cschiewek-imdb 0.5.1

data/README.rdoc

@@ -0,0 +1,79 @@
+= imdb
+
+The code, issue tracker and wiki can be found at:
+
+* http://github.com/ariejan/imdb
+
+== DESCRIPTION:
+
+This packages allows you to easy access publicly available data from IMDB. 
+
+== FEATURES/PROBLEMS:
+
+IMDB currently features the following:
+
+* Querying details movie info
+* Searching for movies
+* Command-line utility included.
+
+== SYNOPSIS:
+
+Movies:
+
+  i = Imdb::Movie.new("0095016")
+  
+  i.title
+  #=> "Die Hard"
+  i.cast_member.first
+  #=> "Bruce Willis"
+
+Searching:
+
+    i = Imdb::Search.new("Star Trek")
+
+    i.movies.size
+    #=> 97
+    
+Using the command line utility is quite easy:
+
+    $ imdb Star Trek
+    
+or to get movie info
+
+    $ imdb 0095016
+
+== REQUIREMENTS:
+
+All required gems are installed automagically through RubyGems.
+
+* Hpricot 0.8.1
+* HTTParty 0.4.3
+
+== INSTALL:
+
+* sudo gem install imdb
+
+== LICENSE:
+
+(The MIT License)
+
+Copyright (c) 2009 Ariejan de Vroom
+
+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/bin/imdb

@@ -0,0 +1,10 @@
+#!/usr/bin/env ruby
+#
+#  Created on 2009-6-4.
+#  Copyright (c) 2009. All rights reserved.
+
+require File.expand_path(File.dirname(__FILE__) + "/../lib/imdb")
+
+require "imdb/cli"
+
+Imdb::CLI.execute(STDOUT, ARGV)

data/lib/imdb.rb

@@ -0,0 +1,16 @@
+$:.unshift(File.dirname(__FILE__)) unless
+  $:.include?(File.dirname(__FILE__)) || $:.include?(File.expand_path(File.dirname(__FILE__)))
+
+require 'open-uri'
+require 'rubygems'
+require 'hpricot'
+
+require 'imdb/movie'
+require 'imdb/movie_list'
+require 'imdb/search'
+require 'imdb/top_250'
+require 'imdb/string_extensions'
+
+module Imdb
+  VERSION = '0.5.0'
+end

data/lib/imdb/cli.rb

@@ -0,0 +1,104 @@
+require 'optparse'
+
+module Imdb
+  class CLI
+    
+    # Run the imdb command
+    #
+    # Searching
+    #
+    #   imdb Star Trek
+    #
+    # Get a movie, supply a 7 digit IMDB id
+    #
+    #   imdb 0095016
+    #
+    def self.execute(stdout, arguments=[])
+      
+      @stdout = stdout
+      
+      options = {
+      }
+      mandatory_options = %w(  )
+      
+      parser = OptionParser.new do |opts|
+        opts.banner = <<-BANNER.gsub(/^          /,'')
+          IMDB #{Imdb::VERSION}
+
+          Usage: #{File.basename($0)} Search Query
+                 #{File.basename($0)} 0095016
+
+        BANNER
+        opts.separator ""
+        opts.on("-v", "--version",
+                "Show the current version.") { stdout.puts "IMDB #{Imdb::VERSION}"; exit }
+        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
+
+      query = arguments.join(" ").strip
+      exit if query.blank?
+      
+      movie, search = nil, nil
+      
+      # If ID, fetch movie
+      if query.match(/\d\d\d\d\d\d\d/)
+        fetch_movie(query)
+      else
+        search_movie(query)
+      end
+    end
+    
+    def self.fetch_movie(imdb_id)
+      @stdout.puts ">> Fetching movie #{imdb_id}"
+      
+      movie = Imdb::Movie.new(imdb_id)
+      
+      display_movie_details(movie)
+    end
+    
+    def self.search_movie(query)
+      @stdout.puts ">> Searching for \"#{query}\""
+      
+      search = Imdb::Search.new(query)
+      
+      if search.movies.size == 1
+        display_movie_details(search.movies.first)
+      else
+        display_search_results(search.movies)
+      end
+    end
+    
+    def self.display_movie_details(movie)
+      title = "#{movie.title} (#{movie.year})"
+      id    = "ID #{movie.id}"
+      
+      @stdout.puts
+      @stdout.puts "#{title}#{" " * (75 - 1 - title.length - id.length)}#{id} "
+      @stdout.puts "=" * 75
+      @stdout.puts "Rating: #{movie.rating}"
+      @stdout.puts "Duration: #{movie.length} minutes"
+      @stdout.puts "Directed by: #{movie.director.join(", ")}"
+      @stdout.puts "Cast: #{movie.cast_members[0..4].join(", ")}"
+      @stdout.puts "Genre: #{movie.genres.join(", ")}"
+      @stdout.puts "Plot: #{movie.plot}"
+      @stdout.puts "IMDB URL: #{movie.url}"
+      @stdout.puts "=" * 75
+      @stdout.puts
+    end
+    
+    def self.display_search_results(movies = [])
+      movies = movies[0..9] # limit to ten top hits
+      
+      movies.each do |movie|
+        @stdout.puts " > #{movie.id} | #{movie.title}"
+      end
+    end
+    
+  end
+end

