rendered paste bodyfrom pprint import pprint
from xml.dom import minidom, Node
def create_tree(parent, tree, level):
for node in parent.childNodes:
# if it's a Textnode
if node.nodeType == Node.TEXT_NODE:
tree.append(node.nodeValue)
# If it's an element:
else:
tree.append(create_tree(node, [], level+1))
return tree
doc = minidom.parseString('<ul><li>example.com<ul><li>Company<ul><li>History</li><li>Our people<ul><li>John</li><li>Mary</li><li>Pat</li></ul></li><li>Careers<ul><li>Current openings</li><li>Working at example.com</li></ul></li></ul></li><li>Services<ul><li>Web development</li><li>Print design</li><li>Identity and branding</li></ul></li><li>Contact us</li><li>Privacy Policy</li></ul></li></ul>')
pprint(create_tree(doc.documentElement, [], 0))
####
~/toy/etc$ python recurse.py
[[u'example.com',
[[u'Company',
[[u'History'],
[u'Our people', [[u'John'], [u'Mary'], [u'Pat']]],
[u'Careers', [[u'Current openings'], [u'Working at example.com']]]]],
[u'Services',
[[u'Web development'], [u'Print design'], [u'Identity and branding']]],
[u'Contact us'],
[u'Privacy Policy']]]]