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

Looks like you want HTMLParser. (html.parser in Python 3.)

from HTMLParser import HTMLParser
from sys import stdout
class Filter(HTMLParser):
    def __init__(self, ignored_tags):
        super(Filter, self).__init__()
        self.ignorelevel = 0
        self. ignored_tags = ignored_tags
    def handle_starttag(self, tag, attrs):
        if self.ignorelevel > 0:
            self.ignorelevel += 1
        elif tag in self.ignored_tags:
            self.ignorelevel = 1
        else:
            # One of these two.  Test and see.
            stdout.write(self.get_starttag_text())
            #stdout.write('<' + self.get_starttag_text() + '>')
    def handle_startendtag(self, tag, attrs):
        if self.ignorelevel == 0 and tag not in self.ignored_tags:
            # One of these two.  Test and see.
            stdout.write(self.get_starttag_text())
            #stdout.write('<' + self.get_starttag_text() + '/>')
    def handle_endtag(self, tag):
        if self.ignorelevel > 0:
            self.ignorelevel -= 1
            if self.ignorelevel > 0:
                return
        stdout.write('')
    def handle_data(self, data):
        stdout.write(data)
    def handle_charref(self, name):
        stdout.write('&#' + name + ';')
    def handle_entityref(self, name):
        stdout.write('&' + name + ';')
    def handle_comment(self, data):
        stdout.write('')
    def handle_decl(self, data):
        stdout.write('')
    def handle_pi(self, data):
        stdout.write('')