data/lib/imdb/movie.rb

@@ -0,0 +1,107 @@
+module Imdb
+  
+  # Represents a Movie on IMDB.com
+  class Movie
+    attr_accessor :id, :url, :title
+    
+    # Initialize a new IMDB movie object with it's IMDB id (as a String)
+    #
+    #   movie = Imdb::Movie.new("0095016")
+    #
+    # Imdb::Movie 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)
+      @id = imdb_id
+      @url = "http://www.imdb.com/title/tt#{imdb_id}/"
+      @title = title.gsub(/"/, "") if title
+    end
+    
+    # Returns an array with cast members
+    def cast_members
+      document.search("table.cast td.nm a").map { |link| link.innerHTML.strip.imdb_unescape_html } rescue []
+    end
+    
+    # Returns the name of the director
+    def director
+      # document.at("h5[text()='Director:'] ~ a").innerHTML.strip.imdb_unescape_html rescue nil
+      document.search("h5[text()^='Director'] ~ a").map { |link| link.innerHTML.strip.imdb_unescape_html } rescue []
+    end
+    
+    # Returns an array of genres (as strings)
+    def genres
+      document.search("h5[text()='Genre:'] ~ a[@href*=/Sections/Genres/']").map { |link| link.innerHTML.strip.imdb_unescape_html } rescue []
+    end
+    
+    # Returns the duration of the movie in minutes as an integer.
+    def length
+      document.search("//h5[text()^='Runtime']/..").innerHTML[/\d+ min/].to_i rescue nil
+    end
+    
+    # Returns a string containing the plot.
+    def plot
+      document.search("//h5[text()^='Plot']/..").innerHTML.split("\n")[2].gsub(/<.+>.+<\/.+>/, '').strip.imdb_unescape_html rescue nil
+    end
+    
+    # Returns a string containing the URL to the movie poster.
+    def poster
+      document.at("a[@name='poster'] img")['src'][/http:.+@@/] + '.jpg' rescue nil
+    end
+    
+    # Returns a float containing the average user rating
+    def rating
+      document.at(".general.rating b").innerHTML.strip.imdb_unescape_html.split('/').first.to_f rescue nil
+    end
+    
+    # Returns a string containing the tagline
+    def tagline
+      document.search("//h5[text()^='Tagline']/..").innerHTML.split("\n")[2].gsub(/<.+>.+<\/.+>/, '').strip.imdb_unescape_html rescue nil
+    end
+    
+    # Returns a string containing the title
+    def title(force_refresh = false)
+      if @title && !force_refresh
+        @title
+      else
+        @title = document.at("h1").innerHTML.split('<span').first.strip.imdb_unescape_html rescue nil 
+      end
+    end
+    
+    # Returns an integer containing the year (CCYY) the movie was released in.
+    def year
+      document.search('a[@href^="/Sections/Years/"]').innerHTML.to_i
+    end
+    
+    # Returns a date containing the release date fo the movie.
+    def release_date
+      @date = Date.strptime(document.search("//h5[text()^='Release Date']/..").innerHTML.split("\n")[2].gsub(/<.+>.+<\/.+>/, '').split('(').first.strip,
+                            '%d %b %Y') rescue nil
+    end
+        
+    private
+    
+    # Returns a new Hpricot document for parsing.
+    def document
+      @document ||= Hpricot(Imdb::Movie.find_by_id(@id))
+    end
+    
+    private 
+    
+    # Use HTTParty to fetch the raw HTML for this movie.
+    def self.find_by_id(imdb_id)
+      open("http://www.imdb.com/title/tt#{imdb_id}/")
+    end
+    
+    # Convenience method for search
+    def self.search(query)
+      Imdb::Search.new(query).movies
+    end
+
+    def self.top_250
+      Imdb::Top250.new.movies
+    end
+    
+  end # Movie
+  
+end # Imdb

