# 解析web端提交的bytes信息，返回str信息（可以解析中文信息）
def parse_data(msg):
    global g_code_length
    g_code_length = msg[1] & 127
    if g_code_length == 126:
        g_code_length = struct.unpack('>H', msg[2:4])[0]
        masks = msg[4:8]
        data = msg[8:]
    elif g_code_length == 127:
        g_code_length = struct.unpack('>Q', msg[2:10])[0]
        masks = msg[10:14]
        data = msg[14:]
    else:
        masks = msg[2:6]
        data = msg[6:]
    en_bytes = b""
    cn_bytes = []
    for i, d in enumerate(data):
        nv = chr(d ^ masks[i%4])
        nv_bytes = nv.encode()
        nv_len = len(nv_bytes)
        if nv_len == 1:
            en_bytes += nv_bytes
        else:
            en_bytes += b'%s'
            cn_bytes.append(ord(nv_bytes.decode()))
    if len(cn_bytes) > 2:
        cn_str = ""
        clen = len(cn_bytes)
        count = int(clen / 3)
        for x in range(count):
            i = x * 3
            b = bytes([cn_bytes[i], cn_bytes[i + 1], cn_bytes[i + 2]])
            cn_str += b.decode()
        new = en_bytes.replace(b'%s%s%s', b'%s')
        new = new.decode()
        res = (new % tuple(list(cn_str)))
    else:
        res = en_bytes.decode()
    return res

說明

此函數(shù)需要著重關(guān)注這個地方:

for i, d in enumerate(data):
        nv = chr(d ^ masks[i%4])
        nv_bytes = nv.encode()
        nv_len = len(nv_bytes)
        if nv_len == 1:
            en_bytes += nv_bytes
        else:
            en_bytes += b'%s'
            cn_bytes.append(ord(nv_bytes.decode()))

nv是解除掩碼后的數(shù)據(jù)，通過nv.encode()的方式編碼后計(jì)算編碼后的bytes長度，如果長度不為1，則作為非英文字符處理，考慮到中英文混雜的情況，需要添加占位符。