I want to remove all html tags except from my string with python i use this:
from HTMLParser import HTMLParser
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()
But this remove all my html tags.
If I understand it right, you want to strip html tags, but to keep some specific ones ? If that's the case - then just keep monitoring the start/end tags, and process them if needed. Example:
MY_TAGS = ["tag1", "tag2"]
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 handle_starttag(self, tag, attrs):
if tag in MY_TAGS:
self.fed.append("<%s>" % tag) # tag is only string, no < or >.
def handle_endtag(self, tag):
if tag in MY_TAGS:
self.fed.append("</%s>" % tag)