myimdb 0.3.13 → 0.4.0

data/VERSION

@@ -1 +1 @@
-0.3.13
+0.4.0

data/bin/myimdb

@@ -48,13 +48,13 @@ def details(klass_name, name)
   search_scope  = "#{klass_name.downcase}.com"
   
   search_result = Myimdb::Search::Google.search_text(name, :restrict_to=> search_scope)[0]
-  site          = "Myimdb::Scraper::#{klass_name}".constantize.new(search_result["url"])
-  print "====================================================\n"
-  print "#{klass_name} details for: #{name}\n"
-  print "====================================================\n"
-  print "#{site.summary}\n"
+  site          = eval("Myimdb::Scraper::#{klass_name}").new(search_result[:url])
+  puts "===================================================="
+  puts "#{klass_name} details for: #{name}"
+  puts "===================================================="
+  puts "#{site.summary}\n"
 rescue Exception=> ex
-  p "Unable to fetch #{klass_name} details for: #{name} because: #{ex.message}"
+  puts "Unable to fetch #{klass_name} details for: #{name} because: #{ex.message}"
 end
 
 ['Imdb', 'RottenTomatoes', 'Metacritic'].each do |site|

data/bin/myimdb-catalogue

@@ -118,7 +118,7 @@ def repair_permissions_for(target_dir)
     `attrib -r "#{target_dir}"`
     `attrib +r "#{target_dir}"`
   else
-    p 'Skipping permission repair; Windows required for this command'
+    p 'Skipping permission repair; Only works on Windows.'
   end
 end
 
@@ -128,7 +128,7 @@ end
 
 def save_image(target_dir, name, image_index=0)
   image_data = Myimdb::Search::Google.search_images(name, :size=> 'medium')[image_index]
-  image_url  = image_data["url"] if image_data
+  image_url  = image_data[:url] if image_data
 
   if image_url
     image_file_path = File.join(target_dir, 'movie.jpg')
@@ -148,7 +148,7 @@ def generate_metadata(path, name)
   search_scope  = "imdb.com"
 
   search_result = Myimdb::Search::Google.search_text(name, :restrict_to=> search_scope)[0]
-  imdb          = Myimdb::Scraper::Imdb.new(search_result["url"])
+  imdb          = Myimdb::Scraper::Imdb.new(search_result[:url])
   new_name      = name.gsub(/\[\S+\]/, "").strip
   new_name      << " [#{imdb.year}] [#{imdb.rating},#{imdb.votes}] [#{imdb.directors.join(',')}]"
   puts "Renaming: #{name} to: #{new_name}"

data/lib/myimdb.rb

@@ -1,7 +1,14 @@
-require 'rubygems'
-require 'httparty'
-require 'nokogiri'
-require 'open-uri'
-
-require 'myimdb/search'
-require 'myimdb/scraper'
+require 'rubygems'
+require 'httparty'
+require 'nokogiri'
+require 'open-uri'
+
+require 'myimdb/search'
+require 'myimdb/scraper'
+
+class ImdbMovie
+  def self.search(movie_name)
+    search_result = Myimdb::Search::Google.search_text(movie_name, :restrict_to=> 'imdb.com')[0]
+    Myimdb::Scraper::Imdb.new(search_result[:url]) if search_result
+  end
+end

data/lib/myimdb/scraper/base.rb

@@ -5,10 +5,10 @@ module HandleExceptions
     base.send(:include, InstanceMethods)
     base.send(:extend, ClassMethods)
   end
-  
+
   module InstanceMethods
   end
-  
+
   module ClassMethods
     def handle_exceptions_for(*method_names)
       method_names.each do |method_name|
@@ -29,47 +29,26 @@ module Myimdb
   module Scraper
     class Base
       include HandleExceptions
-      def directors
-      end
-      
-      def directors_with_url
-      end
-    
-      def writers
-      end
-      
-      def writers_with_url
-      end
-    
-      def rating
-      end
-    
-      def votes
-      end
-    
-      def genres
-      end
-    
-      def tagline
-      end
-    
-      def plot
-      end
-    
-      def year
-      end
-      
-      def release_date
-      end
-      
-      def image
-      end
-      
+      include Myimdb::Scraper::StringExtensions
+
+      def directors; end
+      def directors_with_url; end
+      def writers; end
+      def writers_with_url; end
+      def rating; end
+      def votes; end
+      def genres; end
+      def tagline; end
+      def plot; end
+      def year; end
+      def release_date; end
+      def image; end
+
       def summary
         [:directors, :writers, :rating, :votes, :genres, :tagline, :plot, :year, :release_date].collect do |meth|
           data = send(meth)
           data = data.join(", ") if Array === data
-          sprintf("%-15s : %s", meth.to_s.titleize, data)
+          sprintf("%-15s : %s", meth.to_s.capitalize, data)
         end.join("\n")
       end
 

