rbook 0.4.3 → 0.5

data/lib/rbook/titlepage/wwwclient.rb

@@ -1,96 +0,0 @@
-$LOAD_PATH.unshift(File.dirname(__FILE__) + "/../")
-
-require 'rbook/isbn'
-require 'rbook/errors'
-
-module RBook
-  module TitlePage
-
-    # You should be aware of any limits of query volume imposed by the provider - currently a
-    # maximum of 30 queries per minute is permitted.
-    class WWWClient
-
-      TITLEPAGE_DOMAIN = "www.titlepage.com"
-      @@uri = nil
-
-      def initialize
-      end
-
-      def get_onix_file(isbn)
-        isbn = RBook::ISBN.convert_to_isbn13(isbn)
-        raise ArgumentError, 'Invalid ISBN supplied' if isbn.nil?
-        
-        headers = { 'Cookie' => @cookie }
-        
-        login_response = Net::HTTP.start(TITLEPAGE_DOMAIN, 80) do |http|
-          data = [
-            "posted=yes",
-            "quicksearch=#{isbn}",
-            "qsrchby=ean",
-            "detailed=Search"
-          ].join("&")
-          http.post('/results.php', data, headers)
-        end
-        regex = /onclick=\"bookPopUp\(\'(.+)\'\);\"/
-        code = login_response.body.match(regex)
-        if code.nil?
-          return nil
-        else
-          code = code[1]
-        end
-        onix_file = Net::HTTP.start(TITLEPAGE_DOMAIN, 80) do |http|
-          data = [
-            "download=Download",
-            "rr=#{code}"
-          ].join("&")
-          http.post('/detail.php', data, headers)
-        end
-        return onix_file.body
-      end
-
-      # login to the titlepage website.
-      def login(username, password)
-        login_response = Net::HTTP.start(TITLEPAGE_DOMAIN, 80) do |http|
-          data = [
-            "usr=#{username}",
-            "pwd=#{password}",
-            "login=Login"
-          ].join("&")
-          http.post('/index.php', data)
-        end
-        @cookie = login_response['set-cookie']
-      end
-
-      # logout from the titlepage API
-      def logout
-        if @cookie
-          login_response = Net::HTTP.start(TITLEPAGE_DOMAIN, 80) do |http|
-            http.get("/logout.php")
-          end
-          @cookie = nil
-        end
-      end
-
-      # a convenience method to make queries to title page a little cleaner. This function
-      # essentially calls the login and logout functions for you automatically.
-      #
-      #  RBook::TitlePage::WWWClient.open("username","password") do |tp|
-      #    result = tp.get_onix_file("9780091835132")
-      #  end
-      def self.open(username, password)
-
-        tp = self.new
-
-        begin
-          tp.login(username, password)
-
-          yield(tp)
-
-        ensure
-          tp.logout
-        end
-      end
-
-    end
-  end
-end

