df-jdbc-query.py

queryListingJdbc = """(SELECT * FROM pipeline.ListingMeta WHERE listing_id >= 100000) AS target"""

dfListingJdbcFiltered = spark\
    .read\
    .format("jdbc")\
    .option("driver", "com.mysql.jdbc.Driver")\
    .option("url", "jdbc:mysql://localhost:3306?useSSL=false")\
    .option("dbtable", queryListingJdbc)\
    .option("user", "root")\
    .option("password", "root")\
    .option("partitionColumn", "listing_id")\
    .option("lowerBound", "0")\
    .option("upperBound", "1000")\
    .option("customSchema", "listing_id LONG")\
    .option("numPartitions", "5")\
    .load()