data/lib/myimdb/scraper/imdb.rb

@@ -4,51 +4,51 @@ module Myimdb
       def initialize(url)
         @url = url
       end
-    
+
       def directors
         document.css('.info h5:contains("Director") + .info-content a:not(.tn15more)').collect{ |a| a.text }
       end
-      
+
       def directors_with_url
         document.css('.info h5:contains("Director") + .info-content a:not(.tn15more)').collect{ |a| {:name=> a.text, :url=> "http://www.imdb.com#{a['href']}" } }
       end
-    
+
       def writers
         document.css('.info h5:contains("Writer") + .info-content a:not(.tn15more)').collect{ |a| a.text }
       end
-      
+
       def writers_with_url
         document.css('.info h5:contains("Writer") + .info-content a:not(.tn15more)').collect{ |a| {:name=> a.text, :url=> "http://www.imdb.com#{a['href']}" } }
       end
-    
+
       def rating
         document.css(".starbar-meta b").inner_text.strip.split('/').first.to_f
       end
-    
+
       def votes
         document.css(".starbar-meta a").inner_text.strip.split(' ').first.sub(',', '').to_i
       end
-    
+
       def genres
         document.css('.info h5:contains("Genre:") + .info-content a:not(.tn15more)').collect{ |a| a.text }
       end
-    
+
       def tagline
         document.css('.info h5:contains("Tagline:") + .info-content').children[0].text.strip rescue nil
       end
-    
+
       def plot
         document.css('.info h5:contains("Plot:") + .info-content').children[0].text.strip
       end
-    
+
       def year
         document.css("div#tn15title a:first")[0].text.to_i
       end
-      
+
       def release_date
         Date.parse(document.css('.info h5:contains("Release Date:") + .info-content').inner_text)
       end
-      
+
       def image
         image_url = document.css(".photo:first a").first['href']
         unless image_url.nil? or image_url =~ /addposter/
@@ -56,12 +56,12 @@ module Myimdb
           image_document.css('#principal img:first').first['src']
         end
       end
-      
+
       private
         def document
           @document ||= Nokogiri::HTML(open(@url))
         end
-        
+
         handle_exceptions_for :directors, :directors_with_url, :writers, :writers_with_url, :rating, :votes, :genres, :tagline, :plot, :year, :image
     end
   end

data/lib/myimdb/scraper/metacritic.rb

@@ -4,28 +4,30 @@ module Myimdb
       def initialize(url)
         @url = url
       end
-    
+
       def rating
         document.css("#metascore").inner_text.strip.to_f/10
       end
-    
+
       def votes
         document.at("a[@href='#critics']").inner_text.strip.to_i
       end
-    
+
       def genres
-        document.css("#productinfo p:first").text.gsub(/^\S+:/, '').split("|").map(&:strip_useless_chars)
+        document.css("#productinfo p:first").text.gsub(/^\S+:/, '').split("|").collect do |genre|
+          strip_useless_chars(genre)
+        end
       end
-    
+
       def plot
         document.css("#productsummary .summarytext").inner_text.strip
       end
-    
+
       private
         def document
           @document ||= Nokogiri::HTML(open(@url))
         end
-        
+
         handle_exceptions_for :rating, :votes, :genres, :plot
     end
   end

