python: Removes HTML or XML character references and entities from a text string.

unescape_html_ent.py

# unescape_html_ent.py
#
# thx:
#   http://effbot.org/zone/re-sub.htm#unescape-html

import re, htmlentitydefs

##
# 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)
        if text[:2] == "&#":
            # character reference
            try:
                if text[:3] == "&#x":
                    return unichr(int(text[3:-1], 16))
                else:
                    return unichr(int(text[2:-1]))
            except ValueError:
                pass
        else:
            # named entity
            try:
                text = unichr(htmlentitydefs.name2codepoint[text[1:-1]])
            except KeyError:
                pass
        return text # leave as is
    return re.sub("&#?\w+;", fixup, text)


###### test
if __name__ == '__main__':
    print unescape(r"MXAM Internal Error (For support please contact [email protected]): MXAM Exception 015: Model cannot be set into required compile mode. : Error calling mes_setmode: unable to set system 'sctfs' into compile mode. エラー ==> mes_setmode at 272 複数の原因によるエラー。.")