imdb_celebrity 0.0.1

data/History.txt

@@ -0,0 +1,8 @@
+=== 0.0.1 2010-09-29
+
+* 1 major enhancement:
+  * Initial release
+  * searching for celebrity for exact match or all matches available for query string
+  * fetch data for a celebrity for give imdbid [& name]
+  * Using hpricot or nokogiri for parsing IMDB pages.
+  * 

data/Manifest.txt

@@ -0,0 +1,28 @@
+History.txt
+Manifest.txt
+PostInstall.txt
+README.rdoc
+Rakefile
+bin/imdb_celebrity
+lib/imdb_celebrity.rb
+lib/imdb_celebrity/cli.rb
+lib/imdb_celebrity/search.rb
+lib/imdb_celebrity/celebrity.rb
+lib/imdb_celebrity/string_extensions.rb
+lib/imdb_celebrity/parser/parser.rb
+lib/imdb_celebrity/parser/hpricot_parser.rb
+lib/imdb_celebrity/parser/nokogiri_parser.rb
+lib/imdb_celebrity/parser/hpricot_parser/search_parser.rb
+lib/imdb_celebrity/parser/hpricot_parser/hpricot_parser.rb
+lib/imdb_celebrity/parser/hpricot_parser/celebrity_bio_parser.rb
+lib/imdb_celebrity/parser/nokogiri_parser/nokogiri_parser.rb
+lib/imdb_celebrity/parser/nokogiri_parser/search_parser.rb
+lib/imdb_celebrity/parser/nokogiri_parser/celebrity_bio_parser.rb
+script/console
+script/destroy
+script/generate
+spec/imdb_celebrity_cli_spec.rb
+spec/imdb_celebrity_spec.rb
+spec/spec.opts
+spec/spec_helper.rb
+tasks/rspec.rake

data/PostInstall.txt

@@ -0,0 +1,7 @@
+
+For more information on imdb_celebrity, see http://github.com/sandeepkrao/imdb_celebrity
+
+NOTE: Change this information in PostInstall.txt 
+You can also delete it if you don't want it.
+
+

data/README.rdoc

@@ -0,0 +1,55 @@
+= imdb_celebrity
+
+* http://github.com/sandeepkrao/imdb_celebrity
+
+== DESCRIPTION:
+
+* Imdb_celebrity is a ruby-gem which is used for scrapping celebrity pages from imdb.com . You can install imdb_celebrity as 
+    gem install imdb_celebrity
+  With current initial release we can search a celebrity with name or we can fetch content for a celebrity with given IMDB id or/and name
+  
+  Usages:
+    require 'imdb_celebrity'
+    
+    ** searching a celebrity
+      imdb_celebs = ImdbCelebrity::Search.new("Brad Pitt")
+      imdb_celebs.celebrities
+      # this will return array of celebrity objects. 
+
+
+== SYNOPSIS:
+
+  FIX (code sample of usage)
+
+== REQUIREMENTS:
+
+* FIX (list of requirements)
+
+== INSTALL:
+
+* FIX (sudo gem install, anything else)
+
+== LICENSE:
+
+(The MIT License)
+
+Copyright (c) 2010 FIXME full name
+
+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/Rakefile

@@ -0,0 +1,26 @@
+require 'rubygems'
+gem 'hoe', '>= 2.1.0'
+require 'hoe'
+require 'fileutils'
+require './lib/imdb_celebrity'
+
+Hoe.plugin :newgem
+# Hoe.plugin :website
+# Hoe.plugin :cucumberfeatures
+
+# Generate all the Rake tasks
+# Run 'rake -T' to see list of generated tasks (from gem root directory)
+#$hoe = Hoe.spec 'imdb_celebrity' do
+  #self.developer 'Sandeep Kumar', 'sandeep@sapnasolutions.com'
+  #self.post_install_message = 'PostInstall.txt' # TODO remove if post-install message not required
+  # self.rubyforge_name       = self.name # TODO this is default value
+  # self.extra_deps         = [['activesupport','>= 2.0.2']]
+
+#end
+
+require 'newgem/tasks'
+Dir['tasks/**/*.rake'].each { |t| load t }
+
+# TODO - want other tests/tasks run by default? Add them to the list
+# remove_task :default
+# task :default => [:spec, :features]

