strip tags python

Question

i want the following functionality.

input : this is test  bold text  normal text
expected output: this is test normal text

Answer 1

This is working code taken from my project Supybot, so it's fairly well tested:

class HtmlToText(sgmllib.SGMLParser):
    """Taken from some eff-bot code on c.l.p."""
    entitydefs = htmlentitydefs.entitydefs.copy()
    entitydefs['nbsp'] = ' '
    def __init__(self, tagReplace=' '):
        self.data = []
        self.tagReplace = tagReplace
        sgmllib.SGMLParser.__init__(self)

    def unknown_starttag(self, tag, attr):
        self.data.append(self.tagReplace)

    def unknown_endtag(self, tag):
        self.data.append(self.tagReplace)

    def handle_data(self, data):
        self.data.append(data)

    def getText(self):
        text = ''.join(self.data).strip()
        return normalizeWhitespace(text)

def htmlToText(s, tagReplace=' '):
    """Turns HTML into text.  tagReplace is a string to replace HTML tags with.
    """
    x = HtmlToText(tagReplace)
    x.feed(s)
    return x.getText()

As the docstring notes, it originated with Fredrik Lundh, not me. As they say, great authors steal :)