Python 字节串转Hex字符串（一个久远的问题点总结）

• 时间: 2024.07.30 作者: Yuan

  这是一个发生在很久之前的问题，但是值得被记录和澄清一下！

  在2022年1月份参与的项目中，其中有一个需求是利用 SHT40-AD1B-R2 芯片，读取环境温度。其实就是通过 i2c 与这个温度传感器建立通讯，然后读取温湿度信息。对于上位机的我而言，需要解决的一点就是将从传感器中读回的数据换算为以摄氏度为单位的十进制数值。当时费了一番脑筋，最后我找到了一个"解决"方法。

  在2022年6月份，梳理 Python 知识点的过程中，我猛然间发现似乎不用那么复杂，使用Python内建的函数就可以直接解决…… 顿时感到了自己的“愚蠢且努力”！

  现在是2024年7月份，事情过去都两年了，忽然想起需要整理下这个内容。由于当时对“字节字符串”的认识不足，以及对python基础不够清楚，所以走了弯路。现在再次确认，发现2年前的解决方法实际上是有bug的，现在就来解一解这个两年前的bug！

• 数据内容与说明

"""
当时在看到读回的数据为类似 `b'fX'`、`b'f4'`、`b'd\xac\xd6\xa5\x9f\x1e'` 这样的结果时，一时间有点摸不着头脑，
于是请教了客户那边的软件工程师，客户给我做了一个示例。
有了客户的示例和指导后，我就奔着目标开干了：
将遇到的\x开头的2位16进制字符记为16进制，非\x开头的16进制的字符转为 ascii 码！
"""

# Yuan：I2C 读取温度返回的信息, 有点奇怪: b'f4' 、b'fX' 、b'f`5\x95\xA6\xE1' 
# Kim：什麼型號的溫度感測元件
# Yuan：SHT40-AD1B-R2
# Kim：
b'f4' 算出來是24.866483558 °C
我覺得應該是正常的
b'f4' = 0x66, 0x34
0x6634 = 26164
((26164/65535)*175) - 45 = 24.866483558

b'f'' = 0x66, 0x27
' 這個的ascii code應該是0x27

# Yuan：是用 ascii code 转换成16进制的对吗?
# Kim：
Yes，因為那是byte array
除非看到\x
不然就都要轉ASCII

# Yuan：好的，\x开头的都是2位16进制, 对吗
# Kim：Yes

• 当时的解决方案

#!/usr/bin/env python3

"""
思路：
将 “\x+2位字符” 部分直接记录位 Hex 值，将非“\x+2位字符”的单个字符转换为 ASCII 码，
于是，我突发奇想从utf-8中找了几个希腊字母（因为他们不在ascii表中，避免了重复），先将 “\x+2位字符” 这类已知的Hex字串替换成希腊字母，
然后，再遍历替换后的字符串，遇到的非希腊字母，就将其从 ASCII 码，转换为对应的Hex形式。
最终，将两类Hex字符汇总成纯Hex字符的字符串，再统一转换为十进制数值，再进行下一步温度的计算。
"""

