html_page_title 0.1.0 → 0.1.1

data/README.rdoc

@@ -25,6 +25,9 @@ that will always return some kind of string
 
 You can also have a look at the unit test to find out about the behaviour!
 
+== TODO:
+* Remove arbitrary html from the h1 content
+
 == Note on Patches/Pull Requests
  
 * Fork the project.

data/Rakefile

@@ -12,6 +12,7 @@ begin
     gem.authors = ["Christoph Olszowka"]
     gem.add_dependency "redirect_follower", ">= 0.1.1"
     gem.add_dependency "hpricot", ">= 0.8.2"
+    gem.add_dependency 'htmlentities', '>= 4.0.0'
     gem.add_development_dependency "shoulda", ">= 2.11.1"
     # gem is a Gem::Specification... see http://www.rubygems.org/read/chapter/20 for additional settings
   end

data/VERSION

@@ -1 +1 @@
-0.1.0
+0.1.1

data/html_page_title.gemspec

@@ -5,7 +5,7 @@
 
 Gem::Specification.new do |s|
   s.name = %q{html_page_title}
-  s.version = "0.1.0"
+  s.version = "0.1.1"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.authors = ["Christoph Olszowka"]
@@ -45,15 +45,18 @@ Gem::Specification.new do |s|
     if Gem::Version.new(Gem::VERSION) >= Gem::Version.new('1.2.0') then
       s.add_runtime_dependency(%q<redirect_follower>, [">= 0.1.1"])
       s.add_runtime_dependency(%q<hpricot>, [">= 0.8.2"])
+      s.add_runtime_dependency(%q<htmlentities>, [">= 4.0.0"])
       s.add_development_dependency(%q<shoulda>, [">= 2.11.1"])
     else
       s.add_dependency(%q<redirect_follower>, [">= 0.1.1"])
       s.add_dependency(%q<hpricot>, [">= 0.8.2"])
+      s.add_dependency(%q<htmlentities>, [">= 4.0.0"])
       s.add_dependency(%q<shoulda>, [">= 2.11.1"])
     end
   else
     s.add_dependency(%q<redirect_follower>, [">= 0.1.1"])
     s.add_dependency(%q<hpricot>, [">= 0.8.2"])
+    s.add_dependency(%q<htmlentities>, [">= 4.0.0"])
     s.add_dependency(%q<shoulda>, [">= 2.11.1"])
   end
 end

data/lib/html_page_title.rb

@@ -1,5 +1,7 @@
 require 'redirect_follower'
 require 'hpricot'
+require 'htmlentities'
+
 def HtmlPageTitle(url)
   HtmlPageTitle.new(url)
 rescue SocketError => err
@@ -42,7 +44,7 @@ class HtmlPageTitle
   def title
     return @title if @title
     if title_tag = document.at('head title')
-      @title = title_tag.inner_html.strip.chomp
+      @title = HTMLEntities.new.decode(title_tag.inner_html.strip.chomp)
     end
   end
   
@@ -50,7 +52,7 @@ class HtmlPageTitle
   def heading
     return @heading if @heading
     if heading_tag = document.at('body h1')
-      @heading = heading_tag.inner_html.strip.chomp
+      @heading = HTMLEntities.new.decode(heading_tag.inner_html.strip.chomp)
     end
   end
   

data/test/test_html_page_title.rb

@@ -60,4 +60,9 @@ class TestHtmlPageTitle < Test::Unit::TestCase
     instance = HtmlPageTitle('http://gembundler.com/v1.0/index.html')
     assert_equal instance.title, instance.label
   end
+  
+  def test_title_with_entities
+    instance = HtmlPageTitle('http://metautonomo.us/2010/04/15/introducing-metawhere/')
+    assert_equal 'metautonomo.us  » Blog Archive   » Introducing MetaWhere', instance.title
+  end
 end

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification 
 name: html_page_title
 version: !ruby/object:Gem::Version 
-  hash: 27
+  hash: 25
   prerelease: false
   segments: 
   - 0
   - 1
-  - 0
-  version: 0.1.0
+  - 1
+  version: 0.1.1
 platform: ruby
 authors: 
 - Christoph Olszowka
@@ -51,9 +51,25 @@ dependencies:
   type: :runtime
   version_requirements: *id002
 - !ruby/object:Gem::Dependency 
-  name: shoulda
+  name: htmlentities
   prerelease: false
   requirement: &id003 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        hash: 63
+        segments: 
+        - 4
+        - 0
+        - 0
+        version: 4.0.0
+  type: :runtime
+  version_requirements: *id003
+- !ruby/object:Gem::Dependency 
+  name: shoulda
+  prerelease: false
+  requirement: &id004 !ruby/object:Gem::Requirement 
     none: false
     requirements: 
     - - ">="
@@ -65,7 +81,7 @@ dependencies:
         - 1
         version: 2.11.1
   type: :development
-  version_requirements: *id003
+  version_requirements: *id004
 description: Retrieve the page title for a given url using redirect_follower and hpricot ruby gems
 email: "'christoph at olszowka.de'"
 executables: []