from __future__ import absolute_import import parsers import factories import xml.etree.cElementTree as ET xmlpath = r"C:\roy\NLI-nnl10 - 1MB.xml" whitelist = ['100', '374', '400', '151', '451', '550', '551', '678'] xmltree = ET.parse(xmlpath) entities = list() inl_factory = factories.INLFactory() for record in xmltree.getroot(): inl_parser = parsers.INLXmlParser(record, whitelist) clean_record = inl_parser.clearxml() entities.append(inl_factory.get_entity(clean_record)) for entity in entities: print(entity)