字符串转unicode字符串技术要点:
ord()函数
format()函数
代码:
def str_to_unicode(string, upper=True):
'''字符串转unicode'''
if upper is True:
return ''.join(rf'\u{ord(x):04X}' for x in string)
else:
return ''.join(rf'\u{ord(x):04x}' for x in string)
def unicode_to_str(unicode):
'''unicode转字符串'''
if isinstance(unicode, bytes):
return unicode.decode('unicode_escape')
else:
return unicode.encode('utf-8').decode('unicode_escape')
if __name__ == '__main__':
text = 'hello中国'
lower_uni = str_to_unicode(text, upper=False)
upper_uni = str_to_unicode(text)
print(f'{text} => {lower_uni}')
print(f'{text} => {upper_uni}')
print(f'{lower_uni} => {unicode_to_str(lower_uni)}')
print(f'{upper_uni} => {unicode_to_str(upper_uni)}')
执行结果:
hello中国 => \u0068\u0065\u006c\u006c\u006f\u4e2d\u56fd
hello中国 => \u0068\u0065\u006C\u006C\u006F\u4E2D\u56FD
\u0068\u0065\u006c\u006c\u006f\u4e2d\u56fd => hello中国
\u0068\u0065\u006C\u006C\u006F\u4E2D\u56FD => hello中国