Reading data from CSV file and insert into Salesforce

Question

I am trying to read data from a csv file and insert/upsert (depending on existent of UniqueId) into Salesforce using Python.

I know I have to use iterator to read data from a cvs file, put them into List, but I am not sure how to fetch the data from that List and put (insert or upsert) data in Salesforce.

Each csv file contains two fields (UniqueId, Selection).

Do I use enumerate ?

Here is what I have so far (where action taking place):

How do I fetch the data into Salesforce?

InFiles = glob.glob(inputFolderName + '/SurveySelection*.csv')

InFileslist = []       ##List to put file name
for InFile in InFiles:
    thenStamp = os.path.getmtime(InFile)

    if (thenStamp >= unix_time(dt1)) and (thenStamp >= unix_time(dt2)):
       InFileslist.append(InFile)  ## Expression to append files in certain time range

for filename in InFileslist:
    file = open(filename, 'r')
    lines = file.readlines()

Answer 1

Not too sure what your requirements are, but if you are not integrating two systems why not just import the data directly using tools provided by salesforce like the data import wizard or Salesforce DataLoader? If you are integrating systems then you should look into using the Salesforce REST API, or by using the Salesforce python sdk

pip install salesforce-python-sdk

Answer 2

You are currently in the same position I was about 8 months ago. I have successfully integrated a MySQL Database into Salesforce. Basically a customer will register a product on our website, then I have python pull the data from the database, format it all in a xlsx file and then send that data into salesforce using simple-salesforce package which works great. Below is a code snippet which should help you get started. Let me know if you have any questions.

import os
import sys
import xlrd
import xlwt
import time
import base64
import smtplib
import MySQLdb
import logging
import datetime
import collections
from xlrd.sheet import ctype_text
from collections import OrderedDict
from simple_salesforce import SFType
from simple_salesforce import Salesforce
from xlsxwriter.workbook import Workbook
from MySQLdb import OperationalError
from mysql.connector import MySQLConnection, Error

