日志=>flume=>kafka=>spark streaming=>hbase
日志=>flume=>kafka=>spark streaming=>hbase
日志部分
#coding=UTF-8 import random import time url_paths = [ "class/112.html", "class/128.html", "learn/821", "class/145.html", "class/146.html", "class/131.html", "class/130.html", "course/list" ] ip_slices = [132,156,124,10, 29, 167,143,187,30, 46, 55, 63, 72, 87,98,168] http_referers = [ "http://www.baidu.com/s?wd={query}", "http://www.sogou.com/web?query={query}", "https://search.yahoo.com/search?p={query}", "http://www.bing.com/search?q={query}" ] search_keyword = ["Spark SQL实战", "Hadoop基础", "Storm实战", "Spark Streaming实战", "大数据面试"] status_codes = ["200", "404", "500"] def sample_url(): return random.sample(url_paths,1)[0] def sample_ip(): slice = random.sample(ip_slices,4) return ".".join([str(item) for item in slice]) def sample_status_code(): return random.sample(status_codes,1)[0] def sample_referer(): if random.uniform(0, 1) > 0.2: return "-" refer_str = random.sample(http_referers, 1) query_str = random.sample(search_keyword, 1) return refer_str[0].format(query=query_str[0]) def generate_log(count=3): time_str = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime()) f = open("/home/hadoop/data/project/logs/access.log", "w+") while count >= 1: query_log = "{ip}\t[{local_time}]\t\"GET /{url} HTTP/1.1\"\t{status_code}\t\"{referer}\"".format(ip=sample_ip() , local_time=time_str, url=sample_url(), status_code=sample_status_code(), referer=sample_referer()) print query_log f.write(query_log + "\n") count = count - 1 if __name__ == '__main__': #print sample_ip() #print sample_url() generate_log(10)
flume对接日志部分
exec-memory-kafka.conf
#exec-memory-kafka exec-memory-kafka.sources = exec-source exec-memory-kafka.channels = memory-channel exec-memory-kafka.sinks = kafka-sink exec-memory-kafka.sources.exec-source.type = exec exec-memory-kafka.sources.exec-source.command = tail -F /home/hadoop/data/project/logs/access.log exec-memory-kafka.sources.exec-source.shell = /bin/sh -c exec-memory-kafka.sources.exec-source.channels = memory-channel exec-memory-kafka.channels.memory-channel.type = memory exec-memory-kafka.sinks.kafka-sink.type = org.apache.flume.sink.kafka.KafkaSink exec-memory-kafka.sinks.kafka-sink.topic = streamingtopic exec-memory-kafka.sinks.kafka-sink.brokerList = hadoop:9092 exec-memory-kafka.sinks.kafka-sink.batchSize = 5 exec-memory-kafka.sinks.kafka-sink.requiredAcks = 1 exec-memory-kafka.sinks.kafka-sink.channel = memory-channel
flume-ng agent \
--name exec-memory-kafka \
--conf $FLUME_HOME/conf \
--conf-file /home/hadoop/data/project/exec-memory-kafka.conf \
-Dflume.root.logger=INFO,console
启动kafka测试消费：kafka-console-consumer.sh --zookeeper hadoop:2181 --topic streamingtopic --from-beginning
启动Hadoop：start-dfs.sh
启动hbase: start-hbase.sh
进入hbase shell：hbase shell -> 查看： list
hbase表设计:
create 'lin_course_clickcount' ,'info'
create 'lin_course_search_clickcount','info'
查看表：scan 'lin_course_clickcount'
rowkey设计：
day_courseid
day_search_courseid
