html_page_title 0.1.0

data/.document

@@ -0,0 +1,5 @@
+README.rdoc
+lib/**/*.rb
+bin/*
+features/**/*.feature
+LICENSE

data/.gitignore

@@ -0,0 +1,21 @@
+## MAC OS
+.DS_Store
+
+## TEXTMATE
+*.tmproj
+tmtags
+
+## EMACS
+*~
+\#*
+.\#*
+
+## VIM
+*.swp
+
+## PROJECT::GENERAL
+coverage
+rdoc
+pkg
+
+## PROJECT::SPECIFIC

data/LICENSE

@@ -0,0 +1,20 @@
+Copyright (c) 2010 Christoph Olszowka
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/README.rdoc

@@ -0,0 +1,40 @@
+= HtmlPageTitle
+
+  gem install html_page_title
+
+A simple class for finding the title of a given http url by fetching the
+given url, following all eventual redirects and finally parsing it through
+hpricot.
+
+You can either use the shorthand form or initialize the instance properly:
+ * HtmlPageTitle('http://github.com')
+ * HtmlPageTitle.new('http://github.com')
+
+Those calls are equivalent, except for one subtle difference:
+The shorthand form will swallow SocketErrors and return nil (i.e. this will
+happen for invalid urls), while the regular instantiation via new will 
+throw that error.
+
+You can either get the title, the heading (which will be the content of the
+first h1 tag in the body) or the label, which will be (in the following order 
+by availability) either the heading, or the title, or the target url after
+redirecting. 
+Note that if the title or the heading can not be found (e.g. a non-HTML
+document), both methods will return nil, so the label method is the only one
+that will always return some kind of string
+
+You can also have a look at the unit test to find out about the behaviour!
+
+== Note on Patches/Pull Requests
+ 
+* Fork the project.
+* Make your feature addition or bug fix.
+* Add tests for it. This is important so I don't break it in a
+  future version unintentionally.
+* Commit, do not mess with rakefile, version, or history.
+  (if you want to have your own version, that is fine but bump version in a commit by itself I can ignore when I pull)
+* Send me a pull request. Bonus points for topic branches.
+
+== Copyright
+
+Copyright (c) 2010 Christoph Olszowka. See LICENSE for details.

data/Rakefile

@@ -0,0 +1,55 @@
+require 'rubygems'
+require 'rake'
+
+begin
+  require 'jeweler'
+  Jeweler::Tasks.new do |gem|
+    gem.name = "html_page_title"
+    gem.summary = %Q{Retrieve the page title for a given url (including redirects)}
+    gem.description = %Q{Retrieve the page title for a given url using redirect_follower and hpricot ruby gems}
+    gem.email = "'christoph at olszowka.de'"
+    gem.homepage = "http://github.com/colszowka/html_page_title"
+    gem.authors = ["Christoph Olszowka"]
+    gem.add_dependency "redirect_follower", ">= 0.1.1"
+    gem.add_dependency "hpricot", ">= 0.8.2"
+    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
+  Jeweler::GemcutterTasks.new
+rescue LoadError
+  puts "Jeweler (or a dependency) not available. Install it with: gem install jeweler"
+end
+
+require 'rake/testtask'
+Rake::TestTask.new(:test) do |test|
+  test.libs << 'lib' << 'test'
+  test.pattern = 'test/**/test_*.rb'
+  test.verbose = true
+end
+
+begin
+  require 'rcov/rcovtask'
+  Rcov::RcovTask.new do |test|
+    test.libs << 'test'
+    test.pattern = 'test/**/test_*.rb'
+    test.verbose = true
+  end
+rescue LoadError
+  task :rcov do
+    abort "RCov is not available. In order to run rcov, you must: sudo gem install spicycode-rcov"
+  end
+end
+
+task :test => :check_dependencies
+
+task :default => :test
+
+require 'rake/rdoctask'
+Rake::RDocTask.new do |rdoc|
+  version = File.exist?('VERSION') ? File.read('VERSION') : ""
+
+  rdoc.rdoc_dir = 'rdoc'
+  rdoc.title = "html_page_title #{version}"
+  rdoc.rdoc_files.include('README*')
+  rdoc.rdoc_files.include('lib/**/*.rb')
+end

