Read and write mongodb database files

First , stay ubuntu16.04 Upper use Docker Start a MongoDB 4.0.13 The container of , The basic operation is as follows ：

[email protected]:~$ sudo -i
[sudo] hpl  Password ： 
[email protected]:~# systemctl start docker
[email protected]:~# docker images
REPOSITORY   TAG       IMAGE ID   CREATED   SIZE
[email protected]:~# docker pull mongo:4.0.13
4.0.13: Pulling from library/mongo
976a760c94fc: Pull complete 
c58992f3c37b: Pull complete 
0ca0e5e7f12e: Pull complete 
f2a274cc00ca: Pull complete 
7f6568107a70: Pull complete 
08957b2477b2: Pull complete 
a66dbd57d2a3: Pull complete 
135a9132a862: Pull complete 
c9b7c17ba1df: Pull complete 
7b595c9e65de: Pull complete 
5e74b440cab6: Pull complete 
9c04ed8f6ca0: Pull complete 
3dbe824121e4: Pull complete 
Digest: sha256:1aea2377c5b17dcd5e67d4c33f8f7ee09da62a4dd27ae988958b70efdf3a0a6a
Status: Downloaded newer image for mongo:4.0.13
docker.io/library/mongo:4.0.13
[email protected]:~# docker images
REPOSITORY   TAG       IMAGE ID       CREATED       SIZE
mongo        4.0.13    0712bd00d695   2 years ago   416MB
[email protected]:~# docker run -d -p 27017:27017 --name mongo4.0 0712bd00d695
1e81e661666a5aa01df516663058de8b768a7b09fafa5c53b832c14a6122a97a
[email protected]:~# docker ps
CONTAINER ID   IMAGE          COMMAND                  CREATED         STATUS         PORTS                                           NAMES
1e81e661666a   0712bd00d695   "docker-entrypoint.s…"   5 seconds ago   Up 3 seconds   0.0.0.0:27017->27017/tcp, :::27017->27017/tcp   mongo4.0

see linux Of IP The address is ：192.168.23.129

  On the host, you can use Navicat To test the connection ：

  about 16M Small files within , have access to MongoDB Direct storage ：

import os
import datetime
from pymongo import MongoClient


class DBDataSave(object):
    client = MongoClient('mongodb://192.168.23.129:27017')
    db = client.file_data  #  Database used 
    collection = db.datas  #  Use the collection name in the database 

    def upload_little_file(self):
        upload_dir = r'G:/project/study1/others/mongo_test/upload_files'
        file_list = os.listdir(upload_dir)
        for file in file_list:
            file_path = upload_dir + '/' + file
            file_division = file.split('.')
            file_size = os.stat(file_path).st_size
            f = open(file_path, 'rb')
            data = f.read()
            doc = [{
                    "file_name": file,
                    "filet_type": file_division[-1],
                    'content': data,
                    "size": file_size,
                    'add_time': datetime.datetime.now()
                    }]
            f.close()
            self.collection.insert_many(doc)

    def download_little_file(self):
        if not os.path.exists('./download_files'):
            os.mkdir('./download_files')
        files = self.collection.find()
        for file in files:
            with open('./download_files/' + f"{file.get('file_name')}", 'wb') as f:
                f.write(file.get('content'))


if __name__ == '__main__':
    dds = DBDataSave()
    # dds.upload_little_file()  #  Storage file 
    dds.download_little_file()  #  export file 

 

 MongoDB There is a built-in file system named GridFS, Can be used to store more than 16M Above documents ：

GridFS Have the ability to manage files in a distributed way , It can break through the general file system pair file The limitation of , Segmented storage , Unlike ordinary file systems, the whole storage . In this way, reading large files will not occupy a lot of memory .

from pymongo import MongoClient
from gridfs import *
import os


class DBDataSaveGF(object):
    client = MongoClient('mongodb://192.168.23.129:27017')  #  Connect local MongoDB database 
    db = client.file_data
    file_put = GridFS(db)

    def db_write_file(self):
        upload_path = r'G:/project/study1/others/mongo_test/upload_files'
        files = os.listdir(upload_path)  #  List all the files under the folder 
        for file in files:
            file_path = upload_path + '\\' + file
            with open(file_path, 'rb') as f1:
                self.file_put.put(f1, content_type=file.split('.')[-1], filename=file)

    def db_read_file(self):
        if not os.path.exists('./download_files'):
            os.mkdir('./download_files')
        files = self.file_put.find()
        # files = file_put.find().sort("uploadDate", -1).limit(1)  #  Return to the recently uploaded 1 File 
        for file in files:
            with open('./download_files/' + file.filename, 'wb') as f1:
                f1.write(file.read())


if __name__ == '__main__':
    db = DBDataSaveGF()
    # db.db_write_file()  #  Storage file 
    db.db_read_file()  #  Read the file