Pyspark read from database (Postgres)

pyspark_read_from_database.py

user = 'postgres'
password = 'secret'
db_driver = 'org.postgresql.Driver'
host = '127.0.0.1'
db_url = f'jdbc:postgresql://{host}:5432/dbname?user={user}&password={password}'

df = spark.read.format(
  'jdbc'
).options(
  url=db_url,
  driver=db_driver,
  dbtable='table_name',
  user=user,
  password=password,
  fetchsize=1000,       # optional, increase fetchsize to get bigger chunks - get data faster
).load()