alexandria-book-collection-manager 0.7.3 → 0.7.4

data/lib/alexandria/book_providers/siciliano.rb

@@ -25,27 +25,27 @@
 # Almost completely rewritten by Cathal Mc Ginley (21 Feb 2009)
 # based on the new code for Palatina
 
-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 SicilianoProvider < WebsiteBasedProvider
       include Logging
 
-      SITE = 'http://www.siciliano.com.br'
+      SITE = "http://www.siciliano.com.br"
 
       # The string interpolations in this URL are the search term and search
       # type, respectively.
       BASE_SEARCH_URL = "#{SITE}/pesquisaweb/pesquisaweb.dll/pesquisa?" \
-        '&FIL_ID=102' \
-        '&PALAVRASN1=%s' \
-        '&FILTRON1=%s' \
-        '&ESTRUTN1=0301&ORDEMN2=E'
+        "&FIL_ID=102" \
+        "&PALAVRASN1=%s" \
+        "&FILTRON1=%s" \
+        "&ESTRUTN1=0301&ORDEMN2=E"
 
       def initialize
-        super('Siciliano', 'Livraria Siciliano (Brasil)')
+        super("Siciliano", "Livraria Siciliano (Brasil)")
         # no preferences for the moment
         prefs.read
       end
@@ -57,7 +57,7 @@ module Alexandria
       end
 
       def search(criterion, type)
-        criterion = criterion.encode('ISO-8859-1') # still needed??
+        criterion = criterion.encode("ISO-8859-1") # still needed??
         trying_again = false
         begin
           req = create_search_uri(type, criterion, trying_again)
@@ -71,12 +71,12 @@ module Alexandria
           else
             results.map { |result| get_book_from_search_result(result) }
           end
-        rescue NoResultsError => err
+        rescue NoResultsError => ex
           if (type == SEARCH_BY_ISBN) && (trying_again == false)
             trying_again = true
             retry
           else
-            raise err
+            raise ex
           end
         end
       end
@@ -90,10 +90,10 @@ module Alexandria
       private
 
       def create_search_uri(search_type, search_term, trying_again = false)
-        (search_type_code = { SEARCH_BY_ISBN    => 'G',
-                              SEARCH_BY_TITLE   => 'A',
-                              SEARCH_BY_AUTHORS => 'B',
-                              SEARCH_BY_KEYWORD => 'X' }[search_type]) || 'X'
+        (search_type_code = { SEARCH_BY_ISBN    => "G",
+                              SEARCH_BY_TITLE   => "A",
+                              SEARCH_BY_AUTHORS => "B",
+                              SEARCH_BY_KEYWORD => "X" }[search_type]) || "X"
         search_term_encoded = if search_type == SEARCH_BY_ISBN
                                 if trying_again
                                   # on second attempt, try ISBN-10...
@@ -123,28 +123,28 @@ module Alexandria
         book_search_results = []
         # each result will be a dict with keys :title, :author, :publisher, :url
 
-        list_items = doc.search('div.pesquisa-item-lista-conteudo')
+        list_items = doc.search("div.pesquisa-item-lista-conteudo")
         list_items.each do |item|
           begin
             result = {}
 
             # author & publisher
-            author_publisher = ''
+            author_publisher = ""
             item.children.each do |node|
               author_publisher += node.to_s if node.text?
               author_publisher.strip!
               break unless author_publisher.empty?
             end
-            author, publisher = author_publisher.split('/')
+            author, publisher = author_publisher.split("/")
             result[:author] = author.strip if author
             result[:publisher] = publisher.strip if publisher
 
             # title & url
-            link = item % 'a'
+            link = item % "a"
             result[:title] = link.inner_text.strip
-            link_to_description = link['href']
-            slash = ''
-            slash = '/' unless link_to_description =~ /^\//
+            link_to_description = link["href"]
+            slash = ""
+            slash = "/" unless %r{^/}.match?(link_to_description)
             result[:url] = "#{SITE}#{slash}#{link_to_description}"
 
             book_search_results << result
@@ -161,38 +161,38 @@ module Alexandria
         # checked against Siciliano website 21 Feb 2009
         doc = html_to_doc(html)
         # title
-        title_div = doc % 'div#conteudo//div.titulo'
+        title_div = doc % "div#conteudo//div.titulo"
         raise NoResultsError unless title_div
 
-        title_h = title_div % 'h2'
+        title_h = title_div % "h2"
         title = title_h.inner_text if title_h
         # title = first_non_empty_text_node(title_div)
         # author_spans = doc/'span.rotulo'
-        author_hs = title_div / 'h3.autor'
+        author_hs = title_div / "h3.autor"
         authors = []
         author_hs.each do |h|
           authors << h.inner_text.strip
         end
         ## synopsis_div = doc % 'div#sinopse'
-        details_div = doc % 'div#tab-caracteristica'
+        details_div = doc % "div#tab-caracteristica"
         details = string_array_to_map(lines_of_text_as_array(details_div))
         # ISBN
-        isbn =  details['ISBN']
+        isbn =  details["ISBN"]
         ## ean = details["CdBarras"]
-        translator = details['Tradutor']
+        translator = details["Tradutor"]
         authors << translator if translator
-        binding = details['Acabamento']
+        binding = details["Acabamento"]
         publisher = search_result[:publisher]
         # publish year
         publish_year = nil
-        edition = details['Edio']
+        edition = details["Edio"]
         if edition
           publish_year = Regexp.last_match[1].to_i if edition =~ /([12][0-9]{3})/ # publication date
         end
         # cover
         # ImgSrc[1]="/imagem/imagem.dll?pro_id=1386929&PIM_Id=658849";
         image_urls = []
-        (doc / 'script').each do |script|
+        (doc / "script").each do |script|
           next if script.children.nil?
 
           script.children.each do |ch|
@@ -213,7 +213,7 @@ module Alexandria
       end
 
       def first_non_empty_text_node(elem)
-        text = ''
+        text = ""
         elem.children.each do |node|
           next unless node.text?
 
