alexandria-book-collection-manager 0.7.2 → 0.7.7

data/lib/alexandria/book_providers/thalia.rb

@@ -24,20 +24,20 @@
 # New Tlalia provider, taken from Palatina MetaDataSource and modified
 # for Alexandria. (21 Dec 2009)
 
-require 'net/http'
-require 'cgi'
-require 'alexandria/book_providers/web'
+require "net/http"
+require "cgi"
+require "alexandria/book_providers/web"
 
 module Alexandria
   class BookProviders
     class ThaliaProvider < WebsiteBasedProvider
-      include Alexandria::Logging
+      include Logging
 
-      SITE = 'http://www.thalia.de'
+      SITE = "http://www.thalia.de"
       BASE_SEARCH_URL = "#{SITE}/shop/bde_bu_hg_startseite/suche/?%s=%s" # type,term
 
       def initialize
-        super('Thalia', 'Thalia (Germany)')
+        super("Thalia", "Thalia (Germany)")
         # no preferences for the moment
         prefs.read
       end
@@ -48,24 +48,25 @@ module Alexandria
 
       def search(criterion, type)
         req = create_search_uri(type, criterion)
-        puts req if $DEBUG
+        log.debug { req }
         html_data = transport.get_response(URI.parse(req))
         if type == SEARCH_BY_ISBN
           parse_result_data(html_data.body, criterion)
         else
           results = parse_search_result_data(html_data.body)
           raise NoResultsError if results.empty?
+
           results.map { |result| get_book_from_search_result(result) }
         end
       end
 
       def create_search_uri(search_type, search_term)
         (search_type_code = {
-          SEARCH_BY_ISBN => 'sq',
-          SEARCH_BY_AUTHORS => 'sa', # Autor
-          SEARCH_BY_TITLE => 'st', # Titel
-          SEARCH_BY_KEYWORD => 'ssw' # Schlagwort
-        }[search_type]) || ''
+          SEARCH_BY_ISBN    => "sq",
+          SEARCH_BY_AUTHORS => "sa", # Autor
+          SEARCH_BY_TITLE   => "st", # Titel
+          SEARCH_BY_KEYWORD => "ssw" # Schlagwort
+        }[search_type]) || ""
         search_type_code = CGI.escape(search_type_code)
         search_term_encoded = if search_type == SEARCH_BY_ISBN
                                 # search_term_encoded = search_term.as_isbn_13
@@ -79,12 +80,12 @@ module Alexandria
       def parse_search_result_data(html)
         doc = html_to_doc(html)
         book_search_results = []
-        results_divs = doc / 'div.articlePresentationSearchCH'
+        results_divs = doc / "div.articlePresentationSearchCH"
         results_divs.each do |div|
           result = {}
-          title_link = div % 'div.articleText/h2/a'
+          title_link = div % "div.articleText/h2/a"
           result[:title] = title_link.inner_html
-          result[:lookup_url] = title_link['href']
+          result[:lookup_url] = title_link["href"]
           book_search_results << result
         end
         book_search_results
@@ -93,26 +94,26 @@ module Alexandria
       def data_from_label(node, label_text)
         label_node = node % "strong[text()*='#{label_text}']"
         if (item_node = label_node.parent)
-          data = ''
+          data = ""
           item_node.children.each do |n|
             data += n.to_html if n.text?
           end
           data.strip
         else
-          ''
+          ""
         end
       end
 
       def get_book_from_search_result(result)
         log.debug { "Fetching book from #{result[:lookup_url]}" }
         html_data = transport.get_response(URI.parse(result[:lookup_url]))
-        parse_result_data(html_data.body, 'noisbn', true)
+        parse_result_data(html_data.body, "noisbn", true)
       end
 
       def parse_result_data(html, isbn, recursing = false)
         doc = html_to_doc(html)
 
-        results_divs = doc / 'div.articlePresentationSearchCH'
+        results_divs = doc / "div.articlePresentationSearchCH"
         unless results_divs.empty?
           if recursing
             # already recursing, avoid doing so endlessly second time
@@ -120,6 +121,7 @@ module Alexandria
             # list
             return
           end
+
           # ISBN-lookup results in multiple results (trying to be
           # useful, such as for new editions e.g. 9780974514055
           # "Programming Ruby" )
@@ -128,11 +130,10 @@ module Alexandria
           # e.g. .../dave_thomas/ISBN0-9745140-5-5/ID6017044.html
           chosen = results.first # fallback!
           results.each do |rslt|
-            if rslt[:lookup_url] =~ /\/ISBN(\d+[\d-]*)\//
-              if Regexp.last_match[1].delete('-') == isbn10
-                chosen = rslt
-                break
-              end
+            if rslt[:lookup_url] =~ %r{/ISBN(\d+[\d-]*)/} &&
+                (Regexp.last_match[1].delete("-") == isbn10)
+              chosen = rslt
+              break
             end
           end
           html_data = transport.get_response(URI.parse(chosen[:lookup_url]))
@@ -140,9 +141,9 @@ module Alexandria
         end
 
         begin
-          if (div = doc % 'div#contentFull')
+          if (div = doc % "div#contentFull")
             title_img = ((div % :h2) / :img).first
-            title = title_img['alt']
+            title = title_img["alt"]
 
