alexandria-book-collection-manager 0.7.1 → 0.7.6

data/lib/alexandria/book_providers/ibs_it.rb

@@ -1,147 +0,0 @@
-# Copyright (C) 2005-2006 Claudio Belotti
-# Copyright (C) 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.
-
-require 'fileutils'
-require 'net/http'
-require 'open-uri'
-# require 'cgi'
-
-module Alexandria
-  class BookProviders
-    class IBS_itProvider < GenericProvider
-      BASE_URI = 'http://www.internetbookshop.it'.freeze
-      CACHE_DIR = File.join(Alexandria::Library::DIR, '.ibs_it_cache')
-      REFERER = BASE_URI
-      def initialize
-        super('IBS_it', 'Internet Bookshop (Italy)')
-        FileUtils.mkdir_p(CACHE_DIR) unless File.exist?(CACHE_DIR)
-        # no preferences for the moment
-        at_exit { clean_cache }
-      end
-
-      def search(criterion, type)
-        criterion = criterion.encode('ISO-8859-1')
-        req = BASE_URI + '/ser/'
-        req += case type
-               when SEARCH_BY_ISBN
-                 'serdsp.asp?isbn='
-
-               when SEARCH_BY_TITLE
-                 'serpge.asp?Type=keyword&T='
-
-               when SEARCH_BY_AUTHORS
-                 'serpge.asp?Type=keyword&A='
-
-               when SEARCH_BY_KEYWORD
-                 'serpge.asp?Type=keyword&S='
-
-               else
-                 raise InvalidSearchTypeError
-
-               end
-
-        req += CGI.escape(criterion)
-        p req if $DEBUG
-        data = transport.get(URI.parse(req))
-        if type == SEARCH_BY_ISBN
-          to_book(data) # rescue raise NoResultsError
-        else
-          begin
-            results = []
-            each_book_page(data) do |code, _title|
-              results << to_book(transport.get(URI.parse('http://www.internetbookshop.it/ser/serdsp.asp?cc=' + code)))
-            end
-            return results
-          rescue
-            raise NoResultsError
-          end
-        end
-      end
-
-      def url(book)
-        'http://www.internetbookshop.it/ser/serdsp.asp?isbn=' + book.isbn
-      end
-
-      private
-
-      def to_book(data)
-        raise NoResultsError if data =~ /<b>Il libro che hai cercato non &egrave; presente nel nostro catalogo<\/b><br>/
-        data = data.encode('UTF-8')
-
-        md = />Titolo<\/td><td valign="top" class="lbarrasup">([^<]+)/.match(data)
-        raise 'No title' unless md
-        title = CGI.unescape(md[1].strip)
-
-        authors = []
-        if (md = /<b>Autore<\/b><\/td>.+<b>([^<]+)/.match(data))
-          md[0].strip.gsub(/<.*?>|Autore/m, ' ').split('; ').each { |a| authors << CGI.unescape(a.strip) }
-        end
-
-        md = /<input type=\"hidden\" name=\"isbn\" value=\"([^"]+)\">/i.match(data)
-        raise 'No ISBN' unless md
-        isbn = md[1].strip
-
-        # raise "No publisher" unless
-        md = /<b>Editore<\/b><\/td>.+<b>([^<]+)/.match(data)
-        (publisher = CGI.unescape(md[1].strip)) || md
-
-        # raise "No edition" unless
-        md = /Dati<\/b><\/td><td valign="top">([^<]+)/.match(data)
-        (edition = CGI.unescape(md[1].strip)) || md
-
-        publish_year = nil
-        if (md = /Anno<\/b><\/td><td valign="top">([^<]+)/.match(data))
-          publish_year = CGI.unescape(md[1].strip).to_i
-          publish_year = nil if publish_year.zero?
-        end
-
-        md = /src="http:\/\/giotto.ibs.it\/cop\/copt13.asp\?f=(\d+)">/.match(data)
-        cover_url = 'http://giotto.ibs.it/cop/copt13.asp?f=' + md[1] # use copa13.asp, copt13.asp, copj13.asp, for small, medium, big image
-        cover_filename = isbn + '.tmp'
-        Dir.chdir(CACHE_DIR) do
-          File.open(cover_filename, 'w') do |file|
-            file.write open(cover_url, 'Referer' => REFERER).read
-          end
-        end
-
-        medium_cover = CACHE_DIR + '/' + cover_filename
-        if File.size(medium_cover) > 0 && (File.size(medium_cover) != 1822) # 1822 is the size of the fake image "copertina non disponibile"
-          puts medium_cover + ' has non-0 size' if $DEBUG
-          return [Book.new(title, authors, isbn, publisher, publish_year, edition), medium_cover]
-        end
-        puts medium_cover + ' has 0 size, removing ...' if $DEBUG
-        File.delete(medium_cover)
-        [Book.new(title, authors, isbn, publisher, publish_year, edition)]
-      end
-
-      def each_book_page(data)
-        raise if data.scan(/<a href="http:\/\/www.internetbookshop.it\/ser\/serdsp.asp\?shop=1&amp;cc=([\w\d]+)"><b>([^<]+)/) { |a| yield a }.empty?
-      end
-
-      def clean_cache
-        # FIXME: begin ... rescue ... end?
-        Dir.chdir(CACHE_DIR) do
-          Dir.glob('*.tmp') do |file|
-            puts 'removing ' + file if $DEBUG
-            File.delete(file)
-          end
-        end
-      end
-    end
-  end
-end

