MongoDb之增删改查

user1={
    "_id":1,
    "name":"alex",
    "age":10,
    ‘hobbies‘:[‘music‘,‘read‘,‘dancing‘],
    ‘addr‘:{
        ‘country‘:‘China‘,
        ‘city‘:‘weifang‘
    }
}

user2={
    "_id":2,
    "name":"wupeiqi",
    "age":20,
    ‘hobbies‘:[‘music‘,‘read‘,‘run‘],
    ‘addr‘:{
        ‘country‘:‘China‘,
        ‘city‘:‘hebei‘
    }
}


user3={
    "_id":3,
    "name":"yuanhao",
    "age":30,
    ‘hobbies‘:[‘music‘,‘drink‘],
    ‘addr‘:{
        ‘country‘:‘China‘,
        ‘city‘:‘heibei‘
    }
}

user4={
    "_id":4,
    "name":"jingliyang",
    "age":40,
    ‘hobbies‘:[‘music‘,‘read‘,‘dancing‘,‘tea‘],
    ‘addr‘:{
        ‘country‘:‘China‘,
        ‘city‘:‘BJ‘
    }
}

user5={
    "_id":5,
    "name":"jinxin",
    "age":50,
    ‘hobbies‘:[‘music‘,‘read‘,],
    ‘addr‘:{
        ‘country‘:‘China‘,
        ‘city‘:‘henan‘
    }
}
db.user.insertMany([user1,user2,user3,user4,user5])

批量增加

#逻辑运算:$and,$or,$not
#1 select * from db1.user where id >=3 and id <=4;
db.user.find({"_id":{"$gte":3,"$lte":4}})

#2 select * from db1.user where id >=3 and id <=4 and age >=40;
db.user.find({
    "_id":{"$gte":3,"$lte":4},
    "age":{"$gte":40}
})

db.user.find({"$and":[
{"_id":{"$gte":3,"$lte":4}},
{"age":{"$gte":40}}
]})


#3 select * from db1.user where id >=0 and id <=1 or id >=4 or name = "yuanhao";
db.user.find({"$or":[
{"_id":{"$lte":1,"$gte":0}},
{"_id":{"$gte":4}},
{"name":"yuanhao"}
]})

#4 select * from db1.user where id % 2 = 1;
db.user.find({"_id":{"$mod":[2,1]}})


db.user.find({
    "_id":{"$not":{"$mod":[2,1]}}
})

逻辑运算:$and,$or,$not

#查询数组相关
#查hobbies中有dancing的人
db.user.find({
    "hobbies":"dancing"
})
#查看既有dancing爱好又有tea爱好的人
db.user.find({
    "hobbies":{"$all":["dancing","tea"]}
})
#查看第2个爱好为dancing的人
db.user.find({
    "hobbies.2":"dancing"
})
#查看所有人的第2个到第3个爱好
db.user.find(
{},
{
    "_id":0,
    "name":0,
    "age":0,
    "addr":0,
    "hobbies":{"$slice":[1,2]},
}
)

#查看所有人最后两个爱好，第一个{}表示查询条件为所有，第二个是显示条件
db.user.find(
{},
{
    "_id":0,
    "name":0,
    "age":0,
    "addr":0,
    "hobbies":{"$slice":-2},
}
)

#查询子文档有"country":"China"的人
db.user.find(
{
    "addr.country":"China"
}
)

db.urls.insert({"_id":1,"urls":[]})

db.urls.update(
     {"_id":1},
     {
    "$addToSet":{
        "urls":{
        "$each":[
            ‘http://www.baidu.com‘,
            ‘http://www.baidu.com‘,
            ‘http://www.xxxx.com‘
            ]
            }
        }
    }
)

#1、了解：限制大小"$slice"，只留最后n个

db.user.update({"_id":5},{
    "$push":{"hobbies":{
        "$each":["read",‘music‘,‘dancing‘],
        "$slice":-2
    }
    }
})

#2、了解：排序The $sort element value must be either 1 or -1"
db.user.update({"_id":5},{
    "$push":{"hobbies":{
        "$each":["read",‘music‘,‘dancing‘],
        "$slice":-1,
        "$sort":-1
    }
    }
})

