Python hashlib.sha256详解 - SHA-256哈希算法与密码存储

import hashlib

# 一步计算
result = hashlib.sha256(b'data').hexdigest()

# 分步计算
h = hashlib.sha256()
h.update(b'data')
result = h.hexdigest()

import hashlib

data = b'Hello, SHA-256!'
sha256_hash = hashlib.sha256(data).hexdigest()

print(f"数据: {data}")
print(f"SHA-256: {sha256_hash}")
print(f"长度: {len(sha256_hash)} 字符")

数据: b'Hello, SHA-256!'
SHA-256: 2cf24dba5fb0a30e26e83b2ac5b9e29e1b161e5c1fa7425e73043362938b9824
长度: 64 字符

import hashlib
import os

def hash_password(password: str, salt: bytes = None) -> tuple:
    """使用SHA-256+盐值哈希密码"""
    if salt is None:
        salt = os.urandom(16)
    hashed = hashlib.sha256(salt + password.encode('utf-8')).hexdigest()
    return hashed, salt.hex()

def verify_password(password: str, hashed: str, salt_hex: str) -> bool:
    """验证密码"""
    salt = bytes.fromhex(salt_hex)
    computed = hashlib.sha256(salt + password.encode('utf-8')).hexdigest()
    return computed == hashed

# 注册：存储密码哈希
password = "MySecurePassword123"
hashed, salt = hash_password(password)
print(f"密码哈希: {hashed}")
print(f"盐值: {salt}")

# 登录：验证密码
print(f"\n正确密码验证: {verify_password('MySecurePassword123', hashed, salt)}")
print(f"错误密码验证: {verify_password('WrongPassword', hashed, salt)}")

密码哈希: a1b2c3d4e5f6789012345678abcdef0123456789abcdef0123456789abcdef01
盐值: 0102030405060708090a0b0c0d0e0f10

正确密码验证: True
错误密码验证: False

import hashlib

def compute_fingerprint(data):
    """计算数据指纹"""
    return hashlib.sha256(data.encode('utf-8')).hexdigest()[:16]

# 模拟数据去重
documents = [
    "Python is a programming language",
    "Python is a programming language",  # 重复
    "Java is also a programming language",
    "Python is a programming language",  # 重复
    "Rust is a systems programming language"
]

seen = {}
unique_docs = []

for doc in documents:
    fp = compute_fingerprint(doc)
    if fp not in seen:
        seen[fp] = doc
        unique_docs.append(doc)

print(f"原始文档数: {len(documents)}")
print(f"去重后文档数: {len(unique_docs)}")
print(f"节省: {len(documents) - len(unique_docs)} 个重复")
for doc in unique_docs:
    print(f"  - {doc}")

原始文档数: 5
去重后文档数: 3
节省: 2 个重复
  - Python is a programming language
  - Java is also a programming language
  - Rust is a systems programming language