import re

temp_list = [
        b'dW',
        b'd^',
        b'dB',
        b'd>',
        b'dP',
        b'dD',
        b'dS',
        b'dQ',
        b'dP',
        b'dO',
        b'dK',
        b'',
        b'dU',
        b'df',
        b'd_',
        b'dd(\xa6\x99\x95',
        b'd\xa4o\xa5\xc2,',
        b'd\xb0\xe8\xa5\xddA',
        b'd\xa3\xf8\xa5\xaa.',
        b'd\xb0\xe8\xa5\xac\x88',
        b'd\xb8Q\xa5\xb3\xe5',
        b'd\xac\xd6\xa5\x8b\x99',
        b'd\xaap\xa5\xa41',
        b'd\xae\xb4\xa5\xa7b',
        b'd\xa7<\xa5\x93c',
        b'd\xa5^\xa5\x98\x89',
        b'd\xac\xd6\xa5\x9f\x1e',
        b'd\xb9`\xa5\x9d|',
        b'd\xa7<\xa5\xa3\xa6',
        b'd\xb1\xd9\xa5\x9a\xeb',
        b'd\xb8Q\xa5\x94\xf4',
        b'd\xb9`\xa5\x89\xfb',
        b'd\xb8Q\xa5xH',
        b'',
        b'd\xb3\xbb\xa5\x91\x01',
        b'd\xb0\xe8\xa5\x96\x96',
        b'd\xba3\xa5\x7f\xdf',
        b'd\xb2\x8a\xa5xH',
        b'd\xaap\xa5s\xa2',
        b'd\xabA\xa5s\xa2',
        b'd\xba3\xa5\x81B',
        b'd\xb8Q\xa5n\xad',
        b'd\xb2\x8a\xa5yy',
        b'd\xac\xd6\xa5h\x0b',
        b'd\xb6N\xa5n\xad',
        b'd\xabA\xa5wf',
        b'd\xad\xe7\xa5l\xcf',
        b'd\xbc\x95\xa5i:',
        b'd\xb3\xbb\xa5];',
        b'd\xb1\xd9\xa5eG',
        b'd\xbb\x02\xa5s\xa2',
        b'd\xac\xd6\xa5p\xf1',
        b'',
        b'd\xad\xe7\xa5\\\n',
        b'\n',
        b'd\n',
        b'd\xbc\x95\xa5O\x1a',
        b'd\xb1\xd9\xa5LI']

def get_temperature(_data):
    if _data:
        data1 = str(_data).lstrip("b").strip("'")

        reg = r'\\x([0-9a-f]{2})'
        val_ret = re.findall(reg, data1)

        unichr = 'δλξπσω'
        unidict = {}
        data2 = str(data1)
        if val_ret:
            for i, ret in enumerate(val_ret):
                unidict[unichr[i]] = '0x{}'.format(ret)
                data2 = data2.replace('\\x{}'.format(ret), unichr[i])

        hex_str = []
        for da in data2:
            if da in unidict.keys():
                hex_str.append(unidict[da])
            else:
                hex_str.append(hex(ord(da)))

        data_pool = hex_str
        value1 = int(''.join(data_pool[:2]).replace('0x', ''), 16)
        degc = round(((value1 / 65535) * 175) - 45, 2)
        # prh = round(((value2 / 65535) * 125) - 6, 2)

        # if prh > 100:
        #     prh = 100
        # if prh < 0:
        #     prh = 0

        # unit = chr(8451)
        unit = "°C"

        if degc > 40 or degc < 10:
            result = 'degc: {} {} ({}, {})'.format(degc, unit, _data, val_ret)
        else:
            result = 'degc: {} {}'.format(degc, unit)
        # print('DEG: {} {}'.format(degc, unit), ', PRH: {} {}'.format(prh, '%'))

        # print("{} ==> {} ==> Hex: {} ==> DEG: {} {}".format(_data, val_ret, data_pool, degc, unit))
        print(f"{_data} ==> {val_ret} ==> Hex: {data_pool} ==> DEG: {degc} {unit}")
    else:
        result = '-- no data --'

    return result

if __name__ == '__main__':

    for i, temp in enumerate(temp_list):
        # print('{}: {}    {}'.format(str(i).zfill(2), get_temperature(temp), temp))
        get_temperature(temp)

