link_thumbnailer 2.0.4 → 2.1.0

checksums.yaml

@@ -1,15 +1,15 @@
 ---
 !binary "U0hBMQ==":
   metadata.gz: !binary |-
-    OTU2ZTQyNTc5NzAwYjFmMTcyN2NmNGMwZmM4ZTYzNmNiNDJiN2ZiZg==
+    ZmRlNGRiODRmOGM2ZGZmNmVjYzE4M2MwM2NlY2VhMzdmYTdiYzdjNA==
   data.tar.gz: !binary |-
-    OWVmMWFiOGMwMDA5YTkwMjVjOGQ1YTE4ZTVlMGMyODUxN2FlMTE4NA==
+    OGMyMTFjZTg4Y2M1ODQxMmU3ZWU5NjcwMmEzYTU2MzM2MDkyZjllYg==
 SHA512:
   metadata.gz: !binary |-
-    ZWQzOGNhODhkNzhmMTUwMWIwODNkNGUzZWJhYTliNTI1YTQ4OWQ5YzJmZWJh
-    NzgyNzM3MTE1ZWU2YjZhYzZhNWRkMDJkYmE0NzQ0NTU3NDNhOWE1NDlkNDg4
-    ZjlmM2RjMzA1NzI0MWE1YTM4MWQ0YTkwZWRkZGRhZDk4ZmE5NmY=
+    YmM4YzhlMzcxZWYzZTU5OGE3ZjU2NDRlYmY3MzQwMDUxZDlhNWRlMTdjODYx
+    NzRjYTk1ZTQzMjJlZGUzYzY5YmM2NzlmMDdjMmViM2M3NGU4MTg3ZGJkMWUx
+    MDJkNmVlNWFmZGU0ZTYyMjQ4ZjVkZTYzYzFkNjhjOTc1ZTlhOGE=
   data.tar.gz: !binary |-
-    OGRmNzkyNGJkNWE5N2IxODYwNTAyMzkwNGIxMmNmMTBmN2YxY2M2MmUyNGUy
-    MjIzN2FmZmI1MzhhZGEyMTlkZjVkYmNmZGZmNDRiMDUzODk4OGQ3NzE0MGM2
-    MjY2YTcxMDA1NDcwNmNiOTUxNTU3ODJiOTU2OTNmZWQ5MjNjMDA=
+    MmUwMTY3NmNjNjU3OTJlOTQyOTQ1YWViZTZlNWNkNDNhYWEyNzg5ZWE5MWE4
+    NDNmZDdlZjUyOWUwZTgyZjIxMGQxZGRiMTJjMzNjOGI1MTMwNjJiM2E4NmU1
+    NmY5NWNjNDU4MjgwYzVlMTdkYmVhOWZiMjk5NTg0NTQ3MjJiOTg=

data/CHANGELOG.md

@@ -1,3 +1,10 @@
+# 2.1.0
+
+- Increased `og:image` scraping performance by parsing `og:image:width` and `og:image:height` attribute if specified
+- Introduced `image_stats` option to allow disabling image size and type parsing causing performance issues.
+
+When disabled, size will be `[0, 0]` and type will be `nil`
+
 # 2.0.4
 
 - Fixes [#39](https://github.com/gottfrois/link_thumbnailer/issues/39)

data/README.md

@@ -10,6 +10,8 @@ Ruby gem generating image thumbnails from a given URL. Rank them and give you ba
 
 Demo Application is [here](http://link-thumbnailer-demo.herokuapp.com/) !
 