data/lib/imdb/movie_list.rb

@@ -0,0 +1,33 @@
+module Imdb
+
+  class MovieList
+    def movies
+      @movies ||= parse_movies
+    end
+    
+    private
+    def parse_movies
+      document.search('a[@href^="/title/tt"]').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+\(\d\d\d\d\)$/, '')
+        
+        [id, title]
+      end.uniq.map do |values|
+        Imdb::Movie.new(*values)
+      end
+    end
+  end # MovieList
+
+end # Imdb

data/lib/imdb/search.rb

@@ -0,0 +1,45 @@
+module Imdb
+  
+  # Search IMDB for a title
+  class Search < MovieList
+    attr_reader :query
+
+    # Initialize a new IMDB search with the specified query
+    #
+    #   search = Imdb::Search.new("Star Trek")
+    #
+    # Imdb::Search is lazy loading, meaning that unless you access the +movies+ 
+    # attribute, no query is made to IMDB.com.
+    #
+    def initialize(query)
+      @query = query
+    end
+    
+    # Returns an array of Imdb::Movie objects for easy search result yielded.
+    # If the +query+ was an exact match, a single element array will be returned.
+    def movies
+      @movies ||= (exact_match? ? parse_movie : parse_movies)
+    end
+    
+    private
+    def document
+      @document ||= Hpricot(Imdb::Search.query(@query))
+    end
+    
+    def self.query(query)
+      open("http://www.imdb.com/find?q=#{CGI::escape(query)};s=tt")
+    end
+    
+    def parse_movie
+      id = document.at("a[@name='poster']")['href'][/\d+$/]
+      title = document.at("h1").innerHTML.split('<span').first.strip.imdb_unescape_html
+      [Imdb::Movie.new(id, title)]
+    end
+    
+    # Returns true if the search yielded only one result, an exact match
+    def exact_match?
+      !document.at("//h3[text()^='Overview']/..").nil?
+    end
+    
+  end # Search
+end # Imdb

data/lib/imdb/string_extensions.rb

@@ -0,0 +1,25 @@
+require 'cgi'
+require 'iconv'
+
+ 
+module Imdb #:nordoc:
+  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, Imdb::StringExtensions

data/lib/imdb/top_250.rb

@@ -0,0 +1,10 @@
+module Imdb
+
+  class Top250 < MovieList
+    private
+    def document
+      @document ||= Hpricot(open("http://www.imdb.com/chart/top"))
+    end
+  end # Top250
+
+end # Imdb

data/spec/imdb/cli_spec.rb

@@ -0,0 +1,34 @@
+require File.dirname(__FILE__) + '/../spec_helper'
+require 'imdb/cli'
+
+describe Imdb::CLI, "execute" do
+  
+  describe "yield search results" do
+    before(:each) do
+      @stdout_io = StringIO.new
+      Imdb::CLI.execute(@stdout_io, ["Star Trek"])
+      @stdout_io.rewind
+      @stdout = @stdout_io.read
+    end
+  
+    it "report data" do
+      @stdout.should =~ /0060028/
+      @stdout.should =~ /Star Trek/
+      @stdout.should =~ /1966/
+    end
+  end
+
+  describe "yield one movie" do
+    before(:each) do
+      @stdout_io = StringIO.new
+      Imdb::CLI.execute(@stdout_io, ["0117731"])
+      @stdout_io.rewind
+      @stdout = @stdout_io.read
+    end
+  
+    it "report data" do
+      @stdout.should =~ /Star Trek\: First Contact \(1996\)/
+      @stdout.should =~ /Jonathan Frakes/
+    end
+  end
+end

