大数据小项目之统计pv点击量v1

流程：

1.将可以运行的项目打成jar包（点击左侧maven下Lifecycle的package）,上传到Linux集群上（我上传到hdp-2)，

运行 Java -jar neiminda-0.0.1-SNAPSHOT.jar   。 测试：运行 hdp-2:8886

2.启动nginx  启动nginx目的是为了产生日志，还有负载均衡和反向代理（这里没涉及到负载均衡）

 /usr/local/nginx/conf 路径下nginx.conf 配置文件

启动nginx: ./nginx

关闭nginx： ./nginx -s quit

重启nginx： ./nginx -s reload

#user  nobody;
worker_processes  1;

#error_log  logs/error.log;
#error_log  logs/error.log  notice;
#error_log  logs/error.log  info;

#pid        logs/nginx.pid;


events {
    worker_connections  1024;
}


http {
    include       mime.types;
    default_type  application/octet-stream;
#产生的日志
    log_format  main  '$remote_addr';

    #access_log  logs/access.log  main;

    sendfile        on;
    #tcp_nopush     on;

    #keepalive_timeout  0;
    keepalive_timeout  65;

    #gzip  on;
upstream frame-tomcat {
# 指明nginx转发地址
          server hdp-2:8886 ;
    }
    server {
        listen       80;
#nginx的服务地址
        server_name  hdp-1;

        #charset koi8-r;
# nginx产生的日志存放的地址
        access_log  logs/log.frame.access.log  main;

        location / {
            # root   html;
            # index  index.html index.htm;
            proxy_pass http://frame-tomcat;
        }

        error_page   500 502 503 504  /50x.html;
        location = /50x.html {
            root   html;
        }


    }
    server {
        listen       80;
        server_name  localhost;

        #charset koi8-r;

        #access_log  logs/host.access.log  main;

        location / {
            root   html;
            index  index.html index.htm;
        }

        #error_page  404              /404.html;

        # redirect server error pages to the static page /50x.html
        #
        error_page   500 502 503 504  /50x.html;
        location = /50x.html {
            root   html;
        }

        # proxy the PHP scripts to Apache listening on 127.0.0.1:80
        #
        #location ~ \.php$ {
        #    proxy_pass   http://127.0.0.1;
        #}

        # pass the PHP scripts to FastCGI server listening on 127.0.0.1:9000
        #
        #location ~ \.php$ {
        #    root           html;
        #    fastcgi_pass   127.0.0.1:9000;
        #    fastcgi_index  index.php;
        #    fastcgi_param  SCRIPT_FILENAME  /scripts$fastcgi_script_name;
        #    include        fastcgi_params;
        #}

        # deny access to .htaccess files, if Apache's document root
        # concurs with nginx's one
        #
        #location ~ /\.ht {
        #    deny  all;
        #}
    }


    # another virtual host using mix of IP-, name-, and port-based configuration
    #
    #server {
    #    listen       8000;
    #    listen       somename:8080;
    #    server_name  somename  alias  another.alias;

    #    location / {
    #        root   html;
    #        index  index.html index.htm;
    #    }
    #}


    # HTTPS server
    #
    #server {
    #    listen       443;
    #    server_name  localhost;

    #    ssl                  on;
    #    ssl_certificate      cert.pem;
    #    ssl_certificate_key  cert.key;

    #    ssl_session_timeout  5m;

    #    ssl_protocols  SSLv2 SSLv3 TLSv1;
    #    ssl_ciphers  HIGH:!aNULL:!MD5;
    #    ssl_prefer_server_ciphers   on;

    #    location / {
    #        root   html;
    #        index  index.html index.htm;
    #    }
    #}

}

注：这时nginx产生的日志已经存在nginx的logs下的log.frame.access.log里

3.启动flume 采集nginx产生的日志下沉到Kafka

查看flume的配置文件（flume下的tail-kafka.conf）

#source 为数据源
a1.sources = source1
#sink 下沉数据
a1.sinks = k1
# channel 管道通道
a1.channels = c1

#exec：指明数据源来自一个可执行指令
a1.sources.source1.type = exec
#可执行指令，跟踪一个文件中的内容
a1.sources.source1.command = tail -F /usr/local/nginx/logs/log.frame.access.log
# Describe the sink
#下沉到Kafka的下沉类型
a1.sinks.k1.type = org.apache.flume.sink.kafka.KafkaSink
# topic 作用是生产者和消费者之间的纽扣
a1.sinks.k1.topic = test
#kafka的地址
a1.sinks.k1.brokerList = hdp-1:9092, hdp-2:9092, hdp-3:9092
a1.sinks.k1.requiredAcks = 1
a1.sinks.k1.batchSize = 20
a1.sinks.k1.channel = c1
# Use a channel which buffers events in memory
a1.channels.c1.type = memory
a1.channels.c1.capacity = 1000
a1.channels.c1.transactionCapacity = 100

# Bind the source and sink to the channel
a1.sources.source1.channels = c1
a1.sinks.k1.channel = c1

启动flume：在flume的bin下./flume-ng agent -C ../conf/ -f ../tail-kafka.conf -n a1 -Dflume.root.logger=INFO,console    

