Python 开发模式

Python 开发模式 是做什么的？

构建稳健、高效、可维护应用的 Python 惯用模式与最佳实践。

激活时机

• 编写新的 Python 代码时
• 审查 Python 代码时
• 重构现有 Python 代码时
• 设计 Python 包/模块时

核心原则

1. 可读性至上

Python 优先考虑可读性。代码应清晰易懂。

# 好：清晰且可读
def get_active_users(users: list[User]) -> list[User]:
    """从提供的列表中仅返回活跃用户。"""
    return [user for user in users if user.is_active]


# 差：巧妙但令人困惑
def get_active_users(u):
    return [x for x in u if x.a]

2. 显式优于隐式

避免魔法；明确你的代码做了什么。

# 好：显式配置
import logging

logging.basicConfig(
    level=logging.INFO,
    format='%(asctime)s - %(name)s - %(levelname)s - %(message)s'
)

# 差：隐藏的副作用
import some_module
some_module.setup()  # 这是做什么的？

3. EAFP —— 比起请求许可，更容易请求原谅

Python 更倾向于异常处理而非条件检查。

# 好：EAFP 风格
def get_value(dictionary: dict, key: str, default_value: Any = None) -> Any:
    try:
        return dictionary[key]
    except KeyError:
        return default_value

# 差：LBYL（三思而后行）风格
def get_value(dictionary: dict, key: str, default_value: Any = None) -> Any:
    if key in dictionary:
        return dictionary[key]
    else:
        return default_value

类型提示

基本类型注解

from typing import Optional, List, Dict, Any

def process_user(
    user_id: str,
    data: Dict[str, Any],
    active: bool = True
) -> Optional[User]:
    """处理用户并返回更新后的用户或 None。"""
    if not active:
        return None
    return User(user_id, data)

现代类型提示 (Python 3.9+)

# Python 3.9+ - 使用内置类型
def process_items(items: list[str]) -> dict[str, int]:
    return {item: len(item) for item in items}

# Python 3.8 及更早版本 - 使用 typing 模块
from typing import List, Dict

def process_items(items: List[str]) -> Dict[str, int]:
    return {item: len(item) for item in items}

类型别名与 TypeVar

from typing import TypeVar, Union

# 复杂类型的类型别名
JSON = Union[dict[str, Any], list[Any], str, int, float, bool, None]

def parse_json(data: str) -> JSON:
    return json.loads(data)

# 泛型类型
T = TypeVar('T')

def first(items: list[T]) -> T | None:
    """返回第一个元素，如果列表为空则返回 None。"""
    return items[0] if items else None

基于协议的鸭子类型

from typing import Protocol

class Renderable(Protocol):
    def render(self) -> str:
        """将对象渲染为字符串。"""

def render_all(items: list[Renderable]) -> str:
    """渲染所有实现 Renderable 协议的对象。"""
    return "\n".join(item.render() for item in items)

错误处理模式

捕获特定异常

# 好：捕获特定异常
def load_config(path: str) -> Config:
    try:
        with open(path) as f:
            return Config.from_json(f.read())
    except FileNotFoundError as e:
        raise ConfigError(f"配置文件未找到: {path}") from e
    except json.JSONDecodeError as e:
        raise ConfigError(f"配置 JSON 无效: {path}") from e

# 差：裸 except
def load_config(path: str) -> Config:
    try:
        with open(path) as f:
            return Config.from_json(f.read())
    except:
        return None  # 静默失败！

异常链

def process_data(data: str) -> Result:
    try:
        parsed = json.loads(data)
    except json.JSONDecodeError as e:
        # 链接异常以保留回溯信息
        raise ValueError(f"解析数据失败: {data}") from e

自定义异常层次结构

class AppError(Exception):
    """所有应用程序异常的基类。"""
    pass

class ValidationError(AppError):
    """当输入验证失败时抛出。"""
    pass

class NotFoundError(AppError):
    """当请求的资源未找到时抛出。"""
    pass

# 使用
def get_user(user_id: str) -> User:
    user = db.find_user(user_id)
    if not user:
        raise NotFoundError(f"用户未找到: {user_id}")
    return user

上下文管理器

资源管理

# 好：使用上下文管理器
def process_file(path: str) -> str:
    with open(path, 'r') as f:
        return f.read()

# 差：手动资源管理
def process_file(path: str) -> str:
    f = open(path, 'r')
    try:
        return f.read()
    finally:
        f.close()

