urss 0.0.3 → 0.3.0

data/README.md

@@ -82,6 +82,12 @@ rss.entries.first.medias.first.content_url
 #=> http://farm9.staticflickr.com/8159/6960539484_56665aba46_b.jpg
 ````
 
+## Reporting not working Feed
+
+If you encounter a Feed (RSS or Atom) where an attribute is not well parsed: Open an issue with a dump of the feed.
+
+You can use `curl` to do this and post the output (Use [gists](https://gist.github.com/) if it is very long).
+
 ## Contributing
 
 1. Fork it

data/lib/urss/feed.rb

@@ -1,7 +1,7 @@
 class Urss::Feed
 
   # ~~~~ Attributes ~~~~
-  attr_accessor :title, :url, :description, :updated_at, :entries
+  attr_accessor :title, :url, :description, :updated_at, :entries, :author
 
   # ~~~~ Class methods ~~~~
 
@@ -12,6 +12,12 @@ class Urss::Feed
     self.description = nil
     self.updated_at = nil
     self.entries = []
+    self.author = nil
+  end
+
+  def finalize!
+    # Fill in all entries author field with the Feed#author content when entry author field is empty
+    self.entries.each{|entry| entry.author = self.author if entry.author.nil? || entry.author == ""}
   end
 
 end

data/lib/urss/feed/atom.rb

@@ -13,6 +13,7 @@ class Urss::Feed::Atom < Urss::Feed
     feed_rss.url = nokogiri_instance.xpath("//#{namespace}#{root_node}/#{namespace}link[@rel='self']").attr("href").value
     feed_rss.description = nokogiri_instance.xpath("//#{namespace}#{root_node}/#{namespace}subtitle").text.strip
     feed_rss.updated_at = nokogiri_instance.xpath("//#{namespace}#{root_node}/#{namespace}updated").text
+    feed_rss.author = nokogiri_instance.xpath("//#{namespace}#{root_node}/#{namespace}author/#{namespace}name").text
     nokogiri_instance.xpath("//#{namespace}entry").each {|item| feed_rss.entries << Urss::Feed::Atom::Entry.build(item, namespace)}
 
     feed_rss

data/lib/urss/feed/atom_entry.rb

@@ -11,10 +11,17 @@ class Urss::Feed::Atom::Entry < Urss::Feed::Entry
     entry.url = nokogiri_instance.xpath("./#{namespace}link[@rel='alternate']").attr("href").value
     entry.created_at = nokogiri_instance.xpath("./#{namespace}published").text
     entry.author = nokogiri_instance.xpath("./#{namespace}author/#{namespace}name").text
-    entry.content = nokogiri_instance.xpath("./description").text
+    entry.content = case nokogiri_instance.xpath("./#{namespace}content").attr("type").value
+    when "xhtml", "html"
+      nokogiri_instance.xpath("./#{namespace}content").inner_html
+    else
+      nokogiri_instance.xpath("./#{namespace}content").text
+    end
 
-    if media_url = nokogiri_instance.xpath("./#{namespace}link[@rel='enclosure']").attr("href").value
-      entry.medias << Urss::Media.new(:content_url => media_url)
+    unless (media = nokogiri_instance.xpath("./#{namespace}link[@rel='enclosure']")).empty?
+      if media_url = media.attr("href").value
+        entry.medias << Urss::Media.new(:content_url => media_url)
+      end
     end
 
     entry

data/lib/urss/feed/entry.rb

@@ -16,5 +16,5 @@ class Urss::Feed::Entry
     self.content = nil
     self.medias = []
   end
-  
+
 end

data/lib/urss/rss.rb

@@ -17,6 +17,9 @@ class Urss::Rss
         when "feed"
           Urss::Feed::Atom
         end.build(root_instance, namespace, root)
+
+        rss_object.finalize!
