Use lxml to validate an XML file against a Schema (XSD)

xml_validation.py

# -*- coding: utf-8 -*-
""" Purpose: Use lxml to validate an XML file against a Schema (XSD)

Created: 2017-09-27
Author:  dhohls@csir.co.za

Requires::

    pip install lxml

Usages::

    python xml_validation.py -s myschema.xsd -x myxml.xml
    python xml_validation.py y -s myschema.xsd -x myxml.xml -ll=DEBUG
"""
from __future__ import print_function
import argparse
import logging
import sys
# third party
from lxml import etree

log = logging.getLogger(__name__)


def main(args):
    filename_xsd = args.xsd
    filename_xml = args.xml
    logging.basicConfig(
        stream=sys.stdout,
        format='%(asctime)s %(levelname)-8s [%(filename)s:%(lineno)d %(funcName)s()] %(message)s',
        level=getattr(logging, args.loglevel))
    
    # check xml
    try:
        doc = etree.parse(filename_xml)
        log.debug('XML well formed, syntax ok.')
    except IOError as err:
        log.error(err)
        quit()
    except etree.XMLSyntaxError as err:
        log.error('XML Syntax Error, see error_syntax.log')
        with open('error_syntax.log', 'w') as error_log_file:
            error_log_file.write(str(err.error_log))
        quit()
    except Exception as err:
        log.error(err)
        quit()

    # check xsd
    try:
        xmlschema_doc = etree.parse(filename_xsd)
        xmlschema = etree.XMLSchema(xmlschema_doc)
    except IOError as err:
        log.error(err)
        quit()
    except Exception as err:
        log.error(err)
        quit()

    # validate xml against schema
    try:
        xmlschema.assertValid(doc)
        log.debug('XML valid, schema validation ok.')
    except etree.DocumentInvalid as err:
        log.error('Schema validation error, see error_schema.log')
        with open('error_schema.log', 'w') as error_log_file:
            error_log_file.write(str(err.error_log))
        quit()
    except Exception as err:
        log.error(err)
        quit()


if __name__ == "__main__":
    parser = argparse.ArgumentParser()
    parser.add_argument(
        '-x', '--xml',
        help="Name of XML data file")
    parser.add_argument(
        '-s', '--xsd',
        help="Name of XSD schema file")
    parser.add_argument(
        '-ll', '--loglevel', default='WARNING',
        choices=['DEBUG', 'INFO', 'WARNING', 'ERROR', 'CRITICAL'],
        help="Set log level for process (%s)" % 'WARNING')
    args = parser.parse_args()
    main(args)

See also:

• https://emredjan.github.io/blog/2017/04/08/validating-xml/