data/spec/imdb/movie_spec.rb

@@ -0,0 +1,98 @@
+require File.dirname(__FILE__) + '/../spec_helper.rb'
+
+# This test uses "Die hard (1988)" as a testing sample:
+#   
+#     http://www.imdb.com/title/tt0095016/
+#
+
+describe "Imdb::Movie" do
+  
+  before(:each) do
+    # Get Die Hard (1988)
+    @movie = Imdb::Movie.new("0095016")
+  end
+  
+  it "should find the cast members" do
+    cast = @movie.cast_members
+    
+    cast.should be_an(Array)
+    cast.should include("Bruce Willis")
+    cast.should include("Bonnie Bedelia")
+    cast.should include("Alan Rickman")
+  end
+  
+  it "should find the director" do
+    @movie.director.should be_an(Array)
+    @movie.director.size.should eql(1)
+    @movie.director.first.should =~ /John McTiernan/
+  end
+  
+  it "should find the genres" do
+    genres = @movie.genres
+    
+    genres.should be_an(Array)
+    genres.should include('Action')
+    genres.should include('Crime')
+    genres.should include('Drama')
+    genres.should include('Thriller')
+  end
+  
+  it "should find the length (in minutes)" do
+    @movie.length.should eql(131)
+  end
+  
+  it "should find the plot" do
+    @movie.plot.should eql("New York cop John McClane gives terrorists a dose of their own medicine as they hold hostages in an LA office building.")
+  end
+  
+  it "should find the poster" do
+    @movie.poster.should eql("http://ia.media-imdb.com/images/M/MV5BMTIxNTY3NjM0OV5BMl5BanBnXkFtZTcwNzg5MzY0MQ@@.jpg")
+  end
+  
+  it "should find the rating" do
+    @movie.rating.should eql(8.3)
+  end
+  
+  it "should find the title" do
+    @movie.title.should =~ /Die Hard/
+  end
+  
+  it "should find the tagline" do
+    @movie.tagline.should =~ /It will blow you through the back wall of the theater/
+  end
+  
+  it "should find the year" do
+    @movie.year.should eql(1988)
+  end
+  
+  it "should find the release date" do
+    @movie.release_date.should be_a(Date)
+    @movie.release_date.should eql(Date.new(1988, 7, 15))
+  end
+  
+  describe "special scenarios" do
+    
+    it "should find multiple directors" do
+      # The Matrix Revolutions (2003)
+      movie = Imdb::Movie.new("0242653")
+      
+      movie.director.should be_an(Array)
+      movie.director.size.should eql(2)
+      movie.director.should include("Larry Wachowski")
+      movie.director.should include("Andy Wachowski")
+    end
+  end
+
+  it "should provide a convenience method to search" do
+    movies = Imdb::Movie.search("Star Trek")
+    movies.should respond_to(:each)
+    movies.each { |movie| movie.should be_an_instance_of(Imdb::Movie) }
+  end
+  
+  it "should provide a convenience method to top 250" do
+    movies = Imdb::Movie.top_250
+    movies.should respond_to(:each)
+    movies.each { |movie| movie.should be_an_instance_of(Imdb::Movie) }
+  end
+  
+end

data/spec/imdb/search_spec.rb

@@ -0,0 +1,40 @@
+require File.dirname(__FILE__) + '/../spec_helper.rb'
+
+describe "Imdb::Search with multiple search results" do
+  
+  before(:each) do
+    @search = Imdb::Search.new("Star Trek")
+  end
+
+  it "should remember the query" do
+    @search.query.should == "Star Trek"
+  end
+  
+  it "should find > 10 results" do
+    @search.movies.size.should > 10
+  end
+  
+  it "should return Imdb::Movie objects only" do
+    @search.movies.each { |movie| movie.should be_an(Imdb::Movie) }
+  end
+  
+  it "should not return movies with no title" do
+    @search.movies.each { |movie| movie.title.should_not be_blank }
+  end
+  
+end
+
+describe "Imdb::Search with an exact match" do
+  
+  before(:each) do
+    @search = Imdb::Search.new("Matrix Revolutions")
+  end
+  
+  it "should find one result" do
+    @search.movies.size.should eql(1)
+  end
+  
+  it "should have the corrected title" do
+    @search.movies.first.title.should =~ /The Matrix Revolutions/i
+  end
+end

data/spec/imdb/top_250_spec.rb

@@ -0,0 +1,21 @@
+require File.dirname(__FILE__) + "/../spec_helper"
+
+describe Imdb::Top250 do
+  before(:each) do
+    @movies = Imdb::Top250.new.movies
+  end
+  
+  it "should be a list of movies" do
+    @movies.each { |movie| movie.should be_an_instance_of(Imdb::Movie) }
+  end
+  
+  it "should return the top 250 movies from IMDB.com" do
+    @movies.size.should == 250
+  end
+
+  it "should provide array like access to the movies" do
+    @first = @movies.first
+    @first.title.should == "The Shawshank Redemption"
+    @first.genres.should include("Drama")
+  end
+end

