Library Software
From assela Pathirana
Jump to navigationJump to search
ISBN2MARC
- Original source code here. Following is provided for consistency only. (Full credit should go to William Denton).
#!/usr/local/bin/ruby -w
# isbn2marc - find MARC records for one or more ISBNs
# William Denton <wtd@pobox.com>
# April 2007 - October 2008
# Released under the MIT License.
# Copyright (c) 2008 William Denton
#
# Permission is hereby granted, free of charge, to any person
# obtaining a copy of this software and associated documentation
# files (the "Software"), to deal in the Software without
# restriction, including without limitation the rights to use,
# copy, modify, merge, publish, distribute, sublicense, and/or sell
# copies of the Software, and to permit persons to whom the
# Software is furnished to do so, subject to the following
# conditions:
#
# The above copyright notice and this permission notice shall be
# included in all copies or substantial portions of the Software.
#
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
# OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
# HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
# WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
# FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
# OTHER DEALINGS IN THE SOFTWARE.
# INSTALLATION NOTES
#
# Requires the ruby-zoom package (which requires YAZ) and the marc gem.
#
# ruby-zoom: http://ruby-zoom.rubyforge.org/
# See the installation instructions there
#
# marc gem: http://rubyforge.org/projects/marc/
# $ sudo gem install marc
#
# NOTE ruby-zoom installs its own marc.rb file that will conflict with
# marc! You will need to delete ruby-zoom's marc.rb or rename it
# for the marc gem to work.
#
# On my system it was installed in
# /usr/local/lib/ruby/site_ruby/1.8/marc.rb
# but you'll have to look for it wherever your system put it.
# USAGE
#
# isbn2marc [-q] [-d marcfile] [-x xmlfile] ISBN
#
# -q Run quietly, don't list servers queried and don't
# --quiet dump MARC to STDOUT
# By default isbn2marc tells STDERR what it's doing
#
# -d marcfile Dump MARC record to file
# --dump
#
# -x xmlfile Dump MARCXML record to file
# --dumpxml
#
# -w apikey Query WorldCat using API key
# --worldcat
#
# -l level WorldCat service level (default or full)
# --worldcatlevel Default is default
# EXAMPLES
#
# Find a MARC record for the first volume of Casanova's HISTORY OF
# MY LIFE and pretty print it:
#
# $ isbn2marc 0801856620
#
# Find a MARC record for Terry Pratchett's THIEF OF TIME and write
# a binary MARC file to disk as well as pretty printing it:
#
# $ isbn2marc -d thief.marc 0552148407
#
# Find a MARC record for the first omnibus volume of the University of
# Chicago Press's edition of Anthony Powell's A DANCE TO THE MUSIC OF TIME,
# but don't show the record on the screen:
#
# $ isbn2marc -q -d stringham.marc -x templer.xml 0226677141
#
# Find MARC records for all ISBNs in a file and save them on disk:
#
# $ cat isbns.txt
# 0439064864
# 0439064872
# 0439136350
# 0439136369
# 0439139600
# 059035342X
# 0736646736
# $ isbn2marc -f isbns.txt -d harry-potter.marc
#
# Try WorldCat first, which will speed things up, and get a full record:
#
# $isbn2marc --worldcat yourAPIkeyhere --worldcatlevel full 1551922460
#
# Find a MARC record but don't display it or save it:
#
# $ isbn2marc -q 0195024028
#
# You'd be a bit silly to run that often.
# TO DO
#
# Proper ISBN validity check.
require 'net/http'
require 'optparse'
require "rexml/document"
include REXML
require 'rubygems'
require 'marc'
require 'zoom'
# I don't know if it's cool to use global variables for these
# options, or for the MARC writer and xmlwriter thingies, but
# I am because of the write_record function. Comments welcome.
$options = {}
$options[:quiet] = false
$options[:file] = nil
$options[:dump] = nil
$options[:dumpxml] = nil
# Enter your WorldCat API key here.
# It can also be specified on the command line but that's tiresome.
# To get a key, see
# http://worldcat.org/devnet/wiki/SearchAPIWhoCanUse
# For WorldCat API details see
# http://worldcat.org/devnet/wiki/SearchAPIDetails
$options[:worldcat] = ''
$options[:worldcatlevel]= 'default' # Or full
OptionParser.new do |opts|
opts.banner = "Usage: isbn2marc [-q] [-d marcfile] [-x xmlfile] isbn"
opts.on("-q", "--quiet", "Run silently") { $options[:quiet] = true }
opts.on("-d", "--dump d", "Dump MARC to file d") do |d|
$options[:dump] = d
end
opts.on("-x", "--dumpxml x", "Dump MARCXML to file x") do |x|
$options[:dumpxml] = x
end
opts.on("-f", "--file f", String, "Read ISBNs from file f (one per line)") do |f|
$options[:file] = f
end
opts.on("-w", "--worldcat apikey", String, "WorldCat API key") do |w|
$options[:worldcat] = w
end
opts.on("-l", "--worldcatlevel level", String, "WorldCat service level (default or full)") do |wl|
$options[:worldcatlevel] = wl
end
end.parse!
