Page History

import xml.sax
class XML(xml.sax.handler.ContentHandler):
  def __init__(self):
    self.current = etree.Element("root")
    self.nsmap = { 'xml': 'http://www.w3.org/XML/1998/namespace'}
    self.buffer = ''

  def startElement(self, name, attrs):
    attributes = {}
    for key, value in attrs.items():
        key = key.split(':')
        if len(key) == 2:
            if key[0] == 'xmlns':
                self.nsmap[key[-1]] = value
            else:
                attributes[f"{{{ self.nsmap.get(key[0], key[0]) }}}{ key[-1] }"] = value
        elseelif value:
            attributes[key[-1]] = value

    name = name.split(':')
    if len(name) == 2:
        name = f"{{{ self.nsmap.get(name[0], name[0]) }}}{ name[-1] }"
    else:
        name = name[-1]
    self.current = etree.SubElement(self.current, name, attributes, nsmap=self.nsmap)

  def endElement(self, name):
    self.current.text = self.buffer
    self.current.tail = "\n"
    self.current = self.current.getparent()
    self.buffer = ''

  def characters(self, data):
    d = data.strip()
    if d:
        self.current.textbuffer += d


def parse_xml(io, base_url=None):
    parser = xml.sax.make_parser()
    handler = XML()
    parser.setContentHandler(handler)
    parser.parse(io)
    return etree.ElementTree(handler.current[0])