如何使用Python批量处理Excel和CSV文件

pip install sqlalchemy

# PostgreSQL
pip install psycopg2-binary
# MySQL
pip install mysql-connector-python
# SQLite (Python标准库已包含，无需额外安装)

from sqlalchemy import create_engine
from sqlalchemy.orm import sessionmaker
# 创建数据库连接引擎
# SQLite示例
engine = create_engine('sqlite:///example.db', echo=True)
# PostgreSQL示例
# engine = create_engine('postgresql://username:password@localhost:5432/mydatabase')
# MySQL示例
# engine = create_engine('mysql+mysqlconnector://username:password@localhost:3306/mydatabase')
# 创建会话工厂
SessionLocal = sessionmaker(autocommit=False, autoflush=False, bind=engine)
# 创建会话实例
session = SessionLocal()

from sqlalchemy import Column, Integer, String, ForeignKey
from sqlalchemy.orm import relationship, declarative_base
# 创建基类
Base = declarative_base()
class User(Base):
    __tablename__ = 'users'
    id = Column(Integer, primary_key=True, index=True)
    name = Column(String(50), nullable=False)
    email = Column(String(100), unique=True, index=True)
    # 定义一对多关系
    posts = relationship("Post", back_populates="author")
class Post(Base):
    __tablename__ = 'posts'
    id = Column(Integer, primary_key=True, index=True)
    title = Column(String(100), nullable=False)
    content = Column(String(500))
    author_id = Column(Integer, ForeignKey('users.id'))
    # 定义多对一关系
    author = relationship("User", back_populates="posts")
    # 定义多对多关系（通过关联表）
    tags = relationship("Tag", secondary="post_tags", back_populates="posts")
class Tag(Base):
    __tablename__ = 'tags'
    id = Column(Integer, primary_key=True, index=True)
    name = Column(String(30), unique=True, nullable=False)
    posts = relationship("Post", secondary="post_tags", back_populates="tags")
# 关联表（用于多对多关系）
class PostTag(Base):
    __tablename__ = 'post_tags'
    post_id = Column(Integer, ForeignKey('posts.id'), primary_key=True)
    tag_id = Column(Integer, ForeignKey('tags.id'), primary_key=True)

# 创建所有表
Base.metadata.create_all(bind=engine)
# 删除所有表
# Base.metadata.drop_all(bind=engine)

# 创建新用户
new_user = User(name="张三", email="zhangsan@example.com")
session.add(new_user)
session.commit()
# 批量创建
session.add_all([
    User(name="李四", email="lisi@example.com"),
    User(name="王五", email="wangwu@example.com")
])
session.commit()

# 获取所有用户
users = session.query(User).all()
# 获取第一个用户
first_user = session.query(User).first()
# 根据ID获取用户
user = session.query(User).get(1)

# 查询并更新
user = session.query(User).get(1)
user.name = "张三四"
session.commit()
# 批量更新
session.query(User).filter(User.name.like("张%")).update({"name": "张氏"}, synchronize_session=False)
session.commit()

# 查询并删除
user = session.query(User).get(1)
session.delete(user)
session.commit()
# 批量删除
session.query(User).filter(User.name == "李四").delete(synchronize_session=False)
session.commit()

# 获取所有记录
users = session.query(User).all()
# 获取特定字段
names = session.query(User.name).all()
# 排序
users = session.query(User).order_by(User.name.desc()).all()
# 限制结果数量
users = session.query(User).limit(10).all()
# 偏移量
users = session.query(User).offset(5).limit(10).all()

from sqlalchemy import or_
# 等值过滤
user = session.query(User).filter(User.name == "张三").first()
# 模糊查询
users = session.query(User).filter(User.name.like("张%")).all()
# IN查询
users = session.query(User).filter(User.name.in_(["张三", "李四"])).all()
# 多条件查询
users = session.query(User).filter(
    User.name == "张三", 
    User.email.like("%@example.com")
).all()
# 或条件
users = session.query(User).filter(
    or_(User.name == "张三", User.name == "李四")
).all()
# 不等于
users = session.query(User).filter(User.name != "张三").all()

from sqlalchemy import func
# 计数
count = session.query(User).count()
# 分组计数
user_post_count = session.query(
    User.name, 
    func.count(Post.id)
).join(Post).group_by(User.name).all()
# 求和、平均值等
avg_id = session.query(func.avg(User.id)).scalar()

# 内连接
results = session.query(User, Post).join(Post).filter(Post.title.like("%Python%")).all()
# 左外连接
results = session.query(User, Post).outerjoin(Post).all()
# 指定连接条件
results = session.query(User, Post).join(Post, User.id == Post.author_id).all()

# 创建带关系的对象
user = User(name="赵六", email="zhaoliu@example.com")
post = Post(title="我的第一篇博客", content="Hello World!", author=user)
session.add(post)
session.commit()
# 通过关系访问
print(f"文章 '{post.title}' 的作者是 {post.author.name}")
print(f"用户 {user.name} 的所有文章:")
for p in user.posts:
    print(f"  - {p.title}")
# 多对多关系操作
python_tag = Tag(name="Python")
sqlalchemy_tag = Tag(name="SQLAlchemy")
post.tags.append(python_tag)
post.tags.append(sqlalchemy_tag)
session.commit()
print(f"文章 '{post.title}' 的标签:")
for tag in post.tags:
    print(f"  - {tag.name}")

# 自动提交事务
try:
    user = User(name="测试用户", email="test@example.com")
    session.add(user)
    session.commit()
except Exception as e:
    session.rollback()
    print(f"发生错误: {e}")
# 使用事务上下文管理器
from sqlalchemy.orm import Session
def create_user(session: Session, name: str, email: str):
    try:
        user = User(name=name, email=email)
        session.add(user)
        session.commit()
        return user
    except:
        session.rollback()
        raise
# 嵌套事务
with session.begin_nested():
    user = User(name="事务用户", email="transaction@example.com")
    session.add(user)
# 保存点
savepoint = session.begin_nested()
try:
    user = User(name="保存点用户", email="savepoint@example.com")
    session.add(user)
    savepoint.commit()
except:
    savepoint.rollback()

# 使用上下文管理器管理会话
from contextlib import contextmanager
@contextmanager
def get_db():
    db = SessionLocal()
    try:
        yield db
        db.commit()
    except Exception:
        db.rollback()
        raise
    finally:
        db.close()
# 使用示例
with get_db() as db:
    user = User(name="上下文用户", email="context@example.com")
    db.add(user)