"""
输出:
b'dW' ==> [] ==> Hex: ['0x64', '0x57'] ==> DEG: 23.59 °C
b'd^' ==> [] ==> Hex: ['0x64', '0x5e'] ==> DEG: 23.61 °C
b'dB' ==> [] ==> Hex: ['0x64', '0x42'] ==> DEG: 23.54 °C
b'd>' ==> [] ==> Hex: ['0x64', '0x3e'] ==> DEG: 23.53 °C
b'dP' ==> [] ==> Hex: ['0x64', '0x50'] ==> DEG: 23.57 °C
b'dD' ==> [] ==> Hex: ['0x64', '0x44'] ==> DEG: 23.54 °C
b'dS' ==> [] ==> Hex: ['0x64', '0x53'] ==> DEG: 23.58 °C
b'dQ' ==> [] ==> Hex: ['0x64', '0x51'] ==> DEG: 23.58 °C
b'dP' ==> [] ==> Hex: ['0x64', '0x50'] ==> DEG: 23.57 °C
b'dO' ==> [] ==> Hex: ['0x64', '0x4f'] ==> DEG: 23.57 °C
b'dK' ==> [] ==> Hex: ['0x64', '0x4b'] ==> DEG: 23.56 °C
b'dU' ==> [] ==> Hex: ['0x64', '0x55'] ==> DEG: 23.59 °C
b'df' ==> [] ==> Hex: ['0x64', '0x66'] ==> DEG: 23.63 °C
b'd_' ==> [] ==> Hex: ['0x64', '0x5f'] ==> DEG: 23.61 °C
b'dd(\xa6\x99\x95' ==> ['a6', '99', '95'] ==> Hex: ['0x64', '0x64', '0x28', '0xa6', '0x99', '0x95'] ==> DEG: 23.63 °C
b'd\xa4o\xa5\xc2,' ==> ['a4', 'a5', 'c2'] ==> Hex: ['0x64', '0xa4', '0x6f', '0xa5', '0xc2', '0x2c'] ==> DEG: 23.8 °C
b'd\xb0\xe8\xa5\xddA' ==> ['b0', 'e8', 'a5', 'dd'] ==> Hex: ['0x64', '0xb0', '0xe8', '0xa5', '0xdd', '0x41'] ==> DEG: 23.83 °C
b'd\xa3\xf8\xa5\xaa.' ==> ['a3', 'f8', 'a5', 'aa'] ==> Hex: ['0x64', '0xa3', '0xf8', '0xa5', '0xaa', '0x2e'] ==> DEG: 23.8 °C
b'd\xb0\xe8\xa5\xac\x88' ==> ['b0', 'e8', 'a5', 'ac', '88'] ==> Hex: ['0x64', '0xb0', '0xe8', '0xa5', '0xac', '0x88'] ==> DEG: 23.83 °C
b'd\xb8Q\xa5\xb3\xe5' ==> ['b8', 'a5', 'b3', 'e5'] ==> Hex: ['0x64', '0xb8', '0x51', '0xa5', '0xb3', '0xe5'] ==> DEG: 23.85 °C
b'd\xac\xd6\xa5\x8b\x99' ==> ['ac', 'd6', 'a5', '8b', '99'] ==> Hex: ['0x64', '0xac', '0xd6', '0xa5', '0x8b', '0x99'] ==> DEG: 23.82 °C
b'd\xaap\xa5\xa41' ==> ['aa', 'a5', 'a4'] ==> Hex: ['0x64', '0xaa', '0x70', '0xa5', '0xa4', '0x31'] ==> DEG: 23.81 °C
b'd\xae\xb4\xa5\xa7b' ==> ['ae', 'b4', 'a5', 'a7'] ==> Hex: ['0x64', '0xae', '0xb4', '0xa5', '0xa7', '0x62'] ==> DEG: 23.83 °C
b'd\xa7<\xa5\x93c' ==> ['a7', 'a5', '93'] ==> Hex: ['0x64', '0xa7', '0x3c', '0xa5', '0x93', '0x63'] ==> DEG: 23.81 °C
