rbook 0.1

data/lib/rbook/www/oup_scraper.rb

@@ -0,0 +1,64 @@
+
+module RBook
+  module WWW
+  
+  class OUPScraper < Base
+
+    SCRAPER_ID = :oup
+    SCRAPER_NAME = "Oxford University Press"
+    SCRAPER_SITE = "http://au.oup.com/"
+    
+    #add_publisher( self, "978019200000", "978019999999")
+    add_scraper( self )
+    
+    def get_info(isbn)
+     
+      isbn = ISBN::convert_to_isbn10(isbn)
+      
+      @protocol = "http://"
+      @host = "au.oup.com"
+      @path = "/searchbuy/SearchBook.asp?isbn="
+      @link = @protocol + @host + @path + isbn
+      
+      oup = Scraper.define do
+        process "div.isbn13", :isbn => :text
+        process "td.title", :title => :text
+        process "td.author", :author => :text
+        process "div.BookInfo", :misc => :text
+        process "td>p.blurb", :description => :text
+        process "td>img[width=100]", :cover => "@src"
+        result :isbn, :title, :author, :misc, :description, :cover
+      end
+      
+      content = Net::HTTP.get URI.parse(@link)
+      
+      result = oup.scrape(content)
+
+      
+      if result.isbn.nil?
+        return nil
+      else 
+      
+        info = {}
+        info[:isbn] = result.isbn.gsub(/\ ISBN-13:\n/, "")
+        info[:title] = result.title
+        info[:author] = result.author
+        info[:description] = result.description
+        info[:cover_thumb] = @protocol + @host + result.cover
+        info[:link] = @link
+        tmp = result.misc.match(/\n(.+)\n(.+) pages\n(.+)\n(.+)\n(.+)/)
+        if !tmp.nil? && tmp.length == 5
+          info[:published] = tmp[1]
+          info[:pages] = tmp[2]
+          info[:format] = tmp[3]
+          info[:rrp] = tmp[4]
+        end
+        info[:from_name] = SCRAPER_NAME
+        info[:from_url] = SCRAPER_SITE
+        return info
+      end 
+    end
+    
+  end
+  end
+end

data/lib/rbook/www/paulist_scraper.rb

@@ -0,0 +1,53 @@
+
+module RBook
+  module WWW
+  
+  class PaulistScraper < Base
+
+    SCRAPER_ID = :paulist
+    SCRAPER_NAME = "Paulist Press".freeze
+    SCRAPER_SITE = "http://www.paulistpress.com/".freeze
+    
+    #add_publisher( self, "9780809100000", "9780809199999" )
+    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.paulistpress.com"
+      @path = "/"
+      @abv_isbn = ISBN::convert_to_isbn10(isbn)[-5, 5]
+      @suffix = ".html"
+      @link = @protocol + @host + @path + @abv_isbn[0,4] + "-" + @abv_isbn[-1,1] + @suffix
+      
+      rba = Scraper.define do
+        process "tr>td>h4", :title => :text
+        process "img[width=120][height=180]", :cover => "@src"
+        result :title, :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.gsub("Details for ", "")
+        info[:cover_thumb] = @protocol + @host + 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/pearson_au_scraper.rb

@@ -0,0 +1,52 @@
+
+module RBook
+  module WWW
+  
+  class PearsonAUScraper < Base
+
+    SCRAPER_ID = :pearson_au
+    SCRAPER_NAME = "Pearson Education Australia".freeze
+    SCRAPER_SITE = "http://www.pearsoned.com.au/".freeze
+    
+    #add_publisher( self, "9780130000000", "9780139999999" )
+    #add_publisher( self, "9780321000000", "9780321999999" )
+    #add_publisher( self, "9780201000000", "9780201999999" )
+    #add_publisher( self, "9780201000000", "9780201999999" )
+    add_scraper( self )
+
+    def get_info(isbn)
+      @protocol = "http://"
+      @host = "www.pearsoned.com.au"
+      @path = "/Catalogue/TitleDetails.aspx?isbn="
+      @link = @protocol + @host + @path + ISBN::convert_to_isbn10(isbn)
+      
+      rba = Scraper.define do
+        process "span.PageHeading", :title => :text
+        process "span#_publishedLabel", :pubdate => :text
+        process "span#_priceLabel", :rrp => :text
+        process "img.CoverImage", :cover_thumb => "@src"
+        result :title, :pubdate, :rrp, :cover_thumb
+      end
+      
+      content = Net::HTTP.get URI.parse(@link)
+      result = rba.scrape(content)
+      
+      if result.rrp.nil?
+        return nil
+      else 
+      
+        info = {}
+        info[:isbn] = isbn
+        info[:pubdate] = result.pubdate
+        info[:rrp] = result.rrp
+        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/penguin_scraper.rb

