Python中bytes与str类型的转换技巧

1text = "Hello, 世界"
2
3# 使用UTF-8编码（最常用）
4bytes_data = text.encode('utf-8')
5print(bytes_data)  # 输出: b'Hello, \xe4\xb8\x96\xe7\x95\x8c'
6
7# 使用GBK编码（中文常用）
8bytes_gbk = text.encode('gbk')
9print(bytes_gbk)  # 输出: b'Hello, \xca\xc0\xbd\xe7'
10
11# 忽略无法编码的字符（不推荐）
12bytes_ignore = text.encode('ascii', errors='ignore')
13print(bytes_ignore)  # 输出: b'Hello, '
14

1bytes_data = b'Hello, \xe4\xb8\x96\xe7\x95\x8c'
2
3# 使用UTF-8解码
4text = bytes_data.decode('utf-8')
5print(text)  # 输出: Hello, 世界
6
7# 使用GBK解码（会报错，因为原始数据是UTF-8编码的）
8try:
9    text_gbk = bytes_data.decode('gbk')
10except UnicodeDecodeError as e:
11    print(f"解码错误: {e}")
12
13# 处理可能的解码错误
14safe_text = bytes_data.decode('utf-8', errors='replace')
15print(safe_text)  # 无法解码的字符会被替换为?
16

1# 写入文本文件（自动编码为系统默认编码）
2with open('text.txt', 'w', encoding='utf-8') as f:
3    f.write("这是文本内容")
4
5# 读取文本文件
6with open('text.txt', 'r', encoding='utf-8') as f:
7    content = f.read()
8
9# 二进制文件操作
10with open('image.png', 'rb') as f:
11    image_data = f.read()  # 得到bytes
12
13with open('copy.png', 'wb') as f:
14    f.write(image_data)  # 写入bytes
15

1import requests
2
3# 发送GET请求（响应内容通常是bytes）
4response = requests.get('https://example.com')
5print(type(response.content))  # <class 'bytes'>
6
7# 解码为字符串
8html_text = response.content.decode('utf-8')
9print(type(html_text))  # <class 'str'>
10
11# 或者直接使用text属性（requests会自动解码）
12html_text = response.text
13

1import socket
2
3# 创建socket
4s = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
5s.connect(('example.com', 80))
6
7# 发送HTTP请求（需要编码为bytes）
8request = "GET / HTTP/1.1\r\nHost: example.com\r\n\r\n"
9s.send(request.encode('utf-8'))
10
11# 接收响应（得到bytes）
12response = s.recv(4096)
13print(response.decode('utf-8'))  # 解码为字符串
14
15s.close()
16

1import chardet
2
3bytes_data = b'\xe4\xb8\xad\xe6\x96\x87'
4result = chardet.detect(bytes_data)
5print(result)  # {'encoding': 'UTF-8', 'confidence': 0.99, 'language': ''}
6
7text = bytes_data.decode(result['encoding'])
8print(text)  # 中文
9

1def safe_decode(bytes_data, default_encoding='utf-8'):
2    try:
3        return bytes_data.decode('utf-8')
4    except UnicodeDecodeError:
5        try:
6            return bytes_data.decode('gbk')
7        except UnicodeDecodeError:
8            return bytes_data.decode(default_encoding, errors='replace')
9
10mixed_bytes = b'abc\xe4\xb8\xad\xff'
11print(safe_decode(mixed_bytes))  # abc中?
12

1def batch_encode(texts, encoding='utf-8'):
2    return (text.encode(encoding) for text in texts)
3
4def batch_decode(bytes_list, encoding='utf-8'):
5    return (b.decode(encoding) for b in bytes_list)
6
7texts = ["文本1", "文本2", "文本3"]
8encoded = list(batch_encode(texts))
9decoded = list(batch_decode(encoded))
10