findart 0.0.1

data/features/step_definitions/findalbumarturls_steps.rb

@@ -0,0 +1,9 @@
+gem "fakeweb"
+require "fakeweb"
+
+Before do 
+  FakeWeb.allow_net_connect = false
+end
+
+
+Given /^that i want to find artwork for the album "([^\"]*)"$/ do |query| end

data/features/support/common.rb

@@ -0,0 +1,29 @@
+module CommonHelpers
+  def in_tmp_folder(&block)
+    FileUtils.chdir(@tmp_root, &block)
+  end
+
+  def in_project_folder(&block)
+    project_folder = @active_project_folder || @tmp_root
+    FileUtils.chdir(project_folder, &block)
+  end
+
+  def in_home_folder(&block)
+    FileUtils.chdir(@home_path, &block)
+  end
+
+  def force_local_lib_override(project_name = @project_name)
+    rakefile = File.read(File.join(project_name, 'Rakefile'))
+    File.open(File.join(project_name, 'Rakefile'), "w+") do |f|
+      f << "$:.unshift('#{@lib_path}')\n"
+      f << rakefile
+    end
+  end
+
+  def setup_active_project_folder project_name
+    @active_project_folder = File.join(@tmp_root, project_name)
+    @project_name = project_name
+  end
+end
+
+World(CommonHelpers)

data/features/support/env.rb

@@ -0,0 +1,14 @@
+require File.dirname(__FILE__) + "/../../lib/FindArt"
+
+gem 'cucumber'
+require 'cucumber'
+gem 'rspec'
+require 'spec'
+
+Before do
+  @tmp_root = File.dirname(__FILE__) + "/../../tmp"
+  @home_path = File.expand_path(File.join(@tmp_root, "home"))
+  FileUtils.rm_rf   @tmp_root
+  FileUtils.mkdir_p @home_path
+  ENV['HOME'] = @home_path
+end

data/features/support/matchers.rb

@@ -0,0 +1,11 @@
+module Matchers
+  def contain(expected)
+    simple_matcher("contain #{expected.inspect}") do |given, matcher|
+      matcher.failure_message = "expected #{given.inspect} to contain #{expected.inspect}"
+      matcher.negative_failure_message = "expected #{given.inspect} not to contain #{expected.inspect}"
+      given.index expected
+    end
+  end
+end
+
+World(Matchers)

data/lib/FindArt.rb

@@ -0,0 +1,20 @@
+$:.unshift(File.dirname(__FILE__)) unless
+  $:.include?(File.dirname(__FILE__)) || $:.include?(File.expand_path(File.dirname(__FILE__)))
+ 
+require 'rubygems'
+require 'mechanize'
+require 'hpricot'
+
+#meta programming patch
+class Object # http://whytheluckystiff.net/articles/seeingMetaclassesClearly.html
+  def meta_def name, &blk
+    (class << self; self; end).instance_eval { define_method name, &blk }
+  end
+end
+  
+module FindArt
+  VERSION = '0.0.1'
+end   
+
+require "#{File.dirname(__FILE__)}/FindArt/scraper.rb"
+Dir["#{File.dirname(__FILE__)}/FindArt/scrapers/*.rb"].each {|file| require file }