data/lib/myimdb/scraper/rotten_tomatoes.rb

@@ -8,24 +8,24 @@ module Myimdb
       def rating
         document.css("#tomatometer_data p:nth-child(4) span").inner_text.strip.to_i
       end
-    
+
       def votes
         document.css("#tomatometer_data p:nth-child(1) span").inner_text.strip.to_i
       end
-    
+
       def genres
-        document.css("#movie_stats .fl:first p:last .content a").inner_text.scraper_unescape_html.to_a
+        document.css("#movie_stats .fl:first p:last .content a").inner_text.strip.to_a
       end
-    
+
       def plot
         document.css("#movie_synopsis_all").inner_text.strip
       end
-    
+
       private
         def document
           @document ||= Nokogiri::HTML(open(@url))
         end
-        
+
         handle_exceptions_for :rating, :votes, :genres, :plot
     end
   end

data/lib/myimdb/scraper/string_extensions.rb

@@ -4,38 +4,13 @@ require 'iconv'
 module Myimdb
   module Scraper
     module StringExtensions
-      def scraper_unescape_html
-        Iconv.conv("UTF-8", 'ISO-8859-1', CGI::unescapeHTML(self))
+      def scraper_unescape_html(string)
+        Iconv.conv("UTF-8", 'ISO-8859-1', CGI::unescapeHTML(string))
       end
 
-      def scraper_strip_tags
-        gsub(/<\/?[^>]*>/, "")
-      end
-    
-      def strip_useless_chars
-        gsub(/[^a-zA-z0-9\|\-_\(\)@$\/\\]/, '')
-      end
-      
-      def titleize
-        humanize.gsub(/\b('?[a-z])/) { $1.capitalize }
-      end
-      
-      def humanize
-        gsub(/_/, " ").capitalize
-      end
-      
-      def constantize
-        names = self.split('::')
-        names.shift if names.empty? || names.first.empty?
-      
-        constant = Object
-        names.each do |name|
-          constant = constant.const_defined?(name) ? constant.const_get(name) : constant.const_missing(name)
-        end
-        constant
+      def strip_useless_chars(string)
+        string.gsub(/[^a-zA-z0-9\|\-_\(\)@$\/\\]/, '')
       end
     end
   end
-end
-
-String.send :include, Myimdb::Scraper::StringExtensions
+end

data/lib/myimdb/search.rb

@@ -1,2 +1,4 @@
 require 'httparty'
-require 'myimdb/search/google'
+require 'myimdb/search/base'
+require 'myimdb/search/google'
+require 'myimdb/search/bing'

data/lib/myimdb/search/base.rb

@@ -0,0 +1,14 @@
+module Myimdb
+  module Search
+    class Base
+      class << self
+        def spell_movie( text, options={} )
+          search_results = search_text(text, :restrict_to=> 'imdb.com')
+          search_results and search_results.collect do |search_result|
+            search_result[:title].gsub(/ \(.*$/, "")
+          end
+        end
+      end
+    end
+  end
+end

data/lib/myimdb/search/bing.rb

@@ -0,0 +1,42 @@
+module Myimdb
+  module Search
+    class Bing < Base
+      include HTTParty
+      format  :json
+      headers 'Content-Type' => 'application/json'
+      
+      AppKey = '36C1CEF363A00C6536C4420D356B5E507C4C2AF1'
+      base_uri  'api.search.live.net'
+      
+      class << self
+        def search_text( text, options={} )
+          text = text + " site:#{options[:restrict_to]}" if !options[:restrict_to].blank?
+          response = get( '/json.aspx', :query=> {:Appid=> AppKey, :query=> text, :sources=> 'web'} )
+          parse_search_result(response, 'Web')
+        end
+        
+        def search_images( text, options={} )
+          text = text + " site:#{options[:restrict_to]}" if !options[:restrict_to].blank?
+          response = get( '/json.aspx', :query=> {:Appid=> AppKey, :query=> text, :sources=> 'image'} )
+          parse_search_result(response, 'Image')
+        end
+        
+        def spell( text, options={} )
+          text = text + " site:#{options[:restrict_to]}" if !options[:restrict_to].blank?
+          response = get( '/json.aspx', :query=> {:Appid=> AppKey, :query=> text, :sources=> 'spell'} )
+          parse_search_result(response, 'Spell')
+        end
+        
+        private
+          def parse_search_result( response, type )
+            response['SearchResponse'][type]['Results'].collect do |response_element|
+              {
+                :url    => response_element['Url'],
+                :title  => response_element['Title']
+              }
+            end
+          end
+      end
+    end
+  end
+end

data/lib/myimdb/search/google.rb

@@ -1,29 +1,41 @@
 module Myimdb
   module Search
-    class Google
+    class Google < Base
       include HTTParty
+      format  :json
+      headers 'Content-Type' => 'application/json'
 