data/VERSION

@@ -0,0 +1 @@
+0.1.0

data/html_page_title.gemspec

@@ -0,0 +1,60 @@
+# Generated by jeweler
+# DO NOT EDIT THIS FILE DIRECTLY
+# Instead, edit Jeweler::Tasks in Rakefile, and run the gemspec command
+# -*- encoding: utf-8 -*-
+
+Gem::Specification.new do |s|
+  s.name = %q{html_page_title}
+  s.version = "0.1.0"
+
+  s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
+  s.authors = ["Christoph Olszowka"]
+  s.date = %q{2010-07-15}
+  s.description = %q{Retrieve the page title for a given url using redirect_follower and hpricot ruby gems}
+  s.email = %q{'christoph at olszowka.de'}
+  s.extra_rdoc_files = [
+    "LICENSE",
+     "README.rdoc"
+  ]
+  s.files = [
+    ".document",
+     ".gitignore",
+     "LICENSE",
+     "README.rdoc",
+     "Rakefile",
+     "VERSION",
+     "html_page_title.gemspec",
+     "lib/html_page_title.rb",
+     "test/helper.rb",
+     "test/test_html_page_title.rb"
+  ]
+  s.homepage = %q{http://github.com/colszowka/html_page_title}
+  s.rdoc_options = ["--charset=UTF-8"]
+  s.require_paths = ["lib"]
+  s.rubygems_version = %q{1.3.7}
+  s.summary = %q{Retrieve the page title for a given url (including redirects)}
+  s.test_files = [
+    "test/helper.rb",
+     "test/test_html_page_title.rb"
+  ]
+
+  if s.respond_to? :specification_version then
+    current_version = Gem::Specification::CURRENT_SPECIFICATION_VERSION
+    s.specification_version = 3
+
+    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_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<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<shoulda>, [">= 2.11.1"])
+  end
+end
+

data/lib/html_page_title.rb

@@ -0,0 +1,78 @@
+require 'redirect_follower'
+require 'hpricot'
+def HtmlPageTitle(url)
+  HtmlPageTitle.new(url)
+rescue SocketError => err
+  nil
+end
+
+#
+# A simple class for finding the title of a given http url by fetching the
+# given url, following all eventual redirects and finally parsing it through
+# hpricot.
+# 
+# You can either use the shorthand form or initialize the instance properly:
+#  * HtmlPageTitle('http://github.com')
+#  * HtmlPageTitle.new('http://github.com')
+# 
+# Those calls are equivalent, except for one subtle difference:
+# The shorthand form will swallow SocketErrors and return nil (i.e. this will
+# happen for invalid urls), while the regular instantiation via new will 
+# throw that error.
+# 
+# You can either get the title, the heading (which will be the content of the
+# first h1 tag in the body) or the label, which will be (in the following order 
+# by availability) either the heading, or the title, or the target url after
+# redirecting. 
+# Note that if the title or the heading can not be found (e.g. a non-HTML
+# document), both methods will return nil, so the label method is the only one
+# that will always return some kind of string
+#
+class HtmlPageTitle
+  attr_reader :original_url
+  def initialize(original_url)
+    @original_url = original_url
+    title # retrieve data so exceptions can be thrown
+  end
+  
+  def document
+    @document ||= Hpricot(redirect.body)
+  end
+  
+  def title
+    return @title if @title
+    if title_tag = document.at('head title')
+      @title = title_tag.inner_html.strip.chomp
+    end
+  end
+  
+  # Retrieves the first h1 tag in the page and returns it's content
+  def heading
+    return @heading if @heading
+    if heading_tag = document.at('body h1')
+      @heading = heading_tag.inner_html.strip.chomp
+    end
+  end
+  
+  # Returns either the heading, or the title, or the url in this order
+  # by availability
+  def label
+    heading or title or url
+  end
+
+  # Returns the redirect follower instance used for resolving
+  # this instances url
+  def redirect
+    @redirect = RedirectFollower.new(original_url)    
+  end
+  
+  # Returns the target url after all redirects
+  def url
+    redirect.url
+  end
+  
+  # Returns the body of the document at the (redirected?) target
+  def body
+    redirect.body
+  end
+end

data/test/helper.rb

@@ -0,0 +1,10 @@
+require 'rubygems'
+require 'test/unit'
+require 'shoulda'
+
+$LOAD_PATH.unshift(File.join(File.dirname(__FILE__), '..', 'lib'))
+$LOAD_PATH.unshift(File.dirname(__FILE__))
+require 'html_page_title'
+
+class Test::Unit::TestCase
+end

