alexandria-book-collection-manager 0.7.2 → 0.7.3

data/lib/alexandria/book_providers/deastore.rb

@@ -1,265 +0,0 @@
-# frozen_string_literal: true
-
-# -*- ruby -*-
-#
-# Copyright (C) 2009 Cathal Mc Ginley
-# Copyright (C) 2011, 2014, 2016 Matijs van Zuijlen
-#
-# Alexandria is free software; you can redistribute it and/or
-# modify it under the terms of the GNU General Public License as
-# published by the Free Software Foundation; either version 2 of the
-# License, or (at your option) any later version.
-#
-# Alexandria is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
-# General Public License for more details.
-#
-# You should have received a copy of the GNU General Public
-# License along with Alexandria; see the file COPYING.  If not,
-# write to the Free Software Foundation, Inc., 51 Franklin Street,
-# Fifth Floor, Boston, MA 02110-1301 USA.
-
-# New DeaStore provider, taken from the Palatina MetaDataSource and
-# modified to fit the structure of Alexandria book providers.
-# (24 Feb 2009)
-
-require 'cgi'
-require 'alexandria/net'
-require 'alexandria/book_providers/web'
-
-module Alexandria
-  class BookProviders
-    class DeaStoreProvider < WebsiteBasedProvider
-      include Alexandria::Logging
-
-      SITE = 'http://www.deastore.com'
-      BASE_SEARCH_URL = "#{SITE}/search/italian_books/0/%s/%s" # type/term
-
-      def initialize
-        super('DeaStore', 'DeaStore (Italy)')
-        prefs.read
-        @agent = nil
-      end
-
-      def agent
-        unless @agent
-          @agent = Alexandria::WWWAgent.new
-          @agent.language = :it
-        end
-        @agent
-      end
-
-      def get_book_from_search_result(result)
-        log.debug { "Fetching book from #{result[:url]}" }
-        html_data = agent.get(result[:url])
-        # File.open("rsltflarn#{Time.now().usec()}.html", 'wb') do |f|
-        #  f.write(html_data.body)
-        # end
-        parse_result_data(html_data.body)
-      end
-
-      def search(criterion, type)
-        begin
-          criterion = criterion.encode('ISO-8859-1') # still needed??
-        rescue Encoding::UndefinedConversionError
-          log.info { "Cannot search for non-ISO-8859-1 terms at DeaStore : #{criterion}" }
-          raise NoResultsError
-        end
-        html_data = agent.get(create_search_uri(type, criterion))
-        # File.open("flarn#{Time.now().usec()}.html", 'wb') do |f|
-        #  f.write(html_data.body)
-        # end
-        results = parse_search_result_data(html_data.body)
-        raise NoResultsError if results.empty?
-
-        if type == SEARCH_BY_ISBN
-          get_book_from_search_result(results.first)
-        else
-          results.map { |result| get_book_from_search_result(result) }
-        end
-      end
-
-      # it isn't possible to create a URL for a book given only the ISBN...
-      def url(_book)
-        nil
-      end
-
-      private
-
-      def create_search_uri(search_type, search_term)
-        # bah! very, very similar to the siciliano code! refactor out this duplication
-        (search_type_code = { SEARCH_BY_ISBN => 'isbn',
-                              SEARCH_BY_TITLE => 'title',
-                              SEARCH_BY_AUTHORS => 'author',
-                              SEARCH_BY_KEYWORD => 'keywords' }[search_type]) || 'keywords'
-
-        search_term_encoded = if search_type == SEARCH_BY_ISBN
-                                Library.canonicalise_isbn(search_term) # isbn-10
-                              else
-                                CGI.escape(search_term)
-                              end
-
-        uri = format(BASE_SEARCH_URL, search_type_code, search_term_encoded)
-        log.debug { uri }
-        uri
-      end
-
-      def parse_search_result_data(html)
-        doc = html_to_doc(html)
-        book_search_results = []
-
-        result_divs = doc.search('div.scheda_prodotto')
-        result_divs.each do |div|
-          begin
-            # The layout...
-            # a > img
-            # div.scheda_content
-            #  a[link->productpage] title ##  a.titolo_link
-            #  p (genre I think) ##  !ignore
-            #  a[link->author] author ## a.info
-            #  p.editore (publisher? editor?)
-            #  p Data di pubblicazione: \n     2009
-            #  p.prezzo (price)
-
-            #             cover_url = ''
-            #             cover_images = div/'a/img'
-            #             unless cover_images.empty?
