html5parser.py 文件源码

def normalizeToken(self, token):
        """ HTML5 specific normalizations to the token stream """

        if token["type"] == tokenTypes["StartTag"]:
            raw = token["data"]
            token["data"] = OrderedDict(raw)
            if len(raw) > len(token["data"]):
                # we had some duplicated attribute, fix so first wins
                token["data"].update(raw[::-1])

        return token