Quick-and-dirty HTML tag stripper

striphtml.py

#!/usr/bin/env python

from HTMLParser import HTMLParser
import sys, os

class MLStripper(HTMLParser):
    def __init__(self):
        self.reset()
        self.fed = []
    def handle_data(self, d):
        self.fed.append(d)
    def get_data(self):
        return ''.join(self.fed)

def strip_tags(html):
    s = MLStripper()
    s.feed(html)
    return s.get_data()

for line in strip_tags(open(sys.argv[1], 'r').read().replace("<br>", "\r\n")).splitlines():
    if len(line.strip()) > 0:
        print line.strip()