b'd\xa5^\xa5\x98\x89' ==> ['a5', 'a5', '98', '89'] ==> Hex: ['0x64', '0xa5', '0x5e', '0xa5', '0x98', '0x89'] ==> DEG: 23.8 °C
b'd\xac\xd6\xa5\x9f\x1e' ==> ['ac', 'd6', 'a5', '9f', '1e'] ==> Hex: ['0x64', '0xac', '0xd6', '0xa5', '0x9f', '0x1e'] ==> DEG: 23.82 °C
b'd\xb9`\xa5\x9d|' ==> ['b9', 'a5', '9d'] ==> Hex: ['0x64', '0xb9', '0x60', '0xa5', '0x9d', '0x7c'] ==> DEG: 23.85 °C
b'd\xa7<\xa5\xa3\xa6' ==> ['a7', 'a5', 'a3', 'a6'] ==> Hex: ['0x64', '0xa7', '0x3c', '0xa5', '0xa3', '0xa6'] ==> DEG: 23.81 °C
b'd\xb1\xd9\xa5\x9a\xeb' ==> ['b1', 'd9', 'a5', '9a', 'eb'] ==> Hex: ['0x64', '0xb1', '0xd9', '0xa5', '0x9a', '0xeb'] ==> DEG: 23.83 °C
b'd\xb8Q\xa5\x94\xf4' ==> ['b8', 'a5', '94', 'f4'] ==> Hex: ['0x64', '0xb8', '0x51', '0xa5', '0x94', '0xf4'] ==> DEG: 23.85 °C
b'd\xb9`\xa5\x89\xfb' ==> ['b9', 'a5', '89', 'fb'] ==> Hex: ['0x64', '0xb9', '0x60', '0xa5', '0x89', '0xfb'] ==> DEG: 23.85 °C
b'd\xb8Q\xa5xH' ==> ['b8', 'a5'] ==> Hex: ['0x64', '0xb8', '0x51', '0xa5', '0x78', '0x48'] ==> DEG: 23.85 °C
b'd\xb3\xbb\xa5\x91\x01' ==> ['b3', 'bb', 'a5', '91', '01'] ==> Hex: ['0x64', '0xb3', '0xbb', '0xa5', '0x91', '0x01'] ==> DEG: 23.84 °C
b'd\xb0\xe8\xa5\x96\x96' ==> ['b0', 'e8', 'a5', '96', '96'] ==> Hex: ['0x64', '0xb0', '0xe8', '0xa5', '0x96', '0x96'] ==> DEG: 23.83 °C
b'd\xba3\xa5\x7f\xdf' ==> ['ba', 'a5', '7f', 'df'] ==> Hex: ['0x64', '0xba', '0x33', '0xa5', '0x7f', '0xdf'] ==> DEG: 23.86 °C
b'd\xb2\x8a\xa5xH' ==> ['b2', '8a', 'a5'] ==> Hex: ['0x64', '0xb2', '0x8a', '0xa5', '0x78', '0x48'] ==> DEG: 23.84 °C
b'd\xaap\xa5s\xa2' ==> ['aa', 'a5', 'a2'] ==> Hex: ['0x64', '0xaa', '0x70', '0xa5', '0x73', '0xa2'] ==> DEG: 23.81 °C
b'd\xabA\xa5s\xa2' ==> ['ab', 'a5', 'a2'] ==> Hex: ['0x64', '0xab', '0x41', '0xa5', '0x73', '0xa2'] ==> DEG: 23.82 °C
b'd\xba3\xa5\x81B' ==> ['ba', 'a5', '81'] ==> Hex: ['0x64', '0xba', '0x33', '0xa5', '0x81', '0x42'] ==> DEG: 23.86 °C
b'd\xb8Q\xa5n\xad' ==> ['b8', 'a5', 'ad'] ==> Hex: ['0x64', '0xb8', '0x51', '0xa5', '0x6e', '0xad'] ==> DEG: 23.85 °C