data/lib/alexandria/book_providers/mcu.rb

@@ -1,169 +0,0 @@
-# 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?'.freeze
-      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=&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="
-
-               when SEARCH_BY_TITLE
-                 "WGEN-C=&WISB-C=&WAUT-C=&WTIT-C=#{CGI.escape(criterion)}&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="
-
-               when SEARCH_BY_AUTHORS
-                 "WGEN-C=&WISB-C=&WAUT-C=#{CGI.escape(criterion)}&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="
-
-               when SEARCH_BY_KEYWORD
-                 "WGEN-C=#{CGI.escape(criterion)}&WISB-C=&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="
-
-               else
-                 raise InvalidSearchTypeError
-               end
-        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
-          if (line =~ /CMD=VERDOC.*&DOCN=([^&]*)&NDOC=([^&]*)/) && (!products[Regexp.last_match[1]]) && (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
-        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

data/lib/alexandria/book_providers/renaud.rb

@@ -1,140 +0,0 @@
-# Copyright (C) 2005-2006-2006 Mathieu Leduc-Hamel
-#
-# 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.
-
-# http://en.wikipedia.org/wiki/Renaud-Bray
-
-require 'net/http'
-require 'cgi'
-
-module Alexandria
-  class BookProviders
-    class RENAUDProvider < GenericProvider
-      include GetText
-      # GetText.bindtextdomain(Alexandria::TEXTDOMAIN, :charset => "UTF-8")
-      BASE_URI = 'http://www.renaud-bray.com/'.freeze
-      ACCENTUATED_CHARS = 'áàâäçéèêëíìîïóòôöúùûü'.freeze
-
-      def initialize
-        super('RENAUD', 'Renaud-Bray (Canada)')
-      end
-
-      def search(criterion, type)
-        criterion = criterion.encode('ISO-8859-1')
-        req = BASE_URI + 'francais/menu/gabarit.asp?Rubrique=&Recherche=&Entete=Livre&Page=Recherche_wsc.asp&OnlyAvailable=false&Tri='
-        #        req = BASE_URI + "francais/menu/gabarit.asp?Rubrique=&Recherche=&Entete=Livre&Page=Recherche_section_wsc.asp&OnlyAvailable=false&Tri="
-        req += case type
-               when SEARCH_BY_ISBN
-                 'ISBN'
-               when SEARCH_BY_TITLE
-                 'Titre'
-               when SEARCH_BY_AUTHORS
-                 'Auteur'
-               when SEARCH_BY_KEYWORD
-                 ''
-               else
-                 raise InvalidSearchTypeError
-               end
-        req += '&Phrase='
-
-        req += CGI.escape(criterion)
-        p req if $DEBUG
-        data = transport.get(URI.parse(req))
-        begin
-          if type == SEARCH_BY_ISBN
-            return to_books(data).pop
-          else
-            results = []
-            to_books(data).each { |book|
-              results << book