<?xml version="1.0" encoding="UTF-8"?> <project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd"> <modelVersion>4.0.0</modelVersion> <groupId>com.lin.spark</groupId> <artifactId>SparkStreaming</artifactId> <version>1.0-SNAPSHOT</version> <properties> <scala.version>2.11.8</scala.version> <kafka.version>0.9.0.0</kafka.version> <spark.version>2.2.0</spark.version> <hadoop.version>2.6.0-cdh5.7.0</hadoop.version> <hbase.version>1.2.0-cdh5.7.0</hbase.version> </properties> <!--添加cloudera的repository--> <repositories> <repository> <id>cloudera</id> <url>https://repository.cloudera.com/artifactory/cloudera-repos</url> </repository> </repositories> <dependencies> <dependency> <groupId>org.scala-lang</groupId> <artifactId>scala-library</artifactId> <version>${scala.version}</version> </dependency> <!-- Kafka 依赖--> <!-- <dependency> <groupId>org.apache.kafka</groupId> <artifactId>kafka_2.11</artifactId> <version>${kafka.version}</version> </dependency> --> <!-- Hadoop 依赖--> <dependency> <groupId>org.apache.hadoop</groupId> <artifactId>hadoop-client</artifactId> <version>${hadoop.version}</version> </dependency> <!-- HBase 依赖--> <dependency> <groupId>org.apache.hbase</groupId> <artifactId>hbase-client</artifactId> <version>${hbase.version}</version> </dependency> <dependency> <groupId>org.apache.hbase</groupId> <artifactId>hbase-server</artifactId> <version>${hbase.version}</version> </dependency> <!-- Spark Streaming 依赖--> <dependency> <groupId>org.apache.spark</groupId> <artifactId>spark-streaming_2.11</artifactId> <version>${spark.version}</version> </dependency> <!-- Spark Streaming整合Flume 依赖--> <dependency> <groupId>org.apache.spark</groupId> <artifactId>spark-streaming-flume_2.11</artifactId> <version>${spark.version}</version> </dependency> <dependency> <groupId>org.apache.spark</groupId> <artifactId>spark-streaming-flume-sink_2.11</artifactId> <version>${spark.version}</version> </dependency> <dependency> <groupId>org.apache.spark</groupId> <artifactId>spark-streaming-kafka-0-8_2.11</artifactId> <version>${spark.version}</version> </dependency> <dependency> <groupId>org.apache.commons</groupId> <artifactId>commons-lang3</artifactId> <version>3.5</version> </dependency> <!-- Spark SQL 依赖--> <dependency> <groupId>org.apache.spark</groupId> <artifactId>spark-sql_2.11</artifactId> <version>${spark.version}</version> </dependency> <dependency> <groupId>com.fasterxml.jackson.module</groupId> <artifactId>jackson-module-scala_2.11</artifactId> <version>2.6.5</version> </dependency> <dependency> <groupId>net.jpountz.lz4</groupId> <artifactId>lz4</artifactId> <version>1.3.0</version> </dependency> <dependency> <groupId>mysql</groupId> <artifactId>mysql-connector-java</artifactId> <version>5.1.38</version> </dependency> <dependency> <groupId>org.apache.flume.flume-ng-clients</groupId> <artifactId>flume-ng-log4jappender</artifactId> <version>1.6.0</version> </dependency> </dependencies> <build> <!-- <sourceDirectory>src/main/scala</sourceDirectory> <testSourceDirectory>src/test/scala</testSourceDirectory> --> <plugins> <plugin> <groupId>org.scala-tools</groupId> <artifactId>maven-scala-plugin</artifactId> <executions> <execution> <goals> <goal>compile</goal> <goal>testCompile</goal> </goals> </execution> </executions> <configuration> <scalaVersion>${scala.version}</scalaVersion> <args> <arg>-target:jvm-1.5</arg> </args> </configuration> </plugin> <plugin> <groupId>org.apache.maven.plugins</groupId> <artifactId>maven-eclipse-plugin</artifactId> <configuration> <downloadSources>true</downloadSources> <buildcommands> <buildcommand>ch.epfl.lamp.sdt.core.scalabuilder</buildcommand> </buildcommands> <additionalProjectnatures> <projectnature>ch.epfl.lamp.sdt.core.scalanature</projectnature> </additionalProjectnatures> <classpathContainers> <classpathContainer>org.eclipse.jdt.launching.JRE_CONTAINER</classpathContainer> <classpathContainer>ch.epfl.lamp.sdt.launching.SCALA_CONTAINER</classpathContainer> </classpathContainers> </configuration> </plugin> </plugins> </build> <reporting> <plugins> <plugin> <groupId>org.scala-tools</groupId> <artifactId>maven-scala-plugin</artifactId> <configuration> <scalaVersion>${scala.version}</scalaVersion> </configuration> </plugin> </plugins> </reporting> </project>
package com.lin.spark.streaming.project.spark import com.lin.spark.streaming.project.dao.{CourseClickCountDAO, CourseSearchClickCountDAO} import com.lin.spark.streaming.project.domain.{ClickLog, CourseClickCount, CourseSearchClickCount} import com.lin.spark.streaming.project.utils.DateUtils import org.apache.spark.SparkConf import org.apache.spark.streaming.kafka.KafkaUtils import org.apache.spark.streaming.{Seconds, StreamingContext} import scala.collection.mutable.ListBuffer /** * Created by Administrator on 2019/6/6. */ object StatStreamingApp { def main(args: Array[String]): Unit = { if (args.length != 4) { System.err.println("参数有误！") System.exit(1) } //hadoop:2181 test streamingtopic 2 val Array(zkQuorum, group, topics, numThreads) = args val conf = new SparkConf().setAppName("KafkaUtil").setMaster("local[4]") val ssc = new StreamingContext(conf, Seconds(60)) val topicMap = topics.split(",").map((_, numThreads.toInt)).toMap val clickLog = KafkaUtils.createStream(ssc, zkQuorum, group, topicMap).map(_._2) val cleanData = clickLog.map(line => { val infos = line.split("\t") //29.98.156.124 2019-06-06 05:37:01 "GET /class/131.html HTTP/1.1" 500 http://www.baidu.com/s?wd=Storm实战 //case class ClickLog(ip:String, time:String, courseId:Int, statusCode:Int, referer:String) var courseId = 0 val url = infos(2).split(" ")(1) if (url.startsWith("/class")) { val urlHTML = url.split("/")(2) courseId = urlHTML.substring(0, urlHTML.lastIndexOf(".")).toInt } ClickLog(infos(0), DateUtils.parseToMinute(infos(1)), courseId, infos(3).toInt, infos(4)) }).filter(clickLog => clickLog.courseId != 0) //存储点击日志 cleanData.map(log => { (log.time.substring(0, 8) + "_" + log.courseId, 1) }).reduceByKey(_ + _).foreachRDD(rdd => { rdd.foreachPartition(partitionReconrds => { val list = new ListBuffer[CourseClickCount] partitionReconrds.foreach(pair => { list.append(CourseClickCount(pair._1, pair._2)) }) CourseClickCountDAO.save(list) }) }) //存储查询点击日志 cleanData.map(log => { val referer = log.referer.replaceAll("//", "/") val splits = referer.split("/") var host = "" if (splits.length > 2) { host = splits(1) } (host, log.courseId, log.time) }).filter(x => { x._1 != "" }).map(searchLog=>{ (searchLog._3.substring(0,8) + "_" + searchLog._1 + "_" + searchLog._2 , 1) }).reduceByKey(_ + _).foreachRDD(rdd => { rdd.foreachPartition(partitionReconrds => { val list = new ListBuffer[CourseSearchClickCount] partitionReconrds.foreach(pair => { list.append(CourseSearchClickCount(pair._1, pair._2)) }) CourseSearchClickCountDAO.save(list) }) }) ssc.start() ssc.awaitTermination() } }