             # note, the following img also has alt="von Author, Author..."
 
@@ -150,7 +151,7 @@ module Alexandria
               authors = []
               author_links = author_h.parent / :a
               author_links.each do |a|
-                if a['href'] =~ /BUCH\/sa/
+                if a["href"].include? "BUCH/sa"
                   # 'sa' means search author, there may also be 'ssw' (search keyword) links
                   authors << a.inner_text[0..-2].strip
                   # NOTE stripping the little >> character here...
@@ -158,36 +159,36 @@ module Alexandria
               end
             end
 
-            item_details = doc % 'ul.itemDataList'
+            item_details = doc % "ul.itemDataList"
             isbns = []
-            isbns << data_from_label(item_details, 'EAN')
-            isbns << data_from_label(item_details, 'ISBN')
+            isbns << data_from_label(item_details, "EAN")
+            isbns << data_from_label(item_details, "ISBN")
 
             year = nil
-            date = data_from_label(item_details, 'Erschienen:')
-            year = Regexp.last_match[1].to_i if date =~ /([\d]{4})/
+            date = data_from_label(item_details, "Erschienen:")
+            year = Regexp.last_match[1].to_i if date =~ /(\d{4})/
 
-            binding = data_from_label(item_details, 'Einband')
+            binding = data_from_label(item_details, "Einband")
 
-            publisher = data_from_label(item_details, 'Erschienen bei:')
+            publisher = data_from_label(item_details, "Erschienen bei:")
 
             book = Book.new(title, authors, isbns.first,
                             publisher, year, binding)
 
             image_url = nil
-            if (image_link = doc % 'a[@id=itemPicStart]')
-              image_url = image_link['href']
+            if (image_link = doc % "a[@id=itemPicStart]")
+              image_url = image_link["href"]
             end
 
-            return [book, image_url]
+            [book, image_url]
 
           end
-        rescue => ex
+        rescue StandardError => ex
           trace = ex.backtrace.join("\n> ")
-          log.warn {
-            'Failed parsing search results for Thalia ' \
+          log.warn do
+            "Failed parsing search results for Thalia " \
             "#{ex.message} #{trace}"
-          }
+          end
           raise NoResultsError
         end
       end

data/lib/alexandria/book_providers/web.rb

@@ -1,27 +1,11 @@
 # frozen_string_literal: true
 
-# -*- ruby -*-
+# This file is part of Alexandria.
 #
-# Copyright (C) 2009 Cathal Mc Ginley
-# Copyright (C) 2014 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.
+# See the file README.md for authorship and licensing information.
 
-require 'hpricot'
-require 'htmlentities'
+require "hpricot"
+require "htmlentities"
 
 module Alexandria
   class BookProviders
@@ -31,9 +15,9 @@ module Alexandria
         @htmlentities = HTMLEntities.new
       end
 
-      def html_to_doc(html, source_data_charset = 'ISO-8859-1')
+      def html_to_doc(html, source_data_charset = "ISO-8859-1")
         html.force_encoding source_data_charset
-        utf8_html = html.encode('utf-8')
+        utf8_html = html.encode("utf-8")
         normalized_html = @htmlentities.decode(utf8_html)
         Hpricot(normalized_html)
       end
@@ -42,19 +26,17 @@ module Alexandria
       def text_of(node)
         if node.nil?
           nil
-        else
-          if node.text?
-            node.to_html
-          elsif node.elem?
-            if node.children.nil?
-              nil
-            else
-              node_text = node.children.map { |n| text_of(n) }.join
-              node_text.strip.squeeze(' ')
-            end
+        elsif node.text?
+          node.to_html
+        elsif node.elem?
+          if node.children.nil?
+            nil
+          else
+            node_text = node.children.map { |n| text_of(n) }.join
+            node_text.strip.squeeze(" ")
           end
-          # node.inner_html.strip
         end
+        # node.inner_html.strip
       end
     end
   end

data/lib/alexandria/book_providers/worldcat.rb

@@ -1,24 +1,9 @@
 # frozen_string_literal: true
 
-# -*- ruby -*-
+# This file is part of Alexandria.
 #
-# Copyright (C) 2009 Cathal Mc Ginley
-# Copyright (C) 2011, 2014 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.
+# See the file README.md for authorship and licensing information.
+# frozen_string_literal: true
 