data/test/test_html_page_title.rb

@@ -0,0 +1,63 @@
+require 'helper'
+
+class TestHtmlPageTitle < Test::Unit::TestCase
+  def test_quick_access
+    instance = HtmlPageTitle('http://www.spiegel.de')
+    assert_equal "SPIEGEL ONLINE - Nachrichten", instance.title
+    assert_equal 'http://www.spiegel.de', instance.url
+    assert_equal 'SPIEGEL ONLINE', instance.heading
+    assert_equal instance.heading, instance.label
+  end
+  
+  def test_access_with_instantiation
+    instance = HtmlPageTitle.new('http://www.spiegel.de')
+    assert_equal "SPIEGEL ONLINE - Nachrichten", instance.title
+    assert_equal 'http://www.spiegel.de', instance.url
+    assert_equal 'SPIEGEL ONLINE', instance.heading
+    assert_equal instance.heading, instance.label
+
+    assert instance.body.kind_of?(String)
+    assert_equal instance.redirect.url, instance.url
+    assert_equal RedirectFollower, instance.redirect.class
+    assert_equal Hpricot::Doc, instance.document.class
+  end
+  
+  def test_with_redirect
+    instance = HtmlPageTitle.new('http://is.gd/bNZYZ')
+    assert_equal "TASCHEN Books: Byrne, Six Books of Euclid", instance.title
+    assert_equal 'http://www.taschen.com/pages/en/catalogue/classics/all/06724/facts.byrne_six_books_of_euclid.htm', instance.url
+    assert_equal 'Byrne, Six Books of Euclid', instance.heading
+    assert_equal instance.heading, instance.label
+
+    assert instance.body.kind_of?(String)
+    assert_equal instance.redirect.url, instance.url
+    assert_equal RedirectFollower, instance.redirect.class
+    assert_equal Hpricot::Doc, instance.document.class
+  end
+  
+  def test_quick_access_with_invalid_urls
+    assert_nil HtmlPageTitle('http://www.thisdoesnotexistforrealsure.de')
+    assert_nil HtmlPageTitle('http://www.notldisntniceeh')
+  end
+  
+  def test_regular_access_with_invalid_urls
+    assert_raise SocketError do 
+      HtmlPageTitle.new('http://www.thisdoesnotexistforsure.de')
+    end
+    assert_raise SocketError do
+      HtmlPageTitle.new('http://www.thisdoesnotexistforsur')
+    end
+  end
+  
+  def test_non_html_url
+    instance = HtmlPageTitle.new('http://gist.github.com/raw/93965/64e0b8445d0c3481f755fe65fd79297fcf6da909/x')
+    assert_nil instance.title
+    assert_nil instance.heading
+    assert_equal 'http://gist.github.com/raw/93965/64e0b8445d0c3481f755fe65fd79297fcf6da909/x', instance.label
+  end
+  
+  def test_url_without_h1
+    instance = HtmlPageTitle('http://gembundler.com/v1.0/index.html')
+    assert_equal instance.title, instance.label
+  end
+end

metadata

@@ -0,0 +1,125 @@
+--- !ruby/object:Gem::Specification 
+name: html_page_title
+version: !ruby/object:Gem::Version 
+  hash: 27
+  prerelease: false
+  segments: 
+  - 0
+  - 1
+  - 0
+  version: 0.1.0
+platform: ruby
+authors: 
+- Christoph Olszowka
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2010-07-15 00:00:00 +02:00
+default_executable: 
+dependencies: 
+- !ruby/object:Gem::Dependency 
+  name: redirect_follower
+  prerelease: false
+  requirement: &id001 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        hash: 25
+        segments: 
+        - 0
+        - 1
+        - 1
+        version: 0.1.1
+  type: :runtime
+  version_requirements: *id001
+- !ruby/object:Gem::Dependency 
+  name: hpricot
+  prerelease: false
+  requirement: &id002 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        hash: 59
+        segments: 
+        - 0
+        - 8
+        - 2
+        version: 0.8.2
+  type: :runtime
+  version_requirements: *id002
+- !ruby/object:Gem::Dependency 
+  name: shoulda
+  prerelease: false
+  requirement: &id003 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        hash: 33
+        segments: 
+        - 2
+        - 11
+        - 1
+        version: 2.11.1
+  type: :development
+  version_requirements: *id003
+description: Retrieve the page title for a given url using redirect_follower and hpricot ruby gems
+email: "'christoph at olszowka.de'"
+executables: []
+
+extensions: []
+
+extra_rdoc_files: 
+- LICENSE
+- README.rdoc
+files: 
+- .document
+- .gitignore
+- LICENSE
+- README.rdoc
+- Rakefile
+- VERSION
+- html_page_title.gemspec
+- lib/html_page_title.rb
+- test/helper.rb
+- test/test_html_page_title.rb
+has_rdoc: true
+homepage: http://github.com/colszowka/html_page_title
+licenses: []
+
+post_install_message: 
+rdoc_options: 
+- --charset=UTF-8
+require_paths: 
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement 
+  none: false
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      hash: 3
+      segments: 
+      - 0
+      version: "0"
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  none: false
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      hash: 3
+      segments: 
+      - 0
+      version: "0"
+requirements: []
+
+rubyforge_project: 
+rubygems_version: 1.3.7
+signing_key: 
+specification_version: 3
+summary: Retrieve the page title for a given url (including redirects)
+test_files: 
+- test/helper.rb
+- test/test_html_page_title.rb