Python进阶之路：模块、包与异常处理的实战指南

# 糟糕的示例：所有功能堆砌在一个文件
def add_to_cart(user_id, product_id): ...
def calculate_total(cart): ...
def apply_discount(total, coupon): ...
def process_payment(total, payment_method): ...
def send_order_email(order_data): ...
# 1000行代码后...

# math_utils.py
def add(a, b):
    """加法运算"""
    return a + b

def multiply(a, b):
    """乘法运算"""
    return a * b

# main.py
import math_utils

result = math_utils.add(3, 5)
print(math_utils.multiply(result, 2))  # 输出16

# math_utils.py
__name__  # 模块名（当直接运行时为'__main__'）
__file__  # 模块文件路径
__doc__   # 模块文档字符串

if __name__ == '__main__':
    # 测试代码放在这里
    print(add(2, 3))  # 直接运行时执行，被导入时不执行

my_project/
├── __init__.py
├── utils/
│   ├── __init__.py
│   ├── math_utils.py
│   └── string_utils.py
└── core/
    ├── __init__.py
    ├── order.py
    └── payment.py

# core/order.py
from ..utils import math_utils  # 相对导入上级目录的模块

def calculate_order_total(items):
    total = 0
    for item in items:
        total += math_utils.multiply(item.price, item.quantity)
    return total

def divide(a, b):
    return a / b

print(divide(10, 0))  # 程序崩溃，输出Traceback

try:
    # 可能出错的代码
    result = 10 / 0
except ZeroDivisionError:
    # 处理特定异常
    print("不能除以零！")
except Exception as e:
    # 处理其他异常
    print(f"发生未知错误: {e}")
else:
    # 没有异常时执行
    print("计算成功")
finally:
    # 无论是否异常都执行
    print("计算结束")

class InvalidInputError(Exception):
    """自定义异常类"""
    pass

def validate_age(age):
    if age < 0:
        raise InvalidInputError("年龄不能为负数")
    return age

try:
    # 业务代码
    process_data()
except DatabaseError as e:
    raise ConnectionError("数据库连接失败") from e

# 使用with语句自动处理资源
with open("file.txt") as f:
    data = f.read()
# 无需手动调用f.close()

import logging

logging.basicConfig(filename='app.log', level=logging.ERROR)

try:
    risky_operation()
except Exception as e:
    logging.error(f"操作失败: {str(e)}", exc_info=True)

def calculate_discount(price, discount):
    assert 0 <= discount <= 1, "折扣必须在0-1之间"
    return price * (1 - discount)

web_crawler/
├── __init__.py
├── exceptions.py
├── requester.py
└── parser.py

# exceptions.py
class CrawlerError(Exception):
    """爬虫基础异常"""
    pass

class RequestError(CrawlerError):
    """请求相关异常"""
    pass

class ParseError(CrawlerError):
    """解析相关异常"""
    pass

# requester.py
import requests
from .exceptions import RequestError

def fetch_url(url, max_retries=3):
    for attempt in range(max_retries):
        try:
            headers = {
                'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64)'
            }
            resp = requests.get(url, headers=headers, timeout=10)
            resp.raise_for_status()  # 自动处理HTTP错误
            return resp.text
        except requests.exceptions.RequestException as e:
            if attempt == max_retries - 1:
                raise RequestError(f"请求失败: {str(e)}") from e

# parser.py
from bs4 import BeautifulSoup
from .exceptions import ParseError

def extract_titles(html):
    try:
        soup = BeautifulSoup(html, 'html.parser')
        titles = [h.get_text() for h in soup.find_all(['h1', 'h2', 'h3'])]
        if not titles:
            raise ParseError("未找到标题")
        return titles
    except Exception as e:
        raise ParseError(f"解析失败: {str(e)}") from e

# __init__.py
from .requester import fetch_url
from .parser import extract_titles
from .exceptions import CrawlerError

def crawl_website(url):
    try:
        html = fetch_url(url)
        titles = extract_titles(html)
        return titles
    except CrawlerError as e:
        print(f"爬取失败: {str(e)}")
        return []

import traceback

try:
    risky_operation()
except Exception:
    print("完整堆栈:")
    traceback.print_exc()  # 打印到控制台
    # 或写入文件: traceback.format_exc()