+
         return rss_object
         break
       end

data/lib/urss/version.rb

@@ -1,3 +1,3 @@
 module Urss
-  VERSION = "0.0.3"
+  VERSION = "0.3.0"
 end

data/spec/spec_helper.rb

@@ -12,6 +12,15 @@ require "support/webmocks"
 
 require "urss"
 
+# Logging is enabled when logs/ folder exists
+logs_path = "logs"
+if File.exists?(logs_path)
+  require "logger"
+  log_file_path = File.join(logs_path, "test.log")
+  FileUtils.touch(log_file_path) unless File.exists?(log_file_path)
+  @@logger = Logger.new(log_file_path)
+end
+
 RSpec.configure do |config|
   
 end

data/spec/support/fixtures/atom_with_html.xml

@@ -0,0 +1,82 @@
+<?xml version="1.0" encoding="utf-8"?>
+<feed xmlns:im="http://itunes.apple.com/rss" xmlns="http://www.w3.org/2005/Atom" xml:lang="en">
+  <id>http://itunes.apple.com/lu/rss/topalbums/limit=10/xml</id>
+  <title>iTunes Store: Top Albums</title>
+  <updated>2012-08-20T10:51:05-07:00</updated>
+  <link rel="alternate" type="text/html" href="http://itunes.apple.com/WebObjects/MZStore.woa/wa/viewTop?id=29763&amp;popId=11&amp;s=143451"/>
+  <link rel="self" href="http://itunes.apple.com/lu/rss/topalbums/limit=10/xml"/>
+  <icon>http://itunes.apple.com/favicon.ico</icon>
+  <author>
+    <name>iTunes Store</name>
+    <uri>http://www.apple.com/uk/itunes/</uri>
+  </author>
+  <rights>Copyright 2008 Apple Inc.</rights>
+  <entry>
+    <updated>2012-08-20T10:51:05-07:00</updated>
+    <id im:id="538385017">http://itunes.apple.com/lu/album/nrj-party-summer-edition-2012/id538385017?uo=2</id>
+    <title>NRJ Party Summer Edition - 2012 - Various Artists</title>
+    <im:name>NRJ Party Summer Edition - 2012</im:name>
+    <link rel="alternate" type="text/html" href="http://itunes.apple.com/lu/album/nrj-party-summer-edition-2012/id538385017?uo=2"/>
+    <im:contentType term="Music" label="Music">
+      <im:contentType term="Album" label="Album"/>
+    </im:contentType>
+    <category im:id="17" term="Dance" scheme="http://itunes.apple.com/lu/genre/music-dance/id17?uo=2" label="Dance"/>
+    <im:artist>Various Artists</im:artist>
+    <im:price amount="9.99000" currency="EUR">9,99 €</im:price>
+    <im:image height="55">http://a5.mzstatic.com/us/r1000/085/Music/v4/81/12/01/811201e7-96da-4c95-4fc1-c85ac3e716b1/5414165055532.55x55-70.jpg</im:image>
+    <im:image height="60">http://a2.mzstatic.com/us/r1000/085/Music/v4/81/12/01/811201e7-96da-4c95-4fc1-c85ac3e716b1/5414165055532.60x60-50.jpg</im:image>
+    <im:image height="170">http://a1.mzstatic.com/us/r1000/085/Music/v4/81/12/01/811201e7-96da-4c95-4fc1-c85ac3e716b1/5414165055532.170x170-75.jpg</im:image>
+    <rights>℗ 2012 541 / N.E.W.S.</rights>
+    <im:releaseDate label="29 June 2012">2012-06-29T00:00:00-07:00</im:releaseDate>
+    <im:itemCount>25</im:itemCount>
+    <content type="html">&lt;table border="0" width="100%"&gt;
+    &lt;tr&gt;
+        &lt;td&gt;
+            &lt;table border="0" width="100%" cellspacing="0" cellpadding="0"&gt;
+                &lt;tr valign="top" align="left"&gt;
+                    
+                        &lt;td align="center" width="166" valign="top"&gt;
+                            &lt;a href="http://itunes.apple.com/lu/album/nrj-party-summer-edition-2012/id538385017?uo=2"&gt;&lt;img border="0" alt="NRJ Party Summer Edition - 2012artwork" src="http://a1.mzstatic.com/us/r1000/085/Music/v4/81/12/01/811201e7-96da-4c95-4fc1-c85ac3e716b1/5414165055532.170x170-75.jpg" /&gt;&lt;/a&gt;
+                        &lt;/td&gt;
+                        &lt;td width="10"&gt;&lt;img alt="" width="10" height="1" src="http://r.mzstatic.com/images/spacer.gif" /&gt;&lt;/td&gt;
+                    	&lt;td width="95%"&gt;
