Retrieving Text from HTML Documents : Parse HTML « Network « Python Tutorial

1. Python Tutorial
2. Network
3. Parse HTML

import HTMLParser
import urllib

urlText = []

class parseText(HTMLParser.HTMLParser):
    def handle_data(self, data):
        if data != '\n':
            urlText.append(data)


lParser = parseText()

lParser.feed(urllib.urlopen("http://www.python.org/index.html").read())
lParser.close()
for item in urlText:
    print item