data/lib/FindArt/scraper.rb

@@ -0,0 +1,76 @@
+
+# Factory that contains site specific scapers.
+# Scrapers are classes that collect urls of album art for a given artist and title.
+# Scraper classes can self register them self by calling register_scraper in the class body.
+# == Example       
+#  
+#  @scraper = Scraper.new
+#
+#  class TestScraper < Scraper
+#     register_scraper :test_scraper       
+#  end
+# 
+#  @scraper.scrapers 
+#  {:test_scraper=>TestScraper}
+module FindArt  
+  class Scraper
+    @@scrapers = {} 
+   
+  
+    # class method for registering scrapers
+    def self.register_scraper(name)
+      @@scrapers[name] = self
+    end
+  
+    # hash of all registerd scrapers
+    def scrapers
+       @@scrapers
+    end  
+  
+    def self.registerd_sites
+      @@scrapers.map {|scraper_name,klass| URI(klass.url).host}
+    end
+                           
+    # clears all registerd scapers
+    def self.unregister_scrapers!
+      @@scrapers = {}
+    end
+  
+    # all registerd scrapers are used to find album art 
+    # returns an array of urls
+    def find_art(artist,title,opts=nil)
+      threads = []       
+      @@scrapers.each do |scraper_name,klass|  
+        scraper = klass.new    
+        threads << Thread.new { Thread.current["results"] = scraper.scrape(artist,title,opts)}                  
+      end  
+      results = []                
+      begin
+      threads.each {|t| t.join;  results << t["results"] unless t['results'].nil? }           
+      rescue
+      end
+      results
+    end
+
+    private
+  
+    # helper method for setting the url where the scraper starts its search for album art
+    #  
+    #  == Example 
+    #             
+    #  class JunoDownload < Scraper          
+    #     start_url "http://www.junodownload.com/search/"  
+    #     register_scraper :junodownload  
+    #  end
+    #  
+    def self.start_url(url) 
+      class_variable_set "@@url", url     
+      meta_def :url do
+       class_variable_get "@@url"
+      end    
+    end 
+  end         
+end
+
+
+                 

data/lib/FindArt/scrapers/albumartexchange.rb

@@ -0,0 +1,22 @@
+module FindArt
+  class AlbumArtExchange < Scraper          
+    start_url "http://www.albumartexchange.com/covers.php?sort=7&q="  
+    register_scraper :albumartexchange
+  
+    def scrape(artist,title,opts={})
+      url = nil    
+      search_url =  "#{@@url}#{CGI.escape("#{artist} #{title}")}"
+      browser = WWW::Mechanize.new    
+      browser.get(search_url) do |page|
+        doc = Hpricot(page.body)    
+        element =  doc.at("* table tr td a img[@width='150']")
+        src = element["src"] if !element.nil? && !element["src"].nil?
+        if src
+          path = src.split("src=").last
+          url = "http://www.albumartexchange.com#{URI.decode(path)}"      
+        end
+      end
+     url
+    end    
+  end                           
+end

data/lib/FindArt/scrapers/amazon.rb.disabled

@@ -0,0 +1,47 @@
+module FindArt
+  class Amazon < Scraper          
+    start_url "http://webservices.amazon.com/"  
+    register_scraper :amazon
+    @@urls = [                               
+     "http://webservices.amazon.com/",    
+     "http://webservices.amazon.co.uk/",
+     "http://webservices.amazon.co.jp/",
+     "http://webservices.amazon.ca/",
+     "http://webservices.amazon.fr/",
+     "http://webservices.amazon.de/",
+    ]
+  
+  
+    # Uses the artist webservice to search for album covers.
+    # Tries all international amazon sites
+    def scrape(artist,title,opts={})
+      search_url = "onca/xml?Service=AWSECommerceService&AWSAccessKeyId=0NK019CD48HNEDK3PBG2&Operation=ItemSearch&SearchIndex=Music&ResponseGroup=Small,Images&Keywords=#{CGI.escape("#{artist} #{title}")}"    
+      @@urls.each do |url|
+        art = find_best_art("#{url}#{search_url}") 
+        return art unless art.nil?
+      end
+      nil
+    end  
+  
+    private
+  
+    # Finds the best quality artwork availible at amazon
+    def find_best_art(search_url)
+     	browser = WWW::Mechanize.new
+      search = browser.get(search_url)
+      doc = Hpricot(search.body)
+    
+      large,medium,small = [],[],[]        
+      (doc/:item).each do |item|      
+         large    << item.at("largeimage").at("url").innerHTML  if item.at("largeimage")
+         medium   << item.at("mediumimage").at("url").innerHTML if item.at("mediumimage")    
+         small    << item.at("smallimage").at("url").innerHTML  if item.at("smallimage")       
+      end
+    
+      url = small.first  unless small.empty?   
+      url = medium.first unless medium.empty?  
+      url = large.first  unless large.empty?
+    end
+    
+  end 
+end