+                    
+                    
+                        &lt;b&gt;&lt;a href="http://itunes.apple.com/lu/album/nrj-party-summer-edition-2012/id538385017?uo=2"&gt;NRJ Party Summer Edition - 2012&lt;/a&gt;&lt;/b&gt;&lt;br/&gt;
+                        
+                        
+                        
+                        
+
+                        Various Artists
+
+                       &lt;font size="2" face="Helvetica,Arial,Geneva,Swiss,SunSans-Regular"&gt;
+						
+						 	&lt;br/&gt;
+                            &lt;b&gt;Genre:&lt;/b&gt; &lt;a href="http://itunes.apple.com/lu/genre/music-dance/id17?uo=2"&gt;Dance&lt;/a&gt;
+                        
+						 	&lt;br/&gt;
+                            &lt;b&gt;Price:&lt;/b&gt; 9,99 €
+                        
+						 	&lt;br/&gt;
+                            &lt;b&gt;Release Date:&lt;/b&gt; 29 June 2012
+                        
+                        &lt;/font&gt;
+                    &lt;/td&gt;
+                &lt;/tr&gt;
+            &lt;/table&gt;
+        &lt;/td&gt;
+    &lt;/tr&gt;
+    &lt;tr&gt;
+        &lt;td&gt;
+            
+            
+            
+                &lt;font size="2" face="Helvetica,Arial,Geneva,Swiss,SunSans-Regular"&gt; &amp;#169; ℗ 2012 541 / N.E.W.S.&lt;/font&gt;
+	        
+        &lt;/td&gt;
+    &lt;/tr&gt;
+&lt;/table&gt;
+   </content>
+  </entry>
+</feed>

data/spec/support/webmocks.rb

@@ -6,4 +6,5 @@ stub_request(:get, "http://slashdot.org/").to_return(:status => 200, :body => Fi
 stub_request(:get, "http://example.org/feed.atom").to_return(:status => 200, :body => File.open(File.join(File.dirname(__FILE__), "fixtures", "atom.xml")).read, :headers => {})
 stub_request(:get, "http://api.flickr.com/services/feeds/photos_public.gne?format=rss_200&id=90313708@N00&lang=en-us").to_return(:status => 200, :body => File.open(File.join(File.dirname(__FILE__), "fixtures", "flickr_rss_200.xml")).read, :headers => {})
 stub_request(:get, "http://api.flickr.com/services/feeds/photos_public.gne?id=90313708@N00&lang=en-us&format=atom").to_return(:status => 200, :body => File.open(File.join(File.dirname(__FILE__), "fixtures", "flickr_atom.xml")).read, :headers => {})
-stub_request(:get, "http://api.flickr.com/services/feeds/geo/?id=90313708@N00&lang=en-us").to_return(:status => 200, :body => File.open(File.join(File.dirname(__FILE__), "fixtures", "flickr_geo.xml")).read, :headers => {})
+stub_request(:get, "http://api.flickr.com/services/feeds/geo/?id=90313708@N00&lang=en-us").to_return(:status => 200, :body => File.open(File.join(File.dirname(__FILE__), "fixtures", "flickr_geo.xml")).read, :headers => {})
+stub_request(:get, "http://example.org/feed.atom-html").to_return(:status => 200, :body => File.open(File.join(File.dirname(__FILE__), "fixtures", "atom_with_html.xml")).read, :headers => {})

data/spec/urss/feed_spec.rb

@@ -27,6 +27,11 @@ describe Urss::Feed do
       subject.should respond_to(:entries)
       subject.should respond_to(:entries=)
     end
+
+    it "should have an attribute :author" do
+      subject.should respond_to(:author)
+      subject.should respond_to(:author=)
+    end
   end
 
 end

data/spec/urss_spec.rb

@@ -108,8 +108,8 @@ describe Urss do
                 end
               end
               describe "author" do
-                it "should be empty" do
-                  @first_parsed_rss.author.should be_empty
+                it "should be nil" do
+                  @first_parsed_rss.author.should be_nil
                 end
               end
               describe "categories" do
@@ -418,68 +418,209 @@ The difference between -- and : is huge for me [...]"""