b'd\xb2\x8a\xa5yy' ==> ['b2', '8a', 'a5'] ==> Hex: ['0x64', '0xb2', '0x8a', '0xa5', '0x79', '0x79'] ==> DEG: 23.84 °C
b'd\xac\xd6\xa5h\x0b' ==> ['ac', 'd6', 'a5', '0b'] ==> Hex: ['0x64', '0xac', '0xd6', '0xa5', '0x68', '0x0b'] ==> DEG: 23.82 °C
b'd\xb6N\xa5n\xad' ==> ['b6', 'a5', 'ad'] ==> Hex: ['0x64', '0xb6', '0x4e', '0xa5', '0x6e', '0xad'] ==> DEG: 23.85 °C
b'd\xabA\xa5wf' ==> ['ab', 'a5'] ==> Hex: ['0x64', '0xab', '0x41', '0xa5', '0x77', '0x66'] ==> DEG: 23.82 °C
b'd\xad\xe7\xa5l\xcf' ==> ['ad', 'e7', 'a5', 'cf'] ==> Hex: ['0x64', '0xad', '0xe7', '0xa5', '0x6c', '0xcf'] ==> DEG: 23.82 °C
b'd\xbc\x95\xa5i:' ==> ['bc', '95', 'a5'] ==> Hex: ['0x64', '0xbc', '0x95', '0xa5', '0x69', '0x3a'] ==> DEG: 23.86 °C
b'd\xb3\xbb\xa5];' ==> ['b3', 'bb', 'a5'] ==> Hex: ['0x64', '0xb3', '0xbb', '0xa5', '0x5d', '0x3b'] ==> DEG: 23.84 °C
b'd\xb1\xd9\xa5eG' ==> ['b1', 'd9', 'a5'] ==> Hex: ['0x64', '0xb1', '0xd9', '0xa5', '0x65', '0x47'] ==> DEG: 23.83 °C
b'd\xbb\x02\xa5s\xa2' ==> ['bb', '02', 'a5', 'a2'] ==> Hex: ['0x64', '0xbb', '0x02', '0xa5', '0x73', '0xa2'] ==> DEG: 23.86 °C
b'd\xac\xd6\xa5p\xf1' ==> ['ac', 'd6', 'a5', 'f1'] ==> Hex: ['0x64', '0xac', '0xd6', '0xa5', '0x70', '0xf1'] ==> DEG: 23.82 °C
b'd\xad\xe7\xa5\\\n' ==> ['ad', 'e7', 'a5'] ==> Hex: ['0x64', '0xad', '0xe7', '0xa5', '0x5c', '0x5c', '0x5c', '0x6e'] ==> DEG: 23.82 °C
b'\n' ==> [] ==> Hex: ['0x5c', '0x6e'] ==> DEG: 18.19 °C
b'd\n' ==> [] ==> Hex: ['0x64', '0x5c', '0x6e'] ==> DEG: 23.61 °C
b'd\xbc\x95\xa5O\x1a' ==> ['bc', '95', 'a5', '1a'] ==> Hex: ['0x64', '0xbc', '0x95', '0xa5', '0x4f', '0x1a'] ==> DEG: 23.86 °C
b'd\xb1\xd9\xa5LI' ==> ['b1', 'd9', 'a5'] ==> Hex: ['0x64', '0xb1', '0xd9', '0xa5', '0x4c', '0x49'] ==> DEG: 23.83 °C
"""

• 半年后发现的办法

# 原始字节数据
byte_data = b'd\xad\xe7\xa5\\\n'

# 转换为十六进制字符串
hex_data = byte_data.hex()

# 打印结果
print(hex_data)

"""
输出:
'64ade7a55c0a'
"""

# 如果需要将十六进制字符串格式化成每个字节两位并用空格分隔的形式，可以使用以下代码

# 原始字节数据
byte_data = b'd\xad\xe7\xa5\\\n'

# 转换为十六进制字符串并分隔每个字节
hex_data = byte_data.hex()
formatted_hex = ' '.join([hex_data[i:i+2] for i in range(0, len(hex_data), 2)])

# 打印结果
print(formatted_hex)