在pyspark中每隔1小时从postgres DB读取数据

from pyspark.sql import SparkSession
from pyspark.sql.functions import *

spark = SparkSession.builder \
    .appName("Read from PostgreSQL") \
    .getOrCreate()

url = "jdbc:postgresql://<host>:<port>/<database>"
properties = {
    "user": "<username>",
    "password": "<password>",
    "driver": "org.postgresql.Driver"
}

df = spark.readStream \
    .format("jdbc") \
    .option("url", url) \
    .option("dbtable", "<table>") \
    .option("query", "<query>") \
    .option("fetchsize", "1000") \
    .option("numPartitions", "10") \
    .option("partitionColumn", "<column>") \
    .option("lowerBound", "0") \
    .option("upperBound", "100") \
    .option("checkpointLocation", "<checkpoint_location>") \
    .options(properties) \
    .load()

processed_df = df.select(<columns>).filter(<condition>)

query = processed_df.writeStream \
    .outputMode("append") \
    .format("console") \
    .start()

query.awaitTermination()