image_scraper 0.1.1 → 0.1.2

data/VERSION

@@ -1 +1 @@
-0.1.1
+0.1.2

data/image_scraper.gemspec

@@ -5,11 +5,11 @@
 
 Gem::Specification.new do |s|
   s.name = %q{image_scraper}
-  s.version = "0.1.1"
+  s.version = "0.1.2"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.authors = ["John McAliley"]
-  s.date = %q{2011-06-02}
+  s.date = %q{2011-06-03}
   s.description = %q{Simple utility to pull image urls from web page}
   s.email = %q{john.mcaliley@gmail.com}
   s.extra_rdoc_files = [

data/lib/image_scraper.rb

@@ -1,4 +1,3 @@
-require 'pp'
 require 'rails'
 require 'open-uri'
 require 'nokogiri'

data/lib/image_scraper/client.rb

@@ -34,10 +34,12 @@ module ImageScraper
         css = file.string rescue IO.read(file)
         
         images += css.scan(/url\((.*?)\)/).collect do |image_url|
+          image_url = image_url[0]
           if image_url.include?("data:image") and @include_css_data_images
-            image_url[0]
+            image_url
           else
-            @convert_to_absolute_url ? ImageScraper::Util.absolute_url(url,image_url[0]) : image_url
+            image_url = ImageScraper::Util.strip_quotes(image_url)
+            @convert_to_absolute_url ? ImageScraper::Util.absolute_url(url,image_url) : image_url
           end
         end
       end

data/lib/image_scraper/util.rb

@@ -16,5 +16,9 @@ module ImageScraper
       uri = URI.parse(url)
       uri.path
     end
+    
+    def self.strip_quotes(image_url)
+      image_url.gsub("'","").gsub('"','')
+    end
   end
 end

data/test/test_image_scraper.rb

@@ -44,4 +44,17 @@ class TestImageScraper < Test::Unit::TestCase
     scraper = ImageScraper::Client.new("http://local.couponshack.com")
     assert scraper.stylesheet_images.include? ("http://local.couponshack.com/images/bg.png")
   end
+  
+  should "strip quotes from a url" do
+    assert_equal "/images/test.png", ImageScraper::Util.strip_quotes("'/images/test.png'")
+    assert_equal "http://www.somsite.com/images/test.png", ImageScraper::Util.strip_quotes("'http://www.somsite.com/images/test.png'")
+    assert_equal "/images/test.png", ImageScraper::Util.strip_quotes('"/images/test.png"')
+  end
+  
+  should "return domain section from a url" do
+    assert_equal "http://ug.ly", ImageScraper::Util.domain("http://ug.ly/what/is/this.html")
+    assert_equal "http://ug.ly", ImageScraper::Util.domain("http://ug.ly/what/is/this/")
+    assert_equal "http://ug.ly", ImageScraper::Util.domain("http://ug.ly/what")
+    assert_equal "http://www.ug.ly", ImageScraper::Util.domain("http://www.ug.ly/what/is/this/")
+  end
 end

metadata

@@ -5,8 +5,8 @@ version: !ruby/object:Gem::Version
   segments: 
   - 0
   - 1
-  - 1
-  version: 0.1.1
+  - 2
+  version: 0.1.2
 platform: ruby
 authors: 
 - John McAliley
@@ -14,7 +14,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2011-06-02 00:00:00 -04:00
+date: 2011-06-03 00:00:00 -04:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency 
@@ -175,7 +175,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements: 
   - - ">="
     - !ruby/object:Gem::Version 
-      hash: 1275395306475000737
+      hash: -738762267344225369
       segments: 
       - 0
       version: "0"