     end
 
     context "Atom" do
-      context "when parsing the atom.xml example file at http://example.org/feed.atom" do
-        before { @parsed_rss = subject.at("http://example.org/feed.atom") }
-        it "should return an instance of Urss::Feed::Atom" do
-          @parsed_rss.should be_an_instance_of(Urss::Feed::Atom)
-        end
-        describe "Urss::Rss" do
-          describe "title" do
-            it "should return \"dive into mark\"" do
-              @parsed_rss.title.should == "dive into mark"
-            end
+      context "with xhtml entry content" do
+        context "when parsing the atom.xml example file at http://example.org/feed.atom" do
+          before { @parsed_rss = subject.at("http://example.org/feed.atom") }
+          it "should return an instance of Urss::Feed::Atom" do
+            @parsed_rss.should be_an_instance_of(Urss::Feed::Atom)
           end
-          describe "url" do
-            it "should return \"http://example.org/feed.atom\"" do
-              @parsed_rss.url.should == "http://example.org/feed.atom"
+          describe "Urss::Rss" do
+            describe "title" do
+              it "should return \"dive into mark\"" do
+                @parsed_rss.title.should == "dive into mark"
+              end
             end
-          end
-          describe "description" do
-            it "should return \"A emlot/em of effort\n    went into making this effortless\"" do
-              @parsed_rss.description.should == "A emlot/em of effort\n    went into making this effortless"
+            describe "url" do
+              it "should return \"http://example.org/feed.atom\"" do
+                @parsed_rss.url.should == "http://example.org/feed.atom"
+              end
             end
-          end
-          describe "updated_at" do
-            it "should return \"2005-07-31T12:29:29Z\"" do
-              @parsed_rss.updated_at.should == "2005-07-31T12:29:29Z"
+            describe "description" do
+              it "should return \"A emlot/em of effort\n    went into making this effortless\"" do
+                @parsed_rss.description.should == "A emlot/em of effort\n    went into making this effortless"
+              end
             end
-          end
-          describe"entries" do
-            describe "size" do
-              it "should be 1" do
-                @parsed_rss.entries.size.should be 1
+            describe "updated_at" do
+              it "should return \"2005-07-31T12:29:29Z\"" do
+                @parsed_rss.updated_at.should == "2005-07-31T12:29:29Z"
               end
             end
-            describe "first" do
-              before { @first_parsed_rss = @parsed_rss.entries.first }
-              describe "title" do
-                it "should return \"Atom draft-07 snapshot\"" do
-                  @first_parsed_rss.title.should == "Atom draft-07 snapshot"
+            describe "entries" do
+              describe "size" do
+                it "should be 1" do
+                  @parsed_rss.entries.size.should be 1
                 end
               end
-              describe "url" do
-                it "should return \"http://example.org/2005/04/02/atom\"" do
-                  @first_parsed_rss.url.should == "http://example.org/2005/04/02/atom"
+              describe "first" do
+                before { @first_parsed_rss = @parsed_rss.entries.first }
+                describe "title" do
+                  it "should return \"Atom draft-07 snapshot\"" do
+                    @first_parsed_rss.title.should == "Atom draft-07 snapshot"
+                  end
                 end
-              end
-              describe "comments_url" do
-                it "should be empty" do
-                  @first_parsed_rss.comments_url.should be_nil
+                describe "url" do
+                  it "should return \"http://example.org/2005/04/02/atom\"" do
+                    @first_parsed_rss.url.should == "http://example.org/2005/04/02/atom"
+                  end
                 end
-              end
-              describe "created_at" do
-                it "should return \"2003-12-13T08:29:29-04:00\"" do
-                  @first_parsed_rss.created_at.should == "2003-12-13T08:29:29-04:00"
+                describe "comments_url" do
+                  it "should be nil" do
+                    @first_parsed_rss.comments_url.should be_nil