logger = logging.getLogger('view_rows')
hdlr = logging.FileHandler('C:\Users\Chris\Documents\Email Logs\myapp.log')
formatter = logging.Formatter('%(asctime)s %(levelname)s %(message)s')
hdlr.setFormatter(formatter)
logger.addHandler(hdlr) 
logger.setLevel(logging.WARNING)
# MySQL Database Credentials
ur = 'user_name' # your username
pd = 'my_password' # your password
ht = 'localhost' # your host
pt = 3306
db = 'my_database' # database where your table is stored
con = MySQLdb.connect(user=ur, passwd=pd, host=ht, port=pt, db=db)
cursor = con.cursor()
con.autocommit(True)
# Salesforce Credentials
sf = Salesforce(username='my_Salesforce_Email@mail.com', password='my_SF_password', security_token='my_Generated_token_from_Salesforce', client_id='This does not really matter')
orderedDict = collections.OrderedDict()
# Gets the new customers that have created an account on the Warranty Portal
def GetNewContact():
        # Creates a xlsx file
    workbook = Workbook('outfile.xlsx')
    sheet = workbook.add_worksheet("Warranty Info")
    query = "SELECT RC.cus_id, RC.cus_username, RC.cus_subsc FROM my_database.rma_customer RC INNER JOIN my_database.rma_customer_address CA ON RC.cus_id=CA.cus_id WHERE CA.cus_address_type=0 AND CA.cus_updated=1"
    query0 = "SELECT RCD.cus_firstname, RCD.cus_lastname, RCD.cus_cell_phone FROM my_database.rma_customer_details RCD INNER JOIN my_database.rma_customer_address CA ON RCD.cus_id=CA.cus_id WHERE CA.cus_address_type=0 AND CA.cus_updated=1"
    query1 = "SELECT CA.cus_address_1, CA.cus_address_2, CA.cus_city, CA.cus_postcode FROM my_database.rma_customer_address CA LEFT JOIN my_database.rma_customer RC ON CA.cus_id=RC.cus_id WHERE CA.cus_address_type=0 AND CA.cus_updated=1"
    cursor.execute(query)
    headers = ['ID', 'Email', 'Newsletter', 'FirstName', 'LastName', 'Phone', 'Street', 'APT', 'City', 'Postal']
    for i, header in enumerate(headers):
        sheet.write(0, i, header)
    for r, row in enumerate(cursor.fetchall()):
        r = r + 1
        for c, col in enumerate(row):
            sheet.write(r, c, col)              
    cursor.execute(query0)  
    for r, row in enumerate(cursor.fetchall()):
        r = r + 1
        for c, col in enumerate(row):
            sheet.write(r, c+3, col)        
    cursor.execute(query1)  
    for r, row in enumerate(cursor.fetchall()):
        r = r + 1
        for c, col in enumerate(row):
            sheet.write(r, c+6, col)
     #Updates the database after it has grabbed the needed info to create a contact in salesforce so that it does not get that same data again
    workbook.close()
def CreateContact():
    # Knows what file to look into for the information to create a contact
    path = 'outfile.xlsx'
    workbook = xlrd.open_workbook(path, on_demand = True)
    sheet = workbook.sheet_by_index(0)
    for rowx in xrange(1, sheet.nrows):
        try:
            Id = sheet.row_values(rowx, start_colx=0, end_colx=None)[0]
            Email1 = sheet.row_values(rowx, start_colx=1, end_colx=None)[0]
            Newsletter = sheet.row_values(rowx, start_colx=2, end_colx=None)[0]
            First = sheet.row_values(rowx, start_colx=3, end_colx=None)[0]
            Last = sheet.row_values(rowx, start_colx=4, end_colx=None)[0]
            Phone = sheet.row_values(rowx, start_colx=5, end_colx=None)[0]
            Street = sheet.row_values(rowx, start_colx=6, end_colx=None)[0]
            Apt = sheet.row_values(rowx, start_colx=7, end_colx=None)[0]
            City = sheet.row_values(rowx, start_colx=8, end_colx=None)[0]
            Postal = sheet.row_values(rowx, start_colx=9, end_colx=None)[0]
            d = sf.query("SELECT Id FROM Contact WHERE Phone ='%s' OR Email='%s'" % (Phone, Email1))
            # d = returns more than just a case number so data = will specifically only get the case number 
            data = [e["Id"] for e in d["records"]]
            sf.Contact.update(data[0],{'OwnerId' : "005U0000005jwPH", 'Phone' : Phone, 'Email' : Email1, 'Newsletter__c' : Newsletter, 'MailingStreet' : Street+" "+Apt, 'MailingCity' : City, 'MailingPostalCode' : Postal, 'AccountId' : "001U000001ZEB89"})
            cursor.execute("UPDATE rma_customer AS RC INNER JOIN rma_customer_address CA ON RC.cus_id = CA.cus_id SET RC.SF_created=1 WHERE RC.cus_id='%s'" % Id)   
            cursor.execute("UPDATE rma_customer_address AS CA INNER JOIN rma_customer RC ON CA.cus_id = RC.cus_id  SET CA.SF_created=1 WHERE CA.cus_id='%s'" % Id)
            cursor.execute("UPDATE rma_customer_address AS CA INNER JOIN rma_customer RC ON CA.cus_id = RC.cus_id SET CA.cus_updated=0 WHERE CA.cus_id='%s'" % Id)
            cursor.execute("UPDATE rma_customer_details AS RCD INNER JOIN rma_customer RC ON RCD.cus_id = RC.cus_id SET RCD.SF_created=1 WHERE RCD.cus_id='%s'" % Id)
        # If Contact exists, skips and goes to next customer in excel sheet.
        except Exception, e:
            #print "Exception %s"%str(e)
            Id = sheet.row_values(rowx, start_colx=0, end_colx=None)[0]
            Email1 = sheet.row_values(rowx, start_colx=1, end_colx=None)[0]
            Newsletter = sheet.row_values(rowx, start_colx=2, end_colx=None)[0]
            First = sheet.row_values(rowx, start_colx=3, end_colx=None)[0]
            Last = sheet.row_values(rowx, start_colx=4, end_colx=None)[0]
            Phone = sheet.row_values(rowx, start_colx=5, end_colx=None)[0]
            Street = sheet.row_values(rowx, start_colx=6, end_colx=None)[0]
            Apt = sheet.row_values(rowx, start_colx=7, end_colx=None)[0]
            City = sheet.row_values(rowx, start_colx=8, end_colx=None)[0]
            Postal = sheet.row_values(rowx, start_colx=9, end_colx=None)[0]
            logger.error("Unable to Create Contact: "+Email1+" "+Phone)
            logger.error(e)
            sf.Contact.create({'FirstName' : First, 'LastName' : Last, 'Newsletter__c' : Newsletter, 'Email' : Email1, 'Phone' : Phone, 'MailingStreet' : Street+" "+Apt, 'MailingCity' : City, 'MailingPostalCode' : Postal, 'AccountId' : "001U000001ZEB89"})
            #print "Contact Not Found. Created New Contact!"
            cursor.execute("UPDATE rma_customer AS RC INNER JOIN rma_customer_address CA ON RC.cus_id = CA.cus_id SET RC.SF_created=1 WHERE RC.cus_id='%s'" % Id)   
            cursor.execute("UPDATE rma_customer_address AS CA INNER JOIN rma_customer RC ON CA.cus_id = RC.cus_id  SET CA.SF_created=1 WHERE CA.cus_id='%s'" % Id)
            cursor.execute("UPDATE rma_customer_address AS CA INNER JOIN rma_customer RC ON CA.cus_id = RC.cus_id SET CA.cus_updated=0 WHERE CA.cus_id='%s'" % Id)
            cursor.execute("UPDATE rma_customer_details AS RCD INNER JOIN rma_customer RC ON RCD.cus_id = RC.cus_id SET RCD.SF_created=1 WHERE RCD.cus_id='%s'" % Id)
            #time.sleep(10)
        # Sleep for 30 seconds to allow Salesforce to catch up before creating the cases to ensure they are correctly associated
    workbook.release_resources()
    time.sleep(5)

GetNewContact()
CreateContact()