guitsaru-scraper 0.1.0

data/.document

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

data/.gitignore

@@ -0,0 +1,5 @@
+*.sw?
+.DS_Store
+coverage
+rdoc
+pkg

data/LICENSE

@@ -0,0 +1,20 @@
+Copyright (c) 2009 Matt Pruitt
+
+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 +1,7 @@
+= scraper
+
+Description goes here.
+
+== Copyright
+
+Copyright (c) 2009 Matt Pruitt. See LICENSE for details.

data/Rakefile

@@ -0,0 +1,59 @@
+require 'rubygems'
+require 'rake'
+
+begin
+  require 'jeweler'
+  Jeweler::Tasks.new do |gem|
+    gem.name = "scraper"
+    gem.summary = %Q{Collects all links on a webpage recursively.}
+    gem.email = "guitsaru@gmail.com"
+    gem.homepage = "http://github.com/guitsaru/scraper"
+    gem.authors = ["Matt Pruitt"]
+    gem.rubyforge_project = "scraper"
+    gem.add_dependency('hpricot', '>= 0.6.161')
+  end
+
+  Jeweler::RubyforgeTasks.new
+rescue LoadError
+  puts "Jeweler (or a dependency) not available. Install it with: sudo 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
+    test.rcov_opts += ['--exclude gems']
+  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 :default => :test
+
+require 'rake/rdoctask'
+Rake::RDocTask.new do |rdoc|
+  if File.exist?('VERSION.yml')
+    config = YAML.load(File.read('VERSION.yml'))
+    version = "#{config[:major]}.#{config[:minor]}.#{config[:patch]}"
+  else
+    version = ""
+  end
+
+  rdoc.rdoc_dir = 'rdoc'
+  rdoc.title = "scraper #{version}"
+  rdoc.rdoc_files.include('README*')
+  rdoc.rdoc_files.include('lib/**/*.rb')
+end
+

data/VERSION

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

data/lib/scraper/link.rb

@@ -0,0 +1,43 @@
+module Scrape
+  class Link
+    attr_accessor :url, :visited, :title
+    def initialize(url, title='')
+      @url = url
+      @title = title
+      @visited = false
+    end
+    
+    def scrape!(div=nil)
+      return [] if @visited
+      @visited = true
+      return get_links(div)
+    end
+    
+    def ==(other)
+      return false unless other.is_a? Link
+      @url == other.url
+    end
+    
+    private
+    def get_links(div)
+      links = []
+      
+      doc = Hpricot(Net::HTTP.get(URI.parse(url)))
+      doc.search("#{div} a").each do |link|
+        url = link['href']
+        if url =~ /^\/(.*)/
+          components = URI::split(@url)
+          url = "#{components[0] || 'http'}://#{components[2]}/url"
+        elsif url =~ /^http:\/\//i
+          url = url
+        else
+          url = (File.dirname(@url) + '/' + (url || ''))
+        end
+        
+        links << Link.new(url, link.inner_html)
+      end
+      
+      return links.uniq
+    end
+  end
+end

data/lib/scraper.rb

@@ -0,0 +1,23 @@
+require 'hpricot'
+require 'open-uri'
+
+require File.join(File.dirname(__FILE__), '..', 'lib/scraper/link')
+
+class Scraper
+  include Scrape
+  
+  attr_accessor :url
+  
+  def initialize(url)
+    self.url = url
+  end
+  
+  def scrape(div=nil)
+    links = [Link.new(self.url)]
+    until (not_visited = links.uniq.select { |link| !link.visited}).empty?
+      not_visited.each { |link| links += link.scrape!(div) }
+    end
+    
+    return links.uniq
+  end
+end

data/test/fake_pages/first_child_page.html

@@ -0,0 +1,15 @@
+<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01//EN"
+   "http://www.w3.org/TR/html4/strict.dtd">
+
+<html lang="en">
+<head>
+  <meta http-equiv="Content-Type" content="text/html; charset=utf-8">
+  <title>untitled</title>
+  <meta name="generator" content="TextMate http://macromates.com/">
+  <meta name="author" content="Matt Pruitt">
+  <!-- Date: 2009-06-17 -->
+</head>
+<body>
+  <div id="content"><a href="/main.html">Main</a></div>
+</body>
+</html>

