logophobia-feedzirra 0.0.15 → 0.0.16

data/README.textile

@@ -1,3 +1,5 @@
+"Changes made from Paul's tree":#changes
+
 h1. Feedzirra
 
 "http://github.com/pauldix/feedzirra/tree/master":http://github.com/pauldix/feedzirra/tree/master 
@@ -168,6 +170,13 @@ Here are some more specific TODOs.
 * Clean up the fetching code inside feed.rb so it doesn't suck so hard.
 * Readdress how feeds determine if they can parse a document. Maybe I should use namespaces instead?
 
+h2(#changes). Updates from Paul's tree
+
+* Add in Media RSS support that should handle the spec with multiple content entries.
+* Add in the missing support for nested iTunes Categories
+* Combined iTunes into RSS, removed extra files
+* Made element names more consistent across RSS and iTunes
+
 h2. LICENSE
 
 (The MIT License)

data/lib/feedzirra.rb

@@ -11,6 +11,7 @@ require 'active_support/basic_object'
 require 'active_support/core_ext/object'
 require 'active_support/core_ext/time'
 
+
 require 'core_ext/date'
 require 'core_ext/string'
 
@@ -19,16 +20,17 @@ require 'feedzirra/feed_entry_utilities'
 require 'feedzirra/feed'
 
 require 'feedzirra/parser/rss_entry'
-require 'feedzirra/parser/itunes_rss_owner'
-require 'feedzirra/parser/itunes_rss_item'
+require 'feedzirra/parser/rss_image'
+require 'feedzirra/parser/mrss_content'
+require 'feedzirra/parser/mrss_restriction'
+require 'feedzirra/parser/itunes_category'
 require 'feedzirra/parser/atom_entry'
 require 'feedzirra/parser/atom_feed_burner_entry'
 
 require 'feedzirra/parser/rss'
-require 'feedzirra/parser/itunes_rss'
 require 'feedzirra/parser/atom'
 require 'feedzirra/parser/atom_feed_burner'
 
 module Feedzirra
   VERSION = "0.0.15"
-end
+end

data/lib/feedzirra/feed.rb

@@ -1,9 +1,9 @@
 module Feedzirra
   class NoParserAvailable < StandardError; end
-  
+
   class Feed
     USER_AGENT = "feedzirra http://github.com/pauldix/feedzirra/tree/master"
-    
+
     # Takes a raw XML feed and attempts to parse it. If no parser is available a Feedzirra::NoParserAvailable exception is raised.
     #
     # === Parameters
@@ -21,7 +21,7 @@ module Feedzirra
     end
 
     # Determines the correct parser class to use for parsing the feed.
-    # 
+    #
     # === Parameters
     # [xml<String>] The XML that you would like determine the parser for.
     # === Returns
@@ -37,7 +37,7 @@ module Feedzirra
     # [klass<Constant>] The class/constant that you want to register.
     # === Returns
     # A updated array of feed parser class names.
-    def self.add_feed_class(klass) 
+    def self.add_feed_class(klass)
       feed_classes.unshift klass
     end
 
@@ -46,10 +46,14 @@ module Feedzirra
     # === Returns
     # A array of class names.
     def self.feed_classes
-      @feed_classes ||= [Feedzirra::Parser::RSS, Feedzirra::Parser::AtomFeedBurner, Feedzirra::Parser::Atom]
+      @feed_classes ||= [
+        Feedzirra::Parser::RSS,
+        Feedzirra::Parser::AtomFeedBurner,
+        Feedzirra::Parser::Atom
+      ]
     end
-    
-    # Makes all entry types look for the passed in element to parse. This is actually just a call to 
+
+    # Makes all entry types look for the passed in element to parse. This is actually just a call to
     # element (a SAXMachine call) in the class
     #
     # === Parameters
@@ -62,7 +66,7 @@ module Feedzirra
         klass.send(:element, element_tag, options)
       end
     end
-    
+
     # Fetches and returns the raw XML for each URL provided.
     #
     # === Parameters
@@ -75,7 +79,7 @@ module Feedzirra
     #                 :on_failure - Block that gets executed after a failed request.
     # === Returns
     # A String of XML if a single URL is passed.
-    # 
+    #
     # A Hash if multiple URL's are passed. The key will be the URL, and the value the XML.
     def self.fetch_raw(urls, options = {})
       url_queue = [*urls]
@@ -127,13 +131,13 @@ module Feedzirra
       url_queue = [*urls]
       multi = Curl::Multi.new
       responses = {}
-      
+
       # I broke these down so I would only try to do 30 simultaneously because
       # I was getting weird errors when doing a lot. As one finishes it pops another off the queue.
       url_queue.slice!(0, 30).each do |url|
         add_url_to_multi(multi, url, url_queue, responses, options)
       end
- 
+
       multi.perform
       return urls.is_a?(String) ? responses.values.first : responses
     end
@@ -150,7 +154,7 @@ module Feedzirra
           gz =  Zlib::GzipReader.new(StringIO.new(c.body_str))
           xml = gz.read
           gz.close
-        rescue Zlib::GzipFile::Error 
+        rescue Zlib::GzipFile::Error
           # Maybe this is not gzipped?
           xml = c.body_str
         end
@@ -179,15 +183,15 @@ module Feedzirra
       feed_queue = [*feeds]
       multi = Curl::Multi.new
       responses = {}
-      
+
       feed_queue.slice!(0, 30).each do |feed|
         add_feed_to_multi(multi, feed, feed_queue, responses, options)
       end
-    
+
       multi.perform
       responses.size == 1 ? responses.values.first : responses.values
     end
-    
+
     # An abstraction for adding a feed by URL to the passed Curb::multi stack.
     #
     # === Parameters
@@ -219,7 +223,7 @@ module Feedzirra
           add_url_to_multi(multi, url_queue.shift, url_queue, responses, options) unless url_queue.empty?
           xml = decode_content(c)
           klass = determine_feed_parser_for_xml(xml)
-          
+
           if klass
             begin
               feed = klass.parse(xml)
@@ -237,7 +241,7 @@ module Feedzirra
             options[:on_failure].call(url, c.response_code, c.header_str, c.body_str) if options.has_key?(:on_failure)
           end
         end
-        
+
         curl.on_failure do |c|
           c = c.select { |e| e.kind_of? Curl::Easy }.first if(c.kind_of? Array)
           add_url_to_multi(multi, url_queue.shift, url_queue, responses, options) unless url_queue.empty?
@@ -247,7 +251,7 @@ module Feedzirra
       end
       multi.add(easy)
     end
-    
+
     # An abstraction for adding a feed by a Feed object to the passed Curb::multi stack.
     #
     # === Parameters
@@ -262,7 +266,7 @@ module Feedzirra
     #                 * :on_failure - Block that gets executed after a failed request.
     # === Returns
     # The updated Curl::Multi object with the request details added to it's stack.
-    def self.add_feed_to_multi(multi, feed, feed_queue, responses, options) 
+    def self.add_feed_to_multi(multi, feed, feed_queue, responses, options)
       easy = Curl::Easy.new(feed.feed_url) do |curl|
         curl.headers["User-Agent"]        = (options[:user_agent] || USER_AGENT)
         curl.headers["If-Modified-Since"] = feed.last_modified.httpdate if feed.last_modified
@@ -306,7 +310,7 @@ module Feedzirra
     end
 