data/bin/imdb_celebrity

@@ -0,0 +1,10 @@
+#!/usr/bin/env ruby
+#
+#  Created on 2010-9-29.
+#  Copyright (c) 2010. All rights reserved.
+
+require 'rubygems'
+require File.expand_path(File.dirname(__FILE__) + "/../lib/imdb_celebrity")
+require "imdb_celebrity/cli"
+
+ImdbCelebrity::CLI.execute(STDOUT, ARGV)

data/imdb_celebrity.gemspec

@@ -0,0 +1,15 @@
+Gem::Specification.new do |s|
+  s.name              = %q{imdb_celebrity}
+  s.version           = "0.0.1"
+  s.date              = %q{2010-10-04}
+  s.authors           = ["Sandeep Kumar"]
+  s.email             = %q{sandeep@sapnasolutions.com}
+  s.summary           = %q{Imdb_celebrity is a ruby-gem which is used to scrap celebrity pages from imdb.com}
+  s.homepage          = %q{http://github.com/sandeepkrao/imdb_celebrity}
+  s.description       = %q{Imdb_celebrity is a ruby-gem which is used to scrap celebrity pages from imdb.com}
+  s.files             = Dir["**/*"]
+  s.test_files        = Dir["spec/**"]
+  s.executables       = ["imdb_celebrity"]
+  s.add_dependency    "nokogiri"
+  s.add_dependency    "hpricot"
+end

data/lib/imdb_celebrity.rb

@@ -0,0 +1,13 @@
+$:.unshift(File.dirname(__FILE__)) unless
+  $:.include?(File.dirname(__FILE__)) || $:.include?(File.expand_path(File.dirname(__FILE__)))
+
+require 'rubygems'
+require 'open-uri'
+require 'imdb_celebrity/celebrity'
+require 'imdb_celebrity/search'
+require 'imdb_celebrity/string_extensions'
+require 'imdb_celebrity/parser/parser'
+
+module ImdbCelebrity
+  VERSION = '0.0.1'
+end

data/lib/imdb_celebrity/celebrity.rb

@@ -0,0 +1,72 @@
+require 'imdb_celebrity/parser/hpricot_parser/celebrity_bio_parser'
+require 'imdb_celebrity/parser/nokogiri_parser/celebrity_bio_parser'
+module ImdbCelebrity
+  #Represents a celebrity on IMDB.com
+  class Celebrity
+    attr_accessor :id, :url, :name, :parser, :real_name, :biography, :height, :nationality
+    
+    # Initialize a new IMDB celebrity object with it's IMDB id (as a String)
+    #
+    #   celebrity = Imdb::Celebrity.new("0095016", "celeb name", "Parsing Class")
+    #
+    # Imdb::Celebrity objects are lazy loading, meaning that no HTTP request
+    # will be performed when a new object is created. Only when you use an 
+    # accessor that needs the remote data, a HTTP request is made (once).
+    #
+    
+    def initialize imdb_id, title = nil, parser = "HpricotParser"
+      @id = imdb_id
+      @url = "http://www.imdb.com/name/nm#{imdb_id}/bio"
+      @name = title.gsub(/"/, "") if title
+      @parser = initialize_parser parser
+    end
+    
+    def to_s
+      [@id, @url, @name, @real_name, @biography, @height, @nationality]
+    end
+    
+    def name(flag=false)
+      if flag==true
+        @name = @parser.name
+      else
+        @name ||= @parser.name
+      end
+    end
+    
+    def real_name
+      @real_name ||=@parser.real_name
+    end
+    
+    def biography
+      @biography ||= @parser.biography
+    end
+    
+    def height
+      @height ||= @parser.height
+    end
+    
+    def nationality
+      @nationality ||= @parser.nationality
+    end
+    
+    def celebrity_data
+      @real_name ||=@parser.real_name
+      @biography ||= @parser.biography
+      @height ||= @parser.height
+      @nationality ||= @parser.nationality
+      return true
+    end
+    
+    private
+    
+    def self.find_by_id imdb_id
+      open("http://www.imdb.com/name/nm#{imdb_id}/")
+    end
+    
+    def initialize_parser parser
+      return ImdbCelebrity::Parser::HpricotParser::CelebrityBioParser.new(@url) if parser == "HpricotParser"
+      return ImdbCelebrity::Parser::NokogiriParser::CelebrityBioParser.new(@url) if parser == "NokogiriParser"
+    end
+    
+  end
+end

