#!/usr/bin/env python

from BeautifulSoup import BeautifulSoup
from urllib import urlopen
from re import match

url = 'http://www.iana.org/assignments/media-types/application/'
html = urlopen(url).read()
soup = BeautifulSoup(html)

for rows in soup.findAll('tr'):
    cells = rows.findAll('td')
    if len(cells) == 3:

        # can be an anchor or just plain text
        mime_type = cells[1].string
        if not mime_type:
            mime_type = cells[1].findNext('a').string
        mime_type = mime_type.strip()

        if match('.*\+xml$', mime_type):
            print "application/%s" % mime_type