自定义上下文管理器

from contextlib import contextmanager

@contextmanager
def timer(name: str):
    """对代码块进行计时的上下文管理器。"""
    start = time.perf_counter()
    yield
    elapsed = time.perf_counter() - start
    print(f"{name} 耗时 {elapsed:.4f} 秒")

# 使用
with timer("数据处理"):
    process_large_dataset()

基于类的上下文管理器

class DatabaseTransaction:
    def __init__(self, connection):
        self.connection = connection

    def __enter__(self):
        self.connection.begin_transaction()
        return self

    def __exit__(self, exc_type, exc_val, exc_tb):
        if exc_type is None:
            self.connection.commit()
        else:
            self.connection.rollback()
        return False  # 不抑制异常

# 使用
with DatabaseTransaction(conn):
    user = conn.create_user(user_data)
    conn.create_profile(user.id, profile_data)

推导式与生成器

列表推导式

# 好：用于简单转换的列表推导式
names = [user.name for user in users if user.is_active]

# 差：手动循环
names = []
for user in users:
    if user.is_active:
        names.append(user.name)

# 复杂的推导式应展开
# 差：过于复杂
result = [x * 2 for x in items if x > 0 if x % 2 == 0]

# 好：使用生成器函数
def filter_and_transform(items: Iterable[int]) -> list[int]:
    result = []
    for x in items:
        if x > 0 and x % 2 == 0:
            result.append(x * 2)
    return result

生成器表达式

# 好：用于惰性求值的生成器
total = sum(x * x for x in range(1_000_000))

# 差：创建大型中间列表
total = sum([x * x for x in range(1_000_000)])

生成器函数

def read_large_file(path: str) -> Iterator[str]:
    """逐行读取大型文件。"""
    with open(path) as f:
        for line in f:
            yield line.strip()

# 使用
for line in read_large_file("huge.txt"):
    process(line)

数据类与命名元组

数据类

from dataclasses import dataclass, field
from datetime import datetime

@dataclass
class User:
    """用户实体，包含自动生成的 __init__、__repr__ 和 __eq__。"""
    id: str
    name: str
    email: str
    created_at: datetime = field(default_factory=datetime.now)
    is_active: bool = True

# 使用
user = User(
    id="123",
    name="Alice",
    email="[email protected]"
)

带验证的数据类

@dataclass
class User:
    email: str
    age: int

    def __post_init__(self):
        # 验证邮箱格式
        if "@" not in self.email:
            raise ValueError(f"无效邮箱: {self.email}")
        # 验证年龄范围
        if self.age < 0 or self.age > 150:
            raise ValueError(f"无效年龄: {self.age}")

命名元组

from typing import NamedTuple

class Point(NamedTuple):
    """不可变的二维点。"""
    x: float
    y: float

    def distance(self, other: 'Point') -> float:
        return ((self.x - other.x) ** 2 + (self.y - other.y) ** 2) ** 0.5

# 使用
p1 = Point(0, 0)
p2 = Point(3, 4)
print(p1.distance(p2))  # 5.0

装饰器

函数装饰器

import functools
import time

def timer(func: Callable) -> Callable:
    """对函数执行进行计时的装饰器。"""
    @functools.wraps(func)
    def wrapper(*args, **kwargs):
        start = time.perf_counter()
        result = func(*args, **kwargs)
        elapsed = time.perf_counter() - start
        print(f"{func.__name__} 耗时 {elapsed:.4f}s")
        return result
    return wrapper

@timer
def slow_function():
    time.sleep(1)

# slow_function() 输出: slow_function 耗时 1.0012s

参数化装饰器

def repeat(times: int):
    """重复执行函数多次的装饰器。"""
    def decorator(func: Callable) -> Callable:
        @functools.wraps(func)
        def wrapper(*args, **kwargs):
            results = []
            for _ in range(times):
                results.append(func(*args, **kwargs))
            return results
        return wrapper
    return decorator

@repeat(times=3)
def greet(name: str) -> str:
    return f"Hello, {name}!"

