content_urls 0.1.0 → 0.1.1

data/lib/content_urls/parsers/java_script_parser.rb

@@ -1,64 +1,64 @@
-require 'uri'
-
-class ContentUrls
-
-  # +JavaScriptParser+ finds and rewrites URLs in JavaScript content.
-  #
-  # === Implementation note:
-  # This methods in this class identify URLs by locating strings which match +URI+'s regexp.
-  class JavaScriptParser
-
-    # Returns the URLs found in the JavaScript content.
-    #
-    # @param [String] content the JavaScript content.
-    # @return [Array] the unique URLs found in the content.
-    #
-    # @example Parse JavaScript code for URLs
-    #   javascript = 'var link="http://example.com/"'
-    #   ContentUrls::JavaScriptParser.urls(javascript).each do |url|
-    #     puts "Found URL: #{url}"
-    #   end
-    #   # => "Found URL: http://example.com/"
-    def self.urls(content)
-      urls = []
-      URI.extract(content).each { |u| urls << u }
-      urls.uniq!
-      urls
-    end
-
-    # Rewrites each URL in the JavaScript content by calling the supplied block with each URL.
-    #
-    # @param [String] content the JavaScript content.
-    #
-    # @example Rewrite URLs in JavaScript code
-    #   javascript = 'var link="http://example.com/"'
-    #   javascript = ContentUrls::JavaScriptParser.rewrite_each_url(javascript) {|url| url.upcase}
-    #   puts "Rewritten: #{javascript}"
-    #   # => "Rewritten: var link="HTTP://EXAMPLE.COM/""
-    #
-    def self.rewrite_each_url(content, &block)
-      done = false
-      remaining = content
-      rewritten = ''
-      while ! remaining.empty?
-        if match = URI.regexp.match(remaining)
-          url = match.to_s
-          rewritten += match.pre_match
-          replacement = url.nil? ? nil : (yield url)
-          if replacement.nil? or replacement == url  # no change in URL
-            rewritten += url[0]
-            remaining = url[1..-1] + match.post_match
-          else
-            rewritten += replacement
-            remaining = match.post_match
-          end
-        else
-          rewritten += remaining
-          remaining = ''
-        end
-      end
-      return rewritten
-    end
-
-  end
-end
+require 'uri'
+
+class ContentUrls
+
+  # +JavaScriptParser+ finds and rewrites URLs in JavaScript content.
+  #
+  # === Implementation note:
+  # This methods in this class identify URLs by locating strings which match +URI+'s regexp.
+  class JavaScriptParser
+
+    # Returns the URLs found in the JavaScript content.
+    #
+    # @param [String] content the JavaScript content.
+    # @return [Array] the unique URLs found in the content.
+    #
+    # @example Parse JavaScript code for URLs
+    #   javascript = 'var link="http://example.com/"'
+    #   ContentUrls::JavaScriptParser.urls(javascript).each do |url|
+    #     puts "Found URL: #{url}"
+    #   end
+    #   # => "Found URL: http://example.com/"
+    def self.urls(content)
+      urls = []
+      URI.extract(content).each { |u| urls << u }
+      urls.uniq!
+      urls
+    end
+
+    # Rewrites each URL in the JavaScript content by calling the supplied block with each URL.
+    #
+    # @param [String] content the JavaScript content.
+    #
+    # @example Rewrite URLs in JavaScript code
+    #   javascript = 'var link="http://example.com/"'
+    #   javascript = ContentUrls::JavaScriptParser.rewrite_each_url(javascript) {|url| url.upcase}
+    #   puts "Rewritten: #{javascript}"
+    #   # => "Rewritten: var link="HTTP://EXAMPLE.COM/""
+    #
+    def self.rewrite_each_url(content, &block)
+      done = false
+      remaining = content
+      rewritten = ''
+      while ! remaining.empty?
