pyspark kafka mysql_Pyspark 从kafka 读取数据 rdd，转成 DataFrame

from __future__ import print_function

import sys

import json

from pyspark import SparkContext

from pyspark.streaming import StreamingContext

from pyspark.streaming.kafka import KafkaUtils

from pyspark.sql import Row, SparkSession

def getSparkSessionInstance(sparkConf):

# 生成单例模式的getSparkSessionInstance

if ('sparkSessionSingletonInstance' not in globals()):

globals()['sparkSessionSingletonInstance'] = SparkSession

.builder

.config(conf=sparkConf)

.getOrCreate()

return globals()['sparkSessionSingletonInstance']

sc = SparkContext("local[2]","NetWordCount")

ssc = StreamingContext(sc,1)

topic = "connect-test"

# kafka 中的 topic

kvs = KafkaUtils.createStream(ssc,"localhost:2181","spark-streaming-consumer",