哈希校验

MD5/SHA1/SHA256 文件哈希、HMAC 消息认证码、文件完整性校验、密码哈希(bcrypt)——生产级脚本。

一、Python 哈希计算

1.1 字符串哈希（MD5 / SHA1 / SHA256）

#!/usr/bin/env python3
"""字符串哈希——一行生成摘要"""
import hashlib

def hash_string(text, algo='sha256'):
    """对字符串做哈希，返回十六进制字符串"""
    h = hashlib.new(algo)
    h.update(text.encode('utf-8'))
    return h.hexdigest()

# ---- 示例 ----
text = "Hello, 你好世界"
print("MD5:   ", hash_string(text, 'md5'))
print("SHA1:  ", hash_string(text, 'sha1'))
print("SHA256:", hash_string(text, 'sha256'))
print("SHA512:", hash_string(text, 'sha512'))
# 输出：
# MD5:    f228ee31a40cd94b0d239b6bad1ca43f
# SHA1:   cec1b98e4bc6cd39c2763ce7a6cdd1d3e00763e0
# SHA256: b6fd48fdd2a0f9caa3fa0c054f1b128567097c3b...

1.2 文件哈希——验证下载完整性

#!/usr/bin/env python3
"""文件哈希——适合大文件（分块读取，不占内存）"""
import hashlib, sys

def file_hash(filepath, algo='sha256', chunk_size=8192):
    """计算文件哈希——分块读，大文件无压力"""
    h = hashlib.new(algo)
    with open(filepath, 'rb') as f:
        while True:
            chunk = f.read(chunk_size)
            if not chunk:
                break
            h.update(chunk)
    return h.hexdigest()

# ---- 命令行工具 ----
if __name__ == '__main__':
    if len(sys.argv) < 2:
        print(f"用法: {sys.argv[0]} <文件路径> [算法: sha256/md5/sha1/sha512]")
        sys.exit(1)

    path = sys.argv[1]
    algo = sys.argv[2] if len(sys.argv) > 2 else 'sha256'
    digest = file_hash(path, algo)
    print(f"{algo.upper()}: {digest}  {path}")

1.3 HMAC——消息认证码（防篡改 + 身份验证）

HMAC = 哈希 + 密钥，用于验证消息在传输中未被篡改，同时证明来源身份：

#!/usr/bin/env python3
"""HMAC——带密钥的消息认证码"""
import hmac, hashlib

def hmac_sign(message, secret, algo='sha256'):
    """生成 HMAC 签名"""
    key = secret.encode('utf-8') if isinstance(secret, str) else secret
    msg = message.encode('utf-8') if isinstance(message, str) else message
    return hmac.new(key, msg, algo).hexdigest()

def hmac_verify(message, secret, signature, algo='sha256'):
    """验证 HMAC 签名——常量时间比较防时序攻击"""
    expected = hmac_sign(message, secret, algo)
    return hmac.compare_digest(expected, signature)  # 安全比较！

# ---- 示例：API 签名 ----
SECRET = "my-api-secret-key"
payload = '{"user":"alice","amount":100}'

sig = hmac_sign(payload, SECRET)
print(f"签名: {sig}")

# 模拟接收端验证
is_valid = hmac_verify(payload, SECRET, sig)
print(f"验证通过: {is_valid}")

# 模拟篡改检测
tampered = '{"user":"alice","amount":99999}'
is_valid2 = hmac_verify(tampered, SECRET, sig)
print(f"篡改检测: {is_valid2}")    # False——一击必现

1.4 密码哈希——bcrypt（scrypt / argon2）

#!/usr/bin/env python3
"""密码存储——绝不能存明文或 MD5，用 bcrypt !"""
import bcrypt

# ---- 注册：哈希密码 ----
password = "user_password_123"
password_bytes = password.encode('utf-8')

# 生成 salt + 哈希（cost=12 表示 2^12 轮迭代）
hashed = bcrypt.hashpw(password_bytes, bcrypt.gensalt(rounds=12))
print(f"存入数据库: {hashed.decode()}")

