|
@@ -0,0 +1,38 @@
|
|
|
+package com.tzld.piaoquan.recommend.feature.produce;
|
|
|
+
|
|
|
+import com.tzld.piaoquan.recommend.feature.produce.service.OSSService;
|
|
|
+import lombok.extern.slf4j.Slf4j;
|
|
|
+import org.apache.commons.lang3.StringUtils;
|
|
|
+import org.apache.spark.SparkConf;
|
|
|
+import org.apache.spark.api.java.JavaRDD;
|
|
|
+import org.apache.spark.api.java.JavaSparkContext;
|
|
|
+
|
|
|
+import java.util.ArrayList;
|
|
|
+import java.util.List;
|
|
|
+
|
|
|
+/**
|
|
|
+ * @author dyp
|
|
|
+ */
|
|
|
+@Slf4j
|
|
|
+public class VideoCleanExecutor {
|
|
|
+ public static void main(String[] args) {
|
|
|
+ SparkConf sparkConf = new SparkConf()
|
|
|
+ //.setMaster("local")
|
|
|
+ .setAppName("VideoCleanODPSToHDFS");
|
|
|
+ JavaSparkContext jsc = new JavaSparkContext(sparkConf);
|
|
|
+
|
|
|
+ JavaRDD<String> multiFileRDD = jsc.textFile("/dyp/oss/video_clean/part-00000");
|
|
|
+
|
|
|
+ OSSService ossService = new OSSService();
|
|
|
+ multiFileRDD.repartition(100).foreachPartition(s -> {
|
|
|
+ List<String> objectNames = new ArrayList<>();
|
|
|
+ if (s.hasNext()) {
|
|
|
+ String[] data = StringUtils.split(s.next(), "\t");
|
|
|
+ objectNames.add(data[2]);
|
|
|
+ //objectNames.add(data[3]);
|
|
|
+ ossService.transToDeepColdArchive("art-pubbucket", objectNames);
|
|
|
+ }
|
|
|
+ });
|
|
|
+ }
|
|
|
+
|
|
|
+}
|