data/test/fake_pages/first_page.html

@@ -0,0 +1,20 @@
+<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01//EN"
+   "http://www.w3.org/TR/html4/strict.dtd">
+
+<html lang="en">
+<head>
+  <meta http-equiv="Content-Type" content="text/html; charset=utf-8">
+  <title>untitled</title>
+  <meta name="generator" content="TextMate http://macromates.com/">
+  <meta name="author" content="Matt Pruitt">
+  <!-- Date: 2009-06-17 -->
+</head>
+<body>
+  <div id="header">
+    <a href="not_added.html">Not Added</a>
+  </div>
+  <div id="content">
+    <a href="http://example.com/first_child_page.html">First Child Page</a>
+  </div>
+</body>
+</html>

data/test/fake_pages/main.html

@@ -0,0 +1,20 @@
+<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01//EN"
+   "http://www.w3.org/TR/html4/strict.dtd">
+
+<html lang="en">
+<head>
+  <meta http-equiv="Content-Type" content="text/html; charset=utf-8">
+  <title>untitled</title>
+  <meta name="generator" content="TextMate http://macromates.com/">
+  <meta name="author" content="Matt Pruitt">
+  <!-- Date: 2009-06-17 -->
+</head>
+<body>
+  <div id="header">
+    <a href="not_added.html">Not Added</a>
+  </div>
+  <div id="content">
+    <a href="first_page.html">First Page</a>
+  </div>
+</body>
+</html>

data/test/fake_pages/not_added.html

@@ -0,0 +1,20 @@
+<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01//EN"
+   "http://www.w3.org/TR/html4/strict.dtd">
+
+<html lang="en">
+<head>
+  <meta http-equiv="Content-Type" content="text/html; charset=utf-8">
+  <title>untitled</title>
+  <meta name="generator" content="TextMate http://macromates.com/">
+  <meta name="author" content="Matt Pruitt">
+  <!-- Date: 2009-06-17 -->
+</head>
+<body>
+  <div id="header">
+    <a href="not_added.html">Not Added</a>
+  </div>
+  <div id="content">
+    <a href="first_child_page_not_added.html">First Child Page Not Added</a>
+  </div>
+</body>
+</html>

data/test/test_helper.rb

@@ -0,0 +1,16 @@
+require 'rubygems'
+require 'test/unit'
+require 'shoulda'
+require 'fakeweb'
+
+$LOAD_PATH.unshift(File.join(File.dirname(__FILE__), '..', 'lib'))
+$LOAD_PATH.unshift(File.dirname(__FILE__))
+require 'scraper'
+
+class Test::Unit::TestCase
+  FakeWeb.register_uri(:get, "http://example.com/main.html", :file => File.join(File.dirname(__FILE__), 'fake_pages/main.html'))
+  FakeWeb.register_uri(:get, "http://example.com/first_page.html", :file => File.join(File.dirname(__FILE__), 'fake_pages/first_page.html'))
+  FakeWeb.register_uri(:get, "http://example.com/first_child_page.html", :file => File.join(File.dirname(__FILE__), 'fake_pages/first_child_page.html'))
+  FakeWeb.register_uri(:get, "http://example.com/not_added.html", :file => File.join(File.dirname(__FILE__), 'fake_pages/not_added.html'))
+end
+