+        if match = URI.regexp.match(remaining)
+          url = match.to_s
+          rewritten += match.pre_match
+          replacement = url.nil? ? nil : (yield url)
+          if replacement.nil? or replacement == url  # no change in URL
+            rewritten += url[0]
+            remaining = url[1..-1] + match.post_match
+          else
+            rewritten += replacement
+            remaining = match.post_match
+          end
+        else
+          rewritten += remaining
+          remaining = ''
+        end
+      end
+      return rewritten
+    end
+
+  end
+end

data/lib/content_urls/version.rb

@@ -1,3 +1,3 @@
-class ContentUrls
-  VERSION = "0.1.0"
-end
+class ContentUrls
+  VERSION = "0.1.1"
+end

data/spec/content_urls_spec.rb

@@ -1,29 +1,29 @@
-require File.expand_path(File.dirname(__FILE__) + '/spec_helper')
-
-describe ContentUrls.to_absolute(nil, 'http://www.sample.com/') do
-  it "returns nil when url is nil" do
-    ContentUrls.to_absolute(nil, 'http://www.sample.com/').should eq nil
-  end
-end
-
-describe ContentUrls.to_absolute('index.html', 'http://www.sample.com/') do
-  it "merges url to base_url" do
-    ContentUrls.to_absolute('index.html', 'http://www.sample.com/one/two/three/').should eq 'http://www.sample.com/one/two/three/index.html'
-    ContentUrls.to_absolute('/index.html', 'http://www.sample.com/one/two/three/').should eq 'http://www.sample.com/index.html'
-    ContentUrls.to_absolute('/four/index.html', 'http://www.sample.com/one/two/three/').should eq 'http://www.sample.com/four/index.html'
-    ContentUrls.to_absolute('../index.html', 'http://www.sample.com/one/two/three/').should eq 'http://www.sample.com/one/two/index.html'
-    ContentUrls.to_absolute('../four/index.html', 'http://www.sample.com/one/two/three/').should eq 'http://www.sample.com/one/two/four/index.html'
-  end
-end
-
-describe ContentUrls.get_parser('bogus/bogus') do
-  it "returns nil when content type is unknown" do
-    ContentUrls.get_parser('bogus/bogus').should eq nil
-  end
-end
-
-describe ContentUrls.register_parser('some_parser_class', %r{^(content/test)\b}) do
-  it "returns the class for the content type" do
-    ContentUrls.get_parser('content/test').should eq 'some_parser_class'
-  end
-end
+require File.expand_path(File.dirname(__FILE__) + '/spec_helper')
+
+describe ContentUrls.to_absolute(nil, 'http://www.sample.com/') do
+  it "returns nil when url is nil" do
+    ContentUrls.to_absolute(nil, 'http://www.sample.com/').should eq nil
+  end
+end
+
+describe ContentUrls.to_absolute('index.html', 'http://www.sample.com/') do
+  it "merges url to base_url" do
+    ContentUrls.to_absolute('index.html', 'http://www.sample.com/one/two/three/').should eq 'http://www.sample.com/one/two/three/index.html'
+    ContentUrls.to_absolute('/index.html', 'http://www.sample.com/one/two/three/').should eq 'http://www.sample.com/index.html'
+    ContentUrls.to_absolute('/four/index.html', 'http://www.sample.com/one/two/three/').should eq 'http://www.sample.com/four/index.html'
+    ContentUrls.to_absolute('../index.html', 'http://www.sample.com/one/two/three/').should eq 'http://www.sample.com/one/two/index.html'
+    ContentUrls.to_absolute('../four/index.html', 'http://www.sample.com/one/two/three/').should eq 'http://www.sample.com/one/two/four/index.html'
+  end
+end
+
+describe ContentUrls.get_parser('bogus/bogus') do
+  it "returns nil when content type is unknown" do
