数据存储之非关系型数据库存储----MongoDB存储

指定数据库

# 指定操作test数据库
# db = client.test 或 db = client[‘test‘]

指定集合

# 指定一个集合要操作的集合students
# collection = db.students 或 collection = db[‘students‘]

插入数据

import pymongo

# 连接MongoDB
client = pymongo.MongoClient(host=‘localhost‘, port=27017)

# 指定数据库
db = client.test

# 指定集合
collection = db.students

# 数据
student = {
    ‘id‘: ‘20180001‘,
    ‘name‘: ‘Jordan‘,
    ‘age‘: 20,
    ‘gender‘: ‘male‘
}

# 利用insert_one()方法插入一条数据
result = collection.insert_one(student)
print(result)

# 运行输出：<pymongo.results.InsertOneResult object at 0x11089b448>
# 在MongoDB中，每条数据其实都有一个_id属性来唯一标识。如果没有显式指明该属性，MongoDB会自动产生一个ObjectId类型的_id属性。
# 使用 insert_one()和 insert_many()方法来分别插入单条记录和多条记录

import pymongo

client = pymongo.MongoClient(host=‘localhost‘, port=27017)
db = client.test
collection = db.students

student1 = {
    ‘id‘: ‘20180002‘,
    ‘name‘: ‘Lee Hua‘,
    ‘age‘: 20,
    ‘gender‘: ‘male‘
}
student2 = {
    ‘id‘: ‘20180003‘,
    ‘name‘: ‘Mike‘,
    ‘age‘: 21,
    ‘gender‘: ‘male‘
}

result = collection.insert_many([student1, student2])
print(result)
print(result.inserted_ids)
# 调用inserted_ids属性可以获取数据的_id列表


# 运行输出：
<pymongo.results.InsertManyResult object at 0x110826d88>
[ObjectId(‘5d28b293e834575faf929428‘), ObjectId(‘5d28b293e834575faf929429‘)]

# insert_one()方法 和 insert_many()方法

查询

import pymongo

client = pymongo.MongoClient(host=‘localhost‘, port=27017)
db = client.test
collection = db.students

result = collection.find_one({‘name‘: ‘Lee Hua‘})
print(result)


# 输出：
{‘_id‘: ObjectId(‘5d28b293e834575faf929428‘), ‘id‘: ‘20180002‘, ‘name‘: ‘Lee Hua‘, ‘age‘: 20, ‘gender‘: ‘male‘}

import pymongo

client = pymongo.MongoClient(host=‘localhost‘, port=27017)
db = client.test
collection = db.students

result = collection.find()
print(result)
for r in result:
    print(r)


# find()方法返回一个迭代器，用for循环逐条输出
# 输出结果：
<pymongo.cursor.Cursor object at 0x10e0f7320>
{‘_id‘: ObjectId(‘5d28ae0360105a198d9d501a‘), ‘id‘: ‘20180001‘, ‘name‘: ‘Jordan‘, ‘age‘: 20, ‘gender‘: ‘male‘}
{‘_id‘: ObjectId(‘5d28ae2d8b3d004feb604874‘), ‘id‘: ‘20180001‘, ‘name‘: ‘Jordan‘, ‘age‘: 20, ‘gender‘: ‘male‘}
{‘_id‘: ObjectId(‘5d28b293e834575faf929428‘), ‘id‘: ‘20180002‘, ‘name‘: ‘Lee Hua‘, ‘age‘: 20, ‘gender‘: ‘male‘}
{‘_id‘: ObjectId(‘5d28b293e834575faf929429‘), ‘id‘: ‘20180003‘, ‘name‘: ‘Mike‘, ‘age‘: 21, ‘gender‘: ‘male‘}

# find_one()方法 和 find()方法

可以在这两个方法里面添加条件，如：

find(
    {
        ‘name‘: {‘$regex‘: ‘^M.*‘}
    }
)
这里查找的是以‘M‘开头的名字的那些数据，

$regex指定的是正则表达式，

^M.*是一条正则表达式

更多功能符号（如$regex）、数值比较符号的查看MongoDB官方文档：https://docs.mongodb.com/?searchProperty=manual

计数

import pymongo

client = pymongo.MongoClient(host=‘localhost‘, port=27017)
db = client.test
collection = db.students

count = collection.count_documents(
    {
        ‘id‘: {‘$regex‘: ‘^(2018)‘}
    }
)
print(count)