#注意：不能只将"$slice"或者"$sort"与"$push"配合使用，且必须使用"$each"

$slice $sort $each

from pymongo import MongoClient
import datetime

client=MongoClient(‘mongodb://root:123@localhost:27017‘)
table=client[‘db1‘][‘emp‘]
# table.drop()

l=[
(‘武大郎‘,‘male‘,18,‘20170301‘,‘烧饼检察官‘,7300.33,401,1), 
(‘武松‘,‘male‘,78,‘20150302‘,‘公务员‘,1000000.31,401,1),
(‘宋江‘,‘male‘,81,‘20130305‘,‘公务员‘,8300,401,1),
(‘林冲‘,‘male‘,73,‘20140701‘,‘公务员‘,3500,401,1),
(‘柴进‘,‘male‘,28,‘20121101‘,‘公务员‘,2100,401,1),
(‘卢俊义‘,‘female‘,18,‘20110211‘,‘公务员‘,9000,401,1),
(‘高俅‘,‘male‘,18,‘19000301‘,‘公务员‘,30000,401,1),
(‘鲁智深‘,‘male‘,48,‘20101111‘,‘公务员‘,10000,401,1),

(‘史进‘,‘female‘,48,‘20150311‘,‘打手‘,3000.13,402,2),
(‘李逵‘,‘female‘,38,‘20101101‘,‘打手‘,2000.35,402,2),
(‘周通‘,‘female‘,18,‘20110312‘,‘打手‘,1000.37,402,2),
(‘石秀‘,‘female‘,18,‘20160513‘,‘打手‘,3000.29,402,2),
(‘李忠‘,‘female‘,28,‘20170127‘,‘打手‘,4000.33,402,2),

(‘吴用‘,‘male‘,28,‘20160311‘,‘文人‘,10000.13,403,3), 
(‘萧让‘,‘male‘,18,‘19970312‘,‘文人‘,20000,403,3),
(‘安道全‘,‘female‘,18,‘20130311‘,‘文人‘,19000,403,3),
(‘公孙胜‘,‘male‘,18,‘20150411‘,‘文人‘,18000,403,3),
(‘朱贵‘,‘female‘,18,‘20140512‘,‘文人‘,17000,403,3)
]

for n,item in enumerate(l):
    d={
        "_id":n,
        ‘name‘:item[0],
        ‘sex‘:item[1],
        ‘age‘:item[2],
        ‘hire_date‘:datetime.datetime.strptime(item[3],‘%Y%m%d‘),
        ‘post‘:item[4],
        ‘salary‘:item[5]
    }
    table.save(d)

数据

{"$match":{"字段":"条件"}},可以使用任何常用查询操作符$gt,$lt,$in等

#例1、select * from db1.emp where post=‘公务员‘;
db.emp.aggregate({"$match":{"post":"公务员"}})

#例2、select * from db1.emp where id > 3 group by post;  
db.emp.aggregate(
    {"$match":{"_id":{"$gt":3}}},
    {"$group":{"_id":"$post",‘avg_salary‘:{"$avg":"$salary"}}}
)

#例3、select * from db1.emp where id > 3 group by post having avg(salary) > 10000;  
db.emp.aggregate(
    {"$match":{"_id":{"$gt":3}}},
    {"$group":{"_id":"$post",‘avg_salary‘:{"$avg":"$salary"}}},
    {"$match":{"avg_salary":{"$gt":10000}}}
)

{"$group":{"_id":分组字段,"新的字段名":聚合操作符}}

#1、将分组字段传给$group函数的_id字段即可
{"$group":{"_id":"$sex"}} #按照性别分组
{"$group":{"_id":"$post"}} #按照职位分组
{"$group":{"_id":{"state":"$state","city":"$city"}}} #按照多个字段分组，比如按照州市分组

#2、分组后聚合得结果,类似于sql中聚合函数的聚合操作符：$sum、$avg、$max、$min、$first、$last
#例1：select post,max(salary) from db1.emp group by post; 
db.emp.aggregate({"$group":{"_id":"$post","max_salary":{"$max":"$salary"}}})

#例2：取每个部门最大薪资与最低薪资
db.emp.aggregate({"$group":{"_id":"$post","max_salary":{"$max":"$salary"},"min_salary":{"$min":"$salary"}}})

