extractula 0.0.2 → 0.0.3

data/lib/extractula/custom_extractors/dinosaur_comics.rb

@@ -3,6 +3,7 @@
 module Extractula
   class DinosaurComics < Extractula::Extractor
     domain          'qwantz'
+    media_type      'image'
     content_path    'img.comic', 'title'
     image_urls_path 'img.comic'
   end

data/lib/extractula/custom_extractors/flickr.rb

@@ -2,7 +2,8 @@ module Extractula
   class Flickr < Extractula::Extractor
     include Extractula::OEmbed
     domain              'flickr'
-    content_path        'div.photoDescription'
+    media_type          'image'
+    content_path        'meta[name=description]', 'content'
     oembed_endpoint     'http://www.flickr.com/services/oembed/'
   end
 end

data/lib/extractula/custom_extractors/you_tube.rb

@@ -2,6 +2,7 @@ module Extractula
   class YouTube < Extractula::Extractor
     include Extractula::OEmbed
     domain              'youtube'
+    media_type          'video'
     content_path        '.description'
     oembed_endpoint     'http://www.youtube.com/oembed'
   end

data/lib/extractula/extracted_content.rb

@@ -1,5 +1,5 @@
 class Extractula::ExtractedContent
-  attr_reader :url, :title, :content, :summary, :image_urls, :video_embed
+  attr_reader :url, :media_type, :title, :content, :summary, :image_urls, :video_embed
 
   def initialize(attributes = {})
     attributes.each_pair {|k, v| instance_variable_set("@#{k}", v)}

data/lib/extractula/extractor.rb

@@ -14,6 +14,11 @@ class Extractula::Extractor
   def self.can_extract? url, html
     @extractable_domain ? @extractable_domain == url.domain : false
   end
+  
+  def self.media_type type = nil
+    @media_type = type if type
+    @media_type
+  end
 
   %w{title content summary image_urls video_embed }.each do |field|
     class_eval <<-EOS
@@ -50,6 +55,7 @@ class Extractula::Extractor
   def extract
     Extractula::ExtractedContent.new({
       :url          => url.url,
+      :media_type   => media_type,
       :title        => title,
       :content      => content,
       :summary      => summary,
@@ -58,6 +64,10 @@ class Extractula::Extractor
     })
   end
 
+  def media_type
+    self.class.media_type || 'text'
+  end
+
   def title
     content_at(title_path, title_attr) || content_at("//title")
   end
@@ -72,7 +82,11 @@ class Extractula::Extractor
 
   def image_urls
     if image_urls_path
-      html.search(image_urls_path).collect { |img| img['src'].strip }
+      html.search(image_urls_path).collect do |img|
+        src = img['src'].strip
+        src = "#{@url.scheme}://#{@url.host}#{src}" if src.start_with?('/')
+        src
+      end
     end
   end
 

data/lib/extractula.rb

@@ -8,7 +8,7 @@ require 'extractula/extracted_content'
 require 'extractula/extractor'
 
 module Extractula
-  VERSION = "0.0.2"
+  VERSION = "0.0.3"
 
   @extractors = []
 

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification 
 name: extractula
 version: !ruby/object:Gem::Version 
-  version: 0.0.2
+  version: 0.0.3
 platform: ruby
 authors: 
 - Paul Dix