Internet Archive / Open Library TSV file to XML for Alma import profile as portfolios

open_library_tsv_to_xml_for_alma.py

# -*- coding: utf-8 -*-
"""

Build XML file of all our books' data for lending
for the purposes of short-term management of our electronic lending
collection in Alma

"""

import os


def xml_record(mmsid, search_id):
    ''' just generate a single record for the xml files '''
    xml = '''    <record xmlns="http://www.loc.gov/MARC21/slim">
      <controlfield tag="001">'''
    xml += str(mmsid)
    xml += '''</controlfield>
      <datafield tag="999" ind1=" " ind2=" ">
         <subfield code="u">https://archive.org/details/'''
    xml += search_id
    xml += '''</subfield> 
         <subfield code="a">Create a free account with the Internet Archive to read online. PDF and EPUB versions are also available for use with Adobe Digital Editions.</subfield>
         <subfield code="p">Digitized copy may be available for checkout.</subfield>'
      </datafield>
    </record>
'''
    return xml


if __name__ == "__main__":
    workingdir = r"G:\My Drive\Alma - IA dump"
    inputfile = os.path.join(workingdir, "FINAL-gl-inlibrary-matches.tsv")
    xml = '''<?xml version="1.0" encoding="UTF-8" ?>
<collection>
'''    
    with open(inputfile, 'r') as fh:
        lines = fh.read().splitlines()
    for line in lines:
        search_id = line.split()[1]
        mmsid = line.split()[2]
        xml += xml_record(mmsid, search_id)
    xml += '</collection>'
    with open(os.path.join(workingdir, 'ia_import.xml'), 'w') as fh:
        fh.write(xml)