     # Determines the etag from the request headers.
-    # 
+    #
     # === Parameters
     # [header<String>] Raw request header returned from the request
     # === Returns
@@ -327,4 +331,4 @@ module Feedzirra
       Time.parse($1) if $1
     end
   end
-end
+end

data/lib/feedzirra/parser/itunes_category.rb

@@ -0,0 +1,12 @@
+module Feedzirra
+  module Parser
+    class RSS
+      class ITunesCategory
+        include SAXMachine
+
+        element :'itunes:category', :as => :name, :value => :text
+        elements :'itunes:category', :as => :sub_categories, :value => :text
+      end
+    end
+  end
+end

data/lib/feedzirra/parser/mrss_content.rb

@@ -0,0 +1,14 @@
+module Feedzirra
+  module Parser
+    class RSSEntry
+      class MRSSContent
+        include SAXMachine
+
+        element :'media:content', :as => :url, :value => :url
+        element :'media:content', :as => :content_type, :value => :type
+        element :'media:content', :as => :medium, :value => :medium
+        element :'media:content', :as => :duration, :value => :duration
+      end
+    end
+  end
+end

data/lib/feedzirra/parser/mrss_credit.rb

@@ -0,0 +1,13 @@
+module Feedzirra
+  module Parser
+    class RSSEntry
+      class MRSSCredit
+        include SAXMachine
+
+        element :'media:credit', :as => :role, :value => :role
+        element :'media:credit', :as => :scheme, :value => :scheme
+        element :'media:credit', :as => :name
+      end
+    end
+  end
+end

data/lib/feedzirra/parser/mrss_restriction.rb

@@ -0,0 +1,13 @@
+module Feedzirra
+  module Parser
+    class RSSEntry
+      class MRSSRestriction
+        include SAXMachine
+
+        element :'media:restriction', :as => :value
+        element :'media:restriction', :as => :scope, :value => :type
+        element :'media:restriction', :as => :relationship, :value => :relationship
+      end
+    end
+  end
+end

data/lib/feedzirra/parser/rss.rb

@@ -1,28 +1,57 @@
 module Feedzirra
-  
   module Parser
     # == Summary
     # Parser for dealing with RSS feeds.
     #
-    # == Attributes
-    # * title
-    # * feed_url
-    # * url
-    # * entries
     class RSS
       include SAXMachine
       include FeedUtilities
+
+      attr_accessor :feed_url
+
+      # RSS 2.0 required elements
       element :title
       element :link, :as => :url
+      element :description
       elements :item, :as => :entries, :class => RSSEntry
 
-      attr_accessor :feed_url
+      # RSS 2.0 optional elements
+      element :language
+      element :copyright
+      element :managingEditor
+      element :webMaster
+      element :pubDate
+      element :lastBuildDate
+      element :category
+      element :generator
+      element :docs
+      element :cloud
+      element :ttl
+      element :image, :class => RSSImage
+      element :rating
+      element :textInput
+      element :skipHours
+      element :skipDays
+
+      # iTunes
+      element :'itunes:author', :as => :author
+      element :'itunes:block', :as => :itunes_block
+      element :'itunes:image', :as => :image, :value => :href
+      element :'itunes:explicit', :as => :explicit
+      element :'itunes:keywords', :as => :keywords
+      element :'itunes:new-feed-url', :as => :feed_url
+      element :'itunes:name', :as => :owner_name
+      element :'itunes:email', :as => :owner_email
+      element :'itunes:subtitle', :as => :subtitle
+      element :'itunes:summary', :as => :summary
+
+      elements :'itunes:category', :as => :categories, :value => :text
+      # elements :'itunes:category', :as => :itunes_categories,
+      #   :class => ITunesCategory
 
       def self.able_to_parse?(xml) #:nodoc:
         xml =~ /\<rss|rdf/
       end
     end
-
   end
-  
 end

data/lib/feedzirra/parser/rss_entry.rb

@@ -1,5 +1,8 @@
+require File.dirname(__FILE__) + '/mrss_content'
+require File.dirname(__FILE__) + '/mrss_credit'
+require File.dirname(__FILE__) + '/mrss_restriction'
+
 module Feedzirra
-  
   module Parser
     # == Summary
     # Parser for dealing with RDF feed entries.
@@ -15,28 +18,71 @@ module Feedzirra
     class RSSEntry
       include SAXMachine
       include FeedEntryUtilities
+
+      # RSS 2.0 elements
       element :title
       element :link, :as => :url
-
-      element :"dc:creator", :as => :author
-      element :author, :as => :author
-      element :"content:encoded", :as => :content
       element :description, :as => :summary
-
+      element :author
+      elements :category, :as => :categories
+      element :comments
+      element :guid, :as => :id
       element :pubDate, :as => :published
-      element :pubdate, :as => :published
+      element :source
+      element :enclosure, :value => :length, :as => :enclosure_length
+      element :enclosure, :value => :type, :as => :enclosure_type
+      element :enclosure, :value => :url, :as => :enclosure_url
+
+
+      # RDF elements
       element :"dc:date", :as => :published
       element :"dc:Date", :as => :published
       element :"dcterms:created", :as => :published
+      element :issued, :as => :published
+      element :"content:encoded", :as => :content
+      element :"dc:creator", :as => :author
+      element :"dcterms:modified", :as => :updated
 