data/lib/imdb_celebrity/cli.rb

@@ -0,0 +1,42 @@
+require 'optparse'
+
+module ImdbCelebrity
+  class CLI
+    def self.execute(stdout, arguments=[])
+
+      # NOTE: the option -p/--path= is given as an example, and should be replaced in your application.
+
+      options = {
+        :path     => '~'
+      }
+      mandatory_options = %w(  )
+
+      parser = OptionParser.new do |opts|
+        opts.banner = <<-BANNER.gsub(/^          /,'')
+          This application is wonderful because...
+
+          Usage: #{File.basename($0)} [options]
+
+          Options are:
+        BANNER
+        opts.separator ""
+        opts.on("-p", "--path PATH", String,
+                "This is a sample message.",
+                "For multiple lines, add more strings.",
+                "Default: ~") { |arg| options[:path] = arg }
+        opts.on("-h", "--help",
+                "Show this help message.") { stdout.puts opts; exit }
+        opts.parse!(arguments)
+
+        if mandatory_options && mandatory_options.find { |option| options[option.to_sym].nil? }
+          stdout.puts opts; exit
+        end
+      end
+
+      path = options[:path]
+
+      # do stuff
+      stdout.puts "To update this executable, look in lib/imdb_celebrity/cli.rb"
+    end
+  end
+end

data/lib/imdb_celebrity/parser/hpricot_parser/celebrity_bio_parser.rb

@@ -0,0 +1,17 @@
+require 'imdb_celebrity/parser/hpricot_parser/hpricot_parser'
+require 'imdb_celebrity/parser/parser'
+
+module ImdbCelebrity
+  module Parser
+    module HpricotParser
+      class CelebrityBioParser < ImdbCelebrity::Parser::HpricotParser::HpricotParser
+        include ImdbCelebrity::Parser::Parser
+        
+        def initialize uri
+          super(uri)
+        end
+
+      end
+    end
+  end
+end

data/lib/imdb_celebrity/parser/hpricot_parser/hpricot_parser.rb

@@ -0,0 +1,22 @@
+require 'hpricot'
+
+module ImdbCelebrity
+  module Parser
+    module HpricotParser
+      class HpricotParser
+        attr_reader :page
+      
+        def initialize uri
+          @page = uri
+        end
+      
+        protected
+       
+        def document
+          @document ||= Hpricot(open(URI.encode(@page), "User-Agent" => "ruby"))
+        end
+    
+      end
+    end
+  end
+end

data/lib/imdb_celebrity/parser/hpricot_parser/search_parser.rb

@@ -0,0 +1,40 @@
+require 'imdb_celebrity/parser/hpricot_parser/hpricot_parser'
+module ImdbCelebrity
+  module Parser
+    module HpricotParser
+      class SearchParser < ImdbCelebrity::Parser::HpricotParser::HpricotParser
+        
+        def initialize uri
+          super uri
+        end
+        
+        # Returns true if search returns specificly only one result, exact match
+        def exact_match?
+          #!document.at("//h3[text()^='Overview'/..]").nil?
+          !document.at("//h3[text()^='Overview']/..").nil?
+        end
+
+        def parse_celebrities parser
+          document.search('a[@href^="/name/nm"]').reject do |element|
+            element.innerHTML.imdb_strip_tags.empty? ||
+            element.parent.innerHTML =~ /media from/i
+          end.map do |element|
+            id = element['href'][/\d+/]
+
+            data = element.parent.innerHTML.split("<br />")
+            if !data[0].nil? && !data[1].nil? && data[0] =~ /img/
+              title = data[1]
+            else
+              title = data[0]
+            end
+
+            title = title.imdb_strip_tags.imdb_unescape_html
+            title.gsub!(/\s+\(\d{4}\)$/, '')
+
+            [id, title, parser]
+          end
+        end
+      end
+    end
+  end
+end

data/lib/imdb_celebrity/parser/nokogiri_parser/celebrity_bio_parser.rb

@@ -0,0 +1,22 @@
+require 'imdb_celebrity/parser/nokogiri_parser/nokogiri_parser'
+require 'imdb_celebrity/parser/parser'
+
+module ImdbCelebrity
+  module Parser
+    module NokogiriParser
+      class CelebrityBioParser < ImdbCelebrity::Parser::NokogiriParser::NokogiriParser
+      
+        include ImdbCelebrity::Parser::Parser
+        
+        def initialize uri
+          super uri
+        end
+        
+        def biography
+          document.at("h5[text()*='Biography']").next_sibling.next_sibling.inner_text rescue nil
+        end
+        
+      end
+    end
+  end
+end