data/spec/spec_helper.rb

@@ -0,0 +1,47 @@
+# By default if you have the FakeWeb gem installed when the specs are
+# run they will hit recorded responses.  However, if you don't have
+# the FakeWeb gem installed or you set the environment variable
+# LIVE_TEST then the tests will hit the live site IMDB.com.
+###
+# Having both methods available for testing allows you to quickly
+# refactor and add features, while also being able to make sure that
+# no changes to the IMDB.com interface have affected the parser.
+###
+
+begin
+  require 'spec'
+rescue LoadError
+  require 'rubygems'
+  gem 'rspec'
+  require 'spec'
+end
+
+$:.unshift(File.dirname(__FILE__) + '/../lib')
+require 'imdb'
+
+def read_fixture(path)
+  File.read(File.expand_path(File.join(File.dirname(__FILE__), "fixtures", path)))
+end
+
+unless ENV['LIVE_TEST']
+  begin
+    require 'rubygems'
+    require 'fakeweb'
+    
+    FakeWeb.allow_net_connect = false
+    { "http://www.imdb.com:80/find?q=Matrix+Revolutions;s=tt" => "search_matrix_revolutions",
+      "http://www.imdb.com:80/find?q=Star+Trek;s=tt" => "search_star_trek",
+      "http://www.imdb.com:80/title/tt0117731/" => "tt0117731",
+      "http://www.imdb.com:80/title/tt0095016/" => "tt0095016",
+      "http://www.imdb.com:80/title/tt0242653/" => "tt0242653",
+      "http://www.imdb.com:80/title/tt0242653/?fr=c2M9MXxsbT01MDB8ZmI9dXx0dD0xfG14PTIwfHFzPU1hdHJpeCBSZXZvbHV0aW9uc3xodG1sPTF8c2l0ZT1kZnxxPU1hdHJpeCBSZXZvbHV0aW9uc3xwbj0w;fc=1;ft=20" => "tt0242653",
+      "http://www.imdb.com:80/chart/top" => "top_250",
+      "http://www.imdb.com/title/tt0111161/" => "tt0111161",
+    }.each do |url, response|
+      FakeWeb.register_uri(:get, url, :response => read_fixture(response))
+    end
+  rescue LoadError
+    puts "Could not load FakeWeb, these tests will hit IMDB.com"
+    puts "You can run `gem install fakeweb` to stub out the responses."
+  end
+end

metadata

@@ -0,0 +1,83 @@
+--- !ruby/object:Gem::Specification 
+name: cschiewek-imdb
+version: !ruby/object:Gem::Version 
+  version: 0.5.1
+platform: ruby
+authors: 
+- Curtis Schiewek
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2009-07-21 00:00:00 -07:00
+default_executable: imdb
+dependencies: 
+- !ruby/object:Gem::Dependency 
+  name: hpricot
+  type: :runtime
+  version_requirement: 
+  version_requirements: !ruby/object:Gem::Requirement 
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        version: 0.8.1
+    version: 
+- !ruby/object:Gem::Dependency 
+  name: httparty
+  type: :runtime
+  version_requirement: 
+  version_requirements: !ruby/object:Gem::Requirement 
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        version: 0.4.3
+    version: 
+description: 
+email: curtis.schiewek@gmail.com
+executables: 
+- imdb
+extensions: []
+
+extra_rdoc_files: 
+- README.rdoc
+files: 
+- README.rdoc
+- lib/imdb.rb
+- lib/imdb/cli.rb
+- lib/imdb/movie.rb
+- lib/imdb/movie_list.rb
+- lib/imdb/search.rb
+- lib/imdb/string_extensions.rb
+- lib/imdb/top_250.rb
+has_rdoc: true
+homepage: 
+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: 
+rubygems_version: 1.2.0
+signing_key: 
+specification_version: 2
+summary: Internet Movie DataBase
+test_files: 
+- spec/imdb/cli_spec.rb
+- spec/imdb/movie_spec.rb
+- spec/imdb/search_spec.rb
+- spec/imdb/top_250_spec.rb
+- spec/spec_helper.rb