+      # MediaRSS support
+      element :'media:thumbnail', :as => :media_thumbnail, :value => :url
+      element :'media:thumbnail', :as => :media_thumbnail_width, :value => :width
+      element :'media:thumbnail', :as => :media_thumbnail_height, :value => :height
+      element :'media:description', :as => :media_description
 
-      element :"dcterms:modified", :as => :updated
-      element :issued, :as => :published
-      elements :category, :as => :categories
+      element :'media:rating', :as => :rating
+      element :'media:rating', :value => :scheme, :as => :rating_scheme
 
-      element :guid, :as => :id
-    end
+      element :'media:title', :as => :media_title
+      element :'media:keywords', :as => :media_keywords
+
+      element :'media:category', :as => :media_category
+      element :'media:category', :value => :scheme, :as => :media_category_scheme
+      element :'media:category', :value => :label, :as => :media_category_label
+
+      element :'media:hash', :as => :media_hash
+      element :'media:hash', :value => :algo, :as => :media_hash_algo
 
+      element :'media:player', :value => :url, :as => :media_player_url
+      element :'media:player', :value => :width, :as => :media_player_width
+      element :'media:player', :value => :height, :as => :media_player_height
+
+      elements :'media:credit', :as => :credits, :class => MRSSCredit
+
+      element :'media:copyright', :as => :copyright
+      element :'media:copyright', :as => :copyright_url, :value => :url
+
+      element :'media:restriction', :as => :media_restriction, :class => MRSSRestriction
+
+      elements :'media:content', :as => :media_content, :class => MRSSContent
+
+      # iTunes
+      element :'itunes:author', :as => :author
+      element :'itunes:block', :as => :itunes_block
+      element :'itunes:duration', :as => :duration
+      element :'itunes:explicit', :as => :explicit
+      element :'itunes:keywords', :as => :keywords
+      element :'itunes:subtitle', :as => :subtitle
+      element :'itunes:summary', :as => :summary
+    end
   end
-  
-end
+end

data/lib/feedzirra/parser/rss_image.rb

@@ -0,0 +1,15 @@
+module Feedzirra
+  module Parser
+    class RSS
+      class RSSImage
+        include SAXMachine
+
+        element :title
+        element :link
+        element :url
+        element :width
+        element :height
+      end
+    end
+  end
+end

data/spec/feedzirra/feed_spec.rb

@@ -5,20 +5,20 @@ describe Feedzirra::Feed do
     before(:all) do
       Feedzirra::Feed.add_common_feed_entry_element("wfw:commentRss", :as => :comment_rss)
     end
-    
+
     it "should parse the added element out of Atom feeds" do
       Feedzirra::Feed.parse(sample_wfw_feed).entries.first.comment_rss.should == "this is the new val"
     end
-    
+
     it "should parse the added element out of Atom Feedburner feeds" do
       Feedzirra::Parser::AtomEntry.new.should respond_to(:comment_rss)
     end
-    
+
     it "should parse the added element out of RSS feeds" do
       Feedzirra::Parser::RSSEntry.new.should respond_to(:comment_rss)
     end
   end
-  
+
   describe "#parse" do # many of these tests are redundant with the specific feed type tests, but I put them here for completeness
     context "when there's an available parser" do
       it "should parse an rdf feed" do
@@ -47,17 +47,17 @@ describe Feedzirra::Feed do
         feed.title.should == "Paul Dix Explains Nothing"
         feed.entries.first.published.to_s.should == "Thu Jan 22 15:50:22 UTC 2009"
         feed.entries.size.should == 5
-      end      
+      end
 
       it "should parse an itunes feed as a standard RSS feed" do
         feed = Feedzirra::Feed.parse(sample_itunes_feed)
         feed.title.should == "All About Everything"
         feed.entries.first.published.should == Time.parse("Wed, 15 Jun 2005 19:00:00 GMT")
-        
+
         # Since the commit 621957879, iTunes feeds will be parsed as standard RSS, so this
         # entry should now not have a method for itunes_author.
         feed.entries.first.should_not respond_to(:itunes_author)
-        feed.entries.size.should == 3
+        feed.entries.size.should == 4
       end
     end
 
