Glue Job Script for reading data from DataDirect Salesforce JDBC driver and write it to S3

script.py

import sys
from awsglue.transforms import *
from awsglue.utils import getResolvedOptions
from pyspark.context import SparkContext
from awsglue.context import GlueContext
from awsglue.dynamicframe import DynamicFrame
from awsglue.job import Job


args = getResolvedOptions(sys.argv, ['JOB_NAME'])

sc = SparkContext()
glueContext = GlueContext(sc)
spark = glueContext.spark_session
job = Job(glueContext)

##Read Data from Salesforce using DataDirect JDBC driver in to DataFrame
source_df = spark.read.format("jdbc").option("url","jdbc:datadirect:sforce://login.salesforce.com;SecurityToken=<token>").option("dbtable", "SFORCE.OPPORTUNITY").option("driver", "com.ddtek.jdbc.sforce.SForceDriver").option("user", "[email protected]").option("password", "pass123").load()

job.init(args['JOB_NAME'], args)

##Convert DataFrames to AWS Glue's DynamicFrames Object
dynamic_dframe = DynamicFrame.fromDF(source_df, glueContext, "dynamic_df")

##Write Dynamic Frames to S3 in CSV format. You can write it to any rds/redshift, by using the connection that you have defined previously in Glue
datasink4 = glueContext.write_dynamic_frame.from_options(frame = dynamic_dframe, connection_type = "s3", connection_options = {"path": "s3://glueuserdata"}, format = "csv", transformation_ctx = "datasink4")

job.commit()