# greet("Alice") 返回 ["Hello, Alice!", "Hello, Alice!", "Hello, Alice!"]

基于类的装饰器

class CountCalls:
    """统计函数被调用次数的装饰器。"""
    def __init__(self, func: Callable):
        functools.update_wrapper(self, func)
        self.func = func
        self.count = 0

    def __call__(self, *args, **kwargs):
        self.count += 1
        print(f"{self.func.__name__} 已被调用 {self.count} 次")
        return self.func(*args, **kwargs)

@CountCalls
def process():
    pass

# 每次调用 process() 都会打印调用次数

并发模式

用于 I/O 密集型任务的线程

import concurrent.futures
import threading

def fetch_url(url: str) -> str:
    """获取 URL（I/O 密集型操作）。"""
    import urllib.request
    with urllib.request.urlopen(url) as response:
        return response.read().decode()

def fetch_all_urls(urls: list[str]) -> dict[str, str]:
    """使用线程并发获取多个 URL。"""
    with concurrent.futures.ThreadPoolExecutor(max_workers=10) as executor:
        future_to_url = {executor.submit(fetch_url, url): url for url in urls}
        results = {}
        for future in concurrent.futures.as_completed(future_to_url):
            url = future_to_url[future]
            try:
                results[url] = future.result()
            except Exception as e:
                results[url] = f"Error: {e}"
    return results

用于 CPU 密集型任务的多进程

def process_data(data: list[int]) -> int:
    """CPU 密集型计算。"""
    return sum(x ** 2 for x in data)

def process_all(datasets: list[list[int]]) -> list[int]:
    """使用多进程处理多个数据集。"""
    with concurrent.futures.ProcessPoolExecutor() as executor:
        results = list(executor.map(process_data, datasets))
    return results

用于并发 I/O 的 Async/Await

import asyncio

async def fetch_async(url: str) -> str:
    """异步获取 URL。"""
    import aiohttp
    async with aiohttp.ClientSession() as session:
        async with session.get(url) as response:
            return await response.text()

async def fetch_all(urls: list[str]) -> dict[str, str]:
    """并发获取多个 URL。"""
    tasks = [fetch_async(url) for url in urls]
    results = await asyncio.gather(*tasks, return_exceptions=True)
    return dict(zip(urls, results))

包组织

标准项目布局

myproject/
├── src/
│   └── mypackage/
│       ├── __init__.py
│       ├── main.py
│       ├── api/
│       │   ├── __init__.py
│       │   └── routes.py
│       ├── models/
│       │   ├── __init__.py
│       │   └── user.py
│       └── utils/
│           ├── __init__.py
│           └── helpers.py
├── tests/
│   ├── __init__.py
│   ├── conftest.py
│   ├── test_api.py
│   └── test_models.py
├── pyproject.toml
├── README.md
└── .gitignore

导入约定

# 好：导入顺序 - 标准库、第三方、本地
import os
import sys
from pathlib import Path

import requests
from fastapi import FastAPI

from mypackage.models import User
from mypackage.utils import format_name

# 好：使用 isort 自动排序导入
# pip install isort

用于包导出的 init.py

# mypackage/__init__.py
"""mypackage - 一个示例 Python 包。"""

__version__ = "1.0.0"

# 在包级别导出主类/函数
from mypackage.models import User, Post
from mypackage.utils import format_name

__all__ = ["User", "Post", "format_name"]

内存与性能

使用 slots 提高内存效率

# 差：常规类使用 __dict__（更占用内存）
class Point:
    def __init__(self, x: float, y: float):
        self.x = x
        self.y = y

# 好：__slots__ 减少内存使用
class Point:
    __slots__ = ['x', 'y']

    def __init__(self, x: float, y: float):
        self.x = x
        self.y = y

用于大数据处理的生成器

# 差：返回完整列表在内存中
def read_lines(path: str) -> list[str]:
    with open(path) as f:
        return [line.strip() for line in f]

# 好：逐行生成
def read_lines(path: str) -> Iterator[str]:
    with open(path) as f:
        for line in f:
            yield line.strip()

避免在循环中进行字符串拼接

# 差：由于字符串不可变性，时间复杂度为 O(n²)
result = ""
for item in items:
    result += str(item)

# 好：使用 join，时间复杂度为 O(n)
result = "".join(str(item) for item in items)

# 好：使用 StringIO 构建
from io import StringIO

buffer = StringIO()
for item in items:
    buffer.write(str(item))
result = buffer.getvalue()

Python 工具集成

基本命令

# 代码格式化
black .
isort .

# 代码检查
ruff check .

# 类型检查
mypy .

# 测试
pytest .

# 构建
python -m build