@@ -0,0 +1,45 @@
+
+module RBook
+  module WWW
+  
+  class PenguinScraper < Base
+
+    SCRAPER_ID = :penguin
+    SCRAPER_NAME = "Penguin Books Australia".freeze
+    SCRAPER_SITE = "http://www.penguin.com.au/".freeze
+    
+    #add_publisher( self, "9781857200000", "9781857299999" )
+    add_scraper( self )
+    
+    def get_info(isbn)
+      @protocol = "http://"
+      @host = "www.penguin.com.au"
+      @path = "/catalog/search-title-details.cfm?SBN="
+      @link = @protocol + @host + @path + ISBN::convert_to_isbn10(isbn)
+      
+      rba = Scraper.define do
+        process "font>b", :title => :text
+        process "img[alt=cover]", :cover_thumb => "@src"
+        result :title, :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[:cover_thumb] = @protocol + @host + result.cover_thumb.gsub("..", "")
+        info[:link] = @link
+        info[:from_name] = SCRAPER_NAME
+        info[:from_url] = SCRAPER_SITE
+        return info
+      end
+    end
+    
+  end
+  end
+end

data/lib/rbook/www/random_au_scraper.rb

@@ -0,0 +1,90 @@
+require 'cgi'
+
+module RBook
+  module WWW
+  
+  class RandomAUScraper < Base
+
+    SCRAPER_ID = :random_au
+    SCRAPER_NAME = "Random AU".freeze
+    SCRAPER_SITE = "http://www.randomhouse.com.au/".freeze
+    
+    #add_publisher( self, "9781400000000", "9781400099999" )
+    #add_publisher( self, "9781863200000", "9781863299999" )
+    #add_publisher( self, "9781904900000", "9781904999999" )
+    add_scraper( self )
+    
+    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
+    
+    def get_info(isbn)
+     
+      @protocol = "http://"
+      @host = "www.randomhouse.com.au"
+      @path = "/Books/Default.aspx?Page=Book&ID="
+      @link = @protocol + @host + @path + isbn
+      
+      random = Scraper.define do
+        process "td.bookTitle", :title => :text
+        process "span#rBodyModule__ctl0_lblISBN13", :isbn => :text
+        process "span#rBodyModule__ctl0_lblAuthor", :author => :text
+        process "span#rBodyModule__ctl0_lblFormat", :form => :text
+        process "span#rBodyModule__ctl0_lblImprint", :imprint => :text
+        process "span#rBodyModule__ctl0_lblRRP", :rrp => :text
+        process "span#rBodyModule__ctl0_lblRelease", :pubdate => :text
+        process "td.detBook>table>tr>td.standard[colspan=2]", :description => :text
+        process "img#rBodyModule__ctl0_imgBook", :cover_thumb => "@src"
+        process "a#rBodyModule__ctl0_hl300Image", :cover_large => "@href"
+        result :title, :isbn, :author, :form, :imprint, :rrp, :pubdate, :description, :cover_thumb, :cover_large
+      end
+      
+      content = Net::HTTP.get URI.parse(@link)
+      result = random.scrape(content)
+      
+      if result.isbn.nil?
+        return nil
+      else 
+        info = {}
+        info[:isbn] = isbn
+        info[:title] = result.title
+        info[:author] = result.author
+        info[:form] = result.form
+        info[:imprint] = result.imprint
+        info[:rrp] = result.rrp
+        info[:pubdate] = result.pubdate
+        info[:description] = result.description
+        info[:cover_thumb] = result.cover_thumb
+        info[:cover_large] = result.cover_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/random_us_scraper.rb