+**OpenSource** and **Free** API available [here](https://github.com/gottfrois/link_thumbnailer_api) !
+
 ## Features
 
 - Dead simple.
@@ -135,6 +137,12 @@ In `config/initializers/link_thumbnailer.rb`
 	  # Numbers of images to fetch. Fetching too many images will be slow.
 	  #
 	  # config.image_limit = 5
+
+	  # Whether you want LinkThumbnailer to return image size and type or not.
+	  # Setting this value to false will increase performance since for each images, LinkThumbnailer
+	  # does not have to fetch its size and type.
+	  #
+	  # config.image_stats = true
 	end
 
 Or at runtime:

data/lib/generators/templates/initializer.rb

@@ -60,4 +60,10 @@ LinkThumbnailer.configure do |config|
   # Numbers of images to fetch. Fetching too many images will be slow.
   #
   # config.image_limit = 5
+
+  # Whether you want LinkThumbnailer to return image size and type or not.
+  # Setting this value to false will increase performance since for each images, LinkThumbnailer
+  # does not have to fetch its size and type.
+  #
+  # config.image_stats = true
 end

data/lib/link_thumbnailer/configuration.rb

@@ -25,7 +25,7 @@ module LinkThumbnailer
     attr_accessor :redirect_limit, :blacklist_urls, :user_agent,
                   :verify_ssl, :http_timeout, :attributes, :graders,
                   :description_min_length, :positive_regex, :negative_regex,
-                  :image_limit
+                  :image_limit, :image_stats
 
     # Create a new instance.
     #
@@ -53,6 +53,7 @@ module LinkThumbnailer
       @positive_regex = /article|body|content|entry|hentry|main|page|pagination|post|text|blog|story/i
       @negative_regex = /combx|comment|com-|contact|foot|footer|footnote|masthead|media|meta|outbrain|promo|related|scroll|shoutbox|sidebar|sponsor|shopping|tags|tool|widget|modal/i
       @image_limit    = 5
+      @image_stats    = true
     end
 
 	end

data/lib/link_thumbnailer/image_parsers/size.rb

@@ -5,11 +5,18 @@ module LinkThumbnailer
     class Size
 
       def self.perform(image)
+        return [0, 0] unless perform?
         ::FastImage.size(image.src.to_s, raise_on_failure: true)
       rescue ::FastImage::FastImageException, ::Errno::ENAMETOOLONG
         [0, 0]
       end
 
+      private
+
+      def self.perform?
+        ::LinkThumbnailer.page.config.image_stats
+      end
+
     end
   end
 end

data/lib/link_thumbnailer/image_parsers/type.rb

@@ -5,9 +5,16 @@ module LinkThumbnailer
     class Type
 
       def self.perform(image)
+        return unless perform?
         ::FastImage.type(image.src.to_s, raise_on_failure: true)
       rescue ::FastImage::FastImageException, ::Errno::ENAMETOOLONG
-        :jpg
+        nil
+      end
+
+      private
+
+      def self.perform?
+        ::LinkThumbnailer.page.config.image_stats
       end
 
     end

data/lib/link_thumbnailer/models/image.rb

@@ -9,10 +9,10 @@ module LinkThumbnailer
 
       attr_reader :src, :type, :size
 
-      def initialize(src)
+      def initialize(src, size = nil, type = nil)
         @src  = src
-        @size = parser.size(self)
-        @type = parser.type(self)
+        @size = size || parser.size(self)
+        @type = type || parser.type(self)
       end
 
       def to_s

data/lib/link_thumbnailer/scrapers/base.rb

@@ -28,12 +28,12 @@ module LinkThumbnailer
         true
       end
 
-      private
-
       def value
         raise 'must implement'
       end
 
+      private
+
       def meta_xpath(options = {})
         meta_xpaths(options).first
       end

data/lib/link_thumbnailer/scrapers/default/description.rb

@@ -5,14 +5,14 @@ module LinkThumbnailer
     module Default
       class Description < ::LinkThumbnailer::Scrapers::Default::Base
 
-        private
-
         def value
           return model_from_meta.to_s if model_from_meta
           return model_from_body.to_s if model_from_body
           nil
         end
 
+        private
+
         def model_from_meta
           modelize(node_from_meta, node_from_meta.attributes['content'].value) if node_from_meta
         end

data/lib/link_thumbnailer/scrapers/default/images.rb

@@ -6,12 +6,12 @@ module LinkThumbnailer
     module Default
       class Images < ::LinkThumbnailer::Scrapers::Default::Base
 