# Probably won't change, but one never knows.
worldcatAPIURL = "http://www.worldcat.org/webservices/catalog/content/isbn/::ISBN::?servicelevel=::LEVEL::&wskey=::KEY::"
isbns = []
if $options[:file].nil?
if ARGV.empty?
STDERR.puts "No ISBN specified"
exit 0
end
else
begin
file = File.open($options[:file], "r")
while (line = file.gets)
line.chomp!
# TODO Proper ISBN validity check
next unless /(978)*\d{9}[0-9X]/.match(line)
# puts "'#{line}'"
isbns << line.gsub(/[^0-9X]/, '')
end
file.close
rescue Exception => e
STDERR.puts "ERROR '#{e}'"
end
end
if ! ARGV.empty?
isbns << ARGV[0].to_s.gsub(/[^0-9X]/, '')
end
if $options[:dump]
begin
$writer = MARC::Writer.new($options[:dump])
rescue Exception => e
STDERR.puts "ERROR Cannot write to #{$options[:dump]}: '#{e}'"
exit 0
end
end
if $options[:dumpxml]
begin
$xmlwriter = MARC::XMLWriter.new($options[:dumpxml])
rescue Exception => e
STDERR.puts "ERROR Cannot write to #{$options[:dumpxml]}: '#{e}'"
exit 0
end
end
# Two lists of open Z39.50 servers:
# http://targettest.indexdata.com/
# http://staff.library.mun.ca/staff/toolbox/z3950hosts.htm
# Could also look at the list in Terry Reese's MarcEdit:
# http://oregonstate.edu/~reeset/marcedit/html/downloads.html
servers = [
# Reorder these so that your preferred servers are first
# North America
['theta.library.yorku.ca', 2200, 'unicorn' ], # York
['sirsi.library.utoronto.ca', 2200, 'unicorn' ], # U Toronto
['amicus.collectionscanada.gc.ca', 210, 'NL' ], # Lib & Archives Canada
['z3950.loc.gov', 7090, 'Voyager' ], # Library of Congress
['aleph.mcgill.ca', 210, 'MUSE' ], # McGill
# ['ualapp.library.ualberta.ca', 2200, 'unicorn', ], # U Alberta
['portage.library.ubc.ca', 7090, 'voyager' ], # UBC
['catnyp.nypl.org', 210, 'INNOPAC' ], # New York Pub Lib
['library.mit.edu', 9909, 'mit01pub' ], # MIT
['prodorbis.library.yale.edu', 7090, 'voyager' ], # Yale
['catalog.princeton.edu', 7090, 'voyager' ], # Princeton
['ipac.lib.uchicago.edu', 210, 'usmarc' ], # Chicago
['www.saclibrarycatalog.org', 210, 'INNOPAC' ], # Sacramento Pub Lib
['library.bu.edu', 210, 'INNOPAC' ], # Boston U
['voyager.wrlc.org', 7090, 'voyager' ], # Wash Res Lib Consor
['catalog.lib.jhu.edu', 210, 'horizon' ], # Johns Hopkins
['z3950.lib.umich.edu', 210, 'miu01_pub' ], # U Michigan
['catalog.library.cornell.edu',7090, 'voyager' ], # Cornell
# UK and Ireland
['library.ucc.ie', 210, 'INNOPAC' ], # U College Cork
['library.ox.ac.uk', 210, 'MAIN*BIBMAST'], # Oxford
['z3950.nls.uk', 7290, 'voyager' ], # Scottish Nat Lib
['lib-15.lse.ac.uk', 7090, 'voyager' ], # LSE
['libsys.lib.hull.ac.uk', 210, 'INNOPAC' ], # Hull
# Europe (non-English)
['sigma.nkp.cz', 9909, 'NKC' ], # Nat Lib Czech R
['lib.mpib-berlin.mpg.de', 2020, 'opac' ], # Max Planck Inst
['ubsun02.biblio.etc.tu-bs.de',2020, 'bac' ], # Bibliotheken Berlins
['z3950.kb.dk', 2100, 'KGL01' ], # Kongelige Bibliothek
['roble.unizar.es', 210, 'INNOPAC' ], # U Zaragoza
['www.helmet.fi', 210, 'INNOPAC' ], # Helsinki Lib
['carmin.sudoc.abes.fr', 210, 'ABES-Z39-PUBLIC' ], # France
['gofor.bibli.ens-cachan.fr', 21210, 'ADVANCE' ], # French school
['gofor.bibli.ens-cachan.fr', 21210, 'MAIN*BIBMAST'], # French school