 # http://en.wikipedia.org/wiki/WorldCat
 # See http://www.oclc.org/worldcat/policies/terms/
@@ -30,34 +15,27 @@
 # Updated from Palatina, to reflect changes in the worldcat website.
 # (1 Sep 2009)
 
-require 'cgi'
-require 'alexandria/net'
-require 'alexandria/book_providers/web'
+require "cgi"
+require "alexandria/net"
+require "alexandria/book_providers/web"
 
 module Alexandria
   class BookProviders
     class WorldCatProvider < WebsiteBasedProvider
-      include Alexandria::Logging
+      include Logging
 
-      SITE = 'http://www.worldcat.org'
+      SITE = "https://www.worldcat.org"
       BASE_SEARCH_URL = "#{SITE}/search?q=%s%s&qt=advanced" # type, term
 
       def initialize
-        super('WorldCat', 'WorldCat')
-        # prefs.add("enabled", _("Enabled"), true, [true,false])
+        super("WorldCat", "WorldCat")
         prefs.read
       end
 
       def search(criterion, type)
-        # puts create_search_uri(type, criterion)
         req = create_search_uri(type, criterion)
-        puts req if $DEBUG
         html_data = transport.get_response(URI.parse(req))
-        # Note: I tried to use Alexandria::WWWAgent,
-        #       but this caused failures here (empty pages...)
-        #       find out how the requests differ
 
-        # puts html_data.class
         if type == SEARCH_BY_ISBN
           parse_result_data(html_data.body, criterion)
         else
@@ -70,18 +48,15 @@ module Alexandria
 
       def url(book)
         create_search_uri(SEARCH_BY_ISBN, book.isbn)
-      rescue => ex
-        log.warn { "Cannot create url for book #{book}; #{ex.message}" }
-        nil
       end
 
       private
 
       def create_search_uri(search_type, search_term)
-        (search_type_code = { SEARCH_BY_ISBN => 'isbn:',
-                              SEARCH_BY_AUTHORS => 'au:',
-                              SEARCH_BY_TITLE => 'ti:',
-                              SEARCH_BY_KEYWORD => '' }[search_type]) || ''
+        (search_type_code = { SEARCH_BY_ISBN    => "isbn:",
+                              SEARCH_BY_AUTHORS => "au:",
+                              SEARCH_BY_TITLE   => "ti:",
+                              SEARCH_BY_KEYWORD => "" }[search_type]) || ""
         search_type_code = CGI.escape(search_type_code)
         search_term_encoded = if search_type == SEARCH_BY_ISBN
                                 Library.canonicalise_ean(search_term) # isbn-13
@@ -98,18 +73,18 @@ module Alexandria
       end
 
       def parse_search_result_data(html)
-        doc = html_to_doc(html, 'UTF-8')
+        doc = html_to_doc(html, "UTF-8")
         book_search_results = []
         begin
-          result_cells = doc / 'td.result/div.name/..'
-          # puts result_cells.length
+          result_cells = doc / "td.result/div.name/.."
           result_cells.each do |td|
-            type_icon = (td % 'div.type/img.icn')
-            next unless type_icon && type_icon['src'] =~ /icon-bks/
-            name_div = td % 'div.name'
+            type_icon = (td % "div.type/img.icn")
+            next unless type_icon && type_icon["src"].include?("icon-bks")
+
+            name_div = td % "div.name"
             title = name_div.inner_text
             anchor = name_div % :a
-            url = anchor['href'] if anchor
+            url = anchor["href"] if anchor
             lookup_url = "#{SITE}#{url}"
             result = {}
             result[:title] = title
@@ -117,31 +92,31 @@ module Alexandria
 
             book_search_results << result
           end
-        rescue => ex
+        rescue StandardError => ex
           trace = ex.backtrace.join("\n> ")
-          log.warn {
-            'Failed parsing search results for WorldCat ' \
+          log.warn do
+            "Failed parsing search results for WorldCat " \
                     "#{ex.message} #{trace}"
-          }
+          end
         end
         book_search_results
       end
 
       def parse_result_data(html, search_isbn = nil, recursing = false)
-        doc = html_to_doc(html, 'UTF-8')
+        doc = html_to_doc(html, "UTF-8")
 
         begin
-          if doc % 'div#div-results-none'
-            log.debug { 'WorldCat reports no results' }
+          if doc % "div#div-results-none"
+            log.debug { "WorldCat reports no results" }
             raise NoResultsError
           end
 
-          if doc % 'table.table-results'
+          if doc % "table.table-results"
             if recursing
-              log.warn { 'Infinite loop prevented redirecting through WorldCat' }
+              log.warn { "Infinite loop prevented redirecting through WorldCat" }
               raise NoResultsError
             end
-            log.info { 'Found multiple results for lookup: checking each' }
+            log.info { "Found multiple results for lookup: checking each" }
             search_results = parse_search_result_data(html)
             book = nil
             cover_url = nil
@@ -153,40 +128,39 @@ module Alexandria
               html2 = rslt2.body
 
               book, cover_url = parse_result_data(html2, search_isbn, true)
-              first_result = [book, cover_url] if first_result.nil?
 