+    ContentUrls.get_parser('bogus/bogus').should eq nil
+  end
+end
+
+describe ContentUrls.register_parser('some_parser_class', %r{^(content/test)\b}) do
+  it "returns the class for the content type" do
+    ContentUrls.get_parser('content/test').should eq 'some_parser_class'
+  end
+end

data/spec/css_parser_spec.rb

@@ -1,34 +1,34 @@
-require File.expand_path(File.dirname(__FILE__) + '/spec_helper')
-
-describe ContentUrls::CssParser do
-  it "should return no URLs given no content" do
-    ContentUrls::CssParser.urls('').should eq []
-  end
-  it "should return no URLs given garbage content" do
-    ContentUrls::CssParser.urls('j;alksdjfkladsjflkajdfaksdjfsdj  kladjsf lkfjalkdfj lkajdf9458094djjf').should eq []
-  end
-end
-
-describe ContentUrls::CssParser do
-  it "should return the URLs in the content" do
-    ContentUrls::CssParser.urls("body {background-image:url('image.png');}").first.should eq 'image.png'
-  end
-end
-
-describe ContentUrls::CssParser do
-  it "should execute the sample code for rewrite_each_url method" do
-    output = ''
-    css = 'body { background: url(/images/rainbows.jpg) }'
-    css = ContentUrls::CssParser.rewrite_each_url(css) {|url| url.sub(/rainbows.jpg/, 'unicorns.jpg')}
-    output += "Rewritten: #{css}" + "\n"
-    output.should eq %Q{Rewritten: body { background: url(/images/unicorns.jpg) }\n}
-  end
-  it "should execute sample code for urls method" do
-    output = ''
-    css = 'body { background: url(/images/rainbows.jpg) }'
-    ContentUrls::CssParser.urls(css).each do |url|
-      output += "Found URL: #{url}" + "\n"
-    end
-    output.should eq %Q{Found URL: /images/rainbows.jpg\n}
-  end
-end
+require File.expand_path(File.dirname(__FILE__) + '/spec_helper')
+
+describe ContentUrls::CssParser do
+  it "should return no URLs given no content" do
+    ContentUrls::CssParser.urls('').should eq []
+  end
+  it "should return no URLs given garbage content" do
+    ContentUrls::CssParser.urls('j;alksdjfkladsjflkajdfaksdjfsdj  kladjsf lkfjalkdfj lkajdf9458094djjf').should eq []
+  end
+end
+
+describe ContentUrls::CssParser do
+  it "should return the URLs in the content" do
+    ContentUrls::CssParser.urls("body {background-image:url('image.png');}").first.should eq 'image.png'
+  end
+end
+
+describe ContentUrls::CssParser do
+  it "should execute the sample code for rewrite_each_url method" do
+    output = ''
+    css = 'body { background: url(/images/rainbows.jpg) }'
+    css = ContentUrls::CssParser.rewrite_each_url(css) {|url| url.sub(/rainbows.jpg/, 'unicorns.jpg')}
+    output += "Rewritten: #{css}" + "\n"
+    output.should eq %Q{Rewritten: body { background: url(/images/unicorns.jpg) }\n}
+  end
+  it "should execute sample code for urls method" do
+    output = ''
+    css = 'body { background: url(/images/rainbows.jpg) }'
+    ContentUrls::CssParser.urls(css).each do |url|
+      output += "Found URL: #{url}" + "\n"
+    end
+    output.should eq %Q{Found URL: /images/rainbows.jpg\n}
+  end
+end

data/spec/html_parser_spec.rb

@@ -1,318 +1,358 @@
-require File.expand_path(File.dirname(__FILE__) + '/spec_helper')
-
-describe ContentUrls::HtmlParser do
-  it "should return no URLs when given no content" do
-    ContentUrls::HtmlParser.urls('').should eq []
-  end
-  it "should return no URLs when given garbage content" do
-    ContentUrls::HtmlParser.urls('j;alksdjfkladsjflkajdfaksdjfsdj  kladjsf lkfjalkdfj lkajdf9458094djjf').should eq []
