim
+		end
+		
+		def self.extract_all(number, options ={})
+			if options[:local_path]
+				html = Nokogiri::HTML(File.read(options[:local_path]))
+			else
+      	html = Nokogiri::HTML(Patento.download_html(number))
+			end
+			
+			return parse_claims(html)
+			
+		end
+		
+		def self.parse_claims(html)
+			hash = parse_claims_from_html(html)
+			
+			formatted_claims = []
+			
+			hash.each do |hash|
+				formatted_claims << Claim.from_hash(hash)
+			end
+			return formatted_claims
+		end
+		
+		def self.parse_claims_from_html(html)
+			elements = html.at_css('#patent_claims_v').children
+
+			claims = []
+			index  = -1
+			
+			
+			elements.each do |element|
+				next if element.children.empty?
+
+				if element.text.is_preamble?
+					index += 1
+					claims[index] = {
+						number: index + 1,
+						type: (element.text.match(/\sclaim\s\d*\s/) ? :dependent : :independent),
+						preamble: element.text.gsub(/^\d*\.\s/,''),
+						body: []
+					}
+				else
+					claims[index][:body] = parse_dl(element)
+				end
+			end
+			
+			return claims
+			
+		end
+		
+		def self.parse_dl(element)
+			elements = []
+			
+			index = 0
+			
+			element.children.each do |e|
+				unless e.css('dl').empty? # nested elements
+					elements[index-1] = [elements[index-1]]
+					elements[index-1] << parse_dl(e.css('dl')) # god i hate recursion
+				else # plain ol elements
+					elements << e.text
+					index += 1
+				end
+				
+			end
+			elements
+		end
+		
+	end
+	
+	
+	
+end

data/lib/patento/document.rb

@@ -0,0 +1,95 @@
+module Patento
+	class Document
+		
+		attr_accessor :number, :html
+    
+		# Note: attributes are lazily evaluated
+    def initialize(number, options = {})
+      @number = number.to_s
+			if options[:local_path]
+				@html = Nokogiri::HTML(File.read(options[:local_path]))
+			else
+      	@html = Nokogiri::HTML(Patento.download_html(number))
+			end
+    end
+
+
+    # Attributes
+    def title
+      @title ||= @html.css('.main-title').text.split(' - ')[1]
+    end
+    
+    def abstract
+      @abstract ||= @html.css('.patent_abstract_text').text
+    end
+    
+    def inventors
+      @inventors ||= parse_bibdata_links_for_url_match('q=ininventor:')
+    end
+    
+    def assignee
+      @assignee ||= parse_bibdata_links_for_url_match('q=inassignee:')
+    end
+    
+    def us_classifications
+      @us_classifications ||= parse_bibdata_links_for_url_match('q=http://www.uspto.gov/web/patents/classification/')
+    end
+    
+		def filing_date
+			@filing_date ||= parse_date(:filing)
+		end
+		
+		def claims
+			@claims ||= Claim.parse_claims(@html)
+		end
+		
+		def forward_citations
+			@forward_citations ||= parse_citations(:forward)
+		end
+		
+		def independent_claims
+			independent_claims = []
+			claims.each do |c| 
+				if c[:type] == :independent 
+					independent_claims << c 
+				end
+			end
+			return independent_claims
+		end
+    
+    # Helpers
+
+		def parse_citations(type)
+			container = (type == :backward ? '#patent_citations_v tr' : '#patent_referenced_by_v tr')
+			trs = @html.css(container)
+			trs.shift
+			citations = []
+			trs.each do |row|
+				citations << {
+					number: row.css('td')[0].css('a').text.gsub(/^US/, ''),
+					filing: Date.parse(row.css('td')[1].text),
+					issue: Date.parse(row.css('td')[2].text),
+					assignee: row.css('td')[3].text,
+					title: row.css('td')[4].text
+				}
+			end				
+			return citations
+		end
+
+	
+		def parse_date(type)
+			nodes = @html.css('#metadata_v .patent_bibdata p').children
+			index = (type == :filing ? 4 : 7)
+			Date.parse(nodes[index].text)
+		end
+
+    def parse_bibdata_links_for_url_match(pattern)
+      @matches = @html.css('#summarytable div.patent_bibdata a').to_a
+      @matches.collect! { |link| link.text if link.attr('href').match(pattern) }     
+      @matches.compact!
+      @matches = @matches.first if @matches.count == 1
+      return @matches
+    end
+    
+	end
+end