jasonrudolph-imdb 0.0.6

data/README

@@ -0,0 +1,70 @@
+
+ImdbMovie
+
+ImdbMovie Indiana Jones and the Last Crusade
+- should query IMDB url
+- should get director
+- should get the poster
+- should get the rating
+- should get cast members
+- should get the writers
+- should get the release date
+- should get the genres
+- should get the plot
+- should get the length
+- should get the countries
+- should get the languages
+- should get the color
+- should get the company
+- should get some photos
+- should get the tagline
+- should get the aspect ratio
+
+ImdbMovie Indiana Jones and the Last Crusade title pre-caching & get_data
+- should have the original title before querying anything
+- should have the updated title after calling get_data
+
+ImdbMovie Han robado una estrella
+- should query IMDB url
+- should get director
+- should not get the poster
+- should get cast members
+- should get the writers
+- should get the release date
+- should get the genres
+- should not get the plot
+- should get the length
+- should get the countries
+- should get the languages
+- should not get the color
+- should get the company
+- should not get any photos
+
+ImdbSearch
+
+ImdbSearch Indiana Jones
+- should query IMDB url
+
+ImdbSearch Indiana Jones movies
+- should be a collection of ImdbMovie instances
+- should include 'Indiana Jones and the Last Crusade'
+- should have titles
+- should not have titles with HTML tags
+
+ImdbSearch searches with potential encoding issues
+
+ImdbSearch searches with potential encoding issues movies
+- should include 'Misión en Marbella'
+
+String
+
+String unescape_html
+- should convert & to &
+- should convert ó to ó
+
+String strip_tags
+- should strip HTML tags
+
+Finished in 3.044303 seconds
+
+42 examples, 0 failures

data/lib/imdb/imdb_movie.rb

@@ -0,0 +1,96 @@
+class ImdbMovie
+  
+  attr_accessor :id, :url, :title
+  
+  def initialize(id, title = nil)
+    @id = id
+    @url = "http://www.imdb.com/title/tt#{self.id}/"
+    @title = title
+  end
+  
+  def director
+    document.at("h5[text()='Director:'] ~ a").innerHTML.strip.unescape_html rescue nil
+  end
+  
+  def poster
+    document.at("a[@name='poster'] img")['src'] rescue nil
+  end
+  
+  def rating
+    document.at("b[text()='User Rating:'] ~ b").innerHTML.strip.unescape_html.split('/').first.to_f rescue nil
+  end
+  
+  def cast_members
+    document.search("table.cast td.nm a").map { |link| link.innerHTML.strip.unescape_html } rescue []
+  end
+  
+  def writers
+    document.search("h5[text()^='Writers'] ~ a").map { |link| link.innerHTML.strip.unescape_html }.reject { |w| w == 'more' }.uniq rescue []
+  end
+
+  def year
+    document.search('a[@href^="/Sections/Years/"]').innerHTML
+  end
+  
+  def release_date
+    date = document.search("//h5[text()^='Release Date']/..").innerHTML[/^\d{1,2} \w+ \d{4}/]
+    Date.parse(Chronic.parse(date).strftime('%Y/%m/%d'))
+  rescue
+    nil
+  end
+  
+  def genres
+    document.search("h5[text()='Genre:'] ~ a[@href*=/Sections/Genres/']").map { |link| link.innerHTML.strip.unescape_html } rescue []
+  end
+  
+  def plot
+    document.search("//h5[text()^='Plot']/..").innerHTML.split("\n")[2].gsub(/<.+>.+<\/.+>/, '').strip.unescape_html rescue nil
+  end
+  
+  def tagline
+    document.search("//h5[text()^='Tagline']/..").innerHTML.split("\n")[2].gsub(/<.+>.+<\/.+>/, '').strip.unescape_html rescue nil
+  end
+  
+  def aspect_ratio
+    document.search("//h5[text()^='Aspect Ratio']/..").innerHTML.split("\n")[2].gsub(/<.+>.+<\/.+>/, '').strip.unescape_html rescue nil
+  end
+  
+  def length
+    document.search("//h5[text()^='Runtime']/..").innerHTML[/\d+ min/] rescue nil
+  end
+
+  def countries
+    document.search("h5[text()='Country:'] ~ a[@href*=/Sections/Countries/']").map { |link| link.innerHTML.strip.unescape_html } rescue []
+  end
+
+  def languages
+    document.search("h5[text()='Language:'] ~ a[@href*=/Sections/Languages/']").map { |link| link.innerHTML.strip.unescape_html } rescue []
+  end
+  
+  def color
+    document.at("h5[text()='Color:'] ~ a[@href*=color-info']").innerHTML.strip.unescape_html rescue nil
+  end
+
+  def company
+    document.at("h5[text()='Company:'] ~ a[@href*=/company/']").innerHTML.strip.unescape_html rescue nil
+  end
+  
+  def photos
+    document.search(".media_strip_thumb img").map { |img| img['src'] } rescue []
+  end
+  
+  def get_data
+    update_title
+  end
+    
+  private
+  
+  def update_title
+    @title = document.at("h1").innerHTML.split('<span').first.strip.unescape_html rescue nil    
+  end
+  
+  def document
+    @document ||= Hpricot(open(self.url).read)
+  end
+  
+end

