unescape.py

#!/usr/bin/python
# -*- coding: utf-8 -*-
import re
##
# Removes HTML or XML character references and entities from a text string.
#
# @param text The HTML (or XML) source text.
# @return The plain text, as a Unicode string, if necessary.

def unescape(text):
    def fixup(m):
        text = m.group(0)
        code = m.group(1)
        try:
            if text[1] == "#":  # character reference
                if text[2] == "x":
                    return unichr(int(code[1:], 16))
                else:
                    return unichr(int(code))
            else:               # named entity
                return unichr(name2codepoint[code])
        except:
            return text # leave as is

    return re.sub("&#?(\w+);", fixup, text)