parsers.py 文件源码

def entity2text(entitydef):
    """Convert an HTML entity reference into unicode.
    http://stackoverflow.com/a/58125/408556
    """
    if entitydef.startswith('&#x'):
        cp = int(entitydef[3:-1], 16)
    elif entitydef.startswith('&#'):
        cp = int(entitydef[2:-1])
    elif entitydef.startswith('&'):
        cp = name2codepoint[entitydef[1:-1]]
    else:
        logger.debug(entitydef)
        cp = None

    return chr(cp) if cp else entitydef