Created
June 4, 2015 16:42
-
-
Save ostephens/75f53bcf65821e72dedb to your computer and use it in GitHub Desktop.
Extract URL from 856$u in MARC (Ruby)
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
!/usr/bin/ruby | |
require 'rubygems' | |
require 'marc' | |
require 'optparse' | |
require 'CSV' | |
options = {} | |
OptionParser.new do |opts| | |
opts.banner = "Usage: 001-856.rb [options]" | |
opts.on("-f", "--format [FORMAT]","Specify format of files to be converted. Currently supported 'marcxml' and 'marc'") do |f| | |
options[:format] = f | |
end | |
opts.on("-s", "--sourcefile [SOURCEFILE]","Specify source file") do |s| | |
options[:sourcefile] = s | |
end | |
opts.on_tail("-h", "--help", "Show this message") do | |
puts opts | |
exit | |
end | |
end.parse! | |
sourcefile = options[:sourcefile] | |
format = options[:format] | |
# reading records from a batch file | |
if(format == "marcxml") | |
reader = MARC::XMLReader.new(sourcefile) | |
elsif(format == "marc") | |
reader = MARC::Reader.new(sourcefile, :external_encoding => "UTF-8", :invalid => :replace) | |
else | |
puts "Not a recognised format. Currently accept 'marcxml' or 'marc'" | |
exit | |
end | |
for record in reader | |
record.each_by_tag('856') {|field| | |
puts record['001'].value.to_s + "," + field['u'].to_s | |
} | |
end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment