使用JDBC从Pyspark更新表

from pyspark.sql import SparkSession

spark = SparkSession.builder \
    .appName("JDBC Update Table") \
    .getOrCreate()

url = "jdbc:mysql://hostname:port/database_name"
properties = {
    "user": "username",
    "password": "password",
    "driver": "com.mysql.jdbc.Driver"
}

data = spark.read.format("jdbc") \
    .option("url", url) \
    .option("dbtable", "table_name") \
    .option("user", properties["user"]) \
    .option("password", properties["password"]) \
    .option("driver", properties["driver"]) \
    .load()

# 假设要将表中的某一列值加1
data = data.withColumn("column_name", data["column_name"] + 1)

data.write.format("jdbc") \
    .option("url", url) \
    .option("dbtable", "table_name") \
    .option("user", properties["user"]) \
    .option("password", properties["password"]) \
    .option("driver", properties["driver"]) \
    .mode("overwrite") \
    .save()