@@ -113,7 +113,7 @@ describe Feedzirra::Feed do
           true
         end
       end
-      
+
       new_feed_type.should be_able_to_parse(feed_text)
       Feedzirra::Feed.add_feed_class(new_feed_type)
       Feedzirra::Feed.determine_feed_parser_for_xml(feed_text).should == new_feed_type
@@ -165,7 +165,7 @@ describe Feedzirra::Feed do
         @curl_easy = stub('curl_easy')
         @curl = stub('curl', :headers => {}, :follow_location= => true, :on_failure => true)
         @curl.stub!(:on_success).and_yield(@cmock)
-        
+
         Curl::Multi.stub!(:new).and_return(@multi)
         Curl::Easy.stub!(:new).and_yield(@curl).and_return(@curl_easy)
       end
@@ -179,7 +179,7 @@ describe Feedzirra::Feed do
         Feedzirra::Feed.fetch_raw(@paul_feed[:url])
         @curl.headers['User-Agent'].should == Feedzirra::Feed::USER_AGENT
       end
-      
+
       it "should set if modified since as an option if passed" do
         Feedzirra::Feed.fetch_raw(@paul_feed[:url], :if_modified_since => Time.parse("Wed, 28 Jan 2009 04:10:32 GMT"))
         @curl.headers["If-Modified-Since"].should == 'Wed, 28 Jan 2009 04:10:32 GMT'
@@ -189,7 +189,7 @@ describe Feedzirra::Feed do
         Feedzirra::Feed.fetch_raw(@paul_feed[:url], :if_none_match => 'ziEyTl4q9GH04BR4jgkImd0GvSE')
         @curl.headers["If-None-Match"].should == 'ziEyTl4q9GH04BR4jgkImd0GvSE'
       end
-      
+
       it 'should set userpwd for http basic authentication if :http_authentication is passed' do
         @curl.should_receive(:userpwd=).with('username:password')
         Feedzirra::Feed.fetch_raw(@paul_feed[:url], :http_authentication => ['username', 'password'])
@@ -207,7 +207,7 @@ describe Feedzirra::Feed do
       it "should take multiple feed urls and return a hash of urls and response xml" do
         multi = stub('curl_multi', :add => true, :perform => true)
         Curl::Multi.stub!(:new).and_return(multi)
-        
+
         paul_response = stub('paul_response', :header_str => '', :body_str => @paul_feed[:xml] )
         trotter_response = stub('trotter_response', :header_str => '', :body_str => @trotter_feed[:xml] )
 
@@ -216,10 +216,10 @@ describe Feedzirra::Feed do
 
         trotter_curl = stub('trotter_curl', :headers => {}, :follow_location= => true, :on_failure => true)
         trotter_curl.stub!(:on_success).and_yield(trotter_response)
-        
+
         Curl::Easy.should_receive(:new).with(@paul_feed[:url]).ordered.and_yield(paul_curl)
         Curl::Easy.should_receive(:new).with(@trotter_feed[:url]).ordered.and_yield(trotter_curl)
-        
+
         results = Feedzirra::Feed.fetch_raw([@paul_feed[:url], @trotter_feed[:url]])
         results.keys.should include(@paul_feed[:url])
         results.keys.should include(@trotter_feed[:url])
@@ -238,7 +238,7 @@ describe Feedzirra::Feed do
         @multi = Curl::Multi.new(@paul_feed[:url])
         @multi.stub!(:add)
         @easy_curl = Curl::Easy.new(@paul_feed[:url])
-        
+
         Curl::Easy.should_receive(:new).and_yield(@easy_curl)
       end
 
@@ -246,12 +246,12 @@ describe Feedzirra::Feed do
         Feedzirra::Feed.add_url_to_multi(@multi, @paul_feed[:url], [], {}, :user_agent => 'My cool application')
         @easy_curl.headers["User-Agent"].should == 'My cool application'
       end
-      
+
       it "should set user agent to default if it's not passed as an option" do
         Feedzirra::Feed.add_url_to_multi(@multi, @paul_feed[:url], [], {}, {})
         @easy_curl.headers["User-Agent"].should == Feedzirra::Feed::USER_AGENT
       end
-      
+
       it "should set if modified since as an option if passed" do
         Feedzirra::Feed.add_url_to_multi(@multi, @paul_feed[:url], [], {}, :if_modified_since => Time.parse("Jan 25 2009 04:10:32 GMT"))
         @easy_curl.headers["If-Modified-Since"].should == 'Sun, 25 Jan 2009 04:10:32 GMT'
@@ -261,12 +261,12 @@ describe Feedzirra::Feed do
         @easy_curl.should_receive(:follow_location=).with(true)
         Feedzirra::Feed.add_url_to_multi(@multi, @paul_feed[:url], [], {}, {})
       end
-      
+
       it 'should set userpwd for http basic authentication if :http_authentication is passed' do
         Feedzirra::Feed.add_url_to_multi(@multi, @paul_feed[:url], [], {}, :http_authentication => ['myusername', 'mypassword'])
         @easy_curl.userpwd.should == 'myusername:mypassword'
       end
-      
+
       it 'should set accepted encodings' do
         Feedzirra::Feed.add_url_to_multi(@multi, @paul_feed[:url], [], {}, {:compress => true})
         @easy_curl.headers["Accept-encoding"].should == 'gzip, deflate'
@@ -276,7 +276,7 @@ describe Feedzirra::Feed do
         Feedzirra::Feed.add_url_to_multi(@multi, @paul_feed[:url], [], {}, :if_none_match => 'ziEyTl4q9GH04BR4jgkImd0GvSE')
         @easy_curl.headers["If-None-Match"].should == 'ziEyTl4q9GH04BR4jgkImd0GvSE'
       end
-      
+
       describe 'on success' do
         before(:each) do
           @feed = mock('feed', :feed_url= => true, :etag= => true, :last_modified= => true)
@@ -292,7 +292,7 @@ describe Feedzirra::Feed do
           Feedzirra::Feed.add_url_to_multi(@multi, @paul_feed[:url], [], {}, {})
           @easy_curl.on_success.call(@easy_curl)
         end
-        
+
         it 'should determine the xml parser class' do
           Feedzirra::Feed.should_receive(:determine_feed_parser_for_xml).with(@paul_feed[:xml]).and_return(Feedzirra::Parser::AtomFeedBurner)
           Feedzirra::Feed.add_url_to_multi(@multi, @paul_feed[:url], [], {}, {})
@@ -304,7 +304,7 @@ describe Feedzirra::Feed do
           Feedzirra::Feed.add_url_to_multi(@multi, @paul_feed[:url], [], {}, {})
           @easy_curl.on_success.call(@easy_curl)
         end
-        
+
         describe 'when a compatible xml parser class is found' do
           it 'should set the last effective url to the feed url' do
             @easy_curl.should_receive(:last_effective_url).and_return(@paul_feed[:url])
@@ -329,11 +329,11 @@ describe Feedzirra::Feed do
             responses = {}
             Feedzirra::Feed.add_url_to_multi(@multi, @paul_feed[:url], [], responses, {})
             @easy_curl.on_success.call(@easy_curl)
-            
+
             responses.length.should == 1
             responses['http://feeds.feedburner.com/PaulDixExplainsNothing'].should == @feed
           end
-          
+
           it 'should call proc if :on_success option is passed' do
             success = lambda { |url, feed| }
             success.should_receive(:call).with(@paul_feed[:url], @feed)
@@ -363,7 +363,7 @@ describe Feedzirra::Feed do
           Feedzirra::Feed.add_url_to_multi(@multi, @paul_feed[:url], [], {}, { :on_failure => failure })
           @easy_curl.on_failure.call(@easy_curl)
         end
-        
+
         it 'should return the http code in the responses' do
           responses = {}
           Feedzirra::Feed.add_url_to_multi(@multi, @paul_feed[:url], [], responses, {})
@@ -389,14 +389,14 @@ describe Feedzirra::Feed do
         Feedzirra::Feed.add_feed_to_multi(@multi, @feed, [], {}, :user_agent => 'My cool application')
         @easy_curl.headers["User-Agent"].should == 'My cool application'
       end
-      
+
       it "should set user agent to default if it's not passed as an option" do
         Feedzirra::Feed.add_feed_to_multi(@multi, @feed, [], {}, {})
         @easy_curl.headers["User-Agent"].should == Feedzirra::Feed::USER_AGENT
       end
 
