利用pymongo存储大空间文件

@Pymongo GridFS

利用pymongo存储大空间文件

pymongo执行插入数据库报错、选用Gridfs插入大于16MB文件,查阅材料并记录如下。

GridFS

GridFS 使用两个集合（collection）存储文件。一个集合是 chunks ，用于存储文件内容的二进制数据；一个集合是 files，用于存储文件的元数据

Please see 下面 code

from pymongo import MongoClient
from gridfs import *
import json
import os


class Grid:
    def __init__(self, db_name=None, collection=None, host="localhost", port=27017):
        self.db_name = db_name
        self.collections = collection
        self.host = host
        self.port = port

    def insert_files(self, file):
        client = MongoClient(self.host, self.port)
        db = client[self.db_name]
        fs = GridFS(db, self.collections)
        with open(file, "rb") as f:
            data = f.read()
            # 自定义文件名字类型
            filename = "{}".format(file.split("\\")[-1])
            id = fs.put(data=data, filename=filename)
            print("id:", id, "Done")

    def get_files(self, file):
        client = MongoClient(self.host, self.port)
        db = client[self.db_name]
        fs = GridFS(db, self.collections)
        file = fs.get_version(filename=file, version=0)
        data = file.read()
        data = json.loads(str(data, encoding="utf8"))
        return data


if __name__ == '__main__':
    gd = Grid(db_name="GUANGDONG", collection="indicator7")
    result = gd.get_files("ind7-2020-06-30.json")
    print(result)