encode(编码) decode(解码) encoding(编码格式)
#-*- coding:utf-8 -*- import chardet #用于查看编码 with open("d:/kk/kk.txt", "rb") as temp: tem = temp.read() print(tem) print(chardet.detect(tem)) print(tem.decode(encoding="gb2312")) print((tem.decode(encoding="gb2312")).encode("utf-8")) print(chardet.detect((tem.decode(encoding="gb2312")).encode("utf-8")))
结果:
b'xc4xe3xbaxc3 xc4xe3xbaxc3 xc4xe3xbaxc3' {'encoding': 'TIS-620', 'confidence': 0.3598212120361634, 'language': 'Thai'} 你好 你好 你好 b'xe4xbdxa0xe5xa5xbd xe4xbdxa0xe5xa5xbd xe4xbdxa0xe5xa5xbd' {'encoding': 'utf-8', 'confidence': 0.99, 'language': ''}
其它编码转换:
aa = "\u672c\u7248\u672c\u5185\u4e0d\u652f\u6301\u7684\u63a5\u53e3\u6216\u8005\u63a5\u53e3\u5df2\u7ecf\u88ab\u5e9f\u5f03\uff0c\u8bf7\u53c2\u8003\u8be5\u63a5\u53e3\u7684\u6587\u6863\u3002" print(type(aa)) print(aa.encode('utf-8').decode('unicode_escape'))