@@ -225,28 +225,28 @@ module Alexandria
 
       def lines_of_text_as_array(elem)
         lines = []
-        current_text = ''
+        current_text = ""
         elem.children.each do |e|
           if e.text?
             current_text += e.to_s
-          elsif e.name == 'br'
+          elsif e.name == "br"
             lines << current_text.strip
-            current_text = ''
+            current_text = ""
           else
             current_text += e.inner_text
           end
         end
         lines << current_text.strip
-        lines.delete('')
+        lines.delete("")
         lines
       end
 
       def string_array_to_map(arr)
         map = {}
         arr.each do |str|
-          key, val = str.split(':')
+          key, val = str.split(":")
           # a real hack for not handling encoding properly :^)
-          map[key.gsub(/[^a-zA-Z]/, '')] = val.strip if val
+          map[key.gsub(/[^a-zA-Z]/, "")] = val.strip if val
         end
         map
       end

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
 
-      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
@@ -62,11 +62,11 @@ module Alexandria
 
       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
@@ -80,12 +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
@@ -94,26 +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
@@ -130,8 +130,8 @@ 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
+            if rslt[:lookup_url] =~ %r{/ISBN(\d+[\d-]*)/}
+              if Regexp.last_match[1].delete("-") == isbn10
                 chosen = rslt
                 break
               end
@@ -142,9 +142,9 @@ 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..."
 
@@ -152,7 +152,7 @@ module Alexandria
               authors = []
               author_links = author_h.parent / :a
               author_links.each do |a|
-                if a['href'] =~ /BUCH\/sa/
+                if a["href"] =~ %r{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...
@@ -160,25 +160,25 @@ 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:')
+            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]
@@ -186,10 +186,10 @@ module Alexandria
           end
         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

@@ -4,8 +4,8 @@
 #
 # See the file README.md for authorship and licensing information.
 
-require 'hpricot'
-require 'htmlentities'
+require "hpricot"
+require "htmlentities"
 
 module Alexandria
   class BookProviders
@@ -15,9 +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
@@ -33,7 +33,7 @@ module Alexandria
             nil
           else
             node_text = node.children.map { |n| text_of(n) }.join
-            node_text.strip.squeeze(' ')
+            node_text.strip.squeeze(" ")
           end
         end
         # node.inner_html.strip

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
 
-      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 StandardError => 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
@@ -98,19 +73,19 @@ 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/..'
+          result_cells = doc / "td.result/div.name/.."
           # puts result_cells.length
           result_cells.each do |td|
-            type_icon = (td % 'div.type/img.icn')
-            next unless type_icon && type_icon['src'] =~ /icon-bks/
+            type_icon = (td % "div.type/img.icn")
+            next unless type_icon && type_icon["src"] =~ /icon-bks/
 
-            name_div = td % 'div.name'
+            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
@@ -120,29 +95,29 @@ module Alexandria
           end
         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
@@ -165,7 +140,7 @@ module Alexandria
                   log.info { "book #{book} is a match" }
                   return [book, cover_url]
                 end
-                log.debug { 'not a match, checking next' }
+                log.debug { "not a match, checking next" }
               else
                 # no constraint to match isbn, just return first result
                 return [book, cover_url]
@@ -173,21 +148,21 @@ module Alexandria
             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 { "no more results to check. Returning first result, just an approximation" }
             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
@@ -195,16 +170,16 @@ 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(';')
+            publication_info =~ if publication_info.index(";")
                                   /;[\s]*([^\d]+)[\s]*[\d]*/
-                                elsif publication_info.index(':')
+                                elsif publication_info.index(":")
                                   /:[\s]*([^;:,]+)/
                                 else
                                   /([^;,]+)/
@@ -220,16 +195,16 @@ module Alexandria
 
           isbn = search_isbn
           unless isbn
-            isbn_row = doc % 'tr#details-standardno' # #bibdata_table % 'th[text()*=ISBN]/..'
+            isbn_row = doc % "tr#details-standardno" # #bibdata_table % 'th[text()*=ISBN]/..'
             if isbn_row
-              isbns = (isbn_row / 'td').last.inner_text.split
+              isbns = (isbn_row / "td").last.inner_text.split
               isbn = Library.canonicalise_isbn(isbns.first)
             else
-              log.warn { 'No ISBN found on page' }
+              log.warn { "No ISBN found on page" }
             end
           end
 
-          binding = '' # not given on WorldCat website (as far as I can tell)
+          binding = "" # not given on WorldCat website (as far as I can tell)
 
           book = Book.new(title, authors, isbn, publisher, year, binding)
 
@@ -240,10 +215,10 @@ module Alexandria
           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