data/lib/imdb_celebrity/parser/nokogiri_parser/nokogiri_parser.rb

@@ -0,0 +1,21 @@
+require 'nokogiri'
+
+module ImdbCelebrity
+  module Parser
+    module NokogiriParser
+      class NokogiriParser
+        
+        def initialize uri
+          @page = uri
+        end
+        
+        protected
+        
+        def document
+          @document ||= Nokogiri::HTML(open(URI.encode(@page), "User-Agent" => "ruby"))
+        end
+        
+      end
+    end
+  end
+end

data/lib/imdb_celebrity/parser/nokogiri_parser/search_parser.rb

@@ -0,0 +1,39 @@
+require 'imdb_celebrity/parser/nokogiri_parser/nokogiri_parser'
+
+module ImdbCelebrity
+  module Parser
+    module NokogiriParser
+      class SearchParser < ImdbCelebrity::Parser::NokogiriParser::NokogiriParser
+        def initialize uri
+          super uri
+        end
+        
+        def exact_match?
+          !document.at("h3[text()^='Overview']").nil?
+        end
+        
+        def parse_celebrities parser
+          document.search('a[@href^="/name/nm"]').reject do |element|
+            element.to_html.imdb_strip_tags.empty? ||
+            element.parent.to_html =~ /media from/i
+          end.map do |element|
+            id = element['href'][/\d+/]
+
+            data = element.parent.to_html.split("<br />")
+            if !data[0].nil? && !data[1].nil? && data[0] =~ /img/
+              title = data[1]
+            else
+              title = data[0]
+            end
+
+            title = title.imdb_strip_tags.imdb_unescape_html
+            title.gsub!(/\s+\(\d{4}\)$/, '')
+
+            [id, title, parser]
+          end
+        end
+      
+      end
+    end
+  end
+end

data/lib/imdb_celebrity/parser/parser.rb

@@ -0,0 +1,25 @@
+module ImdbCelebrity
+  module Parser
+    module Parser
+      def name
+        document.at("a[@class='main']").inner_text rescue nil
+      end
+      
+      def real_name
+        document.at("h5[text()*='Birth Name']").next.inner_text.strip rescue nil
+      end
+      
+      def nationality
+        document.at("a[@href*='birth_place']").inner_text.strip rescue nil
+      end
+      
+      def height
+        document.at("h5[text()*='Height']").next.inner_text[/\(.+\)/] rescue nil
+      end
+      
+      def biography
+        document.at("h5[text()*='Biography']").next_sibling.inner_text rescue nil
+      end
+    end
+  end
+end

data/lib/imdb_celebrity/search.rb

@@ -0,0 +1,45 @@
+require 'imdb_celebrity/parser/hpricot_parser/search_parser'
+require 'imdb_celebrity/parser/nokogiri_parser/search_parser'
+
+module ImdbCelebrity
+
+  class Search
+    attr_reader :query, :parser
+    
+    def initialize(query, parser ="HpricotParser")
+      @query = search_uri query
+      @parser_text = parser
+      @parser = initialize_parser parser
+    end
+    
+    def celebrities
+      @celebrities = (@parser.exact_match? ? @parser.parse_celebrity : parse_celebrities)
+    end
+    
+    private
+    
+    def search_uri query
+      "http://imdb.com/find?s=nm&q=#{query}"
+    end
+    
+    def parse_celebrity
+      id = @document.at("head/link[@rel='canonical']")[:href][/\d+/]
+      name = @document.at("h1").inner_html.split('<span').first.inner_text.imdb_unescape_html
+      [ImdbCelebrity::Celebrity.new(id, name, @parser_text)]
+    end
+    
+    def parse_celebrities
+      celebrities = @parser.parse_celebrities @parser_text
+      celebrities.uniq.map do |values|
+        ImdbCelebrity::Celebrity.new(*values)
+      end      
+    end
+    
+    def initialize_parser parser
+      return ImdbCelebrity::Parser::HpricotParser::SearchParser.new(@query) if parser == "HpricotParser"
+      return ImdbCelebrity::Parser::NokogiriParser::SearchParser.new(@query) if parser == "NokogiriParser"
+    end
+    
+  end
+  
+end