-  end
-end
-
-describe ContentUrls::HtmlParser do
-  it "should return the URLs in the content" do
-    ContentUrls::HtmlParser.urls("<a href='index.html").first.should eq 'index.html'
-  end
-end
-
-describe ContentUrls::HtmlParser do
-  it "should parse HTML Sample 1 and return all a links" do
-
-html_sample_1 =<<SAMPLE_1
-<html>
-<head>
-  <title>HTML Sample 1</title>
-</head>
-<body>
-  <h1>HTML Sample 1</h1>
-  <a href="a-href-link-1.html"></a>
-  <a href="http://www.example.com/1/2/3/a-href-link-2.html"></a>
-  <a href="/folder/a-href-link-3.html?a=1"></a>
-</body>
-</html>
-SAMPLE_1
-
-    urls = ContentUrls::HtmlParser.urls(html_sample_1)
-    urls.include?('a-href-link-1.html').should eq true
-    urls.include?('http://www.example.com/1/2/3/a-href-link-2.html').should eq true
-    urls.include?('/folder/a-href-link-3.html?a=1').should eq true
-  end
-end
-
-describe ContentUrls::HtmlParser do
-  it "should parse HTML Sample 1 and rewrite all a links" do
-
-html_sample_1 =<<SAMPLE_1
-<html>
-<head>
-  <title>HTML Sample 1</title>
-</head>
-<body>
-  <h1>HTML Sample 1</h1>
-  <a href="a-href-link-1.html"></a>
-  <a href="http://www.example.com/1/2/3/a-href-link-2.html"></a>
-  <a href="/folder/a-href-link-3.html?a=1"></a>
-</body>
-</html>
-SAMPLE_1
-
-    content = ContentUrls::HtmlParser.rewrite_each_url(html_sample_1) do |url|
-      url = URI.parse url
-      url.path = url.path.sub(/\.html\b/, '.php')
-      url
-    end
-    urls = ContentUrls::HtmlParser.urls(content)
-    urls.include?('a-href-link-1.php').should eq true
-    urls.include?('http://www.example.com/1/2/3/a-href-link-2.php').should eq true
-    urls.include?('/folder/a-href-link-3.php?a=1').should eq true
-  end
-end
-
-describe ContentUrls::HtmlParser do
-  it "should parse HTML Sample 2 and return all 'area href' URLs" do
-
-html_sample_2 =<<SAMPLE_2
-<html>
-<head>
-  <title>HTML Sample 2</title>
-</head>
-<body>
-  <h1>HTML Sample 2</h1>
-  <img src="sample.gif" width="200" height="200" alt="Click somewhere" usemap="#sample-map">
-  <map name="sample-map">
-    <area shape="rect" coords="0,0,100,100" href="area-href-link-1.html" alt="link 1">
-    <area shape="circle" coords="150,150,2" href="http://www.example.com/1/2/3/area-href-link-2.html" alt="link 2">
-    <area shape="circle" coords="100,180,1" href="/folder/area-href-link-3.html?a=1" alt="link 3">
-  </map>
-</body>
-</html>
-SAMPLE_2
-
-    urls = ContentUrls::HtmlParser.urls(html_sample_2)
-    urls.include?('area-href-link-1.html').should eq true
-    urls.include?('http://www.example.com/1/2/3/area-href-link-2.html').should eq true
-    urls.include?('/folder/area-href-link-3.html?a=1').should eq true
-  end
-end
-
-describe ContentUrls::HtmlParser do
-  it "should parse HTML Sample 3 and return 'body background' URL" do
-
-html_sample_3 =<<SAMPLE_3
-<html>
-<head>
-  <title>HTML Sample 3</title>
-</head>
-<body background="/images/background.png">
-  <h1>HTML Sample 3</h1>
-</body>
-</html>
-SAMPLE_3
-
-    urls = ContentUrls::HtmlParser.urls(html_sample_3)
-    urls.first.should eq '/images/background.png'
-  end
-end
-
-describe ContentUrls::HtmlParser do
-  it "should parse HTML Sample 4 and return 'embed src' URL" do
-
-html_sample_4 =<<SAMPLE_4
-<html>
-<head>
-  <title>HTML Sample 4</title>
-</head>
-<body>
-  <h1>HTML Sample 4</h1>
-  <embed src="sample.swf" />
-</body>
-</html>
