RubyGems - ruby-readability - Versions diffs - 0.5.4 → 0.5.5 - Mend

ruby-readability 0.5.4 → 0.5.5

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Files changed (5) hide show

data/CHANGES.markdown ADDED Viewed

@@ -0,0 +1,3 @@
+Oct 1, 2012:
+- Merged in austinrfnd's `author` handling code.

data/lib/readability.rb CHANGED Viewed

@@ -131,6 +131,55 @@ module Readability
       title ? title.text : nil
     end
+    # Look through the @html document looking for the author
+    # Precedence Information here on the wiki: (TODO attach wiki URL if it is accepted)
+    # Returns nil if no author is detected
+    def author
+      # Let's grab this author:
+      # <meta name="dc.creator" content="Finch - http://www.getfinch.com" />
+      author_elements = @html.xpath('//meta[@name = "dc.creator"]')
+      unless author_elements.empty?
+        author_elements.each do |element|
+          if element['content']
+            return element['content'].strip
+          end
+        end
+      end
+      # Now let's try to grab this
+      # <span class="byline author vcard"><span>By</span><cite class="fn">Austin Fonacier</cite></span>
+      # <div class="author">By</div><div class="author vcard"><a class="url fn" href="http://austinlivesinyoapp.com/">Austin Fonacier</a></div>
+      author_elements = @html.xpath('//*[contains(@class, "vcard")]//*[contains(@class, "fn")]')
+      unless author_elements.empty?
+        author_elements.each do |element|
+          if element.text
+            return element.text.strip
+          end
+        end
+      end
+      # Now let's try to grab this
+      # <a rel="author" href="http://dbanksdesign.com">Danny Banks (rel)</a>
+      # TODO: strip out the (rel)?
+      author_elements = @html.xpath('//a[@rel = "author"]')
+      unless author_elements.empty?
+        author_elements.each do |element|
+          if element.text
+            return element.text.strip
+          end
+        end
+      end
+      author_elements = @html.xpath('//*[@id = "author"]')
+      unless author_elements.empty?
+        author_elements.each do |element|
+          if element.text
+            return element.text.strip
+          end
+        end
+      end
+    end
     def content(remove_unlikely_candidates = :default)
       @remove_unlikely_candidates = false if remove_unlikely_candidates == false

data/ruby-readability.gemspec CHANGED Viewed

@@ -3,7 +3,7 @@ $:.push File.expand_path("../lib", __FILE__)
 Gem::Specification.new do |s|
   s.name        = "ruby-readability"
-  s.version     = '0.5.4'
+  s.version     = '0.5.5'
   s.authors     = ["Andrew Cantino", "starrhorne", "libc", "Kyle Maxwell"]
   s.email       = ["andrew@iterationlabs.com"]
   s.homepage    = "http://github.com/iterationlabs/ruby-readability"

data/spec/readability_spec.rb CHANGED Viewed

@@ -128,6 +128,75 @@ describe Readability do
     end
   end
+  describe "author" do
+    it "should pick up <meta name='dc.creator'></meta> as an author" do
+      doc = Readability::Document.new(<<-HTML)
+        <html>
+          <head>
+            <meta name='dc.creator' content='Austin Fonacier' />
+          </head>
+          <body></body>
+        </html>
+      HTML
+      doc.author.should eql("Austin Fonacier")
+    end
+    it "should pick up readability's recommended author format" do
+      doc = Readability::Document.new(<<-HTML)
+        <html>
+          <head>
+          </head>
+          <body>
+            <p class="byline author vcard">
+            By <cite class="fn">Austin Fonacier</span>
+            </p>
+          </body>
+        </html>
+      HTML
+      doc.author.should eql("Austin Fonacier")
+    end
+    it "should pick up vcard fn" do
+      doc = Readability::Document.new(<<-HTML)
+        <html>
+          <head>
+          </head>
+          <body>
+            <div class="author">By</div>
+            <div class="author vcard">
+              <a class="url fn" href="http://austinlivesinyotests.com/">Austin Fonacier</a>
+            </div>
+          </body>
+        </html>
+      HTML
+      doc.author.should eql("Austin Fonacier")
+    end
+    it "should pick up <a rel='author'>" do
+      doc = Readability::Document.new(<<-HTML)
+        <html>
+          <head></head>
+          <body>
+            <a rel="author" href="http://google.com">Danny Banks (rel)</a>
+          </body>
+        </html>
+      HTML
+      doc.author.should eql("Danny Banks (rel)")
+    end
+    it "should pick up <div id='author'>" do
+      doc = Readability::Document.new(<<-HTML)
+        <html>
+          <head></head>
+          <body>
+            <div id="author">Austin Fonacier (author)</div>
+          </body>
+        </html>
+      HTML
+      doc.author.should eql("Austin Fonacier (author)")
+    end
+  end
   describe "score_node" do
     before do
       @doc = Readability::Document.new(<<-HTML)

metadata CHANGED Viewed

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: ruby-readability
 version: !ruby/object:Gem::Version
-  version: 0.5.4
+  version: 0.5.5
   prerelease:
 platform: ruby
 authors:
@@ -12,7 +12,7 @@ authors:
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2012-07-27 00:00:00.000000000 Z
+date: 2012-10-02 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rspec
@@ -105,6 +105,7 @@ files:
 - .document
 - .gitignore
 - .rspec
+- CHANGES.markdown
 - Gemfile
 - README.markdown
 - Rakefile
@@ -150,8 +151,26 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: ruby-readability
-rubygems_version: 1.8.19
+rubygems_version: 1.8.21
 signing_key:
 specification_version: 3
 summary: Port of arc90's readability project to ruby
-test_files: []
+test_files:
+- spec/fixtures/bbc.html
+- spec/fixtures/cant_read.html
+- spec/fixtures/images/dim_1416768a.jpg
+- spec/fixtures/nytimes.html
+- spec/fixtures/sample.html
+- spec/fixtures/samples/blogpost_with_links-fragments.rb
+- spec/fixtures/samples/blogpost_with_links.html
+- spec/fixtures/samples/channel4-1-fragments.rb
+- spec/fixtures/samples/channel4-1.html
+- spec/fixtures/samples/foxnews-india1-fragments.rb
+- spec/fixtures/samples/foxnews-india1.html
+- spec/fixtures/samples/globemail-ottawa-cuts-fragments.rb
+- spec/fixtures/samples/globemail-ottawa-cuts.html
+- spec/fixtures/should_not_truncate.txt
+- spec/fixtures/thesun.html
+- spec/readability_spec.rb
+- spec/spec.opts
+- spec/spec_helper.rb