data/lib/imdb_celebrity/string_extensions.rb

@@ -0,0 +1,24 @@
+require 'cgi'
+require 'iconv'
+ 
+module ImdbCelebrity 
+  module StringExtensions
+  
+    # Unescape HTML
+    def imdb_unescape_html
+      Iconv.conv("UTF-8", 'ISO-8859-1', CGI::unescapeHTML(self))
+    end
+  
+    # Strip tags
+    def imdb_strip_tags
+      gsub(/<\/?[^>]*>/, "")
+    end
+    
+    # Strips out whitespace then tests if the string is empty.
+    def blank?
+      strip.empty?
+    end unless method_defined?(:blank?)
+  end
+end
+
+String.send :include, ImdbCelebrity::StringExtensions

data/script/console

@@ -0,0 +1,10 @@
+#!/usr/bin/env ruby
+# File: script/console
+irb = RUBY_PLATFORM =~ /(:?mswin|mingw)/ ? 'irb.bat' : 'irb'
+
+libs =  " -r irb/completion"
+# Perhaps use a console_lib to store any extra methods I may want available in the cosole
+# libs << " -r #{File.dirname(__FILE__) + '/../lib/console_lib/console_logger.rb'}"
+libs <<  " -r #{File.dirname(__FILE__) + '/../lib/imdb_celebrity.rb'}"
+puts "Loading imdb_celebrity gem"
+exec "#{irb} #{libs} --simple-prompt"

data/script/destroy

@@ -0,0 +1,14 @@
+#!/usr/bin/env ruby
+APP_ROOT = File.expand_path(File.join(File.dirname(__FILE__), '..'))
+
+begin
+  require 'rubigen'
+rescue LoadError
+  require 'rubygems'
+  require 'rubigen'
+end
+require 'rubigen/scripts/destroy'
+
+ARGV.shift if ['--help', '-h'].include?(ARGV[0])
+RubiGen::Base.use_component_sources! [:rubygems, :newgem, :newgem_theme, :test_unit]
+RubiGen::Scripts::Destroy.new.run(ARGV)

data/script/generate

@@ -0,0 +1,14 @@
+#!/usr/bin/env ruby
+APP_ROOT = File.expand_path(File.join(File.dirname(__FILE__), '..'))
+
+begin
+  require 'rubigen'
+rescue LoadError
+  require 'rubygems'
+  require 'rubigen'
+end
+require 'rubigen/scripts/generate'
+
+ARGV.shift if ['--help', '-h'].include?(ARGV[0])
+RubiGen::Base.use_component_sources! [:rubygems, :newgem, :newgem_theme, :test_unit]
+RubiGen::Scripts::Generate.new.run(ARGV)

data/spec/imdb_celebrity/celebrity_spec.rb

@@ -0,0 +1,48 @@
+require File.dirname(__FILE__) + '/../spec_helper.rb'
+
+describe "Celebrity Spec" do
+  
+  before(:all) do
+    @celeb1 = ImdbCelebrity::Celebrity.new("0000093", "brad pitt")
+    @celeb2 = ImdbCelebrity::Celebrity.new("0000093", "brad pitt", "NokogiriParser")
+  end
+  
+  after :all do
+    @celeb1 = nil
+    @celeb2 = nil
+  end
+  
+  it "should use the Hpricot as default parser class" do
+    #celeb = ImdbCelebrity::Celebrity.new("0000093", "brad pitt")
+    @celeb1.parser.class.should == ImdbCelebrity::Parser::HpricotParser::CelebrityBioParser
+  end
+  
+  it "should use the Parser class with Parser type we are sending" do
+    #celeb = ImdbCelebrity::Celebrity.new("0000093", "brad pitt", "NokogiriParser")
+    @celeb2.parser.class.should == ImdbCelebrity::Parser::NokogiriParser::CelebrityBioParser
+  end
+  
+  it "should return biography of the celebrity" do
+    @celeb1.biography.should == "Brad Pitt was born in 1963 in Oklahoma and raised in Springfield, Missouri. His mother's name is Jane Etta Hillhouse. His father, William (Bill) Pitt, worked in management at a trucking firm in Springfield. He has a younger brother, Douglas (Doug) Pitt and a younger sister Julie Neal Pitt. At Kickapoo High School, Pitt was involved in sports, debating, student government and school musicals. Pitt attended the University of Missouri, where he majored in journalism with a focus on advertising. He occasionally acted in fraternity shows. He left college two credits short of graduating to move to California. Before he became successful at acting, Pitt supported himself by driving strippers in limos, moving refrigerators and dressing as a giant chicken while working for \"el Pollo Loco.\""
+    @celeb1.parser.stub!(:biography).and_return("Incosistent Data")
+    @celeb1.biography.should_not == "Inconsistent Data"
+  end
+  
+  it "should return height of the celebrity" do
+    @celeb1.height.should == "(1.80 m)"
+    @celeb1.parser.stub!(:height).and_return("1.9m")
+    @celeb1.height.should_not == "1.9m"
+  end
+  
+  it "should return nationality of the celebrity" do 
+    @celeb1.nationality.should == "Shawnee, Oklahoma, USA"
+    @celeb1.parser.stub!(:nationality).and_return("New Jersy, USA")
+    @celeb1.nationality.should_not == "New Jersy, USA"
+  end
+  
+  it "should return array of attribute accessors of celebrity" do
+    @celeb1.to_s.class.should == Array
+    @celeb1.to_s.length.should == 7
+  end
+  
+end