-SAMPLE_4
-
-    urls = ContentUrls::HtmlParser.urls(html_sample_4)
-    urls.first.should eq 'sample.swf'
-  end
-end
-
-describe ContentUrls::HtmlParser do
-  it "should parse HTML Sample 5 and return 'img src' URL" do
-
-html_sample_5 =<<SAMPLE_5
-<html>
-<head>
-  <title>HTML Sample 5</title>
-</head>
-<body>
-  <h1>HTML Sample 5</h1>
-  <img src="sample.gif">
-</body>
-</html>
-SAMPLE_5
-
-    urls = ContentUrls::HtmlParser.urls(html_sample_5)
-    urls.first.should eq 'sample.gif'
-  end
-end
-
-describe ContentUrls::HtmlParser do
-  it "should parse HTML Sample 6 and return 'link href' URL" do
-
-html_sample_6 =<<SAMPLE_6
-<html>
-<head>
-  <title>HTML Sample 6</title>
-  <link href="/index.php" REL="index">
-</head>
-<body>
-  <h1>HTML Sample 6</h1>
-</body>
-</html>
-SAMPLE_6
-
-    urls = ContentUrls::HtmlParser.urls(html_sample_6)
-    urls.first.should eq '/index.php'
-  end
-end
-
-describe ContentUrls::HtmlParser do
-  it "should parse HTML Sample 7 and return 'object data' URL" do
-
-html_sample_7 =<<SAMPLE_7
-<html>
-<head>
-  <title>HTML Sample 7</title>
-</head>
-<body>
-  <h1>HTML Sample 7</h1>
-  <object width="400" height="400" data="/stuff/example.swf"></object>
-</body>
-</html>
-SAMPLE_7
-
-    urls = ContentUrls::HtmlParser.urls(html_sample_7)
-    urls.first.should eq '/stuff/example.swf'
-  end
-end
-
-describe ContentUrls::HtmlParser do
-  it "should parse HTML Sample 8 and return 'script src' URL" do
-
-html_sample_8 =<<SAMPLE_8
-<html>
-<head>
-  <title>HTML Sample 8</title>
-</head>
-<body>
-  <h1>HTML Sample 8</h1>
-  <script language="javascript" src="../scripts/go.js"></script>
-</body>
-</html>
-SAMPLE_8
-
-    urls = ContentUrls::HtmlParser.urls(html_sample_8)
-    urls.first.should eq '../scripts/go.js'
-  end
-end
-
-describe ContentUrls::HtmlParser do
-  it "should parse HTML Sample 9 and return 'meta content' URL" do
-
-html_sample_9 =<<SAMPLE_9
-<html>
-<head>
-  <title>HTML Sample 9</title>
-  <meta http-equiv="refresh" content="5;URL='http://example.com/'">
-</head>
-<body>
-  <h1>HTML Sample 9</h1>
-</body>
-</html>
-SAMPLE_9
-
-    urls = ContentUrls::HtmlParser.urls(html_sample_9)
-    urls.first.should eq 'http://example.com/'
-  end
-end
-
-describe ContentUrls::HtmlParser do
-  it "should parse HTML Sample 10 and return URLs found within 'style' attributes" do
-
-html_sample_10 =<<SAMPLE_10
-<html>
-<head>
-  <title>HTML Sample 10</title>
-</head>
-<body style="background-image:url('background.jpg');">
-  <h1>HTML Sample 10</h1>
-</body>
-</html>
-SAMPLE_10
-
-    urls = ContentUrls::HtmlParser.urls(html_sample_10)
-    urls.first.should eq 'background.jpg'
-  end
-end
-
-describe ContentUrls::HtmlParser do
-  it "should parse HTML Sample 11 and return URLs found within 'style' tags" do
-
-html_sample_11 =<<SAMPLE_11
-<html>
-<head>
-  <title>HTML Sample 11</title>
-  <style type="text/css">
-body {background-image:url('/image/background.jpg');}
-  </style>
-</head>
-<body>
-  <h1>HTML Sample 11</h1>
-</body>
-</html>
-SAMPLE_11
-
-    urls = ContentUrls::HtmlParser.urls(html_sample_11)
-    urls.first.should eq '/image/background.jpg'
-  end
-end
-
-describe ContentUrls::HtmlParser do
-  it "should parse HTML Sample 12 and return URLs found within 'script' tags" do
-
-html_sample_12 =<<SAMPLE_12
-<html>
-<head>
-  <title>HTML Sample 12</title>
-<script type="text/javascript">
-var link="http://www.sample.com/index.html"
-// ...