-        private
-
         def value
           abs_urls.each_with_index.take_while { |_, i| i < config.image_limit }.map { |e| modelize(e.first) }
         end
 
+        private
+
         def urls
           document.search('//img').map { |i| i['src'] }.compact
         end

data/lib/link_thumbnailer/scrapers/default/title.rb

@@ -5,12 +5,12 @@ module LinkThumbnailer
     module Default
       class Title < ::LinkThumbnailer::Scrapers::Default::Base
 
-        private
-
         def value
           model.to_s
         end
 
+        private
+
         def model
           modelize(node)
         end

data/lib/link_thumbnailer/scrapers/opengraph/base.rb

@@ -9,12 +9,12 @@ module LinkThumbnailer
           meta.any? { |node| opengraph_node?(node) }
         end
 
-        private
-
         def value
           model.to_s
         end
 
+        private
+
         def model
           modelize(node, node.attributes['content'].to_s) if node
         end

data/lib/link_thumbnailer/scrapers/opengraph/image.rb

@@ -16,7 +16,7 @@ module LinkThumbnailer
         end
 
         def modelize(node, text = nil)
-          model_class.new(text)
+          model_class.new(text, size)
         end
 
         def nodes
@@ -24,6 +24,46 @@ module LinkThumbnailer
           nodes.empty? ? meta_xpaths(attribute: attribute, key: :name) : nodes
         end
 
+        def size
+          [width.to_i, height.to_i] if width && height
+        end
+
+        def width
+          Width.new(document).value
+        end
+
+        def height
+          Height.new(document).value
+        end
+
+        class Width < ::LinkThumbnailer::Scrapers::Opengraph::Base
+
+          def value
+            node.attributes['content'].to_s if node
+          end
+
+          private
+
+          def attribute
+            "og:image:width"
+          end
+
+        end
+
+        class Height < ::LinkThumbnailer::Scrapers::Opengraph::Base
+
+          def value
+            node.attributes['content'].to_s if node
+          end
+
+          private
+
+          def attribute
+            "og:image:height"
+          end
+
+        end
+
       end
     end
   end

data/lib/link_thumbnailer/version.rb

@@ -1,3 +1,3 @@
 module LinkThumbnailer
-  VERSION = '2.0.4'
+  VERSION = '2.1.0'
 end

data/spec/configuration_spec.rb

@@ -15,6 +15,7 @@ describe LinkThumbnailer::Configuration do
   it { expect(instance.positive_regex).to_not     be_nil }
   it { expect(instance.negative_regex).to_not     be_nil }
   it { expect(instance.image_limit).to            eq(5) }
+  it { expect(instance.image_stats).to            eq(true) }
 
   describe '.config' do
 

data/spec/fixture_spec.rb

@@ -25,6 +25,7 @@ describe 'Fixture' do
       it { expect(action.description).to            eq(description) }
       it { expect(action.images.count).to           eq(1) }
       it { expect(action.images.first.src.to_s).to  eq(png_url) }
+      it { expect(action.images.first.size).to      eq([100, 100]) }
 
     end
 

data/spec/fixtures/og_valid_example.html

@@ -6,6 +6,8 @@
     <meta property="og:title" content="Title from og">
     <meta property="og:description" content="Description from og">
     <meta property="og:image" content="http://foo.com/foo.png">
+    <meta property="og:image:width" content="100">
+    <meta property="og:image:height" content="100">
     <title>Title</title>
   </head>
 

data/spec/image_parsers/type_spec.rb

@@ -25,7 +25,7 @@ describe LinkThumbnailer::ImageParsers::Type do
         expect(FastImage).to receive(:type).with(src, raise_on_failure: true).and_raise(FastImage::FastImageException)
       end
 
-      it { expect(action).to eq(:jpg) }
+      it { expect(action).to be_nil }
 
     end
 

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: link_thumbnailer
 version: !ruby/object:Gem::Version
-  version: 2.0.4
+  version: 2.1.0
 platform: ruby
 authors:
 - Pierre-Louis Gottfrois
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-06-09 00:00:00.000000000 Z
+date: 2014-06-10 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: activesupport