#例3：如果字段是排序后的，那么$first,$last会很有用,比用$max和$min效率高
db.emp.aggregate({"$group":{"_id":"$post","first_id":{"$first":"$_id"}}})

#例4：求每个部门的总工资
db.emp.aggregate({"$group":{"_id":"$post","count":{"$sum":"$salary"}}})

#例5：求每个部门的人数
db.emp.aggregate({"$group":{"_id":"$post","count":{"$sum":1}}})

#3、数组操作符
{"$addToSet":expr}#不重复
{"$push":expr}#重复

#例：查询岗位名以及各岗位内的员工姓名:select post,group_concat(name) from db1.emp group by post;
db.emp.aggregate({"$group":{"_id":"$post","names":{"$push":"$name"}}})
db.emp.aggregate({"$group":{"_id":"$post","names":{"$addToSet":"$name"}}})

{"$project":{"要保留的字段名":1,"要去掉的字段名":0,"新增的字段名":"表达式"}}

#select name,post,(age+1) as new_age from db1.emp;
db.emp.aggregate(
    {"$project":{
        "name":1,
        "post":1,
        "new_age":{"$add":["$age",1]}
        }
})

#1、表达式之数学表达式
{"$add":[expr1,expr2,...,exprN]} #相加
{"$subtract":[expr1,expr2]} #第一个减第二个
{"$multiply":[expr1,expr2,...,exprN]} #相乘
{"$divide":[expr1,expr2]} #第一个表达式除以第二个表达式的商作为结果
{"$mod":[expr1,expr2]} #第一个表达式除以第二个表达式得到的余数作为结果

#2、表达式之日期表达式:$year,$month,$week,$dayOfMonth,$dayOfWeek,$dayOfYear,$hour,$minute,$second
#例如：select name,date_format("%Y") as hire_year from db1.emp
db.emp.aggregate(
    {"$project":{"name":1,"hire_year":{"$year":"$hire_date"}}}
)

#例如查看每个员工的工作多长时间
db.emp.aggregate(
    {"$project":{"name":1,"hire_period":{
        "$subtract":[
            {"$year":new Date()},
            {"$year":"$hire_date"}
        ]
    }}}
)


#3、字符串表达式
{"$substr":[字符串/$值为字符串的字段名,起始位置,截取几个字节]}
{"$concat":[expr1,expr2,...,exprN]} #指定的表达式或字符串连接在一起返回,只支持字符串拼接
{"$toLower":expr}
{"$toUpper":expr}

db.emp.aggregate( {"$project":{"NAME":{"$toUpper":"$name"}}})

#4、逻辑表达式
$and
$or
$not

更多自定义表达式

{"$sort":{"字段名":1,"字段名":-1}} #1升序，-1降序
{"$limit":n} 
{"$skip":n} #跳过多少个文档

#例1、取平均工资最高的前两个部门
db.emp.aggregate(
{
    "$group":{"_id":"$post","平均工资":{"$avg":"$salary"}}
},
{
    "$sort":{"平均工资":-1}
},
{
    "$limit":2
}
)
#例2、
db.emp.aggregate(
{
    "$group":{"_id":"$post","平均工资":{"$avg":"$salary"}}
},
{
    "$sort":{"平均工资":-1}
},
{
    "$limit":2
},
{
    "$skip":1
}
)

 排序：$sort、限制：$limit、跳过：$skip

#集合users包含的文档如下
{ "_id" : 1, "name" : "dave123", "q1" : true, "q2" : true }
{ "_id" : 2, "name" : "dave2", "q1" : false, "q2" : false  }
{ "_id" : 3, "name" : "ahn", "q1" : true, "q2" : true  }
{ "_id" : 4, "name" : "li", "q1" : true, "q2" : false  }
{ "_id" : 5, "name" : "annT", "q1" : false, "q2" : true  }
{ "_id" : 6, "name" : "li", "q1" : true, "q2" : true  }
{ "_id" : 7, "name" : "ty", "q1" : false, "q2" : true  }

#下述操作时从users集合中随机选取3个文档
db.users.aggregate(
   [ { $sample: { size: 3 } } ]
)

随机选取n个：$sample