-            #               img = cover_images.first
-            #               image_url = img['src']
-            #               if image_url =~ /^http/
-            #                 cover_url = '' # image_url
-            #               elsif image_url[0..0] != '/'
-            #                 cover_url = "#{SITE}/#{image_url}"
-            #               else
-            #                 cover_url = "#{SITE}#{image_url}"
-            #               end
-            #               log.debug { "Search Cover Image URL #{cover_url}" }
-
-            #             end
-
-            content = div / 'div.scheda_content'
-            title_link = (content / :a).first
-            title = normalize(title_link.inner_text)
-            link_to_description = title_link['href']
-            lookup_url = "#{SITE}#{link_to_description}"
-
-            authors = []
-            (content / 'a.info').each do |link|
-              authors << normalize(link.inner_text)
-            end
-
-            result = {}
-            result[:author] = authors.first # HACK, what about multiple authors
-            result[:title] = title
-            result[:url] = lookup_url
-
-            publishers = (content / 'p.editore')
-            result[:publisher] = normalize(publishers.first.inner_text) unless publishers.empty?
-
-            book_search_results << result
-          rescue => ex
-            trace = ex.backtrace.join("\n> ")
-            log.error { "Failed parsing DeaStore search page #{ex.message}\n#{trace}" }
-          end
-        end
-        book_search_results
-      end
-
-      def parse_result_data(html)
-        doc = html_to_doc(html)
-        data = doc % 'div#dati_scheda'
-        # sotto_data_hdr = doc % 'div.sotto_schede/h1.titolo_sotto[text()*="Informazioni generali"]/..'
-        # title
-        title_span = data % 'h1.titolo_scheda'
-        title = normalize(title_span.inner_text)
-        # cover
-        cover_link = nil
-        cover_img = data / 'a/img'
-        cover_link = cover_img.first['src'] unless cover_img.empty?
-        # author(s)
-        authors = []
-        author_span = data % 'span.int_scheda[text()*=Autore]'
-        author_span ||= data % 'span.int_scheda[text()*=cura]'
-        if author_span
-          author_links = author_span / 'a.info'
-          authors = []
-          author_links.each do |link|
-            authors << normalize(link.inner_html)
-          end
-        end
-        # if author_span
-        #  author_links = author_span/'a.info'
-        #  author_links.each do |link|
-        #    authors << normalize(link.inner_text)
-        #  end
-        # end
-        # publisher
-        publisher_par = data % 'span.int_scheda[text()*=Editore]/..'
-        publisher_link = publisher_par % 'a.info'
-        publisher = normalize(publisher_link.inner_text)
-        # skip 'Collana', (ummm, possibly genre information, Babelfish
-        # says "Necklace")
-        # format
-        format_par = data % 'span.int_scheda[text()*=Formato]/..'
-        format_par.inner_text =~ /:[\s]*(.+)[\s]*$/
-        binding = normalize(Regexp.last_match[1])
-        # year
-        date_par = data % 'span.int_scheda[text()*=Data di pubblicazione]/..'
-        date_par.inner_text =~ /:[\s]*([12][0-9]{3})[\s]*$/
-        publish_year = nil
-        publish_year = Regexp.last_match[1].to_i if Regexp.last_match[1]
-        isbn_spans = data / 'div.sotto/span.isbn'
-        isbns = []
-        isbn_spans.each do |span|
-          span.inner_text =~ /:[\s]*(.+)[\s]*$/
-          isbns << Regexp.last_match[1]
-        end
-        isbn = nil
-        isbn = Library.canonicalise_isbn(isbns.first) unless isbns.empty?
-        # Editore & Imprint : as publisher info above...
-        # pages
-        # page_par = data % 'span.int_scheda[text()*=Pagine]/..'
-        # if page_par
-        #  page_par.inner_text =~ /:[\s]*([0-9]+)[\s]*$/
-        #  pages = $1.to_i
-        # end
-        # synopsis_div = doc % 'div.sotto_schede' # exclude the first span though
-        # book = Book.new(title, isbns.first, authors)
-        # if publisher
-        #  book.publisher = Publisher.new(publisher)
-        # end
-        # if format
-        #  book.binding = CoverBinding.new(format, binding_type(format))
-        # end
-        # cover
-        image_url = nil
-        if cover_link
-          image_url = if cover_link =~ /^http/
-                        # e.g. http://images.btol.com/ContentCafe/Jacket.aspx?\
-                        # Return=1&amp;Type=M&amp;Value=9788873641803&amp;password=\
-                        # CC70580&amp;userID=DEA40305
-                        # seems not to work, or to be blank anyway, so set to nil
-                        nil
-                      elsif cover_link[0..0] != '/'
-                        "#{SITE}/#{cover_link}"
-                      else
-                        "#{SITE}#{cover_link}"
-                      end
-          log.debug { "Cover Image URL:: #{image_url}" }
-        end
-        book = Book.new(title, authors, isbn, publisher, publish_year, binding)
-        [book, image_url]
-      rescue => ex
-        trace = ex.backtrace.join("\n> ")
-        log.error { "Failed parsing DeaStore product page #{ex.message}\n#{trace}" }
-        nil
-      end
-
-      def normalize(str)
-        str = str.squeeze(' ').strip unless str.nil?
