import re
from urllib import urlopen
from BeautifulSoup import BeautifulSoup as BS

url = 'http://www.w3.org/TR/html5/named-character-references.html'
page = BS(urlopen(url))

total = 0
for tr in page.findAll('tr', id=re.compile('^entity-')):
    name_td, value_td, _ = tr.findAll('td')
    name = name_td.code.string.rstrip(';')
    values = [int(value[2:], 16) for value in value_td.string.split()]
    hex_values = ', '.join(map(hex, values))
    print "    '{}': [{}],".format(name, hex_values)
    total += 1
print total, 'entities found.'