Sorting XML in python etree

Question

I know this question has been asked before but I am struggling to get it to work with my example and would really appreciate some help. What I am trying to achieve seems fai

Answer 1

If your want to sort in a recursive way, handling comments and sort along all attributes:

#!/usr/bin/env python
# encoding: utf-8

from __future__ import print_function

import logging
from lxml import etree


def get_node_key(node, attr=None):
    """Return the sorting key of an xml node
    using tag and attributes
    """
    if attr is None:
        return '%s' % node.tag + ':'.join([node.get(attr)
                                        for attr in sorted(node.attrib)])
    if attr in node.attrib:
        return '%s:%s' % (node.tag, node.get(attr))
    return '%s' % node.tag


def sort_children(node, attr=None):
    """ Sort children along tag and given attribute.
    if attr is None, sort along all attributes"""
    if not isinstance(node.tag, str):  # PYTHON 2: use basestring instead
        # not a TAG, it is comment or DATA
        # no need to sort
        return
    # sort child along attr
    node[:] = sorted(node, key=lambda child: get_node_key(child, attr))
    # and recurse
    for child in node:
        sort_children(child, attr)


def sort(unsorted_file, sorted_file, attr=None):
    """Sort unsorted xml file and save to sorted_file"""
    tree = etree.parse(unsorted_file)
    root = tree.getroot()
    sort_children(root, attr)

    sorted_unicode = etree.tostring(root,
                                    pretty_print=True,
                                    encoding='unicode')
    with open(sorted_file, 'w') as output_fp:
        output_fp.write('%s' % sorted_unicode)
        logging.info('written sorted file %s', sorted_unicode)

Note: I am using lxml.etree (http://lxml.de/tutorial.html)

Answer 2

Using ElementTree you can do this:

import xml.etree.ElementTree as ET

def sortchildrenby(parent, attr):
    parent[:] = sorted(parent, key=lambda child: child.get(attr))

tree = ET.parse('input.xml')
root = tree.getroot()

sortchildrenby(root, 'NAME')
for child in root:
    sortchildrenby(child, 'NAME')

tree.write('output.xml')