       it "should set if modified since as an option if passed"
-      
+
       it 'should set follow location to true' do
         @easy_curl.should_receive(:follow_location=).with(true)
         Feedzirra::Feed.add_feed_to_multi(@multi, @feed, [], {}, {})
@@ -425,7 +425,7 @@ describe Feedzirra::Feed do
         end
 
         it 'should process the next feed in the queue'
-        
+
         it 'should parse the updated feed' do
           Feedzirra::Parser::AtomFeedBurner.should_receive(:parse).and_return(@new_feed)
           Feedzirra::Feed.add_feed_to_multi(@multi, @feed, [], {}, {})
@@ -466,7 +466,7 @@ describe Feedzirra::Feed do
           Feedzirra::Feed.add_feed_to_multi(@multi, @feed, [], {}, { :on_success => success })
           @easy_curl.on_success.call(@easy_curl)
         end
-        
+
         it 'should call update from feed on the old feed with the updated feed' do
           @feed.should_receive(:update_from_feed).with(@new_feed)
           Feedzirra::Feed.add_feed_to_multi(@multi, @feed, [], {}, {})
@@ -491,7 +491,7 @@ describe Feedzirra::Feed do
           Feedzirra::Feed.add_feed_to_multi(@multi, @feed, [], {}, { :on_success => success })
           @easy_curl.on_failure.call(@easy_curl)
         end
-        
+
         it 'should return the http code in the responses' do
           responses = {}
           Feedzirra::Feed.add_feed_to_multi(@multi, @feed, [], responses, {})
@@ -523,7 +523,7 @@ describe Feedzirra::Feed do
         Zlib::GzipReader.should_receive(:new).with(string_io).and_return(string_io)
         Feedzirra::Feed.decode_content(@curl_easy)
       end
-      
+
       it 'should deflate the response body using inflate if the Content-Encoding: is deflate' do
         @curl_easy.stub!(:header_str).and_return('Content-Encoding: deflate')
         Zlib::Inflate.should_receive(:inflate).with(@curl_easy.body_str)
@@ -540,7 +540,7 @@ describe Feedzirra::Feed do
       it 'should perform the updating using multicurl'
       it "should pass any request options through to add_feed_to_multi"
       it "should return a feed object if a single feed is passed in"
-      it "should return an return an array of feed objects if multiple feeds are passed in" 
+      it "should return an return an array of feed objects if multiple feeds are passed in"
     end
   end
 end

data/spec/feedzirra/parser/rss_entry_spec.rb

@@ -1,32 +1,32 @@
 require File.join(File.dirname(__FILE__), %w[.. .. spec_helper])
 
