Strip HTML tags using BeautifulSoup

strip_tags.py

def strip(untrusted_html):
    """Strips out all tags from untrusted_html, leaving only text.

    Converts XML entities to Unicode characters.  This is desirable because it 
    reduces the likelihood that a filter further down the text processing chain 
    will double-encode the XML entities."""
    soup = BeautifulStoneSoup(untrusted_html, convertEntities=BeautifulStoneSoup.ALL_ENTITIES)
    safe_html = ''.join(soup.findAll(text=True))
    return safe_html