-        str
-      end
-    end
-  end
-end

data/lib/alexandria/book_providers/mcu.rb

@@ -1,182 +0,0 @@
-# frozen_string_literal: true
-
-# Copyright (C) 2004 Javier Fernandez-Sanguino
-# Copyright (C) 2007 Javier Fernandez-Sanguino and Marco Costantini
-# Copyright (C) 2011, 2016 Matijs van Zuijlen
-#
-# Alexandria is free software; you can redistribute it and/or
-# modify it under the terms of the GNU General Public License as
-# published by the Free Software Foundation; either version 2 of the
-# License, or (at your option) any later version.
-#
-# Alexandria is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
-# General Public License for more details.
-#
-# You should have received a copy of the GNU General Public
-# License along with Alexandria; see the file COPYING.  If not,
-# write to the Free Software Foundation, Inc., 51 Franklin Street,
-# Fifth Floor, Boston, MA 02110-1301 USA.
-
-require 'cgi'
-require 'net/http'
-
-# http://www.mcu.es/libro/CE/AgenciaISBN/BBDDLibros/Sobre.html
-# http://www.mcu.es/comun/bases/isbn/ISBN.html
-
-module Alexandria
-  class BookProviders
-    class MCUProvider < GenericProvider
-      include Logging
-      include GetText
-      GetText.bindtextdomain(Alexandria::TEXTDOMAIN, charset: 'UTF-8')
-
-      LANGUAGES = {
-        'es' => '1'
-      }.freeze
-
-      #        BASE_URI = "http://www.mcu.es/cgi-bin/BRSCGI3701?"
-      BASE_URI = 'http://www.mcu.es/cgi-brs/BasesHTML/isbn/BRSCGI?'
-      def initialize
-        super('MCU', _('Spanish Culture Ministry'))
-        # No preferences
-        prefs.read
-      end
-
-      def search(criterion, type)
-        prefs.read
-        criterion = criterion.encode('ISO-8859-1') # still needed??
-        print "Doing search with MCU #{criterion}, type: #{type}\n" if $DEBUG # for DEBUGing
-        req = BASE_URI +
-          'CMD=VERLST&BASE=ISBN&DOCS=1-15&CONF=AEISPA.cnf&OPDEF=AND&DOCS=1-1000&SEPARADOR=&'
-        req += case type
-               when SEARCH_BY_ISBN
-                 "WGEN-C=&WISB-C=#{CGI.escape(criterion)}&WAUT-C=&WTIT-C="
-
-               when SEARCH_BY_TITLE
-                 "WGEN-C=&WISB-C=&WAUT-C=&WTIT-C=#{CGI.escape(criterion)}"
-
-               when SEARCH_BY_AUTHORS
-                 "WGEN-C=&WISB-C=&WAUT-C=#{CGI.escape(criterion)}&WTIT-C="
-
-               when SEARCH_BY_KEYWORD
-                 "WGEN-C=#{CGI.escape(criterion)}&WISB-C=&WAUT-C=&WTIT-C="
-
-               else
-                 raise InvalidSearchTypeError
-               end
-        req +=
-          '&WMAT-C=&WEDI-C=&WFEP-C=&%40T353-GE=&%40T353-LE=&WSER-C=&WLUG-C=' \
-          '&WDIS-C=%28DISPONIBLE+or+AGOTADO%29&WLEN-C=&WCLA-C=&WSOP-C='
-        products = {}
-        print "Request page is #{req}\n" if $DEBUG # for DEBUGing
-        transport.get(URI.parse(req)).each do |line|
-          print "Reading line: #{line}" if $DEBUG # for DEBUGing
-          next unless line =~ /CMD=VERDOC.*&DOCN=([^&]*)&NDOC=([^&]*)/
-          next if products[Regexp.last_match[1]]
-          next unless (book = parseBook(Regexp.last_match[1], Regexp.last_match[2]))
-          products[Regexp.last_match[1]] = book
-          puts Regexp.last_match[1] if $DEBUG # for DEBUGing
-        end
-
-        raise NoResultsError if products.values.empty?