-            }
-            while /Suivant/ =~ data
-              md = /Enteterouge\">([\d]*)<\/b>/.match(data)
-              num = md[1].to_i + 1
-              data = transport.get(URI.parse(req + '&PageActuelle=' + num.to_s))
-              to_books(data).each { |book|
-                results << book
-              }
-            end
-            return results
-          end
-        rescue
-          raise NoResultsError
-        end
-      end
-
-      def url(book)
-        #        "http://www.renaud-bray.com/francais/menu/gabarit.asp?Rubrique=&Recherche=&Entete=Livre&Page=Recherche_section_wsc.asp&OnlyAvailable=false&Tri=ISBN&Phrase=" + book.isbn
-        'http://www.renaud-bray.com/francais/menu/gabarit.asp?Rubrique=&Recherche=&Entete=Livre&Page=Recherche_wsc.asp&OnlyAvailable=false&Tri=ISBN&Phrase=' + book.isbn
-      end
-
-      private
-
-      def to_books(data)
-        data = CGI.unescapeHTML(data)
-        data = data.encode('UTF-8')
-        raise NoResultsError if data =~ /<strong class="Promotion">Aucun article trouv. selon les crit.res demand.s<\/strong>/
-
-        titles = []
-        data.scan(/"(Jeune|Lire)Hyperlien" href.*><strong>([-,'\(\)&\#;\w\s#{ACCENTUATED_CHARS}]*)<\/strong><\/a><br>/).each { |md|
-          titles << md[1].strip
-        }
-        raise if titles.empty?
-        authors = []
-        data.scan(/Nom_Auteur.*><i>([,'.&\#;\w\s#{ACCENTUATED_CHARS}]*)<\/i>/).each { |md|
-          authors2 = []
-          for author in md[0].split('  ')
-            authors2 << author.strip
-          end
-          authors << authors2
-        }
-        raise if authors.empty?
-        isbns = []
-        data.scan(/ISBN : ?<\/td><td>(\d+)/).each { |md|
-          isbns << md[0].strip
-        }
-        raise if isbns.empty?
-        editions = []
-        publish_years = []
-        data.scan(/Parution : <br>(\d{4,}-\d{2,}-\d{2,})/).each { |md|
-          editions << md[0].strip
-          publish_years << md[0].strip.split(/-/)[0].to_i
-        }
-        raise if editions.empty? || publish_years.empty?
-        publishers = []
-        data.scan(/diteur : ([,'.&\#;\w\s#{ACCENTUATED_CHARS}]*)<\/span><br>/).each { |md|
-          publishers << md[0].strip
-        }
-        raise if publishers.empty?
-        book_covers = []
-        data.scan(/(\/ImagesEditeurs\/[\d]*\/([\dX]*-f.(jpg|gif))|\/francais\/suggestion\/images\/livre\/livre.gif)/).each { |md|
-          book_covers << BASE_URI + md[0].strip
-        }
-        raise if book_covers.empty?
-
-        books = []
-        titles.each_with_index { |title, i|
-          books << [Book.new(title, authors[i], isbns[i], publishers[i], publish_years[i], editions[i]),
-                    book_covers[i]]
-          # print books
-        }
-        raise if books.empty?
-
-        books
-      end
-    end
-  end
-end