metainspector 1.3.0 → 1.4.0

data/.gitignore

@@ -1,5 +1,7 @@
 *.gem
 .bundle
 .rvmrc
+.rspec
 Gemfile.lock
 pkg/*
+.idea/

data/.rspec.example

@@ -0,0 +1 @@
+--colour --format d

data/README.rdoc

@@ -31,6 +31,7 @@ Then you can see the scraped data like this:
   page.meta_description   # meta description, as string
   page.meta_keywords      # meta keywords, as string
   page.image              # Most relevant image, if defined with og:image
+  page.rss                # Get rss or atom links in meta data fields as array
 
 MetaInspector uses dynamic methods for meta_tag discovery, so all these will work, and will be converted to a search of a meta tag by the corresponding name, and return its content attribute
 
@@ -84,7 +85,10 @@ You can find some sample scripts on the samples folder, including a basic scrapi
 
 = ZOMG Fork! Thank you!
 
-You're welcome to fork this project and send pull requests. I want to thank Ryan Romanchuk for his help https://github.com/rromanchuk
+You're welcome to fork this project and send pull requests. I want to thank specially:
+
+* Ryan Romanchuk https://github.com/rromanchuk
+* Edmund Haselwanter https://github.com/ehaselwanter
 
 = To Do
 

data/Rakefile

@@ -1,2 +1,5 @@
 require 'bundler'
+require 'rspec/core/rake_task'
+
 Bundler::GemHelper.install_tasks
+RSpec::Core::RakeTask.new :spec

data/lib/meta_inspector.rb

@@ -1,6 +1,6 @@
 # -*- encoding: utf-8 -*-
 
-require_relative 'meta_inspector/scraper'
+require File.expand_path(File.join(File.dirname(__FILE__), 'meta_inspector/scraper'))
 
 module MetaInspector
   extend self

data/lib/meta_inspector/scraper.rb

@@ -28,6 +28,15 @@ module MetaInspector
       @links ||= parsed_document.search("//a").map {|link| link.attributes["href"].to_s.strip} rescue nil
     end
 
+    # Returns the parsed document meta rss links
+    def feed
+      @feed ||= parsed_document.xpath("//link").select{ |link|
+          link.attributes["type"] && link.attributes["type"].value =~ /(atom|rss)/
+        }.map { |link|
+          absolutify_url(link.attributes["href"].value)
+        }.first rescue nil
+    end
+
     # Returns the parsed image from Facebook's open graph property tags
     # Most all major websites now define this property and is usually very relevant
     # See doc at http://developers.facebook.com/docs/opengraph/
@@ -81,5 +90,11 @@ module MetaInspector
         super
       end
     end
+
+    private
+
+    def absolutify_url(url)
+      url =~ /^http.*/ ? url : File.join(@url,url)
+    end
   end
 end

data/lib/meta_inspector/version.rb

@@ -1,5 +1,5 @@
 # -*- encoding: utf-8 -*-
 
 module MetaInspector
-  VERSION = "1.3.0"
+  VERSION = "1.4.0"
 end

data/meta_inspector.gemspec

@@ -22,5 +22,5 @@ Gem::Specification.new do |s|
   s.add_dependency 'nokogiri', '1.4.4'
   s.add_dependency 'charguess', '1.3.20110226181011'
 
-  s.add_development_dependency 'rspec', '2.5.0'
+  s.add_development_dependency 'rspec', '~> 2.6.0'
 end

data/spec/metainspector_spec.rb

@@ -37,7 +37,7 @@ describe MetaInspector do
     end
 
     it "should get the links" do
-      @m.links.size.should == 8
+      @m.links.size.should == 9
     end
 
     it "should have a Nokogiri::HTML::Document as parsed_document" do
@@ -47,6 +47,16 @@ describe MetaInspector do
     it "should have a String as document" do
       @m.document.class.should == String
     end
+
+    it "should get rss feed" do
+      @m = MetaInspector.new('http://www.iteh.at')
+      @m.feed.should == 'http://www.iteh.at/de/rss/'
+    end
+
+    it "should get atom feed" do
+      @m = MetaInspector.new('http://www.tea-tron.com/jbravo/blog/')
+      @m.feed.should == 'http://www.tea-tron.com/jbravo/blog/feed/'
+    end
   end
 
   context 'Getting meta tags by ghost methods' do

metadata

@@ -4,9 +4,9 @@ version: !ruby/object:Gem::Version
   prerelease: false
   segments: 
   - 1
-  - 3
+  - 4
   - 0
-  version: 1.3.0
+  version: 1.4.0
 platform: ruby
 authors: 
 - Jaime Iniesta
@@ -14,7 +14,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2011-05-09 00:00:00 +02:00
+date: 2011-05-30 00:00:00 +02:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency 
@@ -53,13 +53,13 @@ dependencies:
   requirement: &id003 !ruby/object:Gem::Requirement 
     none: false
     requirements: 
-    - - "="
+    - - ~>
       - !ruby/object:Gem::Version 
         segments: 
         - 2
-        - 5
+        - 6
         - 0
-        version: 2.5.0
+        version: 2.6.0
   type: :development
   version_requirements: *id003
 description: MetaInspector lets you scrape a web page and get its title, charset, link and meta tags
@@ -73,6 +73,7 @@ extra_rdoc_files: []
 
 files: 
 - .gitignore
+- .rspec.example
 - Gemfile
 - MIT-LICENSE
 - README.rdoc