data/test/test_link.rb

@@ -0,0 +1,63 @@
+require 'test_helper'
+
+class TestLink < Test::Unit::TestCase
+  include Scrape
+  
+  context "initialization" do
+    setup do
+      @link = Link.new('http://example.com')
+    end
+
+    should "set the url" do
+      assert_equal('http://example.com', @link.url)
+    end
+    
+    should "set the title" do
+      assert_equal('', @link.title)
+      assert_equal('title', Link.new('http://example.com', 'title').title)
+    end
+    
+    should "set the visited flag" do
+      assert_equal(false, @link.visited)
+    end
+  end
+  
+  context "scraping" do
+    setup do
+      @link = Link.new('http://example.com/main.html')
+      @results = @link.scrape!
+    end
+    
+    should "set the visited flag to true" do
+      assert(@link.visited, "Link was not visited")
+    end
+    
+    should "return an array of links on the page" do
+      assert_not_nil(@results)
+      assert(@results.is_a?(Array))
+      assert(@results.include?(Link.new('http://example.com/first_page.html')))
+      assert(@results.include?(Link.new('http://example.com/not_added.html')))
+    end
+  end
+  
+  context "scraping inside a div" do
+    setup do
+      @link = Link.new('http://example.com/main.html')
+      @results = @link.scrape!('#content')
+    end
+
+    should "return an array of links on the page" do
+      assert_not_nil(@results)
+      assert(@results.is_a?(Array))
+      assert(@results.include?(Link.new('http://example.com/first_page.html')))
+    end
+    
+    should "not return links not in the div" do
+      assert(!@results.include?(Link.new('http://example.com/not_added.html')), "Includes a link outside of the correct div.")
+    end
+  end
+  
+  should "be equal to another link with the same url" do
+    assert(Link.new('http://example.com') == Link.new('http://example.com'))
+  end
+end

data/test/test_scraper.rb

@@ -0,0 +1,32 @@
+require 'test_helper'
+
+class TestScraper < Test::Unit::TestCase
+  include Scrape
+  
+  context "initialization" do
+    setup do
+      @scraper = Scraper.new('http://example.com')
+    end
+
+    should "set the url" do
+      assert_equal('http://example.com', @scraper.url)
+    end
+  end
+  
+  context "scraping" do
+    setup do
+      @scraper = Scraper.new('http://example.com/main.html')
+      @results = @scraper.scrape('#content')
+    end
+    
+    should "Include a list of links on the pages." do
+      assert(@results.include?(Link.new('http://example.com/first_page.html')))
+      assert(@results.include?(Link.new('http://example.com/first_child_page.html')))
+      assert(@results.include?(Link.new('http://example.com/main.html')))
+    end
+    
+    should "Not include any links outside of the content div" do
+      assert(!@results.include?(Link.new('http://example.com/not_added.html')))
+    end
+  end
+end

metadata

@@ -0,0 +1,79 @@
+--- !ruby/object:Gem::Specification 
+name: guitsaru-scraper
+version: !ruby/object:Gem::Version 
+  version: 0.1.0
+platform: ruby
+authors: 
+- Matt Pruitt
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2009-06-17 00:00:00 -07:00
+default_executable: 
+dependencies: 
+- !ruby/object:Gem::Dependency 
+  name: hpricot
+  type: :runtime
+  version_requirement: 
+  version_requirements: !ruby/object:Gem::Requirement 
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        version: 0.6.161
+    version: 
+description: 
+email: guitsaru@gmail.com
+executables: []
+
+extensions: []
+
+extra_rdoc_files: 
+- LICENSE
+- README.rdoc
+files: 
+- .document
+- .gitignore
+- LICENSE
+- README.rdoc
+- Rakefile
+- VERSION
+- lib/scraper.rb
+- lib/scraper/link.rb
+- test/fake_pages/first_child_page.html
+- test/fake_pages/first_page.html
+- test/fake_pages/main.html
+- test/fake_pages/not_added.html
+- test/test_helper.rb
+- test/test_link.rb
+- test/test_scraper.rb
+has_rdoc: false
+homepage: http://github.com/guitsaru/scraper
+post_install_message: 
+rdoc_options: 
+- --charset=UTF-8
+require_paths: 
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      version: "0"
+  version: 
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      version: "0"
+  version: 
+requirements: []
+
+rubyforge_project: scraper
+rubygems_version: 1.2.0
+signing_key: 
+specification_version: 3
+summary: Collects all links on a webpage recursively.
+test_files: 
+- test/test_helper.rb
+- test/test_link.rb
+- test/test_scraper.rb