extractula 0.0.9 → 0.0.10

data/lib/extractula/extractor.rb

@@ -130,7 +130,11 @@ class Extractula::Extractor
   end
 
   def extract_content
-    candidate_nodes = html.search("//div|//p|//br").collect do |node|
+    fragment = content_node ? content_node.inner_html.strip : ""
+  end
+  
+  def candidate_nodes
+    @candidate_nodes ||= html.search("//div|//p|//br").collect do |node|
       parent = node.parent
       if node.node_name == 'div'
         text_size = calculate_children_text_size(parent, "div")
@@ -170,9 +174,23 @@ class Extractula::Extractor
       else
         nil
       end
-    end.compact.uniq
+    end.compact.uniq    
+  end
 
-    fragment = candidate_nodes.detect {|n| n[:text_size] > 140}[:parent].inner_html.strip rescue ""
+  def content_node_selector
+    Proc.new { |n| n[:text_size] > content_node_text_size_cutoff }
+  end
+  
+  def content_node_text_size_cutoff
+    140
+  end
+  
+  def content_node
+    @content_node ||= begin
+      if node = candidate_nodes.detect(&content_node_selector)
+        node[:parent]
+      end
+    end
   end
 
   def calculate_children_text_size(parent, node_type)

data/lib/extractula/oembed.rb

@@ -86,13 +86,17 @@ module Extractula
       end
       
       def oembed_request
-        request = "#{oembed_endpoint}?url=#{url.url}"
+        request = "#{oembed_endpoint}?url=#{oembed_request_url}"
         request += "&format=json" if oembed_format_param_required?
         request += "&maxwidth=#{oembed_max_width}" if oembed_max_width
         request += "&maxheight=#{oembed_max_height}" if oembed_max_height
         request
       end
       
+      def oembed_request_url
+        url.url
+      end
+      
       def title
         oembed.title
       end

data/lib/extractula.rb

@@ -9,7 +9,7 @@ require 'extractula/extracted_content'
 require 'extractula/extractor'
 
 module Extractula
-  VERSION = "0.0.9"
+  VERSION = "0.0.10"
 
   @extractors = []
 

metadata

@@ -1,7 +1,12 @@
 --- !ruby/object:Gem::Specification 
 name: extractula
 version: !ruby/object:Gem::Version 
-  version: 0.0.9
+  prerelease: false
+  segments: 
+  - 0
+  - 0
+  - 10
+  version: 0.0.10
 platform: ruby
 authors: 
 - Paul Dix
@@ -15,24 +20,32 @@ default_executable:
 dependencies: 
 - !ruby/object:Gem::Dependency 
   name: nokogiri
-  type: :runtime
-  version_requirement: 
-  version_requirements: !ruby/object:Gem::Requirement 
+  prerelease: false
+  requirement: &id001 !ruby/object:Gem::Requirement 
     requirements: 
     - - ">"
       - !ruby/object:Gem::Version 
+        segments: 
+        - 0
+        - 0
+        - 0
         version: 0.0.0
-    version: 
+  type: :runtime
+  version_requirements: *id001
 - !ruby/object:Gem::Dependency 
   name: loofah
-  type: :runtime
-  version_requirement: 
-  version_requirements: !ruby/object:Gem::Requirement 
+  prerelease: false
+  requirement: &id002 !ruby/object:Gem::Requirement 
     requirements: 
     - - ">="
       - !ruby/object:Gem::Version 
+        segments: 
+        - 0
+        - 4
+        - 2
         version: 0.4.2
-    version: 
+  type: :runtime
+  version_requirements: *id002
 description: 
 email: paul@pauldix.net
 executables: []
@@ -79,18 +92,20 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements: 
   - - ">="
     - !ruby/object:Gem::Version 
+      segments: 
+      - 0
       version: "0"
-  version: 
 required_rubygems_version: !ruby/object:Gem::Requirement 
   requirements: 
   - - ">="
     - !ruby/object:Gem::Version 
+      segments: 
+      - 0
       version: "0"
-  version: 
 requirements: []
 
 rubyforge_project: 
-rubygems_version: 1.3.5
+rubygems_version: 1.3.6
 signing_key: 
 specification_version: 2
 summary: "Extracts content like title, summary, and images from web pages like Dracula extracts blood: with care and finesse."