# 输出id为2018开头的数据的条数

# collection.count_documents({条件}) 方法

排序

 1 import pymongo
 2 
 3 client = pymongo.MongoClient(host=‘localhost‘, port=27017)
 4 db = client.test
 5 collection = db.students
 6 
 7 result = collection.find().sort(‘id‘, pymongo.ASCENDING)
 8 for r in result:
 9     print(r)
10 
11 
12 # 以id升序输出所有的数据：
13 {‘_id‘: ObjectId(‘5d28ae0360105a198d9d501a‘), ‘id‘: ‘20180001‘, ‘name‘: ‘Jordan‘, ‘age‘: 20, ‘gender‘: ‘male‘}
14 {‘_id‘: ObjectId(‘5d28ae2d8b3d004feb604874‘), ‘id‘: ‘20180001‘, ‘name‘: ‘Jordan‘, ‘age‘: 20, ‘gender‘: ‘male‘}
15 {‘_id‘: ObjectId(‘5d28b293e834575faf929428‘), ‘id‘: ‘20180002‘, ‘name‘: ‘Lee Hua‘, ‘age‘: 20, ‘gender‘: ‘male‘}
16 {‘_id‘: ObjectId(‘5d28b293e834575faf929429‘), ‘id‘: ‘20180003‘, ‘name‘: ‘Mike‘, ‘age‘: 21, ‘gender‘: ‘male‘}
17 
18 
19 # sort()方法进行排序
20 # pymongo.ASCENDING指定升序
21 # pymongo.DESCENDING指定降序

# sort()方法

偏移

import pymongo

client = pymongo.MongoClient(host=‘localhost‘, port=27017)
db = client.test
collection = db.students

results = collection.find().sort(‘id‘, pymongo.DESCENDING).skip(1)
print(
    [
        result[‘id‘] for result in results
    ]
)


# 输出：
[‘20180002‘, ‘20180001‘, ‘20180001‘]

# skip(1)表示偏移1，即忽略前面一个元素

import pymongo

client = pymongo.MongoClient(host=‘localhost‘, port=27017)
db = client.test
collection = db.students

results = collection.find().sort(‘id‘, pymongo.DESCENDING).skip(1).limit(2)
print(
    [
        result[‘id‘] for result in results
    ]
)

# 输出：
[‘20180002‘, ‘20180001‘]

# limit(2) 即表示限制输出的数据条数为两条

# 数据量很大时，不使用大的偏移量来查询数据

更新

import pymongo

client = pymongo.MongoClient(host=‘localhost‘, port=27017)
db = client[‘test‘]
collection = db[‘students‘]

# 查询条件：age >= 20
query_condition = {
    ‘age‘: {‘$gte‘: 20}
}

# 更新条件：数据的age加1
update_condition = {
    ‘$inc‘: {‘age‘: 1}
}

result = collection.update_one(query_condition, update_condition)
print(result)
print(result.matched_count, result.modified_count)


# 输出：
<pymongo.results.UpdateResult object at 0x110a11c88>
1 1


# 返回的结果是UpdateResul类型的
# 调用matched_count属性，获得匹配数据的条数
# 调用modified_count属性，获得影响数据的条数
# $gte ： 大于等于
# $inc ： 将字段递增指定的值
# updata_one()更新与筛选器匹配的单个文档

import pymongo

client = pymongo.MongoClient(host=‘localhost‘, port=27017)
db = client[‘test‘]
collection = db[‘students‘]

query_condition = {
    ‘age‘: {‘$gte‘: 20}
}
update_condition = {
    ‘$inc‘: {‘age‘: 1}
}

result = collection.update_many(query_condition, update_condition)
print(result)
print(result.matched_count, result.modified_count)


# 输出：
<pymongo.results.UpdateResult object at 0x111c84448>
4 4

# update_one()方法 和 update_many()方法

删除

import pymongo

client = pymongo.MongoClient(host=‘localhost‘, port=27017)
db = client[‘test‘]
collection = db[‘students‘]

result = collection.delete_one({‘age‘: 21})
print(result.deleted_count)


# delete_one()方法：删除第一条符合条件的数据
# delete_count属性：获取删除数据的条数

import pymongo

client = pymongo.MongoClient(host=‘localhost‘, port=27017)
db = client[‘test‘]
collection = db[‘students‘]

result = collection.delete_many({‘age‘: 21})
print(result.deleted_count)


# delete_many()方法：删除所有符合条件的数据

PyMongo的详细用法：http://api.mongodb.com/python/current/api/pymongo/collection.html