How to convert ASCII extended names to HTML objects in Python?

Question

I am currently doing this to replace extended ascii characters with their equivalent HTML object equivalents:

s.encode('ascii', 'xmlcharrefreplace')

What I would like to do is convert to the equivalent of the equivalent of an HTML entity (i.e. ©instead ©). This small program below shows what I'm trying to do, this is unsuccessful. Is there any way to do this other than search / replace?

#coding=latin-1

def convertEntities(s):
    return s.encode('ascii', 'xmlcharrefreplace')

ok = 'ascii: !@#$%^&*()<>'
not_ok = u'extended-ascii: ©®°±¼'

ok_expected = ok
not_ok_expected = u'extended-ascii: &copy;&reg;&deg;&plusmn;&frac14;'

ok_2 = convertEntities(ok)
not_ok_2 = convertEntities(not_ok)

if ok_2 == ok_expected:
    print 'ascii worked'
else:
    print 'ascii failed: "%s"' % ok_2

if not_ok_2 == not_ok_expected:
    print 'extended-ascii worked'
else:
    print 'extended-ascii failed: "%s"' % not_ok_2

Answer 1

Update . This is the solution I'm going with, with a little fix, to verify that entitydefs contains a mapping for the character that we have.

def convertEntities(s):
    return ''.join([getEntity(c) for c in s])

def getEntity(c):
    ord_c = ord(c)
    if ord_c > 127 and ord_c in htmlentitydefs.codepoint2name:
        return "&%s;" % htmlentitydefs.codepoint2name[ord_c]
    return c

Answer 2

htmlentitydefs, . :

from htmlentitydefs import entitydefs as symbols

for tag, val in symbols.iteritems():
   mystr = mystr.replace("&{0};".format(tag), val)

.

Answer 3

htmlentitydefs, ?

import htmlentitydefs
htmlentitydefs.codepoint2name.get(ord(c),c)

Answer 4

, , , htmlentitydefs . .

Answer 5

, , ? ok_expected , , & , . , & , cgi.escape, .

, : , . , getEntity.

#coding=latin-1
import cgi
import re
import htmlentitydefs

def replace_entity(match):
    c = int(match.group(1))
    name = htmlentitydefs.codepoint2name.get(c, None)
    if name:
        return "&%s;" % name
    return match.group(0)

def convertEntities(s):
    s = cgi.escape(s) # Remove if you want ok_expected to pass!
    s = s.encode('ascii', 'xmlcharrefreplace')
    s = re.sub("&#([0-9]+);", replace_entity, s)
    return s

ok = 'ascii: !@#$%^&*()<>'
not_ok = u'extended-ascii: ©®°±¼'

ok_expected = ok
not_ok_expected = u'extended-ascii: &copy;&reg;&deg;&plusmn;&frac14;'

ok_2 = convertEntities(ok)
not_ok_2 = convertEntities(not_ok)

if ok_2 == ok_expected:
    print 'ascii worked'
else:
    print 'ascii failed: "%s"' % ok_2

if not_ok_2 == not_ok_expected:
    print 'extended-ascii worked'
else:
    print 'extended-ascii failed: "%s"' % not_ok_2