exampleScript.py

#
# This is an example of a script for the ETL job, this one is generated in AWS console
# The one we'll generate using the createScript API is a bit different, as it's missing the ApplyMapping phase
#
import sys
from awsglue.transforms import *
from awsglue.utils import getResolvedOptions
from pyspark.context import SparkContext
from awsglue.context import GlueContext
from awsglue.job import Job

args = getResolvedOptions(sys.argv, ["JOB_NAME"])
sc = SparkContext()
glueContext = GlueContext(sc)
spark = glueContext.spark_session
job = Job(glueContext)
job.init(args["JOB_NAME"], args)

# Script generated for node S3 bucket
S3bucket_node1 = glueContext.create_dynamic_frame.from_catalog(
    database="dynamoathenadb",
    table_name="dynamoathenastack_dynamoathenatable55d76dac_1byymlxk3b3of",
    transformation_ctx="S3bucket_node1",
)

# Script generated for node ApplyMapping
ApplyMapping_node2 = ApplyMapping.apply(
    frame=S3bucket_node1,
    mappings=[
        ("newvalue1", "long", "newvalue1", "long"),
        ("newvalue", "string", "newvalue", "string"),
        ("pk", "string", "pk", "string"),
    ],
    transformation_ctx="ApplyMapping_node2",
)

# Script generated for node S3 bucket
S3bucket_node3 = glueContext.write_dynamic_frame.from_options(
    frame=ApplyMapping_node2,
    connection_type="s3",
    format="glueparquet",
    connection_options={
        "path": "s3://aws-glue-cirit-dynamo-athena-test/",
        "partitionKeys": [],
    },
    transformation_ctx="S3bucket_node3",
)

job.commit()