روش عملی استفاده از چسب AWS با Postgresql

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
import boto3

# Initialize Glue context and 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)

# Read data from S3
s3_path="s3://your-S3-REPO/"
datasource = glueContext.create_dynamic_frame.from_options(
    connection_type="s3",
    connection_options={"paths": [s3_path]},
    format="csv",  # Adjust format as necessary
    format_options={"withHeader": True, "separator": ","}
)

datasource.printSchema()

# Transform data if needed (this is a simple pass-through in this example)
transformed = ApplyMapping.apply(
    frame = datasource, 
    mappings = [
        ("id", "string", "id", "int"),
        ("name", "string", "name", "string"),
        ("age", "string", "age", "int")
    ]
)

transformed.printSchema()

# Write data to PostgreSQL
glueContext.write_dynamic_frame.from_options(
    frame = transformed,
    connection_type = "postgresql",
    connection_options = {
        "url": "jdbc:postgresql://your-PostgresqlDB-Endpoint",
        "dbtable": "your_table",
        "user": "your-Posgresql-User",
        "password": "your-Posgresql-Password"
    }
)

# Commit the job
job.commit()

id,name,age
1,John Doe,30
2,Jane Smith, 15
3,Bob Yellow,20
4,Roshan Brown,18
5,Bam Black,55