-      format    :json
-      headers   'Content-Type' => 'application/json' 
       base_uri  'ajax.googleapis.com'
+      
+      class << self
+        def search_text( text, options={} )
+          text = text + " site:#{options[:restrict_to]}" if !options[:restrict_to].blank?
+          response = get( '/ajax/services/search/web', :query=> {:v=> '1.0', :q=> text} )
+          parse_search_result( response )
+        end
 
-      def self.search_text( text, options={} )
-        text = text + " site:#{options[:restrict_to]}" if !options[:restrict_to].blank?
-        response = get( '/ajax/services/search/web', :query=> {:v=> '1.0', :q=> text} )
-        response['responseData'] and response['responseData']['results']
-      end
-
-      def self.search_images( text, options={} )
-        sizes = {
-          'large'   => 'l',
-          'medium'  => 'm',
-          'small'   => 'i'
-        }
-        search_options = { :v=> '1.0', :q=> text }
-        search_options.merge!(:imgsz=> sizes[options[:size].to_s]) if !options[:size].blank?
-        text = text + " site:#{options[:restrict_to]}" if !options[:restrict_to].blank?
-        response = get( '/ajax/services/search/images', :query=> search_options )
-        response['responseData'] and response['responseData']['results']
+        def search_images( text, options={} )
+          sizes = {
+            'large'   => 'l',
+            'medium'  => 'm',
+            'small'   => 'i'
+          }
+          search_options = { :v=> '1.0', :q=> text }
+          search_options.merge!(:imgsz=> sizes[options[:size].to_s]) if !options[:size].blank?
+          text = text + " site:#{options[:restrict_to]}" if !options[:restrict_to].blank?
+          response = get( '/ajax/services/search/images', :query=> search_options )
+          parse_search_result( response )
+        end
+        
+        private
+          def parse_search_result( response )
+            response['responseData'] and response['responseData']['results'].collect do |response_element|
+              {
+                :url    => response_element['url'],
+                :title  => response_element['titleNoFormatting']
+              }
+            end
+          end
       end
     end
   end

data/myimdb.gemspec

@@ -5,11 +5,11 @@
 
 Gem::Specification.new do |s|
   s.name = %q{myimdb}
-  s.version = "0.3.13"
+  s.version = "0.4.0"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.authors = ["Gaurav"]
-  s.date = %q{2010-02-01}
+  s.date = %q{2010-02-22}
   s.email = %q{gaurav@vinsol.com}
   s.executables = ["myimdb", "myimdb-catalogue"]
   s.extra_rdoc_files = [
@@ -31,6 +31,8 @@ Gem::Specification.new do |s|
      "lib/myimdb/scraper/rotten_tomatoes.rb",
      "lib/myimdb/scraper/string_extensions.rb",
      "lib/myimdb/search.rb",
+     "lib/myimdb/search/base.rb",
+     "lib/myimdb/search/bing.rb",
      "lib/myimdb/search/google.rb",
      "myimdb.gemspec",
      "test/helper.rb",

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification 
 name: myimdb
 version: !ruby/object:Gem::Version 
-  version: 0.3.13
+  version: 0.4.0
 platform: ruby
 authors: 
 - Gaurav
@@ -9,7 +9,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2010-02-01 00:00:00 +05:30
+date: 2010-02-22 00:00:00 +05:30
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency 
@@ -57,6 +57,8 @@ files:
 - lib/myimdb/scraper/rotten_tomatoes.rb
 - lib/myimdb/scraper/string_extensions.rb
 - lib/myimdb/search.rb
+- lib/myimdb/search/base.rb
+- lib/myimdb/search/bing.rb
 - lib/myimdb/search/google.rb
 - myimdb.gemspec
 - test/helper.rb