metapage 0.1.0 → 0.2.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 9bae1882c2b1169f6554b9b26de750fe67087f09
-  data.tar.gz: 10e23f034e67140017cd0d828d84e0f38466f66d
+  metadata.gz: 840338d16496a43238591046aefc0a503e272a3b
+  data.tar.gz: 83ae64c6920ee76d32fb63953c47bf820a95f992
 SHA512:
-  metadata.gz: 4a84d1afcda95d171349f35c4fa6af500d488cbfebd4a516ebfedfdd058586988a0ea4fbac9775d5f8c36d05cd8eec8bba01d549c7a89f7ae4a2f1e80d7b9b6b
-  data.tar.gz: fcd70936980172149326f7856656daf7873ac05145c862924c50568e6c5bc387a669cead087cea734b5668015a4c23917c5cbc0ec07a66dadb619ebe72d195db
+  metadata.gz: ba8dad8ccd4478ea90ea72e7b5bcb5ee253f1b9bd9c3dffd6e293840bcd325260f603db97d8a79fabbaf9896ce85029fd02afe31943b1937019826f0bb1997c1
+  data.tar.gz: 21813f6a22cc4bdf4d6c9a5c09c9dfc3584437956e0b342b03d8d11fbafd92093fc2c84b0061e4d2c734bf117bc29485420780fd2e1270528e0b622a61f2d56c

data/CHANGELOG.md

@@ -0,0 +1,8 @@
+## v0.2.0, 2015-11-05
+  
+  * Adds handling for urls that return an image (as detected by mimemagic gem) and gracefully
+    return metadata for those, too.
+
+## v0.1.0, 2015-11-04
+
+  * Initial release

data/README.md

@@ -20,15 +20,35 @@ Add `gem 'metapage'` to your `Gemfile` or `gem install metapage` on your command
 
 ## Usage
 
-Fetch a specific URL. Returns `nil` if the content is not html or loading fails due to invalid url, http response or timeout.
+Fetch a specific URL. Returns `nil` if the content is not html or an image or loading fails due to invalid url, http response or timeout.
 
-    Metapage.fetch('https://github.com/colszowka/simplecov').to_h
-    {:title=>"colszowka/simplecov",
-     :description=>"simplecov - Code coverage for Ruby 1.9+ with a powerful configuration library and automatic merging of coverage across test suites",
+    pp Metapage.fetch("https://github.com/colszowka/metapage").to_h
+    {:id=>"9fa08a8cef7450e558723a53c8a122a096599709",
+     :title=>"colszowka/metapage",
+     :description=>
+      "metapage - A tiny class for extracting title, description and some further information from given urls",
      :image_url=>"https://avatars0.githubusercontent.com/u/13972?v=3&s=400",
      :type=>"object",
-     :canonical_url=>"https://github.com/colszowka/simplecov",
-     :site_name=>"GitHub"}
+     :canonical_url=>"https://github.com/colszowka/metapage",
+     :site_name=>"GitHub",
+     :media_type=>"text",
+     :content_type=>"text/html"}
+
+For images, the resulting content is much more minimal:
+
+    pp Metapage.fetch("https://s-media-cache-ak0.pinimg.com/736x/e3/ce/b3/e3ceb3fe3224e104ad0f019117b8e1f0.jpg").to_h
+    {:id=>"7bd710044d61b55c63d1d0089632a6417f370f53",
+     :title=>nil,
+     :description=>nil,
+     :image_url=>
+      "https://s-media-cache-ak0.pinimg.com/736x/e3/ce/b3/e3ceb3fe3224e104ad0f019117b8e1f0.jpg",
+     :type=>"image",
+     :canonical_url=>
+      "https://s-media-cache-ak0.pinimg.com/736x/e3/ce/b3/e3ceb3fe3224e104ad0f019117b8e1f0.jpg",
+     :site_name=>nil,
+     :media_type=>"image",
+     :content_type=>"image/jpeg"}
+
 
 Extract urls from a given string and fetch the metadata for them. Only returns successfully retrieved results.
 

