PyMongo basic setup for connecting with database. For example: find all PDF files and download them to local drive.

pymongo_db.py

#!/usr/bin/env python

# -*- coding: utf-8 -*-

import os

from gridfs import GridFS
from pymongo import MongoClient
from bson.objectid import ObjectId

MONGODB_SERVER = 'you_mongo_server.com'
MONGODB_PORT = 27017
MONGODB_DB = 'your_db_name'
MONGODB_COLLECTION = 'fs.collection_name'


def main():
    connection = MongoClient(
        '{server}:{port}'.format(
            server=MONGODB_SERVER,
            port=MONGODB_PORT,
            connect=False,
        )
    )

    db = connection[MONGODB_DB]

    fs = GridFS(db)

    my_db = db.get_collection(MONGODB_COLLECTION)

    query = my_db.find(
        {
            "metadata.file_type": 'pdf'
        },
        {
            "_id": 1
        }
    )

    print("Extracting ID's")

    ids_data = [str(item['_id']) for item in query]

    print("Extracted --> {} id's".format(len(ids_data)))

    for i, file_id in enumerate(ids_data):
        print("Processing file {index}/{n}".format(
            index=i + 1,
            n=len(ids_data))
        )

        file_from_gridfs = fs.get(ObjectId(file_id)).read()

        dir_path = os.path.join(
            'pdf_files',
            file_id[0:2],
            file_id[2:4],
        )

        os.makedirs(dir_path, exist_ok=True)

        file_path = os.path.join(
            dir_path, "{}.pdf".format(file_id)
        )

        with open(file_path, "wb") as f:
            f.write(file_from_gridfs)

    print("Done!")

main()