-</script>
-</head>
-<body>
-  <h1>HTML Sample 12</h1>
-</body>
-</html>
-SAMPLE_12
-
-    urls = ContentUrls::HtmlParser.urls(html_sample_12)
-    urls.first.should eq 'http://www.sample.com/index.html'
-  end
-end
-
-describe ContentUrls::HtmlParser do
-  it "should execute the sample code for rewrite_each_url method" do
-    #output = ''
-    html = '<html><a href="index.htm">Click me</a></html>'
-    html = ContentUrls::HtmlParser.rewrite_each_url(html) {|url| 'index.php'}
-    #output += "Rewritten: #{html}" + "\n"
-    #output.should eq %Q{Rewritten: <html><a href="index.php">Click me</a></html>\n}
-    ContentUrls::HtmlParser.urls(html).first.should eq 'index.php'  # Nokogiri rewrites HTML, instead check rewritten URL
-  end
-  it "should execute sample code for urls method" do
-    output = ''
-    html = '<html><a href="index.htm">Click me</a></html>'
-    ContentUrls::HtmlParser.urls(html).each do |url|
-      output += "Found URL: #{url}" + "\n"
-    end
-    output.should eq %Q{Found URL: index.htm\n}
-  end
-end
+require File.expand_path(File.dirname(__FILE__) + '/spec_helper')
+
+describe ContentUrls::HtmlParser do
+  it "should return no URLs when given no content" do
+    ContentUrls::HtmlParser.urls('').should eq []
+  end
+  it "should return no URLs when given garbage content" do
+    ContentUrls::HtmlParser.urls('j;alksdjfkladsjflkajdfaksdjfsdj  kladjsf lkfjalkdfj lkajdf9458094djjf').should eq []
+  end
+end
+
+describe ContentUrls::HtmlParser do
+  it "should return the URLs in the content" do
+    ContentUrls::HtmlParser.urls("<a href='index.html").first.should eq 'index.html'
+  end
+end
+
+describe ContentUrls::HtmlParser do
+  it "should parse HTML Sample 1 and return all a links" do
+
+html_sample_1 =<<SAMPLE_1
+<html>
+<head>
+  <title>HTML Sample 1</title>
+</head>
+<body>
+  <h1>HTML Sample 1</h1>
+  <a href="a-href-link-1.html"></a>
+  <a href="http://www.example.com/1/2/3/a-href-link-2.html"></a>
+  <a href="/folder/a-href-link-3.html?a=1"></a>
+</body>
+</html>
+SAMPLE_1
+
+    urls = ContentUrls::HtmlParser.urls(html_sample_1)
+    urls.include?('a-href-link-1.html').should eq true
+    urls.include?('http://www.example.com/1/2/3/a-href-link-2.html').should eq true
+    urls.include?('/folder/a-href-link-3.html?a=1').should eq true
+  end
+end
+
+describe ContentUrls::HtmlParser do
+  it "should parse HTML Sample 1 and rewrite all a links" do
+
+html_sample_1 =<<SAMPLE_1
+<html>
+<head>
+  <title>HTML Sample 1</title>
+</head>
+<body>
+  <h1>HTML Sample 1</h1>
+  <a href="a-href-link-1.html"></a>
+  <a href="http://www.example.com/1/2/3/a-href-link-2.html"></a>
+  <a href="/folder/a-href-link-3.html?a=1"></a>
+</body>
+</html>
+SAMPLE_1
+
+    content = ContentUrls::HtmlParser.rewrite_each_url(html_sample_1) do |url|
+      url = URI.parse url
+      url.path = url.path.sub(/\.html\b/, '.php')
+      url
+    end
+    urls = ContentUrls::HtmlParser.urls(content)
+    urls.include?('a-href-link-1.php').should eq true
+    urls.include?('http://www.example.com/1/2/3/a-href-link-2.php').should eq true
+    urls.include?('/folder/a-href-link-3.php?a=1').should eq true
+  end
+end
+
+describe ContentUrls::HtmlParser do
+  it "should parse HTML Sample 2 and return all 'area href' URLs" do
+
+html_sample_2 =<<SAMPLE_2
+<html>
+<head>
+  <title>HTML Sample 2</title>
+</head>
