from django import template
from BeautifulSoup import BeautifulSoup, Comment
import re

register = template.Library()

def sanitize_html(value,
                  valid_tags='a b i img strong em code br p ul li ol span',
                  valid_attrs = 'href src title style'):
    valid_tags = valid_tags.split()
    valid_attrs = valid_attrs.split()
    soup = BeautifulSoup(value)
    for comment in soup.findAll(
        text=lambda text: isinstance(text, Comment)):
        comment.extract()
    for tag in soup.findAll(True):
        if tag.name not in valid_tags:
            tag.hidden = True
        else:
            for attr, val in tag.attrs:
                if re.match('javascript:', val, re.I) is not None:
                    tag.hidden = True
            tag.attrs = [(attr, val) for attr, val in tag.attrs if attr in valid_attrs]
    #print value
    #print '-'*40
    #print soup.renderContents().decode('utf8')
    return soup.renderContents().decode('utf8')