Python snippet: unicode2htmlentities

htmlentities_01.py

# -*- coding: utf-8 -*-

from htmlentitydefs import codepoint2name 

def unicode2htmlentities(u): 
   htmlentities = list() 
   for c in u: 
      if ord(c) < 128: 
         htmlentities.append(c) 
      else: 
         htmlentities.append('&%s;' % codepoint2name[ord(c)]) 
   return ''.join(htmlentities)

print unicode2htmlentities(u'Juan Pérez')