meta_grabber 0.0.0

data/lib/meta_grabber.rb

@@ -0,0 +1,35 @@
+require 'nokogiri'
+
+class MetaGrabber
+
+	attr_reader :doc, :meta
+	
+	def initialize(page_source)
+		@doc = Nokogiri::HTML::parse(page_source)
+		@meta = {}
+	end
+
+	def title
+		@title ||= @doc.xpath("//title").text rescue nil
+	end
+
+	#Some sites do <meta name="title" ... /> for some wierd reason
+	def meta_title
+		@meta['title'] ||= title
+	end
+
+	def grab_meta
+		# grab each meta tag
+		for i in @doc.xpath("//meta") do
+			next if !i[:name] #dont really care about these, http types etc
+			@meta[i[:name].to_s.downcase] = i[:content]
+		end
+
+		@meta
+	end
+
+	def keywords_array
+		@meta['keywords'] ? @meta['keywords'].split(",").map{|kw| kw.strip} : nil
+	end
+
+end

metadata

@@ -0,0 +1,45 @@
+--- !ruby/object:Gem::Specification
+name: meta_grabber
+version: !ruby/object:Gem::Version
+  version: 0.0.0
+  prerelease: 
+platform: ruby
+authors:
+- Jake Austwick
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2012-12-29 00:00:00.000000000Z
+dependencies: []
+description: A simple gem to extract useful meta info, useful for SEO purposes
+email: contact@mumbodesign.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- lib/meta_grabber.rb
+homepage: 
+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: 1.8.10
+signing_key: 
+specification_version: 3
+summary: Grabs meta title, description, keywords etc
+test_files: []