# ---- 登录：验证密码 ----
login_attempt = "user_password_123"
is_correct = bcrypt.checkpw(login_attempt.encode('utf-8'), hashed)
print(f"密码正确: {is_correct}")                           # True

login_attempt_wrong = "wrong_password"
is_correct = bcrypt.checkpw(login_attempt_wrong.encode('utf-8'), hashed)
print(f"错误密码: {is_correct}")                           # False

# ⚠️ 为什么不用 SHA256(salt + password)？
#    SHA 太快了——攻击者可以每秒尝试百万次
#    bcrypt 故意慢——12 rounds 约 0.3秒/次

二、Shell 一行哈希

#!/bin/bash

# ===== 字符串哈希 =====
echo -n "hello" | md5sum        # 5d41402abc4b2a76b9719d911017c592
echo -n "hello" | sha1sum       # aaf4c61ddcc5e8a2dabede0f3b482cd9aea9434d
echo -n "hello" | sha256sum     # 2cf24dba5fb0a30e26e83b2ac5b9e29e1b161e...

# ===== 文件哈希 =====
md5sum file.tar.gz               # MD5
sha1sum file.tar.gz              # SHA1
sha256sum file.tar.gz            # SHA256（推荐）
sha512sum file.tar.gz            # SHA512

# ===== 批量校验（.sha256 文件）=====
sha256sum -c file.tar.gz.sha256  # 自动读取校验文件

# ===== HMAC（用 openssl）=====
echo -n "message" | openssl dgst -sha256 -hmac "secret-key"

# ===== bcrypt 替代（用 htpasswd）=====
htpasswd -nbB alice "my_password" | cut -d: -f2

三、实战：文件完整性校验工具

#!/usr/bin/env python3
"""
一键生成 + 验证文件校验和
用法：
  python hash_tool.py gen    dir/       # 生成所有文件的 sha256
  python hash_tool.py check  dir/       # 校验所有文件
"""
import os, sys, hashlib, json
from pathlib import Path

CHECKSUM_FILE = ".checksums.json"

def gen_checksums(root_dir):
    """递归生成目录下所有文件的 SHA256"""
    checksums = {}
    for path in Path(root_dir).rglob("*"):
        if path.is_file() and path.name != CHECKSUM_FILE:
            h = hashlib.sha256()
            with open(path, 'rb') as f:
                while chunk := f.read(65536):
                    h.update(chunk)
            checksums[str(path.relative_to(root_dir))] = h.hexdigest()
    with open(Path(root_dir) / CHECKSUM_FILE, 'w') as f:
        json.dump(checksums, f, indent=2)
    print(f"✅ 已生成 {len(checksums)} 个文件的校验和")

def check_checksums(root_dir):
    """校验目录下所有文件"""
    chk_path = Path(root_dir) / CHECKSUM_FILE
    if not chk_path.exists():
        print("❌ 未找到校验文件，请先运行 gen")
        return 1
    checksums = json.loads(chk_path.read_text())
    ok = fail = missing = 0
    for rel, expected in checksums.items():
        path = Path(root_dir) / rel
        if not path.exists():
            print(f"❌ 缺失: {rel}")
            missing += 1; continue
        h = hashlib.sha256()
        with open(path, 'rb') as f:
            while chunk := f.read(65536): h.update(chunk)
        if h.hexdigest() == expected: ok += 1
        else: print(f"❌ 校验失败: {rel}"); fail += 1
    print(f"✅ {ok} ok  ❌ {fail} fail  ⚠️ {missing} missing")
    return 0 if fail == 0 and missing == 0 else 1

if __name__ == '__main__':
    cmd = sys.argv[1] if len(sys.argv) > 1 else 'gen'
    root = sys.argv[2] if len(sys.argv) > 2 else '.'
    {'gen': gen_checksums, 'check': check_checksums}[cmd](root)