['isis.cilea.it', 2100, 'usmarc' ], # U Brescia
['z3950.bibsys.no', 2100, 'BIBSYS' ], # Nat Lib Norway
['z3950.nb.no', 2100, 'norbok' ], # Nat Lib Norway
['alpha.bn.org.pl', 210, 'INNOPAC' ], # Nat Lib Poland
['z3950.btj.se', 210, 'BURK' ], # Sweden
# Australia and New Zealand
['catalogue.nla.gov.au', 7090, 'voyager' ], # Nat Lib Australia
['nlnzcat.natlib.govt.nz', 7190, 'voyager' ], # Nat Lib New Zealand
# Asia
['library.cuhk.edu.hk', 210, 'INNOPAC' ], # Chinesse U HK
['linc.nus.edu.sg', 210, 'INNOPAC' ], # Nat U Singapore
['nbinet.ncl.edu.tw', 210, 'INNOPAC' ], # Nat Cent Lib Taiwan
# Africa
['explore.up.ac.za', 210, 'INNOPAC' ], # U Pretoria
]
# Given an ISBN and some Z39.50 server information, return MARCXML.
# Why MARCXML? Because (now) the ruby-zoom module can't return a
# marc MARC object. It can, however, return MARCXML, which marc can
# grok.
def z3950query (isbn, host, port, db)
begin
ZOOM::Connection.open(host, port) do |conn|
conn.database_name = db
conn.preferred_record_syntax = 'MARC21'
rset = conn.search("@attr 1=7 #{isbn}")
return rset[0].xml
end
rescue Exception => e
STDERR.puts "\nERROR Z39.50 query: '#{e}'" if /failed/.match(e)
return nil
end
end
# Given a MARC reader object, write out the records therein, to
# STDOUT or disk, in the desired format.
# TODO Write out only the *first* one. (Why?)
def write_record (marcxml)
reader = MARC::XMLReader.new(StringIO.new(marcxml))
begin
reader.each do |record|
puts; puts record unless $options[:quiet] == true
$writer.write(record) if $options[:dump]
$xmlwriter.write(record) if $options[:dumpxml]
end
rescue Exception => e
STDERR.puts "\nERROR Record not read: '#{e}'"
end
end
# Now the real business. If we can check WorldCat, do so, because
# it's the best source. If we can't, or if it fails, loop through all
# the servers listed above and ask about the ISBN(s).
isbns.each do |isbn|
if $options[:worldcat].length > 0
STDERR.print "\r#{isbn} WorldCat" + " "*25 unless $options[:quiet] == true
worldcatURL = worldcatAPIURL.gsub(/::ISBN::/, isbn)
worldcatURL = worldcatURL.gsub(/::KEY::/, $options[:worldcat])
worldcatURL = worldcatURL.gsub(/::LEVEL::/, $options[:worldcatlevel])
# STDERR.print "\nGetting #{worldcatURL}"
worldcat_xml = Net::HTTP.get_response(URI.parse(worldcatURL)).body
doc = REXML::Document.new worldcat_xml
error = doc.elements['//diagnostics/diagnostic/message'].nil? ? nil : doc.elements['//diagnostics/diagnostic/message'].text
if error.nil?
write_record(worldcat_xml)
next
else
STDERR.puts "\nERROR from WorldCat: #{error}"
end
end
servers.each do |server|
STDERR.print "\r#{isbn} #{server[0]}" + " "*25 unless $options[:quiet] == true
marcxml = z3950query(isbn, server[0], server[1], server[2])
next if marcxml.nil?
write_record(marcxml)
break
end
end
$writer.close if $options[:dump]
$xmlwriter.close if $options[:dumpxml]
- Essential ruby installation:
wget http://rubyforge.org/frs/download.php/38646/rubygems-1.2.0.tgz
tar -xzvf rubygems-1.2.0.tgz
cd rubygems-1.2.0/
sudo ruby setup.rb
sudo gem update --system
sudo apt-get install libyaz-dev
sudo gem install zoom
sudo gem install marc
