通过spark将数据存储到elasticsearch
maven依赖
<dependency>
<groupId>org.elasticsearch</groupId>
<artifactId>elasticsearch-spark-20_2.11</artifactId>
<version>6.6.0</version>
</dependency>
package hgs.spark.es
import org.apache.spark.SparkConf
import org.apache.spark.SparkContext
import org.apache.spark.SparkContext._
import org.elasticsearch.spark._
import org.apache.spark.sql.SQLContext
object ViaSparkLoadDataToES {
def main(args: Array[String]): Unit = {
val conf = new SparkConf().setAppName("toEs").setMaster("local")
conf.set("es.resource", "mtest/IT")
conf.set("es.nodes", "bigdata00,bigdata01")
conf.set("es.port", "9200")
val context = new SparkContext(conf)
val sqlContext = new SQLContext(context)
import sqlContext.implicits._
val rdd = context.textFile( "d:\\person",1)
//val jsonrddDF = sqlContext.read.json(rdd)
rdd.saveJsonToEs("mtest/IT")
context.stop()
}
}
来自 “ ITPUB博客 ” ，链接：https://blog.itpub.net/31506529/viewspace-2637249/ ，如需转载，请注明出处，否则将追究法律责任。
请登录后发表评论
登录
全部评论
