#!/usr/bin/python2.5

import urllib
data=urllib.urlopen('http://www.pocketsoap.com/weblog/').read()
feedtypes = ['application/atom+xml', 'application/rss+xml']

import sgmllib
class linkparser(sgmllib.SGMLParser):
  def start_link(self,attrs):
    if dict(attrs).get('type',None) in feedtypes:
      print dict(attrs), '\n'

print "sgmllib without monkey patch"
linkparser().feed(data)

import re
sgmllib.tagfind = re.compile('[a-zA-Z][-_.:a-zA-Z0-9]*')
sgmllib.special = re.compile('<!')
sgmllib.charref = re.compile('&#(x?[0-9A-Fa-f]+)[^0-9A-Fa-f]')

print "sgmllib with feedparser 4.1 monkeypatch"
linkparser().feed(data)

if sgmllib.endbracket.search(' <').start(0):
    class EndBracketMatch:
        endbracket = re.compile('''([^'"<>]|"[^"]*"(?=>|/|\s|\w+=)|'[^']*'(?=>|/|\s|\w+=))*(?=[<>])|.*?(?=[<>])''')
        def search(self,string,index=0):
            self.match = self.endbracket.match(string,index)
            if self.match: return self
        def start(self,n):
            return self.match.end(n)
    sgmllib.endbracket = EndBracketMatch()

print "sgmllib with nightly feedparser monkey patch"
linkparser().feed(data)

print "html5lib"
import xml.etree.ElementTree
from html5lib import html5parser, treebuilders
etree = treebuilders.getTreeBuilder('etree', xml.etree.ElementTree)
tree = html5parser.HTMLParser(False, etree).parse(data)
for link in tree.findall('head/link'):
  if link.attrib.get('type') in feedtypes:
    print link.attrib