python字符串操作(去非中文字符)

时间:2021-07-23 07:42:28
清理非中文
def is_ustr(in_str):
    out_str=''
    for i in range(len(in_str)):
        if is_uchar(in_str[i]):
            out_str=out_str+in_str[i]
        else:
            out_str=out_str+' '
    return out_str
def is_uchar(uchar):
    """判断一个unicode是否是汉字"""
    if uchar >= u'\u4e00' and uchar<=u'\u9fa5':
            return True
    """判断一个unicode是否是数字"""
    if uchar >= u'\u0030' and uchar<=u'\u0039':
            return False        
    """判断一个unicode是否是英文字母"""
    if (uchar >= u'\u0041' and uchar<=u'\u005a') or (uchar >= u'\u0061' and uchar<=u'\u007a'):
            return False
    if uchar in ('-',',',',','。','.','>','?'):
            return False
    return False