def strip_and_clean(self, html):
""" Cleans up the HTML structure and strips all tags. """
html = "".join([line.strip() for line in html.split("\n")])
html = re.sub('<!DOCTYPE.*?>', '', html)
html = StringUtil.br2nl(html)
# strip html
html = ''.join(BeautifulSoup(html).findAll(text=True))
return html