 describe Feedzirra::Parser::RSSEntry do
-  before(:each) do
+  before do
     # I don't really like doing it this way because these unit test should only rely on RSSEntry,
     # but this is actually how it should work. You would never just pass entry xml straight to the AtomEnry
     @entry = Feedzirra::Parser::RSS.parse(sample_rss_feed).entries.first
   end
-  
+
   it "should parse the title" do
     @entry.title.should == "Nokogiri’s Slop Feature"
   end
-  
+
   it "should parse the url" do
     @entry.url.should == "http://tenderlovemaking.com/2008/12/04/nokogiris-slop-feature/"
   end
-  
+
   it "should parse the author" do
     @entry.author.should == "Aaron Patterson"
   end
-  
+
   it "should parse the content" do
     @entry.content.should == sample_rss_entry_content
   end
-  
+
   it "should provide a summary" do
     @entry.summary.should == "Oops!  When I released nokogiri version 1.0.7, I totally forgot to talk about Nokogiri::Slop() feature that was added.  Why is it called \"slop\"?  It lets you sloppily explore documents.  Basically, it decorates your document with method_missing() that allows you to search your document via method calls.\nGiven this document:\n\ndoc = Nokogiri::Slop(<<-eohtml)\n<html>\n  <body>\n  [...]"
   end
-  
+
   it "should parse the published date" do
     @entry.published.to_s.should == "Thu Dec 04 17:17:49 UTC 2008"
   end
@@ -34,8 +34,121 @@ describe Feedzirra::Parser::RSSEntry do
   it "should parse the categories" do
     @entry.categories.should == ['computadora', 'nokogiri', 'rails']
   end
-  
+
   it "should parse the guid as id" do
     @entry.id.should == "http://tenderlovemaking.com/?p=198"
   end
+
+  describe "parsing an iTunes feed" do
+    before do
+      @item = Feedzirra::Parser::RSS.parse(sample_itunes_feed).entries.first
+    end
+
+    it "should parse the title" do
+      @item.title.should == "Shake Shake Shake Your Spices"
+    end
+
+    it "should parse the author" do
+      @item.author.should == "John Doe"
+    end
+
+    it "should parse the subtitle" do
+      @item.subtitle.should == "A short primer on table spices"
+    end
+
+    it "should parse the summary" do
+      @item.summary.should == "This week we talk about salt and pepper shakers, comparing and contrasting pour rates, construction materials, and overall aesthetics. Come and join the party!"
+    end
+
+    it "should parse the enclosure" do
+      @item.enclosure_length.should == "8727310"
+      @item.enclosure_type.should == "audio/x-m4a"
+      @item.enclosure_url.should == "http://example.com/podcasts/everything/AllAboutEverythingEpisode3.m4a"
+    end
+
+    it "should parse the id" do
+      @item.id.should == "http://example.com/podcasts/archive/aae20050615.m4a"
+    end
+
+    it "should parse the published date" do
+      @item.published.should == Time.parse('Wed Jun 15 19:00:00 UTC 2005')
+    end
+
+    it "should parse the duration" do
+      @item.duration.should == "7:04"
+    end
+
+    it "should parse the keywords" do
+      @item.keywords.should == "salt, pepper, shaker, exciting"
+    end
+  end
+
+  describe "parsing Media RSS" do
+    before do
+      @item = Feedzirra::Parser::RSS.parse(sample_mrss_feed).entries.first
+    end
+
+    it "should parse media:rating" do
+      @item.rating.should == 'adult'
+      @item.rating_scheme.should == 'urn:simple'
+    end
+
+    it "should parse media:title" do
+      @item.media_title.should == 'The Montauk Monster-Hells Visits New York!'
+    end
+
+    it "should parse media:description" do
+      @item.media_description.should == 'The story began with a July 23 article in a local newspaper, The Independent. Jenna Hewitt, 26, of Montauk, and three friends said they found the ...'
+    end
+
+    it "should parse media:keywords" do
+      @item.media_keywords.should == 'kitty, cat, big dog, yarn, fluffy'
+    end
+
+    it "should parse media:tumbnail" do
+      @item.media_content.size.should == 1
+      @item.media_description.should == 'The story began with a July 23 article in a local newspaper, The Independent. Jenna Hewitt, 26, of Montauk, and three friends said they found the ...'
+      @item.media_thumbnail.should == 'http://3.gvt0.com/vi/Y3rNEu4A8WM/default.jpg'
+      @item.media_thumbnail_width.should == '320'
+      @item.media_thumbnail_height.should == '240'
+    end
+
+    it "should parse media:category" do
+      @item.media_category.should == 'Arts/Movies/Titles/A/Ace_Ventura_Series/Ace_Ventura_-_Pet_Detective'
+      @item.media_category_scheme.should == 'http://dmoz.org'
+      @item.media_category_label.should == 'Ace Ventura - Pet Detective'
+    end
+
+    it "should parse media:hash" do
+      @item.media_hash.should == 'dfdec888b72151965a34b4b59031290a'
+      @item.media_hash_algo.should == 'md5'
+    end
+
+    it "should parse media:player" do
+      @item.media_player_url.should == 'http://www.example.com/player?id=1111'
+      @item.media_player_width.should == '400'
+      @item.media_player_height.should == '200'
+    end
+
+    it "should parse media:credit" do
+      @item.credits.size.should == 2
+      @item.credits.first.role.should == 'producer'
+      @item.credits.first.scheme.should == 'urn:ebu'
+      pending 'not sure why the name isn\'t getting set'
+      @item.credits.first.name.should == 'John Doe'
+    end
+
+    it "should parse media:copyright" do
+      @item.copyright.should == '2009 Example Co.'
+      @item.copyright_url.should == 'http://example.com/copyright.html'
+    end
+
+    it "should parse media:restriction" do
+      pending 'need to figure out why this is getting String'
+      @item.media_restriction.type.should == 'MRSSRestriction'
+      @item.media_restriction.value.should == 'au us'
+      @item.media_restriction.scope.should == 'country'
+      @item.media_restriction.relationship.should == 'allow'
+    end
+  end
 end

data/spec/feedzirra/parser/rss_spec.rb

@@ -6,36 +6,88 @@ describe Feedzirra::Parser::RSS do
       Feedzirra::Parser::RSS.should be_able_to_parse(sample_rss_feed)
     end
 
-    # this is no longer true. combined rdf and rss into one
-    # it "should return false for an rdf feed" do
-    #   Feedzirra::RSS.should_not be_able_to_parse(sample_rdf_feed)
-    # end
-    
+    it "should return true for an rdf feed" do
+      Feedzirra::Parser::RSS.should be_able_to_parse(sample_rdf_feed)
+    end
+
+    it "should return true for an iTunes feed" do
+      Feedzirra::Parser::RSS.should be_able_to_parse(sample_itunes_feed)
+    end
+
     it "should return fase for an atom feed" do
       Feedzirra::Parser::RSS.should_not be_able_to_parse(sample_atom_feed)
     end
   end
 