data/lib/imdb/imdb_search.rb

@@ -0,0 +1,44 @@
+class ImdbSearch
+
+  attr_accessor :query
+
+  def initialize(query)
+    self.query = query
+  end
+
+  def movies
+    @movies ||= parse_movies_from_document
+  end
+
+  private
+  
+  def document
+    @document ||= Hpricot(open("http://www.imdb.com/find?q=#{CGI::escape(query)};s=tt").read)
+  end
+
+  def parse_movies_from_document
+    exact_match? ? parse_exact_match_search_results : parse_multi_movie_search_results
+  end
+
+  def parse_exact_match_search_results
+    id = document.at("a[@name='poster']")['href'][/\d+$/]
+    title = document.at("h1").innerHTML.split('<span').first.strip.unescape_html rescue nil
+    [ImdbMovie.new(id, title)]
+  end
+
+  def parse_multi_movie_search_results
+    ids_and_titles = document.search('a[@href^="/title/tt"]').reject do |element|
+      element.innerHTML.strip_tags.empty?
+    end.map do |element|
+      [element['href'][/\d+/], element.innerHTML.strip_tags.unescape_html]
+    end.uniq
+    ids_and_titles.map do |id_and_title|
+      ImdbMovie.new(id_and_title[0], id_and_title[1])
+    end    
+  end
+  
+  def exact_match?
+    document.search("title[text()='IMDb Title Search']").empty?
+  end
+
+end

data/lib/imdb.rb

@@ -0,0 +1,10 @@
+require 'open-uri'
+require 'date'
+require 'cgi'
+require 'rubygems'
+require 'hpricot'
+require 'chronic'
+
+require File.dirname(__FILE__) + '/imdb/imdb_search'
+require File.dirname(__FILE__) + '/imdb/imdb_movie'
+require File.dirname(__FILE__) + '/string_extensions'

data/lib/string_extensions.rb

@@ -0,0 +1,16 @@
+require 'cgi'
+require 'iconv'
+
+module ImdbStringExtensions
+  
+  def unescape_html
+    Iconv.conv("UTF-8", 'ISO-8859-1', CGI::unescapeHTML(self))
+  end
+  
+  def strip_tags
+    gsub(/<\/?[^>]*>/, "")
+  end
+  
+end
+
+String.send :include, ImdbStringExtensions

metadata

@@ -0,0 +1,74 @@
+--- !ruby/object:Gem::Specification 
+name: jasonrudolph-imdb
+version: !ruby/object:Gem::Version 
+  version: 0.0.6
+platform: ruby
+authors: 
+- Sergio Gil
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2008-10-27 00:00:00 -07:00
+default_executable: 
+dependencies: 
+- !ruby/object:Gem::Dependency 
+  name: hpricot
+  version_requirement: 
+  version_requirements: !ruby/object:Gem::Requirement 
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        version: "0.6"
+    version: 
+- !ruby/object:Gem::Dependency 
+  name: chronic
+  version_requirement: 
+  version_requirements: !ruby/object:Gem::Requirement 
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        version: "0"
+    version: 
+description: 
+email: sgilperez@gmail.com
+executables: []
+
+extensions: []
+
+extra_rdoc_files: []
+
+files: 
+- lib/imdb/imdb_movie.rb
+- lib/imdb/imdb_search.rb
+- lib/imdb.rb
+- lib/string_extensions.rb
+- README
+has_rdoc: false
+homepage: 
+post_install_message: 
+rdoc_options: []
+
+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: []
+