WikiExtractor.py 文件源码

def unescape(text):
    """
    Removes HTML or XML character references and entities from a text string.

    :param text The HTML (or XML) source text.
    :return The plain text, as a Unicode string, if necessary.
    """

    def fixup(m):
        text = m.group(0)
        code = m.group(1)
        try:
            if text[1] == "#":  # character reference
                if text[2] == "x":
                    return chr(int(code[1:], 16))
                else:
                    return chr(int(code))
            else:  # named entity
                return chr(name2codepoint[code])
        except:
            return text  # leave as is

    return re.sub("&#?(\w+);", fixup, text)


# Match HTML comments
# The buggy template {{Template:T}} has a comment terminating with just "->"