html5parser.py 文件源码

def fragment_fromstring(html, create_parent=False,
                        guess_charset=False, parser=None):
    """Parses a single HTML element; it is an error if there is more than
    one element, or if anything but whitespace precedes or follows the
    element.

    If create_parent is true (or is a tag name) then a parent node
    will be created to encapsulate the HTML in a single element.  In
    this case, leading or trailing text is allowed.
    """
    if not isinstance(html, _strings):
        raise TypeError('string required')

    accept_leading_text = bool(create_parent)

    elements = fragments_fromstring(
        html, guess_charset=guess_charset, parser=parser,
        no_leading_text=not accept_leading_text)

    if create_parent:
        if not isinstance(create_parent, _strings):
            create_parent = 'div'
        new_root = Element(create_parent)
        if elements:
            if isinstance(elements[0], _strings):
                new_root.text = elements[0]
                del elements[0]
            new_root.extend(elements)
        return new_root

    if not elements:
        raise etree.ParserError('No elements found')
    if len(elements) > 1:
        raise etree.ParserError('Multiple elements found')
    result = elements[0]
    if result.tail and result.tail.strip():
        raise etree.ParserError('Element followed by text: %r' % result.tail)
    result.tail = None
    return result