metainspector 1.6.0 → 1.7.0

data/README.rdoc

@@ -32,6 +32,8 @@ Then you can see the scraped data like this:
   page.meta_description   # meta description, as string
   page.meta_keywords      # meta keywords, as string
   page.image              # Most relevant image, if defined with og:image
+  page.images             # array of strings, with every img found on the page
+  page.absolute_images    # array of all the images converted to absolute urls
   page.feed               # Get rss or atom links in meta data fields as array
   page.meta_og_title      # opengraph title
   page.meta_og_image      # opengraph image
@@ -101,7 +103,6 @@ You're welcome to fork this project and send pull requests. I want to thank spec
 
 * Get page.base_dir from the URL
 * Distinguish between external and internal links, returning page.links for all of them as found, page.external_links and page.internal_links converted to absolute URLs
-* Return array of images in page as absolute URLs
 * Be able to set a timeout in seconds
 * If keywords seem to be separated by blank spaces, replace them with commas
 * Mocks

data/lib/meta_inspector/scraper.rb

@@ -30,11 +30,19 @@ module MetaInspector
                                 .map {|link| link.attributes["href"] \
                                 .to_s.strip}.uniq) rescue nil
     end
+    
+    def images
+      @data.images ||= parsed_document.search('//img').map{ |i| i.attributes['src'].value }.uniq
+    end
 
     # Returns the links converted to absolute urls
     def absolute_links
       @data.absolute_links ||= links.map { |l| absolutify_url(l) }
     end
+    
+    def absolute_images
+      @data.absolute_images ||= images.map{ |i| absolutify_url(i) }
+    end
 
     # Returns the parsed document meta rss links
     def feed

data/lib/meta_inspector/version.rb

@@ -1,5 +1,5 @@
 # -*- encoding: utf-8 -*-
 
 module MetaInspector
-  VERSION = "1.6.0"
+  VERSION = "1.7.0"
 end

data/spec/metainspector_spec.rb

@@ -45,6 +45,11 @@ describe MetaInspector do
       @m.image.should == "http://o.onionstatic.com/images/articles/article/2772/Apple-Claims-600w-R_jpg_130x110_q85.jpg"
       @m.meta_og_image.should == "http://o.onionstatic.com/images/articles/article/2772/Apple-Claims-600w-R_jpg_130x110_q85.jpg"
     end
+    
+    it "should find all page images" do 
+      @m.absolute_images == ["http://pagerankalert.com/images/pagerank_alert.png?1309512337"]
+      @m.images == ["/images/pagerank_alert.png?1309512337"]
+    end
 
     it "should have a Nokogiri::HTML::Document as parsed_document" do
       @m.parsed_document.class.should == Nokogiri::HTML::Document

metadata

@@ -4,9 +4,9 @@ version: !ruby/object:Gem::Version
   prerelease: false
   segments: 
   - 1
-  - 6
+  - 7
   - 0
-  version: 1.6.0
+  version: 1.7.0
 platform: ruby
 authors: 
 - Jaime Iniesta
@@ -14,7 +14,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2011-06-03 00:00:00 +02:00
+date: 2011-07-05 00:00:00 +02:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency