saxvsdom.py

import time
import xml.sax
from xml.dom import minidom
# SAX Parser Handler
class MySAXHandler(xml.sax.ContentHandler):
    def __init__(self):
        self.current_tag = None

    def startElement(self, tag, attributes):
        self.current_tag = tag

    def characters(self, content):
        if self.current_tag and content.strip():
            pass  # Process characters if needed

    def endElement(self, tag):
        self.current_tag = None


def test_sax():
    parser = xml.sax.make_parser()
    handler = MySAXHandler()
    parser.setContentHandler(handler)
    with open("test.xml", "r") as f:
        parser.parse(f)


def test_dom():
    with open("test.xml", "r") as f:
        minidom.parse(f)


# Measure time for SAX parsing
start_time = time.time()
test_sax()
sax_time = time.time() - start_time
print(f"SAX parsing time: {sax_time:.6f} seconds")

# Measure time for DOM parsing
start_time = time.time()
test_dom()
dom_time = time.time() - start_time
print(f"DOM parsing time: {dom_time:.6f} seconds")

test.xml

SAX parsing time: 0.098901 seconds
DOM parsing time: 0.402619 seconds

on my Apple M1 Max