rbook 0.1

data/lib/rbook/www/aau_scraper.rb

@@ -0,0 +1,76 @@
+
+module RBook
+  module WWW
+  
+  class AAUScraper < Base
+
+    SCRAPER_ID = :aau
+    SCRAPER_NAME = "Allen and Unwin".freeze
+    SCRAPER_SITE = "http://www.allenandunwin.com/".freeze
+    
+    #add_publisher( self, "9781741100000", "9781741199999" )
+    #add_publisher( self, "9781865000000", "9781865099999" )
+    add_scraper( self )
+
+    def initialize
+      @url_protocol = "http://"
+      @url_host = "www.allenandunwin.com"
+      @url_path = "/bookseller/product.aspx?ISBN="
+    end
+
+    def get_info(isbn)
+     
+      raise ArgumentError, 'Supplied isbn is not valid' unless ISBN::valid_isbn?(isbn)
+     
+      isbn = ISBN::convert_to_isbn13(isbn) unless ISBN::valid_isbn13?(isbn)
+      
+      rba = Scraper.define do
+        process "span#lblISBN", :isbn => :text
+        process "h1>span#lblBookTitle", :title => :text
+        process "span#lblAusRRP", :rrp => :text
+        process "span#lblPublisher", :publisher => :text
+        process "span#lblImprint", :imprint => :text
+        process "span#lblBinding", :form => :text
+        process "span#lblExtent", :pages => :text
+        process "span#lblPubDate", :pubdate => :text
+        process "span#lblDescription", :description => :text
+        process "span#lblAuthor_bio", :authorbio => :text
+        process "a#hypHiRes", :cover_large => "@href"
+        process "a#imgProduct", :cover_thumb => "@href"
+        result :isbn, :title, :rrp, :publisher, :imprint, :form, :pages, :pubdate, :description, :authorbio, :cover_thumb, :cover_large
+      end
+      
+      content = Net::HTTP.get URI.parse(get_link(isbn))
+      result = rba.scrape(content)
+      
+      if result.title.nil? || result.title == ""
+        return nil
+      else 
+      
+        info = {}
+        info[:isbn] = result.isbn.gsub("ISBN : ", "")
+        info[:title] = result.title unless result.title.nil?
+        info[:rrp] = result.rrp.gsub("Australian Price : ", "").gsub(/\sInc. GST\n.+/,"") unless result.rrp.nil?
+        info[:publisher] = result.publisher.gsub("Publisher : ", "") unless result.imprint.nil?
+        info[:imprint] = result.imprint.gsub("Imprint : ", "") unless result.imprint.nil?
+        info[:format] = result.form.gsub("Format : ", "") unless result.form.nil?
+        info[:pages] = result.pages.gsub("Number of pages : ", "") unless result.pages.nil?
+        info[:pubdate] = result.pubdate.gsub("Publication Date : ", "") unless result.pubdate.nil?
+        info[:description] = result.description unless result.description.nil?
+        info[:authorbio] = result.authorbio.gsub("About the Author :\n", "") unless result.authorbio.nil?
+        info[:cover_large] = @url_protocol + @url_host + result.cover_large.gsub(/^../, "") unless result.cover_large.nil?
+        info[:cover_thumb] = @url_protocol + @url_host + result.cover_thumb unless result.cover_thumb.nil?
+        info[:link] = get_link(isbn)
+        info[:from_name] = SCRAPER_NAME
+        info[:from_url] = SCRAPER_SITE
+        return info
+      end 
+    end
+   
+    def get_link(isbn)
+      return nil unless ISBN::valid_isbn?(isbn)
+      return @url_protocol + @url_host + @url_path + ISBN::convert_to_isbn10(isbn)
+    end
+  end
+  end
+end

