MongoDB 基本操作

2016-05-20

基本操作

基本查询

以更美观的方式输出

1	db.number.find().pretty()

条件查询

条件操作符

(>) 大于 - $gt
(<) 小于 - $lt
(>=) 大于等于 - $gte
(<= ) 小于等于 - $lte

比如查询uid大于100的一些记录

1	db.sedb.find({uid:{$gt:100}})

判断字段是否存在

查询所有存在age字段的记录
db.users.find({age: {$exists: true}});
查询所有不存在name字段的记录
db.users.find({name: {$exists: false}});
# 比如
db.sedb.count({'username':"%",uid:{$gt:100},email:{$exists:false}})

判断字段值是否为空

1	db.social.find({'email':{$ne:""}}).pretty()

获取数据库的所有聚合名称

1 2	> db.getCollectionNames(); [ "phone_number", "system.indexes" ]

统计数据库特定聚合所有记录数量

1 2	db.phone_number.count() 16119524

获取数据库特定聚合的索引

比如获取phone_number聚合的所有索引

> db.phone_number.getIndexes()
[
	{
		"v" : 1,
		"key" : {
			"_id" : 1
		},
		"name" : "_id_",
		"ns" : "blacklist.phone_number"
	}
]

添加索引

为phone_number的phone字段添加索引

> db.phone_number.ensureIndex({"phone":1})
{
	"createdCollectionAutomatically" : false,
	"numIndexesBefore" : 1,
	"numIndexesAfter" : 2,
	"ok" : 1
}

再查看索引情况验证一下

> db.phone_number.getIndexes()
[
	{
		"v" : 1,
		"key" : {
			"_id" : 1
		},
		"name" : "_id_",
		"ns" : "blacklist.phone_number"
	},
	{
		"v" : 1,
		"key" : {
			"phone" : 1
		},
		"name" : "phone_1",
		"ns" : "blacklist.phone_number"
	}
]

分组查询group count

> db.phone.aggregate([{$group:{_id:"$source", num_tutorial:{$sum:1}}}])
{ "_id" : "youm", "num_tutorial" : 449 }
{ "_id" : "tianma168", "num_tutorial" : 349 }
{ "_id" : "dingdkj", "num_tutorial" : 3259 }
{ "_id" : "ypyun", "num_tutorial" : 10192 }
{ "_id" : "ilezan", "num_tutorial" : 43685 }
{ "_id" : "ism168", "num_tutorial" : 2856 }
{ "_id" : "iyylw", "num_tutorial" : 16284 }
{ "_id" : "iqiyi", "num_tutorial" : 1 }
{ "_id" : "xudan123.com", "num_tutorial" : 74808 }
{ "_id" : "vim6", "num_tutorial" : 26927 }
{ "_id" : "yzm1", "num_tutorial" : 449854 }
{ "_id" : "feiq", "num_tutorial" : 46670 }
{ "_id" : "83r.com", "num_tutorial" : 144898 }
{ "_id" : "maz8", "num_tutorial" : 81461 }
{ "_id" : "kuaima9", "num_tutorial" : 138903 }
{ "_id" : "bmyzm", "num_tutorial" : 6015 }
{ "_id" : "sunvarma.com", "num_tutorial" : 45164 }
{ "_id" : "ema6", "num_tutorial" : 54819 }
{ "_id" : "yma0.com", "num_tutorial" : 417669 }
{ "_id" : "creditease", "num_tutorial" : 101747 }

如果需要排序的话

> db.phone.aggregate([{$group:{_id:"$source", count:{$sum:1}}},{$sort:{"count":-1}}])
{ "_id" : "other", "count" : 6133225 }
{ "_id" : "ly.com", "count" : 5235378 }
{ "_id" : "zmyzm.com", "count" : 1038465 }
{ "_id" : "f02.cn", "count" : 644959 }
{ "_id" : "shjmpt.com", "count" : 502440 }
{ "_id" : "yzm1", "count" : 449854 }
{ "_id" : "yma0.com", "count" : 417669 }
{ "_id" : "6yzm.com", "count" : 297152 }
{ "_id" : "taomapt.com", "count" : 187613 }
{ "_id" : "83r.com", "count" : 144898 }
{ "_id" : "kuaima9", "count" : 138903 }
{ "_id" : "creditease", "count" : 101747 }
{ "_id" : "tongdun", "count" : 95012 }
{ "_id" : "aliqin", "count" : 87845 }
{ "_id" : "maz8", "count" : 81461 }
{ "_id" : "xudan123.com", "count" : 74808 }
{ "_id" : "ema6", "count" : 54819 }
{ "_id" : "feiq", "count" : 46670 }
{ "_id" : "sunvarma.com", "count" : 45164 }
{ "_id" : "yayayama.com", "count" : 44941 }

MongoDB 唯一索引自动删除重复记录

coll.ensureIndex({productid:1}) // 在productid上建立普通索引
coll.ensureIndex({district:1, plate:1}) // 多字段索引
coll.ensureIndex({productid:1}, {unique:true}) // 唯一索引
coll.ensureIndex({productid:1}, {unique:true, dropDups:true}) // 建索引时，如果遇到索引字段值已经出现过的情况，则删除重复记录
coll.getIndexes() // 查看索引
coll.dropIndex({productid:1}) // 删除单个索

Python 相关

import requests
import json
from datetime import datetime
from pymongo import MongoClient
'''连接到mongodb数据库'''
# 使用默认链接
client = MongoClient()
# 数据库名为gznu_all_student_info
db = client.gznu_all_student_info
# 数据库中相关表记录
# 学院相关信息
college_collection = db.college
# 班级相关信息
class_collection = db.class_
all_class_collection = db.all_class
# 学生信息
students_collection = db.students
def _save_class_code(url, college_code):
    '''将班级信息保持到数据库中'''
    print '[*] 正在将班级{}信息保存到数据库中'.format(college_code)
    info = get_info(url)
    for i in json.loads(info):
        for j in i['children']:
            item = {}
            item['class_code'] = j['id']
            item['text'] = j['text']
            item['college_code'] = college_code
            item['update'] = datetime.now()
            class_collection.insert(item)

mongodb.config

port=27017
dbpath=/data/db/
fork=true
logpath=/data/logs/mongodb.log
logappend=true
noauth=true
nohttpinterface=true
rest=false

导入json文件数据

将json数据导入到blacklist的phone_number集合中

1	mongoimport -h 127.0.0.1 -d blacklist -c phone_number --file blacklist3.json

mongoimport

多实例配置

如果想同一台机器跑多个MongoDB，则在启动Mongo的时候指定不同的端口即可，如

# 第一个Mongo
  /dat0/mongodb/bin/mongod --dbpath=/data/db/ --fork --logpath=/data/logs/mongodb.log
# 第二个Mongo
/dat0/mongodb/bin/mongod --port 27018 --dbpath=/data/data1.5t/mongodb/ --fork --logpath=/data/logs/mongodb-1.5t.log

要使用第二个Mongo，加上端口就好

➜  ~ mongo --port 27018
MongoDB shell version: 3.2.9
connecting to: 127.0.0.1:27018/test
Server has startup warnings: