1.官網資料

2.需要下載相關依賴到flume的lib中

3.配置flume的配置檔案

#agent1表示代理名稱

agent1.sources=source1

agent1.sinks=sink1

agent1.channels=channel1

#配置source1

agent1.sources.source1.type=spooldir

agent1.sources.source1.spoolDir=/usr/local/flume/tmp/TestDir

agent1.sources.source1.channels=channel1

agent1.sources.source1.fileHeader = false

agent1.sources.source1.interceptors = i1

agent1.sources.source1.interceptors.i1.type = timestamp

#配置sink1

#agent1.sinks.sink1.type=hdfs

#agent1.sinks.sink1.hdfs.path=hdfs://master:9000/library/flume

#agent1.sinks.sink1.hdfs.fileType=DataStream

#agent1.sinks.sink1.hdfs.writeFormat=TEXT

#agent1.sinks.sink1.hdfs.rollInterval=1

#agent1.sinks.sink1.channel=channel1

#agent1.sinks.sink1.hdfs.filePrefix=%Y-%m-%d

#Spark Streaming 捕獲Flume的資料 SparkStreaming 監聽的host和port

#agent1.sinks.sink1.type=avro

#agent1.sinks.sink1.channel=channel1

#agent1.sinks.sink1.hostname=Master

#agent1.sinks.sink1.port=9999

#Spark Streaming主動從Flume取資料，按需來取

agent1.sinks.sink1.type=org.apache.spark.streaming.flume.sink.SparkSink

agent1.sinks.sink1.hostname=Master

agent1.sinks.sink1.port=9999

agent1.sinks.sink1.channel=channel1

#配置channel1

agent1.channels.channel1.type=file

agent1.channels.channel1.checkpointDir=/usr/local/flume/tmp/checkpointDir

agent1.channels.channel1.dataDirs=/usr/local/flume/tmp/dataDirs

4.配置streaming程式碼

SparkConf conf = new SparkConf().setMaster("local[4]").setAppName("FlumePollDate2SparkStreaming");

JavaStreamingContext jsc = new JavaStreamingContext(conf, Durations.seconds(30));

JavaReceiverInputDStream lines = FlumeUtils.createPollingStream(jsc, "master", 9999);