使用pyspark从RDS MySQL数据库中拉取数据

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

spark = SparkSession.builder \
    .appName("MySQL to Spark") \
    .getOrCreate()

mysql_host = "your_mysql_host"
mysql_port = "your_mysql_port"
mysql_db = "your_mysql_db"
mysql_user = "your_mysql_user"
mysql_password = "your_mysql_password"

jdbc_url = f"jdbc:mysql://{mysql_host}:{mysql_port}/{mysql_db}"
mysql_properties = {
    "user": mysql_user,
    "password": mysql_password,
    "driver": "com.mysql.jdbc.Driver"
}

df = spark.read.jdbc(url=jdbc_url, table="your_table_name", properties=mysql_properties)

df.select("column1", "column2").filter(col("column3") > 10).groupBy("column1").count().show()

df.write.parquet("path_to_save.parquet")