data/spec/imdb_celebrity/parser/hpricot_parser/celebrity_bio_parser_spec.rb

@@ -0,0 +1,21 @@
+require File.dirname(__FILE__) + "/../../../spec_helper.rb"
+
+describe "Celebrity Bio Parser Spec" do
+    
+  before :all do 
+    @celeb_bio_h = ImdbCelebrity::Parser::HpricotParser::CelebrityBioParser.new("http://www.imdb.com/name/nm0000093/bio")
+  end
+  
+  after :all do 
+    @celeb_bio_h = nil
+  end
+  
+  it "should extend Parser module" do
+    @celeb_bio_h.extend ImdbCelebrity::Parser::Parser
+  end
+  
+  it "should extend HpricotParser/NokogiriParser Class" do
+    @celeb_bio_h.class.superclass.should == ImdbCelebrity::Parser::HpricotParser::HpricotParser
+  end
+    
+end

data/spec/imdb_celebrity/parser/nokogiri_parser/celebrity_bio_parser_spec.rb

@@ -0,0 +1,33 @@
+require File.dirname(__FILE__) + "/../../../spec_helper.rb"
+require 'nokogiri'
+
+describe "Celebrity Bio Parser Spec" do
+    
+  before :all do 
+    @celeb_bio_n = ImdbCelebrity::Parser::NokogiriParser::CelebrityBioParser.new("http://www.imdb.com/name/nm0000093/bio")
+  end
+  
+  after :all do
+    @celeb_bio_n = nil
+  end
+  
+  it "should extend Parser module" do
+    @celeb_bio_n.extend ImdbCelebrity::Parser::Parser
+  end
+  
+  it "should extend HpricotParser/NokogiriParser Class" do
+    @celeb_bio_n.class.superclass.should == ImdbCelebrity::Parser::NokogiriParser::NokogiriParser
+  end
+  
+  it "should called the overrided methods" do
+    # biography() method has been overrided, so it should call class method only
+    @celeb_bio_n.biography.should == "Brad Pitt was born in 1963 in Oklahoma and raised in Springfield, Missouri. His mother's name is Jane Etta Hillhouse. His father, William (Bill) Pitt, worked in management at a trucking firm in Springfield. He has a younger brother, Douglas (Doug) Pitt and a younger sister Julie Neal Pitt. At Kickapoo High School, Pitt was involved in sports, debating, student government and school musicals. Pitt attended the University of Missouri, where he majored in journalism with a focus on advertising. He occasionally acted in fraternity shows. He left college two credits short of graduating to move to California. Before he became successful at acting, Pitt supported himself by driving strippers in limos, moving refrigerators and dressing as a giant chicken while working for \"el Pollo Loco.\""
+  end
+  
+  it "should not call the superclass methods for overrided methods" do
+    @superparser = ImdbCelebrity::Parser::NokogiriParser::NokogiriParser.new("http://www.imdb.com/name/nm0000093/bio")
+    @superparser.stub!(:biography).and_return("Demo Biography")
+    @celeb_bio_n.biography.should_not == "Demo Biography"
+  end
+    
+end