data/lib/rbook/www/amazon_uk_scraper.rb

@@ -0,0 +1,44 @@
+
+module RBook
+  module WWW
+  
+  class AmazonUKScraper < Base
+
+    SCRAPER_ID = :amazon_uk
+    SCRAPER_NAME = "Amazon UK".freeze
+    SCRAPER_SITE = "http://www.amazon.co.uk/".freeze
+    
+    #add_retailer( self )
+    add_scraper( self )
+    
+    def get_cover(isbn)
+
+      isbn = ISBN::convert_to_isbn13(isbn)
+      isbn10 = ISBN::convert_to_isbn10(isbn)
+      
+      return nil if isbn.nil? || isbn10.nil?
+
+      url_prefix = "http://images.amazon.com/images/P/"
+      url_suffix = ".02.LZZZZZZZ.jpg"
+      link = url_prefix + isbn10 + url_suffix
+      
+      begin
+        response = Net::HTTP.get_response URI.parse(link)
+          if response.code != "200"
+            return nil
+          elsif response.body.size <= 807
+            return nil
+          else
+            result = {}
+            result[:data] = response.body
+            result[:content_type] = "image/jpeg"
+            return result
+          end
+      rescue
+        return nil
+      end
+    end
+    
+  end
+  end
+end

data/lib/rbook/www/base.rb

@@ -0,0 +1,87 @@
+require 'net/http'
+require 'uri'
+
+module RBook
+  module WWW
+
+  class Base
+   
+    @@scrapers = []
+   
+    # registers a new scraper with the library.
+    # classname - the class to add
+    def self.add_scraper(classname)
+      @@scrapers << classname
+    end
+ 
+    # find a scraper matching the requested id
+    # id - a scraper id as a symbol
+    def self.find_scraper(id)
+      @@scrapers.each do |scraper|
+        return scraper if scraper::SCRAPER_ID == id
+      end
+      return nil
+    end
+
+    # find any scrapers matching the requested ids
+    # ids - an array of scraper id's as symbols
+    def self.find_scrapers(ids)
+      ret = []
+      @@scrapers.each do |scraper|
+        ret << scraper if ids.contains?(scraper::SCRAPER_ID)
+      end
+      return ret
+    end
+    
+    # This method can be overwritten in each scraper. It should return a hash containing the binary data
+    # and mimetype of the largest cover image it can find for the requested isbn
+    def get_cover(isbn)
+
+      info = get_info(isbn)
+      return nil if info.nil?
+      return nil unless info.kind_of?(Hash)
+
+      link = info[:cover_large] || info[:cover_medium] || info[:cover_thumb]
+
+      return nil if link.nil?
+
+      begin
+        response = Net::HTTP.get_response URI.parse(link)
+          if response.code != "200"
+            raise response.code.to_s
+            return nil
+          else
+            result = {}
+            result[:data] = response.body
+            result[:content_type] = "image/jpeg"
+            return result
+          end
+      rescue
+        return nil
+      end
+    end
+    
+    # This method can be overwritten in each scraper. It should return a hash of any information on
+    # the requested isbn it can find
+    def get_info(isbn)
+      nil
+    end
+
+    # This method can be overwritten in each scraper. It should return a link to the requested isbn
+    # on the targets website
+    def get_link(isbn)
+      nil
+    end
+    
+    # return the symbol used to uniquely identify each scraper
+    def scraper_id
+      return SCRAPER_ID
+    end 
+
+    def self.scrapers
+      @@scrapers
+    end
+  end
+
+end
+end

data/lib/rbook/www/harper_au_scraper.rb

@@ -0,0 +1,56 @@
+
+module RBook
+  module WWW
+  
+  class HarperCollinsAUScraper < Base
+
+    SCRAPER_ID = :harper_au
+    SCRAPER_NAME = "Harper Collins Australia".freeze
+    SCRAPER_SITE = "http://www.harpercollins.com.au/".freeze
+    
+    #add_publisher( self, "9780006400000", "9780006499999" )
+    #add_publisher( self, "9780007100000", "9780007199999" )
+    add_scraper( self )
+    
+    def get_info(isbn)
+     
+      raise ArgumentError, 'Supplied isbn is not valid' unless ISBN::valid_isbn?(isbn)
+     
+      isbn = ISBN::convert_to_isbn13(isbn) unless ISBN::valid_isbn13?(isbn)
+      
+      @protocol = "http://"
+      @host = "www.harpercollins.com.au"
+      @path = "/global_scripts/product_catalog/book_xml.asp?isbn="
+      @link = @protocol + @host + @path + ISBN::convert_to_isbn10(isbn)
+      
+      rba = Scraper.define do
+        process "div.header", :title => :text
+        process "div.subtitle", :subtitle => :text
+        process "div.byline", :author => :text
+        process "img.bookJacket", :cover => "@src"
+        result :title, :subtitle, :author, :cover
+      end
+      
+      content = Net::HTTP.get URI.parse(@link)
+      result = rba.scrape(content)
+      
+      if result.title.nil?
+        return nil
+      else 
+      
+        info = {}
+        info[:isbn] = isbn
+        info[:title] = result.title
+        info[:subtitle] = result.subtitle
+        info[:author] = result.author.gsub("by ","")
+        info[:cover] = result.cover
+        info[:link] = @link
+        info[:from_name] = SCRAPER_NAME
+        info[:from_url] = SCRAPER_SITE
+        return info
+      end 
+    end
+    
+  end
+  end
+end