+<body>
+  <h1>HTML Sample 2</h1>
+  <img src="sample.gif" width="200" height="200" alt="Click somewhere" usemap="#sample-map">
+  <map name="sample-map">
+    <area shape="rect" coords="0,0,100,100" href="area-href-link-1.html" alt="link 1">
+    <area shape="circle" coords="150,150,2" href="http://www.example.com/1/2/3/area-href-link-2.html" alt="link 2">
+    <area shape="circle" coords="100,180,1" href="/folder/area-href-link-3.html?a=1" alt="link 3">
+  </map>
+</body>
+</html>
+SAMPLE_2
+
+    urls = ContentUrls::HtmlParser.urls(html_sample_2)
+    urls.include?('area-href-link-1.html').should eq true
+    urls.include?('http://www.example.com/1/2/3/area-href-link-2.html').should eq true
+    urls.include?('/folder/area-href-link-3.html?a=1').should eq true
+  end
+end
+
+describe ContentUrls::HtmlParser do
+  it "should parse HTML Sample 3 and return 'body background' URL" do
+
+html_sample_3 =<<SAMPLE_3
+<html>
+<head>
+  <title>HTML Sample 3</title>
+</head>
+<body background="/images/background.png">
+  <h1>HTML Sample 3</h1>
+</body>
+</html>
+SAMPLE_3
+
+    urls = ContentUrls::HtmlParser.urls(html_sample_3)
+    urls.first.should eq '/images/background.png'
+  end
+end
+
+describe ContentUrls::HtmlParser do
+  it "should parse HTML Sample 4 and return 'embed src' URL" do
+
+html_sample_4 =<<SAMPLE_4
+<html>
+<head>
+  <title>HTML Sample 4</title>
+</head>
+<body>
+  <h1>HTML Sample 4</h1>
+  <embed src="sample.swf" />
+</body>
+</html>
+SAMPLE_4
+
+    urls = ContentUrls::HtmlParser.urls(html_sample_4)
+    urls.first.should eq 'sample.swf'
+  end
+end
+
+describe ContentUrls::HtmlParser do
+  it "should parse HTML Sample 5 and return 'img src' URL" do
+
+html_sample_5 =<<SAMPLE_5
+<html>
+<head>
+  <title>HTML Sample 5</title>
+</head>
+<body>
+  <h1>HTML Sample 5</h1>
+  <img src="sample.gif">
+</body>
+</html>
+SAMPLE_5
+
+    urls = ContentUrls::HtmlParser.urls(html_sample_5)
+    urls.first.should eq 'sample.gif'
+  end
+end
+
+describe ContentUrls::HtmlParser do
+  it "should parse HTML Sample 6 and return 'link href' URL" do
+
+html_sample_6 =<<SAMPLE_6
+<html>
+<head>
+  <title>HTML Sample 6</title>
+  <link href="/index.php" REL="index">
+</head>
+<body>
+  <h1>HTML Sample 6</h1>
+</body>
+</html>
+SAMPLE_6
+
+    urls = ContentUrls::HtmlParser.urls(html_sample_6)
+    urls.first.should eq '/index.php'
+  end
+end
+
+describe ContentUrls::HtmlParser do
+  it "should parse HTML Sample 7 and return 'object data' URL" do
+
+html_sample_7 =<<SAMPLE_7
+<html>
+<head>
+  <title>HTML Sample 7</title>
+</head>
+<body>
+  <h1>HTML Sample 7</h1>
+  <object width="400" height="400" data="/stuff/example.swf"></object>
+</body>
+</html>
+SAMPLE_7
+
+    urls = ContentUrls::HtmlParser.urls(html_sample_7)
+    urls.first.should eq '/stuff/example.swf'
+  end
+end
+
+describe ContentUrls::HtmlParser do
+  it "should parse HTML Sample 8 and return 'script src' URL" do
+
+html_sample_8 =<<SAMPLE_8
+<html>
+<head>
+  <title>HTML Sample 8</title>
+</head>
+<body>
+  <h1>HTML Sample 8</h1>
+  <script language="javascript" src="../scripts/go.js"></script>
+</body>
+</html>
+SAMPLE_8
+
+    urls = ContentUrls::HtmlParser.urls(html_sample_8)
+    urls.first.should eq '../scripts/go.js'
+  end
+end
+
+describe ContentUrls::HtmlParser do
+  it "should parse HTML Sample 9 and return 'meta content' URL" do
+