注意：nginx中conf下的nginx.conf 里面的接收采集数据地址要和flume里tail-kafka.conf的数据源地址相同，也就是要跟踪的路径

4.启动kafka 注意启动之前要先启动zookeeper ，在kafka的消费者中收到数据产生临时文件。

启动zookeeper

启动Kafka

先在Kafka上启动一个消费者，测试一下是否收取到数据

bin/kafka-console-consumer.sh --bootstrap-server hdp-1:9092,hdp-2:9092,hdp-3:9092 --topic test --from-beginning

 

5.利用Java代码实现消费者接收数据产生临时文件,临时文件为 d:/testlog/access.log

package com.zpark.kafkatest.one;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FSDataOutputStream;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.kafka.clients.consumer.ConsumerRecord;
import org.apache.kafka.clients.consumer.ConsumerRecords;
import org.apache.kafka.clients.consumer.KafkaConsumer;
import org.apache.log4j.Logger;


import java.io.BufferedWriter;
import java.io.FileOutputStream;
import java.io.OutputStreamWriter;
import java.net.URI;
import java.net.URISyntaxException;
import java.util.Collections;
import java.util.Properties;

public class ConsumerLocal {

    public static void main(String[] args) {
        Logger logger = Logger.getLogger("logRollingFile");
        //调用接收消息的方法
        receiveMsg();
    }

    /**
     * 获取kafka topic（test）上的数据
     */
    private static void receiveMsg() {
        Logger logger = Logger.getLogger("logRollingFile");
        Properties properties = new Properties();
        properties.put("bootstrap.servers", "hdp-2:9092");
        properties.put("key.deserializer", "org.apache.kafka.common.serialization.StringDeserializer");
        properties.put("value.deserializer", "org.apache.kafka.common.serialization.StringDeserializer");
        properties.put("group.id","aaaa");
        properties.put("enable.auto.commit", true);
        //一个方法
        KafkaConsumer<String, String> consumer = new KafkaConsumer<String, String>(properties);
        consumer.subscribe(Collections.singleton("test"));
//        URI uri = null;
//        Configuration conf = null;
//        String user = "root";
//        try {
//            uri = new URI("hdfs://hdp-1:9000");
//            conf = new Configuration();
//            conf = new Configuration();
//            //dfs.replication：分布式文件系统副本的数量
//            conf.set("dfs.replication", "2");
//            //dfs.blocksize:分布式文件系统的块的大小   100M   64+36
//            conf.set("dfs.blocksize", "64m");
//
//        } catch (URISyntaxException e) {
//            e.printStackTrace();
//        }
        try {
            FileOutputStream fos = new FileOutputStream("d:/testlog/access.log");
            OutputStreamWriter osw = new OutputStreamWriter(fos);


//            FileSystem fs = FileSystem.get(uri, conf, user);
//            FSDataOutputStream fdos = fs.create(new Path("/cf.txt"));
            while(true) {

                /**
                 * 获取kafka
                 */
                ConsumerRecords<String, String> records = consumer.poll(100);
                for(ConsumerRecord<String, String> record: records) {
                    String msg = "key:" + record.key()+ ",value:" + record.value() + ",offset:" + record.offset()+",topic:" + record.topic()+"\r\n";
                    System.out.printf("key=%s,value=%s,offet=%s,topic=%s",record.key() , record.value() , record.offset(), record.topic());
                    logger.debug(record.value());
//                    BufferedWriter bw = new BufferedWriter(osw);
//                    bw.write(msg);
//                    bw.flush();

                }
            }
        }catch (Exception e) {
            e.printStackTrace();
        } finally {
            consumer.close();
        }
    }
}

6.将产生的临时文件上传到hdfs的hive表中

hive中建表： create external table flumetable2 (ip string ) row format delimited location '/usr/';

本地文件上传到hdfs,代码展示：

package com.zpark.kafkatest.one;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;

import java.io.IOException;
import java.net.URI;
import java.net.URISyntaxException;

public class toHDFS {
    public static void main(String[] args) {
        URI uri = null;
        Configuration conf = null;
        String user = "root";
        FileSystem fs = null;
        try {
            uri = new URI("hdfs://hdp-1:9000");
            conf = new Configuration();
            //dfs.replication：分布式文件系统副本的数量
            conf.set("dfs.replication", "2");
            //dfs.blocksize:分布式文件系统的块的大小   100M   64+36
            conf.set("dfs.blocksize", "64m");
            fs = FileSystem.get(uri, conf, user);
            fs.copyFromLocalFile(new Path("d:/testlog/access.log"),new Path("/usr/a.txt"));
            /**
             * 往hdfs中写文件
             */
//            FSDataOutputStream out = fs.create(new Path("/bc.txt"));
//            OutputStreamWriter outWriter = new OutputStreamWriter(out);
//            BufferedWriter bw = new BufferedWriter(outWriter);
//            bw.write("hello");
//            bw.close();
//            out.close();
            fs.close();
        } catch (URISyntaxException e) {
            e.printStackTrace();
        } catch (InterruptedException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        } finally {

        }
    }
}

注意：当消费者接收数据产生临时文件之后，再启动本地文件上传到hdfs的Java代码，

6.hive分析 select count(*) from flumetable2;统计访问总pv。