在Python中操作MongoDB的详细教程和案例分享

目录

• 引言
• 1. 环境准备
• 1.1 安装MongoDB
• 1.2 安装PyMongo
• 2. 连接MongoDB
• 3. 插入数据
• 3.1 插入单条数据
• 3.2 插入多条数据
• 4. 查询数据
• 4.1 查询所有文档
• 4.2 查询单个文档
• 4.3 带条件查询
• 4.4 模糊查询
• 5. 更新数据
• 5.1 更新单个文档
• 5.2 更新多个文档
• 6. 删除数据
• 6.1 删除单个文档
• 6.2 删除多个文档
• 7. 索引
• 8. 聚合管道
• 9. 事务
• 10. 实用技巧和最佳实践
• 10.1 使用连接池
• 10.2 监控和日志
• 10.3 使用游标超时
• 10.4 安全性
• 10.5 性能和优化
• 10.6 使用GridFS存储大文件
• 10.7 异步操作
• 10.8 备份和恢复
• 10.9 学习和社区
• 总结

docker pull mongo:6.0.2

docker run --name mongo -d -p 27017:27017 mongo:6.0.2

pip install pymongo

from pymongo import MongoClient

# 连接到MongoDB
client = MongoClient('localhost', 27017)

# 选择或创建数据库
db = client['mydatabase']

# 选择或创建集合
collection = db['mycollection']

# 插入单条数据
doc = {"name": "John", "age": 30, "city": "New York"}
result = collection.insert_one(doc)

# 打印插入的文档的ID
print(result.inserted_id)

# 插入多条数据
docs = [
    {"name": "Amy", "age": 25, "city": "Los Angeles"},
    {"name": "Hannah", "age": 22, "city": "Chicago"},
    {"name": "Michael", "age": 27, "city": "Boston"}
]
result = collection.insert_many(docs)

# 打印插入的文档的ID列表
print(result.inserted_ids)

# 查询所有文档
for doc in collection.find():
    print(doc)

# 查询单个文档
doc = collection.find_one({"name": "John"})
print(doc)

# 带条件查询
docs = collection.find({"age": {"$gt": 25}})
for doc in docs:
    print(doc)

# 模糊查询
import re
docs = collection.find({"name": re.compile("^J")})
for doc in docs:
    print(doc)

# 使用$regex进行模糊查询
docs = collection.find({"name": {"$regex": "^J"}})
for doc in docs:
    print(doc)

# 更新单个文档
query = {"name": "John"}
newvalues = {"$set": {"age": 31}}
result = collection.update_one(query, newvalues)

# 打印匹配和修改的文档数量
print(result.matched_count, result.modified_count)

# 更新多个文档
query = {"age": {"$gt": 25}}
newvalues = {"$set": {"status": "senior"}}
result = collection.update_many(query, newvalues)

# 打印匹配和修改的文档数量
print(result.matched_count, result.modified_count)

# 删除单个文档
query = {"name": "Amy"}
result = collection.delete_one(query)

# 打印删除的文档数量
print(result.deleted_count)

# 删除多个文档
query = {"status": "senior"}
result = collection.delete_many(query)

# 打印删除的文档数量
print(result.deleted_count)

# 创建索引
collection.create_index([("name", pymongo.ASCENDING)])

# 也可以为多个字段创建复合索引
collection.create_index([("name", pymongo.ASCENDING), ("age", pymongo.DESCENDING)])

# 使用聚合管道
pipeline = [
    {"$match": {"age": {"$gt": 25}}},
    {"$group": {"_id": "$city", "count": {"$sum": 1}}}
]

results = collection.aggregate(pipeline)

for result in results:
    print(result)

from pymongo import MongoClient

# 连接到MongoDB
client = MongoClient('localhost', 27017)

# 确保MongoDB在副本集模式下运行（事务需要副本集）
db = client['mydatabase']

# 开始一个会话
with client.start_session() as session:
    with session.start_transaction():
        # 在此执行事务操作
        collection1.insert_one(doc1, session=session)
        collection2.insert_one(doc2, session=session)

# 注意：事务需要在副本集或分片集群上运行

from pymongo import MongoClient

# 创建一个连接池
client = MongoClient('localhost', 27017, maxPoolSize=100)

# 使用client进行数据库操作
db = client['mydatabase']
collection = db['mycollection']

# 操作完成后，连接会自动返回到连接池中

# 设置游标超时时间
cursor = collection.find().batch_size(10).add_option(pymongo.cursor.NoCursorTimeout)

from pymongo import MongoClient
from gridfs import GridFS

# 连接到MongoDB
client = MongoClient('localhost', 27017)
db = client['mydatabase']

# 创建GridFS实例
fs = GridFS(db)

# 上传文件
with open('large_file.dat', 'rb') as f:
    file_id = fs.put(f, filename='large_file.dat')

# 下载文件
with fs.get(file_id) as f:
    with open('downloaded_large_file.dat', 'wb') as out:
        out.write(f.read())

import asyncio
from motor.motor_asyncio import AsyncIOMongoClient

async def main():
    client = AsyncIOMongoClient('localhost', 27017)
    db = client['mydatabase']
    collection = db['mycollection']

    # 异步插入文档
    await collection.insert_one({"name": "John Doe", "age": 30})

    # 异步查询
    async for doc in collection.find({"age": 30}):
        print(doc)

    # 关闭连接
    await client.close()

# 运行异步主函数
asyncio.run(main())