entity2unicode.py

#!/usr/bin/env python
"""
Reads a series of HTML entities from stdin, and outputs a table of the
corresponding Unicode characters.

"""
import sys
from htmlentitydefs import name2codepoint

def codepoint(entity):
    name = entity[1:-1]
    if name.startswith('#'):
        if name[1] == 'x':
            return int(name[2:], 16)
        else:
            return int(name[1:])
    else:
        return name2codepoint.get(name, None)

def tokens(input):
    return (w for w in input.split() if w.startswith('&') and w.endswith(';'))

def main():
    for token in tokens(sys.stdin.read()):
        try:
            uc = unichr(codepoint(token))
        except TypeError:
            uc = 'n/a'
        print "%s\t%s" % (uc, token)

if __name__ == '__main__':
    main()

EXAMPLE

$ python entity2unicode.py <<< '&#8230; &#x2026; &hellip; &troll; &#9731;'
…	&#8230;
…	&#x2026;
…	&hellip;
n/a	&troll;
☃	&#9731;