如何使用python将csv数据推送到mongodb

时间:2014-12-11 05:56:05

标签: python json mongodb csv

尝试使用python.i将csv数据推入mongodb,初学者是python& mongodb..i使用以下代码

import csv
import json
import pandas as pd
import sys, getopt, pprint
from pymongo import MongoClient
#CSV to JSON Conversion
csvfile = open('C://test//final-current.csv', 'r')
jsonfile = open('C://test//6.json', 'a')
reader = csv.DictReader( csvfile )
header= [ "S.No", "Instrument Name", "Buy Price", "Buy Quantity", "Sell Price", "Sell Quantity", "Last Traded Price", "Total Traded Quantity", "Average Traded Price", "Open Price", "High Price", "Low Price", "Close Price", "V" ,"Time"]
#fieldnames=header
output=[]
for each in reader:
    row={}
    for field in header:
        row[field]=each[field]
    output.append(row)

json.dump(output, jsonfile, indent=None, sort_keys=False , encoding="UTF-8")
mongo_client=MongoClient() 
db=mongo_client.october_mug_talk
db.segment.drop()
data=pd.read_csv('C://test//6.json', error_bad_lines=0)
df = pd.DataFrame(data)
records = csv.DictReader(df)
db.segment.insert(records)

但输出格式为

/* 0 */
{
  "_id" : ObjectId("54891c4ffb2a0303b0d43134"),
  "[{\"AverageTradedPrice\":\"0\"" : "BuyPrice:\"349.75\""
}

/* 1 */
{
  "_id" : ObjectId("54891c4ffb2a0303b0d43135"),
  "[{\"AverageTradedPrice\":\"0\"" : "BuyQuantity:\"3000\""
}

/* 2 */
{
  "_id" : ObjectId("54891c4ffb2a0303b0d43136"),
  "[{\"AverageTradedPrice\":\"0\"" : "ClosePrice:\"350\""
}

/* 3 */
{
  "_id" : ObjectId("54891c4ffb2a0303b0d43137"),
  "[{\"AverageTradedPrice\":\"0\"" : "HighPrice:\"0\""
}

实际上我希望输出类似于单个id所有其他字段应该显示为子类型 例如:

 _id" : ObjectId("54891c4ffb2a0303b0d43137")
    AveragetradedPrice :0
    HighPrice:0
    ClosePrice:350
    buyprice:350.75

请帮帮我Out.Thanks提前

5 个答案:

答案 0 :(得分:11)

感谢您的建议。这是修正后的代码:

import csv
import json
import pandas as pd
import sys, getopt, pprint
from pymongo import MongoClient
#CSV to JSON Conversion
csvfile = open('C://test//final-current.csv', 'r')
reader = csv.DictReader( csvfile )
mongo_client=MongoClient() 
db=mongo_client.october_mug_talk
db.segment.drop()
header= [ "S No", "Instrument Name", "Buy Price", "Buy Quantity", "Sell Price", "Sell Quantity", "Last Traded Price", "Total Traded Quantity", "Average Traded Price", "Open Price", "High Price", "Low Price", "Close Price", "V" ,"Time"]

for each in reader:
    row={}
    for field in header:
        row[field]=each[field]

    db.segment.insert(row)

答案 1 :(得分:2)

最简单的方法是使用熊猫 我的代码是

import json
import pymongo
import pandas as pd
myclient = pymongo.MongoClient()

df = pd.read_csv('yourcsv.csv',encoding = 'ISO-8859-1')   # loading csv file
df.to_json('yourjson.json')                               # saving to json file
jdf = open('yourjson.json').read()                        # loading the json file 
data = json.loads(jdf)                                    # reading json file 

现在您可以将此json插入mangodb数据库中:-]

答案 2 :(得分:0)

为什么要一一插入数据?看看这个。

import pandas as pd
from pymongo import MongoClient

client = MongoClient(<your_credentials>)
database = client['YOUR_DB_NAME']
collection = database['your_collection']

def csv_to_json(file, header=None):
    data = pd.read_csv(filename, header=header)
    return data.to_dict('records')

collection.insert_many(csv_to_json('your_file_path'))

请注意,如果文件太大,可能会使您的应用程序崩溃。

答案 3 :(得分:0)

    from pymongo import MongoClient
    import csv
    import json
    # DB connectivity
    client = MongoClient('localhost', 27017)
    db = client["database name"]
    col = db["collection"]
    # Function to parse csv to dictionary
    def csv_to_dict():
        reader = csv.DictReader(open('File with path','r'))
        result = {}
        for row in reader:
            key = row.pop('id')
            result[key]= row
        return result
    
    # Final insert statement
    x=col.insert_one(csv_to_dict())
            print(x.inserted_id)

# to insert one row

#and to insert many rows following code is to be executed
from pymongo import MongoClient
import csv
# read csv file as a list of lists
client = MongoClient('localhost', 27017)
db = client["data base name"]
col = db["Collection Name"]
with open('File with path', 'r') as read_obj:
    # pass the file object to reader() to get the reader object
    csv_reader = csv.DictReader(read_obj)
    # Pass reader object to list() to get a list of lists
    mylist = list(csv_reader)
    #print(list_of_rows)
    x = col.insert_many(mylist)

    #print list of the _id values of the inserted documents:
    print(x.inserted_ids)

答案 4 :(得分:-1)

假设您的CSV中有标题行,则有更好的导入次数。

from pymongo import MongoClient
import csv

# DB connectivity
client = MongoClient('localhost', 27017)
db = client.db
collection = db.collection

# Function to parse csv to dictionary
def csv_to_dict():
    reader = csv.DictReader(open(FILEPATH))
    result = {}
    for row in reader:
        key = row.pop('First_value')
        result[key] = row
    return query

# Final insert statement
db.collection.insert_one(csv_to_dict())

希望有所帮助