data/spec/imdb_celebrity/parser/parser_spec.rb

@@ -0,0 +1,45 @@
+require File.dirname(__FILE__) + "/../../spec_helper.rb"
+
+# dummy class created to test module's functionality
+class ParserDummy 
+  include ImdbCelebrity::Parser::Parser
+  def initialize uri
+    @page = uri
+  end
+  protected
+  def document
+    @document ||= Hpricot(open(URI.encode(@page), "User-Agent" => "ruby"))
+  end
+end
+
+describe "Parser Spec" do
+  
+  before :all do
+    @parser_dummy = ParserDummy.new("http://imdb.com/name/nm0000093/bio")
+  end
+  
+  after :all do
+    @parser_dummy = nil
+  end
+  
+  it "should return the celebrity real_name" do
+    @parser_dummy.real_name.should == "William Bradley Pitt"
+  end
+  
+  it "should return celebrity biography" do 
+    @parser_dummy.biography.should == "Brad Pitt was born in 1963 in Oklahoma and raised in Springfield, Missouri. His mother's name is Jane Etta Hillhouse. His father, William (Bill) Pitt, worked in management at a trucking firm in Springfield. He has a younger brother, Douglas (Doug) Pitt and a younger sister Julie Neal Pitt. At Kickapoo High School, Pitt was involved in sports, debating, student government and school musicals. Pitt attended the University of Missouri, where he majored in journalism with a focus on advertising. He occasionally acted in fraternity shows. He left college two credits short of graduating to move to California. Before he became successful at acting, Pitt supported himself by driving strippers in limos, moving refrigerators and dressing as a giant chicken while working for \"el Pollo Loco.\""
+  end
+  
+  it "should return celebrity height" do
+    @parser_dummy.height.should == "(1.80 m)"
+  end
+  
+  it "should return celebrity nationality" do
+    @parser_dummy.nationality.should == "Shawnee, Oklahoma, USA"
+  end
+  
+  it "should return celebrity name" do
+    @parser_dummy.name.should == "Brad Pitt"
+  end
+  
+end

data/spec/imdb_celebrity/search_spec.rb

@@ -0,0 +1,28 @@
+require File.dirname(__FILE__) + "/../spec_helper.rb"
+
+describe "Search Spec" do
+  
+  before :all do
+    @search1 = ImdbCelebrity::Search.new("Brad Pitt")
+    @search2 = ImdbCelebrity::Search.new("Brad Pitt", "NokogiriParser")
+  end
+  
+  after :all do
+    @search1 = nil
+    @search2 = nil
+  end
+  
+  it "should use hpricot as defualt parsing class" do
+    @search1.parser.class.should == ImdbCelebrity::Parser::HpricotParser::SearchParser
+  end
+  
+  it "should use the parsing class which we want" do
+    @search2.parser.class.should == ImdbCelebrity::Parser::NokogiriParser::SearchParser
+  end
+  
+  it "should return the celbrities list with given search string" do
+    @search1.celebrities.class.should == Array
+    @search1.celebrities.should_not == []
+  end
+  
+end

data/spec/imdb_celebrity/string_extensions_spec.rb

@@ -0,0 +1,31 @@
+require File.dirname(__FILE__) + "/../spec_helper.rb"
+
+class String
+  include ImdbCelebrity::StringExtensions
+end
+
+describe "String Extensions Spec" do
+  
+  before :all do
+    @dummy = "<small>(Actor, <a href='/title/tt0114369/'>Se7en</a> (1995))</small>"
+  end
+  
+  after :all do
+    @dummy = nil
+  end
+  
+  it "should unescape the html from a string literal" do
+    @dummy.imdb_unescape_html.should == "<small>(Actor, <a href='/title/tt0114369/'>Se7en</a> (1995))</small>"
+  end
+  
+  it "should strip the html tag from the string" do
+    @dummy.imdb_strip_tags.should == "(Actor, Se7en (1995))"
+  end
+  
+  it "should strip out the white space and check whether string is empty or not" do
+    @dummy.blank?.should == false
+    demo = "   "
+    demo.blank?.should == true
+  end
+  
+end

data/spec/imdb_celebrity_cli_spec.rb

@@ -0,0 +1,15 @@
+require File.expand_path(File.dirname(__FILE__) + '/spec_helper')
+require 'imdb_celebrity/cli'
+
+describe ImdbCelebrity::CLI, "execute" do
+  before(:each) do
+    @stdout_io = StringIO.new
+    ImdbCelebrity::CLI.execute(@stdout_io, [])
+    @stdout_io.rewind
+    @stdout = @stdout_io.read
+  end
+  
+  it "should print default output" do
+    @stdout.should =~ /To update this executable/
+  end
+end

data/spec/imdb_celebrity_spec.rb

@@ -0,0 +1,11 @@
+require File.dirname(__FILE__) + '/spec_helper.rb'
+
+# Time to add your specs!
+# http://rspec.info/
+describe "Place your specs here" do
+  
+  it "should return the correct version of the gem" do
+    ImdbCelebrity::VERSION.should == "0.0.1"
+  end
+  
+end

