plist_parse.py

# Apple Property List parser for Python
# (via http://effbot.org/zone/element-iterparse.htm)
#
# ``xml.etree.ElementTree`` is fast (and smart looks) for small xml, 
# but for large (more than 5MB) xml, SAX implementation is still fast.
def xml_plist_parse(self, xml_input):
    import base64, time, datetime
    from xml.etree.ElementTree import iterparse

    callbacks = {
        'array': lambda x: [v.text for v in x],
        'dict': lambda x:
            dict((x[i].text, x[i+1].text) for i in range(0, len(x), 2)),
        'key': lambda x: x.text or "",
        'string': lambda x: x.text or "",
        'data': lambda x: base64.b64decode(x.text),
        'date': lambda x: 
            datetime.datetime(
                *(time.strptime(x.text, "%Y-%m-%dT%H:%M:%SZ")[0:6])),
        'real': lambda x: float(x.text),
        'integer': lambda x: int(x.text),
        'true': lambda x: True,
        'false': lambda x: False,
    }

    parser = iterparse(xml_input)
    for action, element in parser:
        callback = callbacks.get(element.tag)
        if callback:
            data = callback(element)
            element.clear()
            element.text = data
        elif element.tag != 'plist':
            raise IOError("unknown plist tag: %s" % element.tag)
    return parser.root[0].text