File: htmlentitydefs-example-1.py

import htmlentitydefs

entities = htmlentitydefs.entitydefs

for entity in "amp", "quot", "copy", "yen":
    print entity, "=", entities[entity]

amp = &
quot = "
copy = 302251
yen = 302245

File: htmlentitydefs-example-2.py

import htmlentitydefs
import re
import cgi

pattern = re.compile("&(w+?);")

def descape_entity(m, defs=htmlentitydefs.entitydefs):
    # callback: translate one entity to its ISO Latin value
    try:
        return defs[m.group(1)]
    except KeyError:
        return m.group(0) # use as is

def descape(string):
    return pattern.sub(descape_entity, string)

print descape("<spam&eggs>")
print descape(cgi.escape("<spam&eggs>"))

<spam&eggs>
<spam&eggs>

File: htmlentitydefs-example-3.py

import htmlentitydefs
import re, string

# this pattern matches substrings of reserved and non-ASCII characters
pattern = re.compile(r"[&<>"x80-xff]+")

# create character map
entity_map = {}

for i in range(256):
    entity_map[chr(i)] = "&%d;" % i

for entity, char in htmlentitydefs.entitydefs.items():
    if entity_map.has_key(char):
        entity_map[char] = "&%s;" % entity

def escape_entity(m, get=entity_map.get):
    return string.join(map(get, m.group()), "")

def escape(string):
    return pattern.sub(escape_entity, string)

print escape("<spam&eggs>")
print escape("303245 i 303245a 303244 e 303266")

&lt;spam&amp;eggs&gt;
&aring; i &aring;a &auml; e &ouml;