               log.debug { "got book #{book}" }
 
-              if search_isbn
-                search_isbn_canon = Library.canonicalise_ean(search_isbn)
-                rslt_isbn_canon = Library.canonicalise_ean(book.isbn)
-                if search_isbn_canon == rslt_isbn_canon
-                  log.info { "book #{book} is a match" }
-                  return [book, cover_url]
-                end
-                log.debug { 'not a match, checking next' }
-              else
-                # no constraint to match isbn, just return first result
+              return [book, cover_url] unless search_isbn
+
+              first_result = [book, cover_url] if first_result.nil?
+
+              search_isbn_canon = Library.canonicalise_ean(search_isbn)
+              rslt_isbn_canon = Library.canonicalise_ean(book.isbn)
+              if search_isbn_canon == rslt_isbn_canon
+                log.info { "book #{book} is a match" }
                 return [book, cover_url]
               end
+              log.debug { "not a match, checking next" }
             end
 
             # gone through all and no ISBN match, so just return first result
-            log.info { 'no more results to check. Returning first result, just an approximation' }
+            log.info do
+              "no more results to check. Returning first result, just an approximation"
+            end
             return first_result
-
           end
 
-          title_header = doc % 'h1.title'
+          title_header = doc % "h1.title"
           title = title_header.inner_text if title_header
           unless title
-            log.warn { 'Unexpected lack of title from WorldCat lookup' }
+            log.warn { "Unexpected lack of title from WorldCat lookup" }
             raise NoResultsError
           end
           log.info { "Found book #{title} at WorldCat" }
 
           authors = []
-          authors_tr = doc % 'tr#details-allauthors'
+          authors_tr = doc % "tr#details-allauthors"
           if authors_tr
             (authors_tr / :a).each do |a|
               authors << a.inner_text
@@ -194,17 +168,17 @@ module Alexandria
           end
 
           # can we do better? get the City name?? or multiple publishers?
-          bibdata = doc % 'div#bibdata'
+          bibdata = doc % "div#bibdata"
           bibdata_table = bibdata % :table
-          publisher_row = bibdata_table % 'th[text()*=Publisher]/..'
+          publisher_row = bibdata_table % "th[text()*=Publisher]/.."
 
           if publisher_row
-            publication_info = (publisher_row / 'td').last.inner_text
+            publication_info = (publisher_row / "td").last.inner_text
 
-            publication_info =~ if publication_info.index(';')
-                                  /;[\s]*([^\d]+)[\s]*[\d]*/
-                                elsif publication_info.index(':')
-                                  /:[\s]*([^;:,]+)/
+            publication_info =~ if publication_info.index(";")
+                                  /;\s*([^\d]+)\s*\d*/
+                                elsif publication_info.index(":")
+                                  /:\s*([^;:,]+)/
                                 else
                                   /([^;,]+)/
                                 end
@@ -217,34 +191,33 @@ module Alexandria
             year = nil
           end
 
-          isbn = search_isbn
-          unless isbn
-            isbn_row = doc % 'tr#details-standardno' # #bibdata_table % 'th[text()*=ISBN]/..'
-            if isbn_row
-              isbns = (isbn_row / 'td').last.inner_text.split
-              isbn = Library.canonicalise_isbn(isbns.first)
-            else
-              log.warn { 'No ISBN found on page' }
-            end
+          isbn_row = doc % "tr#details-standardno"
+          if isbn_row
+            isbns = (isbn_row / "td").last.inner_text.split
+            isbn = Library.canonicalise_isbn(isbns.first)
+          else
+            log.warn { "No ISBN found on page" }
+            isbn = search_isbn
           end
 
-          binding = '' # not given on WorldCat website (as far as I can tell)
+          book_binding = "" # not given on WorldCat website (as far as I can tell)
 
-          book = Book.new(title, authors, isbn, publisher, year, binding)
+          book = Book.new(title, authors, isbn, publisher, year, book_binding)
 
           image_url = nil # hm, it's on the website, but uses JavaScript...
 
-          return [book, image_url]
-        rescue => ex
+          [book, image_url]
+        rescue StandardError => ex
           raise ex if ex.instance_of? NoResultsError
+
           trace = ex.backtrace.join("\n> ")
-          log.warn {
-            'Failed parsing search results for WorldCat ' \
+          log.warn do
+            "Failed parsing search results for WorldCat " \
                     "#{ex.message} #{trace}"
-          }
+          end
           raise NoResultsError
         end
       end
-    end # class WorldCatProvider
-  end # class BookProviders
-end # module Alexandria
+    end
+  end
+end