data/lib/FindArt/scrapers/discogs.rb

@@ -0,0 +1,44 @@
+# module FindArt
+# #                                          
+# # class Discogs < Scraper          
+# #   start_url "http://www.discogs.com/search?type=all&q="  
+# #   register_scraper :discogs
+# #   
+# #   def scrape(artist,title,opts={})
+# #     url = nil    
+# #     search_url =  "#{@@url}#{CGI.escape("#{artist} #{title}")}"
+# #     browser = WWW::Mechanize.new    
+# #     browser.get(search_url) do |page|
+# #       doc = Hpricot(page.body)    
+# #       
+# #       # check if there are multiple results and get the top result
+# #       element =  doc.at("* .search_result a")        
+# #       if !element.nil?
+# #          # extract and fetch item page
+# #          item_page = browser.get(element.attributes["href"])
+# #          doc = Hpricot(item_page.body)        
+# # 
+# # 
+# #          
+# #       end           
+# # 
+# #       #extract art from product page
+# #     end
+# #    url
+# #   end 
+# #   
+# #   # Extracts album art url from wallmart product page
+# #   def extract_art(doc)
+# #     puts doc
+# #      # url = nil
+# #      #     element =  doc.at("* td[@align='center'] a[href~='/viewimages']")
+# #      #      href = element["href"] if !element.nil? && !element["href"].nil?
+# #      #      if href
+# #      #        match, url = *href.match(/javascript:photo_opener\('(http:\/\/.*.jpg)&/)
+# #      #      end
+# #      #      url        
+# #   end
+# #     
+# # end
+#                
+# end

data/lib/FindArt/scrapers/junodownload.rb

@@ -0,0 +1,31 @@
+module FindArt
+  class JunoDownload < Scraper          
+    start_url "http://www.junodownload.com/search/"  
+    register_scraper :junodownload
+  
+    def scrape(artist,title,opts={})
+      url = nil 
+    
+      browser = WWW::Mechanize.new
+      browser.get(@@url) do |page|    
+        # go to search form
+        search = page.form_with(:action => 'http://www.junodownload.com/search/') do |f|
+           f.q  = "#{artist} #{title}"        
+         end.click_button       
+         doc = Hpricot(search.body) 
+         element = doc.at('.productcover img[@src^="http://cdn.images.juno.co.uk/75/"]')
+         src = nil  
+         if !element.nil?           
+           src = element.attributes['src'] 
+           # instead of cliking on the image to find the uri of the larger image we will replace some parts of the url
+           # lets hope junodownload keeps this convention 
+           src.gsub!("/75/","/full/")
+           src.gsub!("-TN","-BIG")   
+           url = src  
+         end
+      end
+      url   
+    end
+    
+  end           
+end

data/lib/FindArt/scrapers/walmart.rb

@@ -0,0 +1,38 @@
+module FindArt
+  class WalMart < Scraper          
+    start_url "http://www.walmart.com/search/search-ng.do?earch_sort=2&search_query="  
+    register_scraper :walmart
+  
+    def scrape(artist,title,opts={})
+      url = nil    
+      search_url =  "#{@@url}#{CGI.escape("#{artist} #{title}")}"
+      browser = WWW::Mechanize.new    
+      browser.get(search_url) do |page|
+        doc = Hpricot(page.body)    
+      
+        # check if there are multiple results and get the top result
+        element =  doc.at("* .firstRow a")        
+        if !element.nil?
+           # extract and fetch item page
+           item_page = browser.get(element.attributes["href"])
+           doc = Hpricot(item_page.body)
+        end                           
+      
+        #extract art from product page
+        url = extract_art(doc)
+      end
+     url
+    end 
+  
+    # Extracts album art url from wallmart product page
+    def extract_art(doc)
+       url = nil
+       element =  doc.at("* div[@class='LargeItemPhoto150'] a[@href^=javascript]")
+        href = element["href"] if !element.nil? && !element["href"].nil?
+        if href
+          match, url = *href.match(/javascript:photo_opener\('(http:\/\/.*.jpg)&/)
+        end
+        url    
+    end   
+  end  
+end

