busk-ruby-readability 1.0.4 → 1.0.5

data/lib/readability.rb

@@ -43,7 +43,7 @@ module Readability
         :trimRe => /^\s+|\s+$/,
         :normalizeRe => /\s{2,}/,
         :killBreaksRe => /(<br\s*\/?>(\s|&nbsp;?)*){1,}/,
-        :videoRe => /http:\/\/(www\.)?(youtube|vimeo)\.com/i
+        :videoRe => /http:\/\/(www\.)?(youtube|vimeo|ted|player\.vimeo)\.com/i
     }
 
     def content(remove_unlikely_candidates = true)
@@ -51,6 +51,7 @@ module Readability
 
       article = youtube if is_youtube? && remove_unlikely_candidates
       article = vimeo if is_vimeo? && remove_unlikely_candidates
+      article = ted if is_ted? && remove_unlikely_candidates
 
       if article && remove_unlikely_candidates
         return article.to_html.gsub(/[\r\n\f]+/, "\n" ).gsub(/[\t ]+/, " ").gsub(/&nbsp;/, " ")
@@ -79,6 +80,10 @@ module Readability
     def is_vimeo?
       (@input.base_uri.to_s =~ /^http:\/\/(www.)?vimeo.com/)
     end
+
+    def is_ted?
+      (@input.base_uri.to_s =~ /^http:\/\/(www.)?ted.com\/talks/)
+    end
     
     def is_special_case?
       (@input.base_uri.to_s =~ REGEXES[:videoRe])
@@ -87,11 +92,11 @@ module Readability
     def youtube
       if @input.base_uri.request_uri =~ /\?v=([_\-a-z0-9]+)&?/i
         Nokogiri::HTML.fragment <<-HTML
-          <object width="480" height="385">
+          <object width="739" height="416">
             <param name="movie" value="http://www.youtube.com/v/#{$1}?fs=1&amp;hl=en_US"></param>
             <param name="allowFullScreen" value="true"></param>
             <param name="allowscriptaccess" value="always"></param>
-            <embed src="http://www.youtube.com/v/#{$1}?fs=1&amp;hl=en_US" type="application/x-shockwave-flash" allowscriptaccess="always" allowfullscreen="true" width="480" height="385"></embed>
+            <embed src="http://www.youtube.com/v/#{$1}?fs=1&amp;hl=en_US" type="application/x-shockwave-flash" allowscriptaccess="always" allowfullscreen="true" width="739" height="416"></embed>
           </object>
         HTML
       else
@@ -116,6 +121,18 @@ module Readability
         nil
       end
     end
+    
+    def ted
+      if (player = @html.css(".copy_paste")).present?
+        unless player.first.attr("value").blank?
+          Nokogiri::HTML.fragment(player.first.attr("value").to_s)
+        else
+          nil
+        end
+      else
+        nil
+      end
+    end
         
     def get_article(candidates, best_candidate)
       # Now that we have the top candidate, look through its siblings for content that might also be related.
@@ -279,9 +296,15 @@ module Readability
         header.remove if class_weight(header) < 0 || get_link_density(header) > 0.33
       end
 
-      node.css("form, iframe").each do |elem|
+      node.css("form").each do |elem|
         elem.remove
       end
+      
+      node.css("iframe").each do |iframe|
+        unless iframe.attr("src").to_s =~ REGEXES[:videoRe]
+          iframe.remove
+        end
+      end
 
       # remove empty <p> tags
       # node.css("p").each do |elem|
@@ -360,4 +383,4 @@ module Readability
     end
 
   end
-end
+end

metadata

@@ -1,13 +1,7 @@
 --- !ruby/object:Gem::Specification 
 name: busk-ruby-readability
 version: !ruby/object:Gem::Version 
-  hash: 31
-  prerelease: false
-  segments: 
-  - 1
-  - 0
-  - 4
-  version: 1.0.4
+  version: 1.0.5
 platform: ruby
 authors: []
 
@@ -15,7 +9,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2010-09-21 00:00:00 -03:00
+date: 2010-09-22 00:00:00 -03:00
 default_executable: 
 dependencies: []
 
@@ -39,27 +33,21 @@ rdoc_options: []
 require_paths: 
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement 
-  none: false
   requirements: 
   - - ">="
     - !ruby/object:Gem::Version 
-      hash: 3
-      segments: 
-      - 0
       version: "0"
+  version: 
 required_rubygems_version: !ruby/object:Gem::Requirement 
-  none: false
   requirements: 
   - - ">="
     - !ruby/object:Gem::Version 
-      hash: 3
-      segments: 
-      - 0
       version: "0"
+  version: 
 requirements: []
 
 rubyforge_project: 
-rubygems_version: 1.3.7
+rubygems_version: 1.3.5
 signing_key: 
 specification_version: 3
 summary: A rewrite of original ruby-readability