package com.lin.spark.streaming.project.utils import java.util.Date import org.apache.commons.lang3.time.FastDateFormat /** * Created by Administrator on 2019/6/6. */ object DateUtils { val YYYYMMDDHHMMSS_FORMAT = FastDateFormat.getInstance("yyyy-MM-dd HH:mm:ss") val TARGE_FORMAT = FastDateFormat.getInstance("yyyyMMddHHmmss") def getTime(time:String) ={ YYYYMMDDHHMMSS_FORMAT.parse(time).getTime } def parseToMinute(time:String)={ TARGE_FORMAT.format(new Date(getTime(time))) } def main(args: Array[String]): Unit = { println(parseToMinute("2017-10-22 14:46:01")) } }
package com.lin.spark.streaming.project.domain case class ClickLog(ip:String, time:String, courseId:Int, statusCode:Int, referer:String)
package com.lin.spark.streaming.project.domain /** * Created by Administrator on 2019/6/7. */ case class CourseClickCount(day_course:String,click_course:Long)
package com.lin.spark.streaming.project.domain /** * Created by Administrator on 2019/6/7. */ case class CourseSearchClickCount(day_search_course:String, click_count:Long)
package com.lin.spark.streaming.project.dao import com.lin.spark.project.utils.HBaseUtils import com.lin.spark.streaming.project.domain.CourseClickCount import org.apache.hadoop.hbase.client.Get import org.apache.hadoop.hbase.util.Bytes import scala.collection.mutable.ListBuffer /** * Created by Administrator on 2019/6/7. */ object CourseClickCountDAO { val tableName = "lin_course_clickcount" val cf = "info" val qualifer = "click_count" def save(list:ListBuffer[CourseClickCount]):Unit={ val table =HBaseUtils.getInstance().getTable(tableName) for (ele <- list){ table.incrementColumnValue(Bytes.toBytes(ele.day_course), Bytes.toBytes(cf), Bytes.toBytes(qualifer), ele.click_course) } } def count(day_course:String):Long={ val table = HBaseUtils.getInstance().getTable(tableName) val get = new Get(Bytes.toBytes(day_course)) val value = table.get(get).getValue(cf.getBytes,qualifer.getBytes) if(value == null){ 0L }else{ Bytes.toLong(value) } } def main(args: Array[String]): Unit = { val list = new ListBuffer[CourseClickCount] list.append(CourseClickCount("20190606",99)) list.append(CourseClickCount("20190608",89)) list.append(CourseClickCount("20190609",100)) // save(list) println(count("20190609")) } }
package com.lin.spark.streaming.project.dao import com.lin.spark.project.utils.HBaseUtils import com.lin.spark.streaming.project.domain.{CourseClickCount, CourseSearchClickCount} import org.apache.hadoop.hbase.client.Get import org.apache.hadoop.hbase.util.Bytes import scala.collection.mutable.ListBuffer /** * Created by Administrator on 2019/6/7. */ object CourseSearchClickCountDAO { val tableName = "lin_course_search_clickcount" val cf = "info" val qualifer = "click_count" def save(list:ListBuffer[CourseSearchClickCount]):Unit={ val table =HBaseUtils.getInstance().getTable(tableName) for (ele <- list){ table.incrementColumnValue(Bytes.toBytes(ele.day_search_course), Bytes.toBytes(cf), Bytes.toBytes(qualifer), ele.click_count) } } def count(day_course:String):Long={ val table = HBaseUtils.getInstance().getTable(tableName) val get = new Get(Bytes.toBytes(day_course)) val value = table.get(get).getValue(cf.getBytes,qualifer.getBytes) if(value == null){ 0L }else{ Bytes.toLong(value) } } def main(args: Array[String]): Unit = { val list = new ListBuffer[CourseSearchClickCount] list.append(CourseSearchClickCount("20190606_www.baidu.com_99",99)) list.append(CourseSearchClickCount("20190608_www.bing.com_89",89)) list.append(CourseSearchClickCount("20190609_www.csdn.net_100",100)) save(list) // println(count("20190609")) } }