+                  end
+                end
+                describe "created_at" do
+                  it "should return \"2003-12-13T08:29:29-04:00\"" do
+                    @first_parsed_rss.created_at.should == "2003-12-13T08:29:29-04:00"
+                  end
+                end
+                describe "author" do
+                  it "should return \"Mark Pilgrim\"" do
+                    @first_parsed_rss.author.should == "Mark Pilgrim"
+                  end
+                end
+                describe "categories" do
+                  it "should be empty" do
+                    @first_parsed_rss.categories.should be_empty
+                  end
+                end
+                describe "content" do
+                  it "should return the HTML code of the content node without transformation" do
+                    @first_parsed_rss.content.should ==
+                    """
+      <div xmlns=\"http://www.w3.org/1999/xhtml\">
+        <p><i>[Update: The Atom draft is finished.]</i></p>
+      </div>
+    """
+                  end
                 end
               end
-              describe "author" do
-                it "should return \"Mark Pilgrim\"" do
-                  @first_parsed_rss.author.should == "Mark Pilgrim"
+            end
+          end
+        end
+      end
+      context "with html entry content" do
+        context "when parsing the atom_with_html.xml example file at http://example.org/feed.atom-html" do
+          before { @parsed_rss = subject.at("http://example.org/feed.atom-html") }
+          it "should return an instance of Urss::Feed::Atom" do
+            @parsed_rss.should be_an_instance_of(Urss::Feed::Atom)
+          end
+          describe "Urss::Rss" do
+            describe "title" do
+              it "should return \"iTunes Store: Top Albums\"" do
+                @parsed_rss.title.should == "iTunes Store: Top Albums"
+              end
+            end
+            describe "url" do
+              it "should return \"http://itunes.apple.com/lu/rss/topalbums/limit=10/xml\"" do
+                @parsed_rss.url.should == "http://itunes.apple.com/lu/rss/topalbums/limit=10/xml"
+              end
+            end
+            describe "description" do
+              it "should be empty" do
+                @parsed_rss.description.should be_empty
+              end
+            end
+            describe "updated_at" do
+              it "should return \"2012-08-20T10:51:05-07:00\"" do
+                @parsed_rss.updated_at.should == "2012-08-20T10:51:05-07:00"
+              end
+            end
+            describe "author" do
+              it "should return \"iTunes Store\"" do
+                @parsed_rss.author.should == "iTunes Store"
+              end
+            end
+            describe "entries" do
+              describe "size" do
+                it "should be 1" do
+                  @parsed_rss.entries.size.should be 1
                 end
               end
-              describe "categories" do
-                it "should be empty" do
-                  @first_parsed_rss.categories.should be_empty
+              describe "first" do
+                before { @first_parsed_rss = @parsed_rss.entries.first }
+                describe "title" do
+                  it "should return \"NRJ Party Summer Edition - 2012 - Various Artists\"" do
+                    @first_parsed_rss.title.should == "NRJ Party Summer Edition - 2012 - Various Artists"
+                  end
+                end
+                describe "url" do
+                  it "should return \"http://itunes.apple.com/lu/album/nrj-party-summer-edition-2012/id538385017?uo=2\"" do
+                    @first_parsed_rss.url.should == "http://itunes.apple.com/lu/album/nrj-party-summer-edition-2012/id538385017?uo=2"
+                  end
+                end
+                describe "comments_url" do
+                  it "should be nil" do
+                    @first_parsed_rss.comments_url.should be_nil
+                  end
+                end
+                describe "created_at" do
+                  it "should be empty" do
+                    @first_parsed_rss.created_at.should be_empty
+                  end
+                end
+                describe "author" do
+                  it "should return \"iTunes Store\" (the feed author as there is no entry author)" do