data/lib/rbook/www.rb

@@ -1,172 +0,0 @@
-$LOAD_PATH.unshift(File.dirname(__FILE__) + "/../")
-
-require 'rubygems'
-require 'scrapi'
-
-require 'rbook/isbn'
-require 'rbook/www/base'
-
-# load all scraping classes
-files = Dir.entries(File.dirname(__FILE__) + '/www/')
-files.delete(".")
-files.delete("..")
-files.delete(".svn")
-files.delete("base.rb")
-files.each do |file|
-  require 'rbook/www/' + file
-end
-
-module RBook
-  # A set of classes to make scraping title information from various publisher websites easier.
-  #
-  # Basic usage:
-  #   require 'rubygems'
-  #   require 'rbook/www'
-  #   RBook::WWW.find_info(:first, "1841492280", :penguin)   
-  #           #=> Hash
-  #   RBook::WWW.find_info(:all, "1841492280", [:penguin, :harpercollins_au])   
-  #           #=> Array of Hashes
-  module WWW
-
-    # Find any information possible about the supplied isbn using the 
-    # specified scrapers.
-    # 
-    # - isbn - a valid isbn10 or isbn13
-    # - scrapers - a symbol or array of symbols specifying which scrapers to search with
-    # 
-    # Returns the results as an array containing the results
-    # 
-    #   RBook::WWW.find_info(:first, "1841492280", :penguin)   
-    #           #=> Hash
-    #   RBook::WWW.find_info(:all, "1841492280", [:penguin, :harpercollins_au])   
-    #           #=> Array of Hashes
-    def self.find_info(search_type, isbn, scrapers)
-
-      raise ArgumentError, 'search_type must be :first or :all' if !search_type.eql?(:first) && !search_type.eql?(:all)
-      raise ArgumentError, 'Supplied isbn is not valid' unless ISBN::valid_isbn?(isbn)
-      raise ArgumentError, 'scrapers must be a symbol or array of symbols' unless scrapers.kind_of?(Symbol) || scrapers.kind_of?(Array)
-
-      isbn = ISBN::convert_to_isbn13(isbn)
-
-      if scrapers.kind_of?(Symbol)
-        scrapers = [Base::find_scraper(scrapers)]
-      else
-        scrapers = Base::find_scrapers(scrapers)
-      end
-
-      results = []
-
-      scrapers.each do |scraper|
-        worker = scraper.new
-        result = worker.get_info(isbn)
-        if !result.nil? && search_type.eql?(:first)
-          return result
-        elsif !result.nil?
-          results << result
-        end
-      end
-
-      if results.empty?
-        return nil
-      else
-        return results
-      end
-    end
-
-    # Find any information possible about the supplied isbn using the 
-    # specified scrapers.
-    # 
-    # - isbn - a valid isbn10 or isbn13
-    # - scrapers - a symbol or array of symbols specifying which scrapers to search with
-    # 
-    # Returns the results as an array containing the results
-    #
-    #   RBook::WWW.find_cover(:first, "1841492280", :penguin)   
-    #           #=> Hash
-    #   RBook::WWW.find_cover(:all, "1841492280", [:penguin, :harpercollins_au])   
-    #           #=> Array of Hashes
-    def self.find_cover(search_type, isbn, scrapers)
-
-      raise ArgumentError, 'search_type must be :first or :all' if !search_type.eql?(:first) && !search_type.eql?(:all)
-      raise ArgumentError, 'Supplied isbn is not valid' unless ISBN::valid_isbn?(isbn)
-      raise ArgumentError, 'scrapers must be a symbol or array of symbols' unless scrapers.kind_of?(Symbol) || scrapers.kind_of?(Array)
-
-      isbn = ISBN::convert_to_isbn13(isbn)
-
-      if scrapers.kind_of?(Symbol)
-        scrapers = [Base::find_scraper(scrapers)]
-      else
-        scrapers = Base::find_scrapers(scrapers)
-      end
-
-      results = []
-
-      scrapers.each do |scraper|
-        worker = scraper.new
-        result = worker.get_cover(isbn)
-        if !result.nil? && search_type.eql?(:first)
-          return result
-        elsif !result.nil?
-          results << result
-        end
-      end
-
-      if results.empty?
-        return nil
-      else
-        return results
-      end
-    end
-
-    # Find any information possible about the supplied isbn using the 
-    # specified scrapers.
-    #
-    # - isbn - a valid isbn10 or isbn13
-    # - scrapers - a symbol or array of symbols specifying which scrapers to search with
-    # 
-    # Returns the results as an array containing the results
-    #
-    #   RBook::WWW.find_url(:first, "1841492280", :penguin)   
-    #           #=> Hash
-    #   RBook::WWW.find_url(:all, "1841492280", [:penguin, :harpercollins_au])   
-    #           #=> Array of Hashes
-    def self.find_url(search_type, isbn, scrapers)
-
-      raise ArgumentError, 'search_type must be :first or :all' if !search_type.eql?(:first) && !search_type.eql?(:all)
-      raise ArgumentError, 'Supplied isbn is not valid' unless ISBN::valid_isbn?(isbn)
-      raise ArgumentError, 'scrapers must be a symbol or array of symbols' unless scrapers.kind_of?(Symbol) || scrapers.kind_of?(Array)
-
-      isbn = ISBN::convert_to_isbn13(isbn)
-
-      if scrapers.kind_of?(Symbol)
-        scrapers = [Base::find_scraper(scrapers)]
-      else
-        scrapers = Base::find_scrapers(scrapers)
-      end
-
-      results = []
-
-      scrapers.each do |scraper|
-        worker = scraper.new
-        result = worker.get_url(isbn)
-        if !result.nil? && search_type.eql?(:first)
-          return result
-        elsif !result.nil
-          results << result
-        end
-      end
-
-      if results.empty?
-        return nil
-      else
-        return results
-      end
-    end
-
-    # returns an array of all available scrapers
-    def self.scrapers
-      Base.scrapers
-    end
-
-  end
-end

data/lib/rbook/www/aau_scraper.rb

@@ -1,76 +0,0 @@
-
-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

@@ -1,44 +0,0 @@
-
-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/ban_scraper.rb

@@ -1,62 +0,0 @@
-
-module RBook
-  module WWW
-  
-  class BarnesAndNobleScraper < Base
-
-    SCRAPER_ID = :barnesandnoble
-    SCRAPER_NAME = "Barnes and Noble".freeze
-    SCRAPER_SITE = "http://www.barnesandnole.com/".freeze
-    
-    add_scraper( self )
-    
-    def get_info(isbn)
-     
-      @protocol = "http://"
-      @host = "search.barnesandnoble.com"
-      @path = "/booksearch/isbninquiry.asp?z=y&cds2Pid=9481&isbn="
-      @imgviewer_path = "/booksearch/imageviewer.asp?z=y&ean="
-      @link = @protocol + @host + @path + ISBN::convert_to_isbn10(isbn)
-      @imgviewer_link = @protocol + @host + @imgviewer_path + ISBN::convert_to_isbn10(isbn)
-
-      main = Scraper.define do
-        process "h1#title", :title => :text
-        process "h2#contributor>a", :author => :text
-        process "li.format", :form => :text
-        process "div#coverImage>a>noscript>img", :cover_thumb => "@src"
-        result :title, :author, :form, :cover_thumb
-      end
-      
-      imgscraper = Scraper.define do
-        process "div>img[alt=Cover Image]", :cover_large => "@src"
-        result :cover_large
-      end
-
-      content = Net::HTTP.get URI.parse(@link)
-      result = main.scrape(content)
-      if result.title.nil?
-        return nil
-      else 
-
-        info = {}
-        info[:isbn] = isbn
-        info[:title] = result.title unless result.title.nil?
-        info[:author] = result.author unless result.author.nil?
-        info[:format] = result.form unless result.form.nil?
-        info[:cover_thumb] = result.cover_thumb
-        info[:link] = @link
-        info[:from_name] = SCRAPER_NAME
-        info[:from_url] = SCRAPER_SITE
-
-        content = Net::HTTP.get URI.parse(@imgviewer_link)
-        result = imgscraper.scrape(content)
-        
-        info[:cover_large] = result unless result.nil?
-      
-        return info
-      end
-    end
-    
-  end
-  end
-end