relextract.py 文件源码

def descape_entity(m, defs=htmlentitydefs.entitydefs):
    """
    Translate one entity to its ISO Latin value.
    Inspired by example from effbot.org


    """
    #s = 'mcglashan_&_sarrail'
    #l = ['mcglashan', '&', 'sarrail']
    #pattern = re.compile("&(\w+?);")
    #new = list2sym(l)
    #s = pattern.sub(descape_entity, s)
    #print s, new
    try:
        return defs[m.group(1)]

    except KeyError:
        return m.group(0) # use as is