JnsFerreira

import boto3

def get_glue_table_schema(database_name, table_name):
    client = boto3.client('glue')

    response = client.get_table(
        DatabaseName=database_name,
        Name=table_name
    )

JnsFerreira

# References:
# https://aws.amazon.com/blogs/big-data/load-data-incrementally-and-optimized-parquet-writer-with-aws-glue/

import sys

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

JnsFerreira

# Built-in libraries
from time import time
import threading
import logging
import requests
import math

# Project libraries
from config import functions as f
from config import selenium_functions as sf

JnsFerreira

import apache_beam as beam

with beam.Pipeline() as pipeline:
  plants = (
      pipeline
      | 'Gardening plants' >> beam.Create([
          '   🍓Strawberry   \n',
          '   🥕Carrot   \n',
          '   🍆Eggplant   \n',
          '   🍅Tomato   \n',