XML manipuration example

etree_example.py

import xml.etree.ElementTree as ET

xml_data = '''<?xml version="1.0" encoding="utf-8"?>
<root>
    <person id="1">
        <name>John Doe</name>
        <age>30</age>
        <city>Tokyo</city>
    </person>
    <person id="2">
        <name>Jane Smith</name>
        <age>25</age>
        <city>New York</city>
    </person>
</root>
'''

print(xml_data)

root = ET.fromstring(xml_data)

# add and update
for person in root.findall('.//person[@id="1"]'):
    person.set("id", "3")           # update attribute
    name = person.find('name')
    print(f"old_name={name.text}")
    name.text = 'John Doe Jr.'      # update text
    name.set("#test_attr", "test")  # new attribute
    age = person.find('age')
    print(f"old_age={age.text}")
    age.text = '31'
    new_element = ET.SubElement(person, "dc:description")   # populate tag
    new_element.text = "Ikebukuro"

# search again
for person in root.findall('.//person[@id="3"]'):
    name = person.find('name')
    print(f"new_name={name.text}")
    print(f"new_age={age.text}")
print()
edited_xml = ET.tostring(root, encoding='utf-8', method='xml', xml_declaration=True).decode('utf-8')
print(edited_xml)

# remove
for person in root.findall('.//person[@id="3"]'):
    name = person.find('name')

    attr1 = name.get("#test_attr")                  # get attrib
    attr2 = name.attrib.pop("#test_attr", None)     # get and remove attrib
    assert attr1 == attr2
 
    age = person.find('age')
    person.remove(age)                      # remove tag

print()
edited_xml = ET.tostring(root, encoding='utf-8', method='xml', xml_declaration=True).decode('utf-8')
print(edited_xml)