pom.xml

    <properties>
        <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
        <maven.compiler.source>1.8</maven.compiler.source>
        <maven.compiler.target>1.8</maven.compiler.target>
        <spark.version>2.3.0</spark.version>
        <cupid.sdk.version>3.3.8-public</cupid.sdk.version>
        <scala.version>2.11.8</scala.version>
        <scala.binary.version>2.11</scala.binary.version>
    </properties>

    <dependencies>
        <dependency>
            <groupId>junit</groupId>
            <artifactId>junit</artifactId>
            <version>4.11</version>
            <scope>test</scope>
        </dependency>


        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-core_${scala.binary.version}</artifactId>
            <version>${spark.version}</version>
<!--            <scope>provided</scope>-->
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-sql_${scala.binary.version}</artifactId>
            <version>${spark.version}</version>
<!--            <scope>provided</scope>-->
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-mllib_${scala.binary.version}</artifactId>
            <version>${spark.version}</version>
<!--            <scope>provided</scope>-->
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-streaming_${scala.binary.version}</artifactId>
            <version>${spark.version}</version>
<!--            <scope>provided</scope>-->
        </dependency>
        <dependency>
            <groupId>com.aliyun.odps</groupId>
            <artifactId>cupid-sdk</artifactId>
            <version>${cupid.sdk.version}</version>
<!--            <scope>provided</scope>-->
        </dependency>
        <dependency>
            <groupId>com.aliyun.odps</groupId>
            <artifactId>hadoop-fs-oss</artifactId>
            <version>${cupid.sdk.version}</version>
        </dependency>
        <dependency>
            <groupId>com.aliyun.odps</groupId>
            <artifactId>odps-spark-datasource_${scala.binary.version}</artifactId>
            <version>${cupid.sdk.version}</version>
        </dependency>
        <dependency>
            <groupId>org.scala-lang</groupId>
            <artifactId>scala-library</artifactId>
            <version>${scala.version}</version>
        </dependency>
        <dependency>
            <groupId>org.scala-lang</groupId>
            <artifactId>scala-actors</artifactId>
            <version>${scala.version}</version>
        </dependency>


    </dependencies>

报错

Exception in thread "main" java.io.IOException: No FileSystem for scheme: oss
	at org.apache.hadoop.fs.FileSystem.getFileSystemClass(FileSystem.java:2586)
	at org.apache.hadoop.fs.FileSystem.createFileSystem(FileSystem.java:2593)
	at org.apache.hadoop.fs.FileSystem.access$200(FileSystem.java:91)
	at org.apache.hadoop.fs.FileSystem$Cache.getInternal(FileSystem.java:2632)
	at org.apache.hadoop.fs.FileSystem$Cache.get(FileSystem.java:2614)
	at org.apache.hadoop.fs.FileSystem.get(FileSystem.java:370)
	at org.apache.hadoop.fs.Path.getFileSystem(Path.java:296)
	at org.apache.hadoop.mapred.FileInputFormat.singleThreadedListStatus(FileInputFormat.java:256)
	at org.apache.hadoop.mapred.FileInputFormat.listStatus(FileInputFormat.java:228)
	at org.apache.hadoop.mapred.FileInputFormat.getSplits(FileInputFormat.java:313)
	at org.apache.spark.rdd.HadoopRDD.getPartitions(HadoopRDD.scala:200)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:253)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:251)
	at scala.Option.getOrElse(Option.scala:121)
	at org.apache.spark.rdd.RDD.partitions(RDD.scala:251)
	at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:35)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:253)
	at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:251)
	at scala.Option.getOrElse(Option.scala:121)
	at org.apache.spark.rdd.RDD.partitions(RDD.scala:251)
	at org.apache.spark.SparkContext.runJob(SparkContext.scala:2092)
	at org.apache.spark.rdd.RDD.count(RDD.scala:1162)
	at OSSTest$.main(OSSTest.scala:25)
	at OSSTest.main(OSSTest.scala)

scala 代码

指定 spark.hadoop.fs.oss.impl 参数为：

org.apache.hadoop.fs.aliyun.oss.AliyunOSSFileSystem

import org.apache.spark.sql.SparkSession

object OSSTest {
  def main(args: Array[String]): Unit = {

    val spark = SparkSession
      .builder()
      .config("spark.master", "local[4]") // 需要设置spark.master为local[N]才能直接运行，N为并发数。
      //      需要指定oss类型
      .config("spark.hadoop.fs.oss.impl", "org.apache.hadoop.fs.aliyun.oss.AliyunOSSFileSystem")
      .config("spark.hadoop.fs.oss.accessKeyId", "xxxxx")
      .config("spark.hadoop.fs.oss.accessKeySecret", "xxxxxx")
      .config("spark.hadoop.fs.oss.endpoint", "oss-cn-beijing.aliyuncs.com")
      .appName("SparkOSS2")
      .getOrCreate()

    val sc = spark.sparkContext
    try {
      //OSS文件的读取。
      val pathIn = "oss://bucket_name/data/server"
      val inputData = sc.textFile(pathIn, 5)
      //      val cnt = inputData.count
      val cnt = inputData.count()
      println(s"count: $cnt")

      //RDD写入。
      //      inputData.repartition(1).saveAsTextFile("oss://spark-oss/user/data3")

    } finally {
      sc.stop()
    }


  }

}