python mongo to csv use pandas.

mongo_to_csv.py

# @Author: xiewenqian <int>
# @Date:   2016-11-28T20:35:09+08:00
# @Email:  wixb50@gmail.com
# @Last modified by:   int
# @Last modified time: 2016-12-01T19:32:48+08:00


import pandas as pd
from pymongo import MongoClient


def _connect_mongo(host, port, username, password, db):
    """ A util for making a connection to mongo """

    if username and password:
        mongo_uri = 'mongodb://%s:%s@%s:%s/%s' % (username, password, host, port, db)
        conn = MongoClient(mongo_uri)
    else:
        conn = MongoClient(host, port)
    return conn[db]


def read_mongo(db, collection, query={}, host='localhost', port=27017, username=None, password=None, no_id=True):
    """ Read from Mongo and Store into DataFrame """

    # Connect to MongoDB
    db = _connect_mongo(host=host, port=port, username=username, password=password, db=db)

    # Make a query to the specific DB and Collection
    cursor = db[collection].find(query)

    # Expand the cursor and construct the DataFrame
    df =  pd.DataFrame(list(cursor))

    # Delete the _id
    if no_id and '_id' in df:
        del df['_id']

    return df

if __name__ == '__main__':
    df = read_mongo('db_test', 'db_collection', {}, '172.168.203.174', 10800)
    df.to_csv('1.csv', index=False)

如果数据的数据量20多个G内存还可以运行的动吗