   describe "parsing" do
-    before(:each) do
-      @feed = Feedzirra::Parser::RSS.parse(sample_rss_feed)
+    before do
+      @feed = Feedzirra::Parser::RSS.parse(sample_mrss_feed)
     end
-    
+
     it "should parse the title" do
-      @feed.title.should == "Tender Lovemaking"
+      @feed.title.should == "Google Video - Hot videos"
     end
-    
+
     it "should parse the url" do
-      @feed.url.should == "http://tenderlovemaking.com"
+      @feed.url.should == "http://video.google.com/"
     end
-    
+
     it "should provide an accessor for the feed_url" do
       @feed.respond_to?(:feed_url).should == true
       @feed.respond_to?(:feed_url=).should == true
     end
-    
+
     it "should parse entries" do
-      @feed.entries.size.should == 10
+      @feed.entries.size.should == 20
+    end
+
+    it "should parse the image" do
+      pending 'setting NilClass for some reason'
+      @feed.image.class.should == 'RSSImage'
+      @feed.image.title.should == 'Google Video - Hot videos'
+      @feed.image.link.should == 'http://video.google.com/'
+      @feed.image.url.should == 'http://video.google.com/common/google_logo_small.jpg'
+      @feed.image.width.should == '100'
+      @feed.image.height.should == '37'
+    end
+
+    describe "parsing an iTunes feed" do
+      before do
+        @feed = Feedzirra::Parser::RSS.parse(sample_itunes_feed)
+      end
+
+      it "should parse an image" do
+        @feed.image.should == "http://example.com/podcasts/everything/AllAboutEverything.jpg"
+      end
+
+      it "should parse categories" do
+        @feed.categories.size == 2
+        @feed.categories[0].should == "Technology"
+        @feed.categories[1].should == "Gadgets"
+        @feed.categories[2].should == "TV & Film"
+
+        # @feed.categories[0].name.should == "Technology"
+        # @feed.categories[0].sub_categories.size.should == 1
+        # @feed.categories[0].sub_categories[0].should == "Gadgets"
+        # @feed.categories[1].name.should == "TV & Film"
+        # @feed.categories[1].sub_categories.size.should == 0
+      end
+
+      it "should parse the summary" do
+        @feed.summary.should == "All About Everything is a show about everything. Each week we dive into any subject known to man and talk about it as much as we can. Look for our Podcast in the iTunes Music Store"
+      end
+
+      it "should parse entries" do
+        @feed.entries.size.should == 4
+      end
+
+      it "should parse the owner name" do
+        @feed.owner_name.should == 'John Doe'
+      end
+
+      it "should parse the owner email" do
+        @feed.owner_email.should == 'john.doe@example.com'
+      end
     end
   end
 end

data/spec/spec_helper.rb

@@ -55,4 +55,8 @@ end
 
 def sample_wfw_feed
   load_sample("PaulDixExplainsNothingWFW.xml")
-end
+end
+
+def sample_mrss_feed
+  load_sample("GoogleVideoSample.xml")
+end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification 
 name: logophobia-feedzirra
 version: !ruby/object:Gem::Version 
-  version: 0.0.15
+  version: 0.0.16
 platform: ruby
 authors: 
 - Paul Dix
@@ -89,11 +89,13 @@ files:
 - lib/feedzirra/parser/atom_entry.rb
 - lib/feedzirra/parser/atom_feed_burner.rb
 - lib/feedzirra/parser/atom_feed_burner_entry.rb
-- lib/feedzirra/parser/itunes_rss.rb
-- lib/feedzirra/parser/itunes_rss_item.rb
-- lib/feedzirra/parser/itunes_rss_owner.rb
+- lib/feedzirra/parser/itunes_category.rb
 - lib/feedzirra/parser/rss.rb
 - lib/feedzirra/parser/rss_entry.rb
+- lib/feedzirra/parser/rss_image.rb
+- lib/feedzirra/parser/mrss_content.rb
+- lib/feedzirra/parser/mrss_credit.rb
+- lib/feedzirra/parser/mrss_restriction.rb
 - lib/feedzirra/feed_utilities.rb
 - lib/feedzirra/feed_entry_utilities.rb
 - README.textile
@@ -105,9 +107,6 @@ files:
 - spec/feedzirra/parser/atom_entry_spec.rb
 - spec/feedzirra/parser/atom_feed_burner_spec.rb
 - spec/feedzirra/parser/atom_feed_burner_entry_spec.rb
-- spec/feedzirra/parser/itunes_rss_spec.rb
-- spec/feedzirra/parser/itunes_rss_item_spec.rb
-- spec/feedzirra/parser/itunes_rss_owner_spec.rb
 - spec/feedzirra/parser/rss_spec.rb
 - spec/feedzirra/parser/rss_entry_spec.rb
 - spec/feedzirra/feed_utilities_spec.rb

data/lib/feedzirra/parser/itunes_rss.rb

@@ -1,50 +0,0 @@
-module Feedzirra
-  
-  module Parser
-    # iTunes is RSS 2.0 + some apple extensions
-    # Source: http://www.apple.com/itunes/whatson/podcasts/specs.html
-    class ITunesRSS
-      include SAXMachine
-      include FeedUtilities
-
-      attr_accessor :feed_url
-
-      # RSS 2.0 elements that need including
-      element :copyright
-      element :description
-      element :language
-      element :managingEditor
-      element :title
-      element :link, :as => :url
-
-      # If author is not present use managingEditor on the channel
-      element :"itunes:author", :as => :itunes_author
-      element :"itunes:block", :as => :itunes_block
-      element :"itunes:image", :value => :href, :as => :itunes_image
-      element :"itunes:explicit", :as => :itunes_explicit
-      element :"itunes:keywords", :as => :itunes_keywords
-      # New URL for the podcast feed
-      element :"itunes:new-feed-url", :as => :itunes_new_feed_url
-      element :"itunes:subtitle", :as => :itunes_subtitle
-      # If summary is not present, use the description tag
-      element :"itunes:summary", :as => :itunes_summary
-
-      # iTunes RSS feeds can have multiple main categories...
-      # ...and multiple sub-categories per category
-      # TODO subcategories not supported correctly - they are at the same level
-      #   as the main categories
-      elements :"itunes:category", :as => :itunes_categories, :value => :text
-
-      elements :"itunes:owner", :as => :itunes_owners, :class => ITunesRSSOwner
-
-      elements :item, :as => :entries, :class => ITunesRSSItem
-
-      def self.able_to_parse?(xml)
-        xml =~ /xmlns:itunes=\"http:\/\/www.itunes.com\/dtds\/podcast-1.0.dtd\"/
-      end
-
-    end
-    
-  end
-  
-end

