Strip HTML from strings in Python

Question

from mechanize import Browser
br = Browser()
br.open(\'http://somewebpage\')
html = br.response().readlines()
for line in html:
  print line

When p

Answer 1

For one project, I needed so strip HTML, but also css and js. Thus, I made a variation of Eloffs answer:

class MLStripper(HTMLParser):
    def __init__(self):
        self.reset()
        self.strict = False
        self.convert_charrefs= True
        self.fed = []
        self.css = False
    def handle_starttag(self, tag, attrs):
        if tag == "style" or tag=="script":
            self.css = True
    def handle_endtag(self, tag):
        if tag=="style" or tag=="script":
            self.css=False
    def handle_data(self, d):
        if not self.css:
            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()