深入探讨Python复合型数据的常见陷阱与避免方法

# 修改可变对象会影响原始列表
original_list = [[1, 2, 3], [4, 5, 6], [7, 8, 9]]
modified_list = original_list
modified_list[0][0] = 100
print(original_list)  # 输出: [[100, 2, 3], [4, 5, 6], [7, 8, 9]]

import copy

original_list = [[1, 2, 3], [4, 5, 6], [7, 8, 9]]

# 浅拷贝
shallow_copy = copy.copy(original_list)
shallow_copy[0][0] = 100
print(original_list)  # 输出: [[100, 2, 3], [4, 5, 6], [7, 8, 9]]

# 深拷贝
deep_copy = copy.deepcopy(original_list)
deep_copy[0][0] = 1000
print(original_list)  # 输出: [[100, 2, 3], [4, 5, 6], [7, 8, 9]]

# 元组中包含可变对象
tuple_with_list = ([1, 2, 3], [4, 5, 6])
tuple_with_list[0][0] = 100
print(tuple_with_list)  # 输出: ([100, 2, 3], [4, 5, 6])

# 集合不支持索引
my_set = {1, 2, 3}
print(my_set[0])  # 报错: 'set' object is not subscriptable

my_dict = {'a': 1, 'b': 2}
my_dict['a'] = 100
print(my_dict)  # 输出: {'a': 100, 'b': 2}

# 字典的键不能是列表
my_dict = {[1, 2]: 'value'}  # 报错: unhashable type: 'list'

import json

# 读取JSON文件
with open('data.json', 'r') as f:
    data = json.load(f)

# 提取数据并清洗
cleaned_data = []
for item in data:
    if 'name' in item and 'age' in item:
        cleaned_data.append({'name': item['name'], 'age': item['age']})

# 打印清洗后的数据
print(cleaned_data)

from bs4 import BeautifulSoup
import requests

​​​​​​​# 发送HTTP请求获取网页内容
url = 'https://example.com'
response = requests.get(url)
html_content = response.text

# 使用BeautifulSoup解析网页内容
soup = BeautifulSoup(html_content, 'html.parser')

# 提取表格数据
table = soup.find('table')
if table:
    rows = table.find_all('tr')
    data = []
    for row in rows:
        cells = row.find_all('td')
        if cells:
            row_data = [cell.text.strip() for cell in cells]
            data.append(row_data)

# 打印提取的表格数据
print(data)

class Student:
    def __init__(self, name, age, courses):
        self.name = name
        self.age = age
        self.courses = courses

​​​​​​​    def __repr__(self):
        return f"Student(name={self.name}, age={self.age}, courses={self.courses})"

# 创建学生对象
student1 = Student('Alice', 20, ['Math', 'Physics', 'Chemistry'])
student2 = Student('Bob', 22, ['History', 'Literature', 'Geography'])

# 打印学生信息
print(student1)
print(student2)

from sqlalchemy import create_engine, Column, Integer, String
from sqlalchemy.ext.declarative import declarative_base
from sqlalchemy.orm import sessionmaker

# 创建数据库引擎和会话
engine = create_engine('sqlite:///:memory:')
Base = declarative_base()
Session = sessionmaker(bind=engine)
session = Session()

# 定义模型类
class Product(Base):
    __tablename__ = 'products'
    id = Column(Integer, primary_key=True)
    name = Column(String)
    price = Column(Integer)

# 创建数据表
Base.metadata.create_all(engine)

# 创建产品对象并插入数据
product1 = Product(name='Product 1', price=100)
product2 = Product(name='Product 2', price=200)
session.add(product1)
session.add(product2)
session.commit()

# 查询数据
products = session.query(Product).all()

# 打印查询结果
for product in products:
    print(product.name, product.price)