+html_sample_9 =<<SAMPLE_9
+<html>
+<head>
+  <title>HTML Sample 9</title>
+  <meta http-equiv="refresh" content="5;URL='http://example.com/'">
+</head>
+<body>
+  <h1>HTML Sample 9</h1>
+</body>
+</html>
+SAMPLE_9
+
+    urls = ContentUrls::HtmlParser.urls(html_sample_9)
+    urls.first.should eq 'http://example.com/'
+  end
+end
+
+describe ContentUrls::HtmlParser do
+  it "should parse HTML Sample 10 and return URLs found within 'style' attributes" do
+
+html_sample_10 =<<SAMPLE_10
+<html>
+<head>
+  <title>HTML Sample 10</title>
+</head>
+<body style="background-image:url('background.jpg');">
+  <h1>HTML Sample 10</h1>
+</body>
+</html>
+SAMPLE_10
+
+    urls = ContentUrls::HtmlParser.urls(html_sample_10)
+    urls.first.should eq 'background.jpg'
+  end
+end
+
+describe ContentUrls::HtmlParser do
+  it "should parse HTML Sample 11 and return URLs found within 'style' tags" do
+
+html_sample_11 =<<SAMPLE_11
+<html>
+<head>
+  <title>HTML Sample 11</title>
+  <style type="text/css">
+body {background-image:url('/image/background.jpg');}
+  </style>
+</head>
+<body>
+  <h1>HTML Sample 11</h1>
+</body>
+</html>
+SAMPLE_11
+
+    urls = ContentUrls::HtmlParser.urls(html_sample_11)
+    urls.first.should eq '/image/background.jpg'
+  end
+end
+
+describe ContentUrls::HtmlParser do
+  it "should parse HTML Sample 12 and return URLs found within 'script' tags" do
+
+html_sample_12 =<<SAMPLE_12
+<html>
+<head>
+  <title>HTML Sample 12</title>
+<script type="text/javascript">
+var link="http://www.sample.com/index.html"
+// ...
+</script>
+</head>
+<body>
+  <h1>HTML Sample 12</h1>
+</body>
+</html>
+SAMPLE_12
+
+    urls = ContentUrls::HtmlParser.urls(html_sample_12)
+    urls.first.should eq 'http://www.sample.com/index.html'
+  end
+end
+
+describe ContentUrls::HtmlParser do
+  it "should parse HTML Sample 13 and return 'frame src' URL" do
+
+html_sample_13 =<<SAMPLE_13
+<html>
+<head>
+  <title>HTML Sample 8</title>
+</head>
+<body>
+  <h1>HTML Sample 13</h1>
+  <frame src='/info.html'>
+</body>
+</html>
+SAMPLE_13
+
+    urls = ContentUrls::HtmlParser.urls(html_sample_13)
+    urls.first.should eq '/info.html'
+  end
+end
+
+describe ContentUrls::HtmlParser do
+  it "should parse the HTML and return the 'base' URL" do
+
+  html_base_sample =<<BASE_SAMPLE
+<html>
+<head>
+  <base href='/en/'
+  <title>HTML base Sample</title>
+</head>
+<body>
+  <h1>HTML base Sample</h1>
+</body>
+</html>
+BASE_SAMPLE
+
+    url = ContentUrls::HtmlParser.base(html_base_sample)
+    url.should eq '/en/'
+  end
+end
+
+describe ContentUrls::HtmlParser do
+  it "should execute the sample code for rewrite_each_url method" do
+    #output = ''
+    html = '<html><a href="index.htm">Click me</a></html>'
+    html = ContentUrls::HtmlParser.rewrite_each_url(html) {|url| 'index.php'}
+    #output += "Rewritten: #{html}" + "\n"
+    #output.should eq %Q{Rewritten: <html><a href="index.php">Click me</a></html>\n}
+    ContentUrls::HtmlParser.urls(html).first.should eq 'index.php'  # Nokogiri rewrites HTML, instead check rewritten URL
+  end
+  it "should execute sample code for urls method" do
+    output = ''
+    html = '<html><a href="index.htm">Click me</a></html>'
+    ContentUrls::HtmlParser.urls(html).each do |url|
+      output += "Found URL: #{url}" + "\n"
+    end
+    output.should eq %Q{Found URL: index.htm\n}
+  end
+end