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/FindArt.rb'}"
+puts "Loading FindArt 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/albumartexchange_spec.rb

@@ -0,0 +1,26 @@
+require File.dirname(__FILE__) + '/spec_helper.rb'
+
+describe AlbumArtExchange do  
+  
+  it "Should have a start url form where the scaper starts" do
+    AlbumArtExchange.class_variables.should include("@@url")  
+    AlbumArtExchange.url.should ==  'http://www.albumartexchange.com/covers.php?sort=7&q='           
+  end
+  
+  it "Should find the album art url for DJ TIESTO - In Search Of Sunrise 6" do
+     @album =  AlbumArtExchange.new()
+     @album.scrape("DJ TIESTO","In Search of Sunrise 6").should == "http://www.albumartexchange.com/gallery/images/public/ti/tiesto-insear_02.jpg"
+  end                                                               
+  
+  it "Should return nil when no album art is found" do
+    @album =  AlbumArtExchange.new()
+    @album.scrape("Irene Moors & De Smurfen","Ga Je Mee Naar Smurfenland").should be(nil)
+  end
+  
+  it "Should find the album art for the following albums" do
+    @album =  AlbumArtExchange.new()    
+    @album.scrape("Hi_Tack","Let's Dance").should == "http://www.albumartexchange.com/gallery/images/public/hi/hi_tac-letsda.jpg"
+    @album.scrape("24 Grana","underpop").should == "http://www.albumartexchange.com/gallery/images/public/24/24gran-underp_02.jpg"
+    @album.scrape("Green Day","Dookie").should == "http://www.albumartexchange.com/gallery/images/public/gr/greend-dookie_05.jpg"
+  end   
+end

data/spec/amazon_spec.rb

@@ -0,0 +1,34 @@
+# require File.dirname(__FILE__) + '/spec_helper.rb'
+# 
+# describe Amazon do 
+# 
+#   it "Should have a start url form where the scaper starts" do
+#     Amazon.class_variables.should include("@@url")  
+#     Amazon.url.should ==  'http://webservices.amazon.com/'           
+#   end
+#   
+#   it "Should find the album art url for DJ TIESTO - In Search Of Sunrise 6" do
+#      @amazon =  Amazon.new()
+#      @amazon.scrape("DJ TIESTO","In Search of Sunrise 6").should == "http://ecx.images-amazon.com/images/I/515ZxHVU5RL.jpg"
+#   end   
+#   
+#   it "Should find the album art url for Caféine de Christophe Willem  " do
+#      @amazon =  Amazon.new()
+#      @amazon.scrape("Christophe Willem","Caféine").should == "http://ecx.images-amazon.com/images/I/61sOk67nVkL.jpg"
+#   end      
+#   
+#   it "Should find the album art url for Miss Météores de Olivia Ruiz" do
+#      @amazon =  Amazon.new()
+#      @amazon.scrape("Olivia Ruiz","Miss Météores").should == "http://ecx.images-amazon.com/images/I/51S7recnyQL.jpg"
+#   end 
+#   
+#   it "Should find the album art url for  初音ミク ベスト impacts" do
+#      @amazon =  Amazon.new()
+#      @amazon.scrape(" 初音ミク ベスト","impacts").should == "http://ecx.images-amazon.com/images/I/51P-6djocGL.jpg"
+#   end  
+#   
+#   it "Should return nil if no album art is found " do
+#     @amazon =  Amazon.new()
+#     @amazon.scrape("internets","i did it for teh lulz").should == nil
+#   end  
+# end