1、编写flume配置文件

a5.channels=c5
a5.sources=s5
a5.sinks=k5

a5.sources.s5.type=spooldir
a5.sources.s5.spoolDir=/opt/retail_db-csv/datas  //要导入kafka的数据的路径
a5.sources.s5.interceptors=head_filter  //使用拦截器将要导入数据的表头去掉
a5.sources.s5.interceptors.head_filter.type=regex_filter  //拦截器的类型
a5.sources.s5.interceptors.head_filter.regex=^event_id.*
a5.sources.s5.interceptors.head_filter.excludeEvents=true  //将满足正则的数据拦截

a5.sinks.k5.type=org.apache.flume.sink.kafka.KafkaSink  //类型必须是这个
a5.sinks.k5.kafka.bootstrap.servers=192.1