-        type == SEARCH_BY_ISBN ? products.values.first : products.values
-      end
-
-      def url(book)
-        isbn = Library.canonicalise_isbn(book.isbn)
-        'http://www.mcu.es/cgi-brs/BasesHTML/isbn/BRSCGI?CMD=VERLST&BASE=ISBN&DOCS=1-15' \
-          "&CONF=AEISPA.cnf&OPDEF=AND&DOCS=1&SEPARADOR=&WGEN-C=&WISB-C=#{isbn}&WAUT-C=&WTIT-C=" \
-          '&WMAT-C=&WEDI-C=&WFEP-C=&%40T353-GE=&%40T353-LE=&WSER-C=&WLUG-C=' \
-          '&WDIS-C=%28DISPONIBLE+or+AGOTADO%29&WLEN-C=&WCLA-C=&WSOP-C='
-      rescue => ex
-        log.warn { "Cannot create url for book #{book}; #{ex.message}" }
-        nil
-      end
-
-      private
-
-      def parseBook(docn, ndoc)
-        detailspage =
-          'http://www.mcu.es/cgi-brs/BasesHTML/isbn/BRSCGI?' \
-          'CMD=VERDOC&CONF=AEISPA.cnf&BASE=ISBN&DOCN=' + docn + '&NDOC=' + ndoc
-        print "Looking at detailspage: #{detailspage}\n" if $DEBUG # for DEBUGing
-        product = {}
-        product['authors'] = []
-        robotstate = 0
-        transport.get(URI.parse(detailspage)).each do |line|
-          # This is a very crude robot interpreter
-          # Note that the server provides more information
-          # we don't store:
-          # - Language  - Description
-          # - Binding   - Price
-          # - Colection - Theme
-          # - CDU      - Last update
-
-          # There seems to be an issue with accented chars..
-          line = line.encode('UTF-8')
-          print "Reading line (robotstate #{robotstate}): #{line}" if $DEBUG # for DEBUGing
-          if line =~ /^<\/td>$/ || line =~ /^<\/tr>$/
-            robotstate = 0
-          elsif (robotstate == 1) && line =~ /^([^<]+)</
-            author = Regexp.last_match[1].gsub('&nbsp;', ' ').sub(/ +$/, '')
-            if author.length > 3
-              # Only add authors of appropiate length
-              product['authors'] << author
-              print "Authors are #{product['authors']}\n" if $DEBUG # for DEBUGing
-              robotstate = 0
-            end
-          elsif (robotstate == 2) && line =~ /^(.*)$/
-            # The title es the next line to title declaration and has not tags on web src code
-            product['name'] = Regexp.last_match[1].strip
-            print "Name is #{product['name']}\n" if $DEBUG # for DEBUGing
-            robotstate = 0
-          elsif (robotstate == 3) && line =~ /^([0-9]+-[0-9]+-[0-9]+-[0-9]+-[0-9]).*/
-            product['isbn'] = Regexp.last_match[1]
-            print "ISBN is #{product['isbn']}\n" if $DEBUG # for DEBUGing
-            robotstate = 0
-          elsif (robotstate == 4) && line =~ /^([^<]+)</
-            product['manufacturer'] = Regexp.last_match[1].strip
-            print "Manufacturer is #{product['manufacturer']}\n" if $DEBUG # for DEBUGing
-            robotstate = 0
-            #                elsif robotstate == 5 and line =~ /^([^<]+)</
-          elsif (robotstate == 5) && line =~ /<span>([^<]+)</
-            product['media'] = Regexp.last_match[1].strip
-            print "Media is #{product['media']}\n" if $DEBUG # for DEBUGing
-            robotstate = 0
-          elsif line =~ /^.*>Autor:\s*</
-            robotstate = 1
-          elsif line =~ /^.*>T(.|&iacute;)tulo:\s*</
-            robotstate = 2
-          elsif line =~ /^.*>ISBN \(13\):\s*</
-            robotstate = 3
-          elsif line =~ /^.*>Publicaci(.|&oacute;)n:\s*</
-            robotstate = 4
-          elsif line =~ /^.*>Encuadernaci(.|&oacute;)n:\s*</
-            robotstate = 5
-          end
-        end
-
-        # TODO: This provider does not include picture for books
-        #            %w{name isbn media manufacturer}.each do |field|
-        #               print "Checking #{field} for nil\n" if $DEBUG # for DEBUGing
-        #                product[field]="" if product[field].nil?
-        #            end
-
-        print "Creating new book\n" if $DEBUG # for DEBUGing
-        book = Book.new(product['name'],
-                        product['authors'],
-                        product['isbn'].delete('-'),
-                        product['manufacturer'],
-                        nil, # TODO: furnish publish year
-                        product['media'])
-        if book.title.nil?
-          log.warn { "No title was returned for #{book.isbn}" }
-          book.title = ''
-        end
-        [book]
-      end
-    end
-  end
-end