data/lib/rbook/www/harper_us_scraper.rb

@@ -0,0 +1,55 @@
+
+module RBook
+  module WWW
+  
+  class HarperCollinsUSScraper < Base
+
+    SCRAPER_ID = :harper_us
+    SCRAPER_NAME = "Harper Collins United States".freeze
+    SCRAPER_SITE = "http://www.harpercollins.com/".freeze
+    
+    #add_publisher( self, "9780060000000", "9780060999999" )
+    add_scraper( self )
+    
+    def get_info(isbn)
+      raise ArgumentError, 'Supplied isbn is not valid' unless ISBN::valid_isbn?(isbn)
+     
+      isbn = ISBN::convert_to_isbn13(isbn) unless ISBN::valid_isbn13?(isbn)
+      
+      @protocol = "http://"
+      @host = "www.harpercollins.com"
+      @path = "/book/index.aspx?isbn="
+      @link = @protocol + @host + @path + isbn
+      
+      rba = Scraper.define do
+        process "h1.bookTitle", :title => :text
+        process "h2.bookSubTitle", :subtitle => :text
+        process "h3.byLine", :author => :text
+        process "img.bookJacket", :cover => "@src"
+        result :title, :subtitle, :author, :cover
+      end
+      
+      content = Net::HTTP.get URI.parse(@link)
+      result = rba.scrape(content)
+
+      if result.title.nil?
+        return nil
+      else 
+      
+        info = {}
+        info[:isbn] = isbn
+        info[:title] = result.title
+        info[:subtitle] = result.subtitle
+        info[:author] = result.author.gsub("by ", "")
+        info[:cover_thumb] = result.cover
+        info[:cover_medium] = result.cover.gsub("medium", "large")
+        info[:link] = @link
+        info[:from_name] = SCRAPER_NAME
+        info[:from_url] = SCRAPER_SITE
+        return info
+      end 
+    end
+    
+  end
+  end
+end

data/lib/rbook/www/hha_scraper.rb

@@ -0,0 +1,50 @@
+
+module RBook
+  module WWW
+  
+  class HHAScraper < Base
+
+    SCRAPER_ID = :hha
+    SCRAPER_NAME = "Hodder Headline Australia".freeze
+    SCRAPER_SITE = "http://www.hha.com.au/".freeze
+    
+    #add_publisher( self, "9780340800000", "9780340899999" )
+    #add_publisher( self, "9780755300000", "9780755399999" )
+    #add_publisher( self, "9780733600000", "9780733699999" )
+    add_scraper( self )
+    
+    def get_info(isbn)
+      @protocol = "http://"
+      @host = "www.hha.com.au"
+      @path = "/books/"
+      @suffix = ".html"
+      @link = @protocol + @host + @path + ISBN::convert_to_isbn10(isbn) + @suffix
+      
+      rba = Scraper.define do
+        process "h1.fiction", :title => :text
+        process "p.author", :author => :text
+        process "p.thumb>img", :cover_thumb => "@src"
+        result :title, :author, :cover_thumb
+      end
+      
+      content = Net::HTTP.get URI.parse(@link)
+      result = rba.scrape(content)
+      
+      if result.cover_thumb.nil?
+        return nil
+      else 
+      
+        info = {}
+        info[:isbn] = isbn
+        info[:author] = result.author
+        info[:cover_thumb] = @protocol + @host + result.cover_thumb
+        info[:link] = @link
+        info[:from_name] = SCRAPER_NAME
+        info[:from_url] = SCRAPER_SITE
+        return info
+      end
+    end
+    
+  end
+  end
+end

