Python3 中文字符与Unicode字符互转(原创)

中文转Unicode

def cn_to_unicode(in_str, need_str=True, debug=False):
    out = []

    for s in in_str:
        # 获得该字符的数值
        val = ord(s)
        # print(val)

        # 小于0xff则为ASCII码，手动构造\u00xx格式
        if val <= 0xff:
            hex_str = hex(val).replace('0x', '').zfill(4)
            # 这里不能以unicode_escape编码，不然会自动增加一个'\\'
            res = bytes('\\u' + hex_str, encoding='utf-8')
        else:
            res = s.encode("unicode_escape")

        out.append(res)
    
    # 调试
    if debug:
        print(out)
        print(len(out), len(out[0]), len(out[-1]))

    # 转换为str类
    if need_str:
        out_str = ''
        for s in out:
            out_str += str(s, encoding='utf-8')
        return out_str
    else:
        return out

Unicode转中文

def unicode_to_cn(in_str, debug=False):
    out = None

    if isinstance(in_str, bytes):
        temp = str(in_str, encoding='utf-8')
        out = temp.encode('utf-8').decode('unicode_escape')
    else:
        out = in_str.encode('utf-8').decode('unicode_escape')

    return out

测试代码

test.py

...
if __name__ == "__main__":
    val = input("unicode to GBK or GBK to unicode? <enter 1 for the front, 2 for the end>: ")
    if eval(val) == 1:
        s1 = input("input unicode str(like '\\u4f60\\u597d'): ")
        s2 = unicode_to_cn(s1)
        print("result: ", s2)
    elif eval(val) == 2:
        s1 = input("input GBK str(like '你好'): ")
        s2 = cn_to_unicode(s1)
        print("result: ", s2)
    else:
        print("input wrong choice! can only be 1 or 2!")

执行效果

• unicode to 中文

jason@jason-vm:~/test$ python3 test.py 
unicode to GBK or GBK to unicode? <enter 1 for the front, 2 for the end>: 1
input unicode str(like '\u4f60\u597d'): \u4f60\u597d
result:  你好

• 中文 to unicode

jason@jason-vm:~/test$ python3 test.py 
unicode to GBK or GBK to unicode? <enter 1 for the front, 2 for the end>: 2
input GBK str(like '你好'): 你好123
result:  \u4f60\u597d\u0031\u0032\u0033