data/spec/spec.opts

@@ -0,0 +1 @@
+--colour

data/spec/spec_helper.rb

@@ -0,0 +1,19 @@
+begin
+  require 'spec'
+rescue LoadError
+  require 'rubygems' unless ENV['NO_RUBYGEMS']
+  gem 'rspec'
+  require 'spec'
+end
+
+$:.unshift(File.dirname(__FILE__) + '/../lib')
+require 'imdb_celebrity'
+
+Spec::Runner.configure do |config|
+  config.before(:all){
+    
+  }
+  config.after(:all){
+    
+  }
+end

data/tasks/rspec.rake

@@ -0,0 +1,21 @@
+begin
+  require 'spec'
+rescue LoadError
+  require 'rubygems' unless ENV['NO_RUBYGEMS']
+  require 'spec'
+end
+begin
+  require 'spec/rake/spectask'
+rescue LoadError
+  puts <<-EOS
+To use rspec for testing you must install rspec gem:
+    gem install rspec
+EOS
+  exit(0)
+end
+
+desc "Run the specs under spec/models"
+Spec::Rake::SpecTask.new do |t|
+  t.spec_opts = ['--options', "spec/spec.opts"]
+  t.spec_files = FileList['spec/**/*_spec.rb']
+end

metadata

@@ -0,0 +1,129 @@
+--- !ruby/object:Gem::Specification 
+name: imdb_celebrity
+version: !ruby/object:Gem::Version 
+  hash: 29
+  prerelease: false
+  segments: 
+  - 0
+  - 0
+  - 1
+  version: 0.0.1
+platform: ruby
+authors: 
+- Sandeep Kumar
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2010-10-04 00:00:00 +05:30
+default_executable: 
+dependencies: 
+- !ruby/object:Gem::Dependency 
+  name: nokogiri
+  prerelease: false
+  requirement: &id001 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        hash: 3
+        segments: 
+        - 0
+        version: "0"
+  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: 3
+        segments: 
+        - 0
+        version: "0"
+  type: :runtime
+  version_requirements: *id002
+description: Imdb_celebrity is a ruby-gem which is used to scrap celebrity pages from imdb.com
+email: sandeep@sapnasolutions.com
+executables: 
+- imdb_celebrity
+extensions: []
+
+extra_rdoc_files: []
+
+files: 
+- bin/imdb_celebrity
+- History.txt
+- imdb_celebrity.gemspec
+- lib/imdb_celebrity/celebrity.rb
+- lib/imdb_celebrity/cli.rb
+- lib/imdb_celebrity/parser/hpricot_parser/celebrity_bio_parser.rb
+- lib/imdb_celebrity/parser/hpricot_parser/hpricot_parser.rb
+- lib/imdb_celebrity/parser/hpricot_parser/search_parser.rb
+- lib/imdb_celebrity/parser/nokogiri_parser/celebrity_bio_parser.rb
+- lib/imdb_celebrity/parser/nokogiri_parser/nokogiri_parser.rb
+- lib/imdb_celebrity/parser/nokogiri_parser/search_parser.rb
+- lib/imdb_celebrity/parser/parser.rb
+- lib/imdb_celebrity/search.rb
+- lib/imdb_celebrity/string_extensions.rb
+- lib/imdb_celebrity.rb
+- Manifest.txt
+- PostInstall.txt
+- Rakefile
+- README.rdoc
+- script/console
+- script/destroy
+- script/generate
+- spec/imdb_celebrity/celebrity_spec.rb
+- spec/imdb_celebrity/parser/hpricot_parser/celebrity_bio_parser_spec.rb
+- spec/imdb_celebrity/parser/nokogiri_parser/celebrity_bio_parser_spec.rb
+- spec/imdb_celebrity/parser/parser_spec.rb
+- spec/imdb_celebrity/search_spec.rb
+- spec/imdb_celebrity/string_extensions_spec.rb
+- spec/imdb_celebrity_cli_spec.rb
+- spec/imdb_celebrity_spec.rb
+- spec/spec.opts
+- spec/spec_helper.rb
+- tasks/rspec.rake
+has_rdoc: true
+homepage: http://github.com/sandeepkrao/imdb_celebrity
+licenses: []
+
+post_install_message: 
+rdoc_options: []
+
+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: Imdb_celebrity is a ruby-gem which is used to scrap celebrity pages from imdb.com
+test_files: 
+- spec/imdb_celebrity_cli_spec.rb
+- spec/imdb_celebrity_spec.rb
+- spec/spec.opts
+- spec/spec_helper.rb