data/Rakefile

@@ -12,7 +12,15 @@ end
 desc "Generates examples for the readme on the fly"
 task examples: :env do
   require 'pp'
-  cmd = "pp Metapage.fetch('https://github.com/colszowka/simplecov').to_h"
-  puts cmd
-  eval cmd
+
+  [
+    'https://github.com/colszowka/metapage',
+    'https://s-media-cache-ak0.pinimg.com/736x/e3/ce/b3/e3ceb3fe3224e104ad0f019117b8e1f0.jpg'
+  ].each do |url|
+
+    cmd = "pp Metapage.fetch(#{url.inspect}).to_h"
+    puts cmd
+    eval cmd
+
+  end
 end

data/lib/metapage/version.rb

@@ -1,3 +1,3 @@
 module Metapage
-  VERSION = "0.1.0"
+  VERSION = "0.2.0"
 end

data/lib/metapage.rb

@@ -5,6 +5,7 @@ require 'uri'
 require 'resolv'
 require 'ipaddr'
 require 'digest/sha1'
+require 'mimemagic'
 
 module Metapage
   class ResolveError < StandardError; end;
@@ -40,24 +41,40 @@ module Metapage
     end
 
     def title
-      @title ||= metatag_content('og:title') || html_content('title')
+      unless image?
+        @title ||= metatag_content('og:title') || html_content('title')
+      end
     end
 
     def description
-      @description ||= metatag_content('og:description') || metatag_content('description')
+      unless image?
+        @description ||= metatag_content('og:description') || metatag_content('description')
+      end
     end
 
     def image_url
-      # Fallback to apple-touch-icon, fluid-icon, ms-tileicon etc
-      @image_url ||= metatag_content('og:image:secure_url') || metatag_content('og:image') || link_rel('apple-touch-icon-precomposed')
+      if image?
+        url
+      else
+        # Fallback to apple-touch-icon, fluid-icon, ms-tileicon etc
+        @image_url ||= metatag_content('og:image:secure_url') || metatag_content('og:image') || link_rel('apple-touch-icon-precomposed')
+      end
     end
 
     def type
-      @type ||= metatag_content('og:type') || 'website'
+      if image?
+        'image'
+      else
+        @type ||= metatag_content('og:type') || 'website'
+      end
     end
 
     def canonical_url
-      @canonical_url ||= metatag_content('og:url') || link_rel('canonical') || url
+      if image?
+        url
+      else
+        @canonical_url ||= metatag_content('og:url') || link_rel('canonical') || url
+      end
     end
 
     def id
@@ -67,7 +84,17 @@ module Metapage
     end
 
     def site_name
-      @site_name ||= metatag_content('og:site_name') || host
+      unless image?
+        @site_name ||= metatag_content('og:site_name') || host
+      end
+    end
+
+    def media_type
+      mimemagic and mimemagic.mediatype
+    end
+
+    def content_type
+      mimemagic and mimemagic.type
     end
 
     def to_h
@@ -78,7 +105,9 @@ module Metapage
         image_url: image_url,
         type: type,
         canonical_url: canonical_url,
-        site_name: site_name
+        site_name: site_name,
+        media_type: media_type,
+        content_type: content_type
       }
     end
 
@@ -86,7 +115,6 @@ module Metapage
       to_h.to_json
     end
 
-
     private
 
       def uri
@@ -137,8 +165,16 @@ module Metapage
         end
       end
 
+      def image?
+        media_type == 'image'
+      end
+
+      def mimemagic
+        @mimemagic ||= MimeMagic.by_magic(content)
+      end
+
       def content
-        http_response.body        
+        http_response.body
       end
 
       def http_response

data/metapage.gemspec

@@ -20,7 +20,7 @@ Gem::Specification.new do |spec|
 
   spec.add_dependency 'httpclient'
   spec.add_dependency 'nokogiri'
-  spec.add_dependency 'mini_magick'
+  spec.add_dependency 'mimemagic'
 
   spec.add_development_dependency "bundler", "~> 1.10"
   spec.add_development_dependency "rake", "~> 10.0"

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: metapage
 version: !ruby/object:Gem::Version
-  version: 0.1.0
+  version: 0.2.0
 platform: ruby
 authors:
 - Christoph Olszowka
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2015-11-04 00:00:00.000000000 Z
+date: 2015-11-05 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: httpclient
@@ -39,7 +39,7 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
-  name: mini_magick
+  name: mimemagic
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
@@ -147,6 +147,7 @@ files:
 - ".gitignore"
 - ".rspec"
 - ".travis.yml"
+- CHANGELOG.md
 - Gemfile
 - LICENSE.txt
 - README.md