html5parser.py 文件源码-python代码片段

def fromstring(html, guess_charset=True, parser=None):
    """Parse the html, returning a single element/document.

    This tries to minimally parse the chunk of text, without knowing if it
    is a fragment or a document.

    base_url will set the document's base_url attribute (and the tree's docinfo.URL)
    """
    if not isinstance(html, _strings):
        raise TypeError('string required')
    doc = document_fromstring(html, parser=parser,
                              guess_charset=guess_charset)

    # document starts with doctype or <html>, full document!
    start = html[:50].lstrip().lower()
    if start.startswith('<html') or start.startswith('<!doctype'):
        return doc

    head = _find_tag(doc, 'head')

    # if the head is not empty we have a full document
    if len(head):
        return doc

    body = _find_tag(doc, 'body')

    # The body has just one element, so it was probably a single
    # element passed in
    if (len(body) == 1 and (not body.text or not body.text.strip())
        and (not body[-1].tail or not body[-1].tail.strip())):
        return body[0]

    # Now we have a body which represents a bunch of tags which have the
    # content that was passed in.  We will create a fake container, which
    # is the body tag, except <body> implies too much structure.
    if _contains_block_level_tag(body):
        body.tag = 'div'
    else:
        body.tag = 'span'
    return body