从原理到高级详解Python中Base64编码与解码的完全指南

import base64

# 编码示例
original_data = b"hello, world!"
encoded_data = base64.b64encode(original_data)
print(f"编码结果: {encoded_data.decode('utf-8')}")
# 输出: sgvsbg8sifdvcmxkiq==

# 解码示例
decoded_data = base64.b64decode(encoded_data)
print(f"解码结果: {decoded_data.decode('utf-8')}")
# 输出: hello, world!

text_data = "你好，世界！"

# 编码前先将字符串转换为字节
encoded_text = base64.b64encode(text_data.encode('utf-8'))
print(f"base64编码文本: {encoded_text.decode('utf-8')}")

# 解码后转换回字符串
decoded_text = base64.b64decode(encoded_text).decode('utf-8')
print(f"解码后文本: {decoded_text}")

data = b"\xfb\x00\x01\x02"

# 标准base64编码
standard_encoded = base64.b64encode(data)
print(f"标准编码: {standard_encoded.decode()}")  # 输出: +wabag==

# url安全编码
urlsafe_encoded = base64.urlsafe_b64encode(data)
print(f"url安全编码: {urlsafe_encoded.decode()}")  # 输出: -wabag==

# 对应的解码操作
decoded_data = base64.urlsafe_b64decode(urlsafe_encoded)
print(f"解码数据: {decoded_data}")  # 输出: b'\xfb\x00\x01\x02'

def image_to_base64(image_path):
    """将图片文件转换为base64字符串"""
    with open(image_path, 'rb') as img_file:
        encoded_string = base64.b64encode(img_file.read()).decode('utf-8')
    return f"data:image/{image_path.split('.')[-1]};base64,{encoded_string}"

def base64_to_image(encoded_string, output_path):
    """将base64字符串保存为图片文件"""
    # 去除可能的数据uri前缀
    if ',' in encoded_string:
        encoded_string = encoded_string.split(',')[1]
    
    img_data = base64.b64decode(encoded_string)
    with open(output_path, 'wb') as img_file:
        img_file.write(img_data)

# 使用示例
# image_base64 = image_to_base64('logo.png')
# base64_to_image(image_base64, 'decoded_logo.png')

import json
import base64

# 创建包含二进制数据的字典
binary_data = b'binary data here'
data_dict = {
    'text_field': '普通文本',
    'binary_field': base64.b64encode(binary_data).decode('utf-8'),
    'metadata': {'type': 'example', 'size': len(binary_data)}
}

# 转换为json字符串
json_data = json.dumps(data_dict)
print(f"json数据: {json_data}")

# 从json解析并解码base64数据
parsed_data = json.loads(json_data)
decoded_binary = base64.b64decode(parsed_data['binary_field'])
print(f"解码后的二进制数据: {decoded_binary}")

def encode_large_file(input_path, output_path, chunk_size=8192):
    """分块编码大文件为base64"""
    with open(input_path, 'rb') as fin, open(output_path, 'w') as fout:
        while chunk := fin.read(chunk_size):
            encoded_chunk = base64.b64encode(chunk).decode('utf-8')
            fout.write(encoded_chunk)

def decode_large_file(input_path, output_path, chunk_size=10920):
    """分块解码base64文件"""
    # 计算适当的块大小（base64编码后尺寸增加约33%）
    with open(input_path, 'r') as fin, open(output_path, 'wb') as fout:
        while chunk := fin.read(chunk_size):
            # 处理可能的不完整块
            padding = 4 - (len(chunk) % 4)
            if padding != 4:
                chunk += '=' * padding
            decoded_chunk = base64.b64decode(chunk)
            fout.write(decoded_chunk)

import binascii

def safe_b64decode(encoded_string):
    """安全地解码base64字符串，处理各种异常情况"""
    if not isinstance(encoded_string, (str, bytes)):
        raise valueerror("输入必须是字符串或字节")
    
    if isinstance(encoded_string, str):
        encoded_string = encoded_string.encode('utf-8')
    
    # 处理填充缺失的情况
    padding_needed = 4 - (len(encoded_string) % 4)
    if padding_needed != 4:
        encoded_string += b'=' * padding_needed
    
    try:
        return base64.b64decode(encoded_string)
    except binascii.error as e:
        print(f"base64解码错误: {e}")
        return none

# 使用示例
invalid_data = "sgvsbg8gv29ybgq"  # 缺少填充
decoded = safe_b64decode(invalid_data)
if decoded:
    print(f"解码成功: {decoded.decode('utf-8')}")

# 使用pybase64提高性能（需要安装：pip install pybase64）
try:
    import pybase64 as base64
except importerror:
    import base64
    print("使用标准base64库，如需更好性能请安装pybase64")

# 性能对比
data = b"x" * 1000000  # 1mb数据

# 标准库性能
import time
start = time.time()
encoded = base64.b64encode(data)
decoded = base64.b64decode(encoded)
end = time.time()
print(f"处理时间: {end - start:.4f}秒")

# base64不是加密！任何人都可以轻松解码
sensitive_data = "密码123"
encoded = base64.b64encode(sensitive_data.encode('utf-8'))
print(f"base64编码后的敏感数据: {encoded.decode('utf-8')}")  # 可轻松解码

# 对于真正敏感的数据，应该使用加密算法
from cryptography.fernet import fernet

# 生成密钥
key = fernet.generate_key()
cipher = fernet(key)

# 加密数据
encrypted_data = cipher.encrypt(sensitive_data.encode('utf-8'))
print(f"真正加密的数据: {encrypted_data}")

def encode_email_attachment(file_path):
    """编码电子邮件附件"""
    with open(file_path, 'rb') as f:
        file_data = f.read()
    
    encoded_content = base64.b64encode(file_data).decode('ascii')
    
    # 按rfc要求添加换行符（每76个字符）
    lines = []
    for i in range(0, len(encoded_content), 76):
        lines.append(encoded_content[i:i+76])
    
    return '\n'.join(lines)

def decode_email_attachment(encoded_content, output_path):
    """解码电子邮件附件"""
    # 移除可能存在的换行符
    encoded_content = encoded_content.replace('\n', '')
    file_data = base64.b64decode(encoded_content)
    
    with open(output_path, 'wb') as f:
        f.write(file_data)

import requests
import base64

def create_basic_auth_header(username, password):
    """创建http basic认证头"""
    credentials = f"{username}:{password}"
    encoded_credentials = base64.b64encode(credentials.encode('utf-8')).decode('utf-8')
    return {'authorization': f'basic {encoded_credentials}'}

# 使用示例
headers = create_basic_auth_header('user', 'pass')
response = requests.get('https://api.example.com/data', headers=headers)

<!-- 在html中直接嵌入图片 -->
<img src="data:image/png;base64,ivborw0kggoaaaansuheugaaaaua..." alt="base64嵌入图片">

<!-- 在css中嵌入字体 -->
<style>
@font-face {
    font-family: 'myfont';
    src: url(data:font/woff2;base64,d09gmgabaaaa...) format('woff2');
}
</style>