data/lib/rbook/www/macmillan_scraper.rb

@@ -0,0 +1,62 @@
+
+module RBook
+  
+  module WWW
+  
+  class MacmillanScraper < Base
+
+    SCRAPER_ID = :macmillan
+    SCRAPER_NAME = "Pan Macmillan".freeze
+    SCRAPER_SITE = "http://www.panmacmillan.com.au/".freeze
+    
+    #add_publisher( self, "9780312900000", "9780312999999" )
+    #add_publisher( self, "9780330400000", "9780330499999" )
+    #add_publisher( self, "9781403000000", "9781405099999" )
+    add_scraper( self )
+    
+    def initialize
+      @url_protocol = "http://"
+      @url_host = "www.panmacmillan.com.au"
+      @url_path = "/display_title.asp?ISBN="
+      @url_suffix = "&Author=Barker,%20Robin"
+    end
+
+    def get_info(isbn)
+     
+      isbn = ISBN::convert_to_isbn13(isbn)
+      return nil if isbn.nil?
+
+      mac = Scraper.define do
+        process "div.titlecontent>div.isbn>span", :isbn => :text
+        process "td[width=70%]>h1", :title => :text
+        process "a[title=Click on image to view a larger version]>img", :cover_medium => "@src"
+        process "a[title=Click on image to view a larger version]", :cover_large => "@href"
+        result :isbn, :title, :cover_medium, :cover_large
+      end
+      
+      content = Net::HTTP.get URI.parse(get_link(isbn))
+      result = mac.scrape(content)
+      
+      if result.title.nil?
+        return nil
+      else 
+      
+        info = {}
+        info[:isbn] = isbn
+        info[:title] = result.title
+        info[:cover_medium] = @url_protocol + @url_host + result.cover_medium.gsub("..", "") unless result.cover_medium.nil?
+        info[:cover_large] = @url_protocol + @url_host + result.cover_large.gsub("..", "") unless result.cover_large.nil?
+        info[:link] = get_link(isbn)
+        info[:from_name] = SCRAPER_NAME
+        info[:from_url] = SCRAPER_SITE
+        return info
+      end
+    end
+
+    def get_link(isbn)
+      return nil unless ISBN::valid_isbn?(isbn)
+      return @url_protocol + @url_host + @url_path + ISBN::convert_to_isbn10(isbn) + @url_suffix
+    end
+  end
+  end
+end

data/lib/rbook/www/orbis_scraper.rb

@@ -0,0 +1,48 @@
+
+module RBook
+  module WWW
+  
+  class OrbisScraper < Base
+
+    SCRAPER_ID = :orbis
+    SCRAPER_NAME = "Orbis Books"
+    SCRAPER_SITE = "http://www.orbisbooks.com/"
+    
+    #add_publisher( self, "978157070000", "9781570799999")
+    add_scraper( self )
+    
+    def get_info(isbn)
+      
+      @protocol = "http://"
+      @host = "www.maryknollmall.org"
+      @path = "/description.cfm?ISBN="
+      @grouped_isbn = ISBN::add_groups(ISBN::convert_to_isbn10(isbn))
+      @link = @protocol + @host + @path + @grouped_isbn
+      
+      oup = Scraper.define do
+        process "tr>td[colspan=4]>font[size=3]", :description => :text # doesn't currently work
+        process "table>tr>td[rowspan=2]>img", :cover_thumb => "@src"
+        result :description, :cover_thumb
+      end
+      
+      content = Net::HTTP.get URI.parse(@link)
+       
+      result = oup.scrape(content)
+
+      if result.cover_thumb.nil?
+        return nil
+      else 
+      
+        info = {}
+        info[:isbn] = isbn
+        info[:cover_thumb] = @protocol + @host + result.cover_thumb unless result.cover_thumb.nil?
+        info[:link] = @link
+        info[:from_name] = SCRAPER_NAME
+        info[:from_url] = SCRAPER_SITE
+        return info
+      end 
+    end
+    
+  end
+  end
+end