Glue Python Hello World Job Dataframe

glue_python_spark_hello_world_job.py

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
from awsglue.dynamicframe import DynamicFrame
 
## @params: [JOB_NAME]
args = getResolvedOptions(sys.argv, ['JOB_NAME'])
 
sc = SparkContext()
glueContext = GlueContext(sc)
spark = glueContext.spark_session
job = Job(glueContext)
job.init(args['JOB_NAME'], args)

# Assign the target bucket to a variable
s3_bucket = "s3://my-bucket-name/output/hello_world/"
 
# Create Hello World Dataframe
dataframe = spark.createDataFrame([("Hello", "World", "!")])

# Coalesce the data to 1 file
# Note that when you convert back to a Dynamic Frame, this will be ignored.
dataframe.coalesce(1)

# Convert to Dynamic Frame
hello_world_dynamic_frame = DynamicFrame.fromDF(dataframe, glueContext, "hello_world_dynamic_frame")

# Output the Dynamic Frame to S3 as a CSV
output_result = glueContext.write_dynamic_frame.from_options(frame = hello_world_dynamic_frame, connection_type = "s3", connection_options = {"path":s3_bucket}, format = "csv")

job.commit()