Stripping control characters in Python

Want to remove ASCII control characters from a string? Have Unicode control characters that can't be encoded into XML? Here is how to strip them with regex in Python.

def strip_control_characters(input):

    if input:

        import re

        # unicode invalid characters
        RE_XML_ILLEGAL = u'([\u0000-\u0008\u000b-\u000c\u000e-\u001f\ufffe-\uffff])' + \
                         u'|' + \
                         u'([%s-%s][^%s-%s])|([^%s-%s][%s-%s])|([%s-%s]$)|(^[%s-%s])' % \
                          (unichr(0xd800),unichr(0xdbff),unichr(0xdc00),unichr(0xdfff),
                           unichr(0xd800),unichr(0xdbff),unichr(0xdc00),unichr(0xdfff),
                           unichr(0xd800),unichr(0xdbff),unichr(0xdc00),unichr(0xdfff),
                           )
        input = re.sub(RE_XML_ILLEGAL, "", input)

        # ascii control characters
        input = re.sub(r"[\x01-\x1F\x7F]", "", input)

    return input

Unicode section adapted from Max Harper.