+                    @first_parsed_rss.author.should == "iTunes Store"
+                  end
+                end
+                describe "categories" do
+                  it "should be empty" do
+                    @first_parsed_rss.categories.should be_empty
+                  end
+                end
+                describe "content" do
+                  it "should return the HTML code of the content node without transformation" do
+                    @first_parsed_rss.content.should ==
+                    """&lt;table border=\"0\" width=\"100%\"&gt;
+    &lt;tr&gt;
+        &lt;td&gt;
+            &lt;table border=\"0\" width=\"100%\" cellspacing=\"0\" cellpadding=\"0\"&gt;
+                &lt;tr valign=\"top\" align=\"left\"&gt;
+                    
+                        &lt;td align=\"center\" width=\"166\" valign=\"top\"&gt;
+                            &lt;a href=\"http://itunes.apple.com/lu/album/nrj-party-summer-edition-2012/id538385017?uo=2\"&gt;&lt;img border=\"0\" alt=\"NRJ Party Summer Edition - 2012artwork\" src=\"http://a1.mzstatic.com/us/r1000/085/Music/v4/81/12/01/811201e7-96da-4c95-4fc1-c85ac3e716b1/5414165055532.170x170-75.jpg\" /&gt;&lt;/a&gt;
+                        &lt;/td&gt;
+                        &lt;td width=\"10\"&gt;&lt;img alt=\"\" width=\"10\" height=\"1\" src=\"http://r.mzstatic.com/images/spacer.gif\" /&gt;&lt;/td&gt;
+                    	&lt;td width=\"95%\"&gt;
+                    
+                    
+                        &lt;b&gt;&lt;a href=\"http://itunes.apple.com/lu/album/nrj-party-summer-edition-2012/id538385017?uo=2\"&gt;NRJ Party Summer Edition - 2012&lt;/a&gt;&lt;/b&gt;&lt;br/&gt;
+                        
+                        
+                        
+                        
+
+                        Various Artists
+
+                       &lt;font size=\"2\" face=\"Helvetica,Arial,Geneva,Swiss,SunSans-Regular\"&gt;
+						
+						 	&lt;br/&gt;
+                            &lt;b&gt;Genre:&lt;/b&gt; &lt;a href=\"http://itunes.apple.com/lu/genre/music-dance/id17?uo=2\"&gt;Dance&lt;/a&gt;
+                        
+						 	&lt;br/&gt;
+                            &lt;b&gt;Price:&lt;/b&gt; 9,99 €
+                        
+						 	&lt;br/&gt;
+                            &lt;b&gt;Release Date:&lt;/b&gt; 29 June 2012
+                        
+                        &lt;/font&gt;
+                    &lt;/td&gt;
+                &lt;/tr&gt;
+            &lt;/table&gt;
+        &lt;/td&gt;
+    &lt;/tr&gt;
+    &lt;tr&gt;
+        &lt;td&gt;
+            
+            
+            
+                &lt;font size=\"2\" face=\"Helvetica,Arial,Geneva,Swiss,SunSans-Regular\"&gt; &amp;#169; ℗ 2012 541 / N.E.W.S.&lt;/font&gt;
+	        
+        &lt;/td&gt;
+    &lt;/tr&gt;
+&lt;/table&gt;
+   """
+                  end
                 end
               end
             end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: urss
 version: !ruby/object:Gem::Version
-  version: 0.0.3
+  version: 0.3.0
   prerelease: 
 platform: ruby
 authors:
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-04-24 00:00:00.000000000 Z
+date: 2012-08-21 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri
@@ -57,6 +57,7 @@ files:
 - lib/urss/version.rb
 - spec/spec_helper.rb
 - spec/support/fixtures/atom.xml
+- spec/support/fixtures/atom_with_html.xml
 - spec/support/fixtures/flickr_atom.xml
 - spec/support/fixtures/flickr_geo.xml
 - spec/support/fixtures/flickr_rss_200.xml
@@ -93,7 +94,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
       version: '0'
       segments:
       - 0
-      hash: 4327753447225132504
+      hash: -4392561072410245503
 required_rubygems_version: !ruby/object:Gem::Requirement
   none: false
   requirements:
@@ -102,16 +103,17 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
       segments:
       - 0
-      hash: 4327753447225132504
+      hash: -4392561072410245503
 requirements: []
 rubyforge_project: 
-rubygems_version: 1.8.23
+rubygems_version: 1.8.24
 signing_key: 
 specification_version: 3
 summary: Ultra RSS is a Feed RSS parser.
 test_files:
 - spec/spec_helper.rb
 - spec/support/fixtures/atom.xml
+- spec/support/fixtures/atom_with_html.xml
 - spec/support/fixtures/flickr_atom.xml
 - spec/support/fixtures/flickr_geo.xml
 - spec/support/fixtures/flickr_rss_200.xml