data/lib/feedzirra/parser/itunes_rss_item.rb

@@ -1,31 +0,0 @@
-module Feedzirra
-  
-  module Parser
-    # iTunes extensions to the standard RSS2.0 item
-    # Source: http://www.apple.com/itunes/whatson/podcasts/specs.html
-    class ITunesRSSItem
-      include SAXMachine
-      include FeedUtilities
-      element :author
-      element :guid
-      element :title
-      element :link, :as => :url
-      element :description, :as => :summary
-      element :pubDate, :as => :published
-
-      # If author is not present use author tag on the item
-      element :"itunes:author", :as => :itunes_author
-      element :"itunes:block", :as => :itunes_block
-      element :"itunes:duration", :as => :itunes_duration
-      element :"itunes:explicit", :as => :itunes_explicit
-      element :"itunes:keywords", :as => :itunes_keywords
-      element :"itunes:subtitle", :as => :itunes_subtitle
-      # If summary is not present, use the description tag
-      element :"itunes:summary", :as => :itunes_summary
-      element :enclosure, :value => :length, :as => :enclosure_length
-      element :enclosure, :value => :type, :as => :enclosure_type
-      element :enclosure, :value => :url, :as => :enclosure_url
-    end
-  end
-  
-end

data/lib/feedzirra/parser/itunes_rss_owner.rb

@@ -1,12 +0,0 @@
-module Feedzirra
-  
-  module Parser
-    class ITunesRSSOwner
-      include SAXMachine
-      include FeedUtilities
-      element :"itunes:name", :as => :name
-      element :"itunes:email", :as => :email
-    end
-  end
-  
-end

data/spec/feedzirra/parser/itunes_rss_item_spec.rb

@@ -1,48 +0,0 @@
-require File.join(File.dirname(__FILE__), %w[.. .. spec_helper])
-
-describe Feedzirra::Parser::ITunesRSSItem do
-  before(:each) do
-    # I don't really like doing it this way because these unit test should only rely on ITunesRssItem,
-    # but this is actually how it should work. You would never just pass entry xml straight to the ITunesRssItem
-    @item = Feedzirra::Parser::ITunesRSS.parse(sample_itunes_feed).entries.first
-  end
-  
-  it "should parse the title" do
-    @item.title.should == "Shake Shake Shake Your Spices"
-  end
-  
-  it "should parse the author" do
-    @item.itunes_author.should == "John Doe"
-  end  
-
-  it "should parse the subtitle" do
-    @item.itunes_subtitle.should == "A short primer on table spices"
-  end  
-
-  it "should parse the summary" do
-    @item.itunes_summary.should == "This week we talk about salt and pepper shakers, comparing and contrasting pour rates, construction materials, and overall aesthetics. Come and join the party!"
-  end  
-
-  it "should parse the enclosure" do
-    @item.enclosure_length.should == "8727310"
-    @item.enclosure_type.should == "audio/x-m4a"
-    @item.enclosure_url.should == "http://example.com/podcasts/everything/AllAboutEverythingEpisode3.m4a"
-  end  
-
-  it "should parse the guid" do
-    @item.guid.should == "http://example.com/podcasts/archive/aae20050615.m4a"
-  end  
-
-  it "should parse the published date" do
-    @item.published.should == "Wed, 15 Jun 2005 19:00:00 GMT"
-  end  
-
-  it "should parse the duration" do
-    @item.itunes_duration.should == "7:04"
-  end  
-
-  it "should parse the keywords" do
-    @item.itunes_keywords.should == "salt, pepper, shaker, exciting"
-  end  
-
-end

data/spec/feedzirra/parser/itunes_rss_owner_spec.rb

@@ -1,18 +0,0 @@
-require File.join(File.dirname(__FILE__), %w[.. .. spec_helper])
-
-describe Feedzirra::Parser::ITunesRSSOwner do
-  before(:each) do
-    # I don't really like doing it this way because these unit test should only rely on RSSEntry,
-    # but this is actually how it should work. You would never just pass entry xml straight to the ITunesRssOwner
-    @owner = Feedzirra::Parser::ITunesRSS.parse(sample_itunes_feed).itunes_owners.first
-  end
-  
-  it "should parse the name" do
-    @owner.name.should == "John Doe"
-  end
-  
-  it "should parse the email" do
-    @owner.email.should == "john.doe@example.com"
-  end  
-
-end

data/spec/feedzirra/parser/itunes_rss_spec.rb

@@ -1,50 +0,0 @@
-require File.join(File.dirname(__FILE__), %w[.. .. spec_helper])
-
-describe Feedzirra::Parser::ITunesRSS do
-  describe "#will_parse?" do
-    it "should return true for an itunes RSS feed" do
-      Feedzirra::Parser::ITunesRSS.should be_able_to_parse(sample_itunes_feed)
-    end
-
-    it "should return fase for an atom feed" do
-      Feedzirra::Parser::ITunesRSS.should_not be_able_to_parse(sample_atom_feed)
-    end
-  end
-
-  describe "parsing" do
-    before(:each) do
-      @feed = Feedzirra::Parser::ITunesRSS.parse(sample_itunes_feed)
-    end
-    
-    it "should parse the subtitle" do
-      @feed.itunes_subtitle.should == "A show about everything"
-    end
-    
-    it "should parse the author" do
-      @feed.itunes_author.should == "John Doe"
-    end
-    
-    it "should parse an owner" do
-      @feed.itunes_owners.size.should == 1
-    end
-    
-    it "should parse an image" do
-      @feed.itunes_image.should == "http://example.com/podcasts/everything/AllAboutEverything.jpg"
-    end
-    
-    it "should parse categories" do
-      @feed.itunes_categories.size == 3
-      @feed.itunes_categories[0] == "Technology"
-      @feed.itunes_categories[1] == "Gadgets"
-      @feed.itunes_categories[2] == "TV & Film"
-    end
-
-    it "should parse the summary" do
-      @feed.itunes_summary.should == "All About Everything is a show about everything. Each week we dive into any subject known to man and talk about it as much as we can. Look for our Podcast in the iTunes Music Store"
-    end
-    
-    it "should parse entries" do
-      @feed.entries.size.should == 3
-    end
-  end
-end