@@ -0,0 +1,59 @@
+require 'cgi'
+
+module RBook
+  module WWW
+  
+  class RandomUSScraper < Base
+
+    SCRAPER_ID = :random_us
+    SCRAPER_NAME = "Random US".freeze
+    SCRAPER_SITE = "http://www.randomhouse.com/".freeze
+    
+    #add_publisher( self, "9780517300000", "9780517399999" )
+    #add_publisher( self, "9780553800000", "9780553899999" )
+    #add_publisher( self, "9780307000000", "9780307999999" )
+    #add_publisher( self, "9780385500000", "9780385599999" )
+    #add_publisher( self, "9780767900000", "9780767999999" )
+    #add_publisher( self, "9780679600000", "9780679699999" )
+    #add_publisher( self, "9781400000000", "9781400099999" )
+    add_scraper( self )
+
+    def get_info(isbn)
+     
+      @protocol = "http://"
+      @host = "www.randomhouse.com"
+      @path = "/catalog/display.pperl?isbn="
+      @link = @protocol + @host + @path + isbn
+      
+      random = Scraper.define do
+        process "div#catalog_display>h1", :title => :text
+        process "meta[name=gsa.format]", :form => "@content"
+        process "meta[name=gsa.author]", :author => "@content"
+        process "div#catalog_content>p", :description => :text
+        process "div.rhbw_cover>img", :cover_large => "@src"
+        result :title, :author, :form, :description, :cover_large
+      end
+      
+      content = Net::HTTP.get URI.parse(@link)
+      result = random.scrape(content)
+      
+      if result.title.nil?
+        return nil
+      else 
+        info = {}
+        info[:isbn] = isbn
+        info[:title] = result.title
+        info[:author] = result.author
+        info[:form] = result.form
+        info[:description] = result.description
+        info[:cover_large] = @protocol + @host + result.cover_large.gsub("&amp;","&").gsub("=150","=600") unless result.cover_large.nil?
+        info[:link] = @link
+        info[:from_name] = SCRAPER_NAME
+        info[:from_url] = SCRAPER_SITE
+        return info
+      end
+    end
+    
+  end
+  end
+end

data/lib/rbook/www/sas_scraper.rb

@@ -0,0 +1,54 @@
+
+module RBook
+  module WWW
+  
+  class SASScraper < Base
+
+    SCRAPER_ID = :sas_us
+    SCRAPER_NAME = "Simon and Schuster US".freeze
+    SCRAPER_SITE = "http://www.simonsays.com/".freeze
+    
+    #add_publisher( self, "9780671700000", "9780671799999" )
+    #add_publisher( self, "9780731800000", "9780731899999" )
+    #add_publisher( self, "9780743200000", "9780743299999" )
+    #add_publisher( self, "9781416500000", "9781416599999" )
+    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.simonsays.com"
+      @path = "/subs/book.cfm?areaid=288&isbn="
+      @link = @protocol + @host + @path + ISBN::convert_to_isbn10(isbn)
+      
+      rba = Scraper.define do
+        process "font[face=Verdana, Arial, Helvetica]>b", :title => :text
+        process "td[rowspan=3]>img[border=0]", :cover_thumb => "@src"
+        result :title, :cover_thumb
+      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[: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

data/lib/rbook/www/unireps_scraper.rb

@@ -0,0 +1,58 @@
+
+module RBook
+  module WWW
+  
+  class UnirepsScraper < Base
+
+    SCRAPER_ID = :unireps
+    SCRAPER_NAME = "Unireps".freeze
+    SCRAPER_SITE = "http://www.unireps.com.au/".freeze
+    
+    #add_publisher( self, "9780643000000", "9780643099999" )
+    #add_publisher( self, "9780868400000", "9780868499999" )
+    #add_publisher( self, "9780908800000", "9780908999999" )
+    #add_publisher( self, "9780909600000", "9780909699999" )
+    #add_publisher( self, "9781877000000", "9781877099999" )
+    #add_publisher( self, "9781920700000", "9781920799999" )
+    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)
+      isbn10 = ISBN::convert_to_isbn10(isbn)
+
+      @protocol = "http://"
+      @host = "www.unireps.com.au"
+      @path = "/isbn/"
+      @suffix = ".htm"
+      @link = @protocol + @host + @path + isbn10 + @suffix
+      
+      rba = Scraper.define do
+        process "h4", :title => :text
+        process "img[alt=#{isbn10}]", :cover_thumb => "@src"
+        result :title, :cover_thumb
+      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 unless result.title.nil?
+        info[:cover_thumb] = @protocol + @host + @path + 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