clean_input.py 文件源码

def _sanitize_html_frags(html_value, valid_tags, valid_attributes):
    fragments = html.fragments_fromstring(html_value)
    for f in fragments:
        if isinstance(f, html.HtmlElement):
            _sanitize_html_rec(f, valid_tags, valid_attributes)
            if f.tag in valid_tags:
                _clean_attributes(f, valid_attributes)
                yield html.tostring(f, encoding="unicode")
            else:
                if f.text:
                    yield f.text
                for sub in f:
                    yield html.tostring(sub, encoding="unicode")
                if f.tail:
                    yield f.tail
                if f.tag in ('p', 'br'):
                    yield '\n'
        else:
            yield f