Result文件数据说明:
Ip:106.39.41.166,(城市)
Date:10/Nov/2016:00:01:02 +0800,(日期)
Day:10,(天数)
Traffic: 54 ,(流量)
Type: video,(类型:视频video或文章article)
Id: 8701(视频或者文章的id)
测试要求:
1、 数据清洗:按照进行数据清洗,并将清洗后的数据导入hive数据库中。
两阶段数据清洗:
(1)第一阶段:把需要的信息从原始日志中提取出来
ip: 199.30.25.88
time: 10/Nov/2016:00:01:03 +0800
traffic: 62
文章: article/11325
视频: video/3235
(2)第二阶段:根据提取出来的信息做精细化操作
ip--->城市 city(IP)
date--> time:2016-11-10 00:01:03
day: 10
traffic:62
type:article/video
id:11325
(3)hive数据库表结构:
create table data( ip string, time string , day string, traffic bigint,
type string, id string )
2、数据处理:
·统计最受欢迎的视频/文章的Top10访问次数 (video/article)
·按照地市统计最受欢迎的Top10课程 (ip)
·按照流量统计最受欢迎的Top10课程 (traffic)
3、数据可视化:将统计结果倒入MySql数据库中,通过图形化展示的方式展现出来。
阶段一:
/* * 将日志文件首先利用mapreduce清洗出来,然后导入hive里 * */ package classtest3; import java.io.IOException; import java.text.SimpleDateFormat; import java.util.Date; import java.util.Iterator; import java.util.Locale; import java.util.StringTokenizer; import org.apache.hadoop.conf.Configuration; import org.apache.hadoop.fs.Path; import org.apache.hadoop.io.IntWritable; import org.apache.hadoop.io.LongWritable; import org.apache.hadoop.io.Text; import org.apache.hadoop.mapreduce.Job; import org.apache.hadoop.mapreduce.Mapper; import org.apache.hadoop.mapreduce.Reducer; import org.apache.hadoop.mapreduce.lib.input.FileInputFormat; import org.apache.hadoop.mapreduce.lib.input.TextInputFormat; import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat; import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat; public class Result{ public static final SimpleDateFormat FORMAT = new SimpleDateFormat("d/MMM/yyyy:HH:mm:ss", Locale.ENGLISH); //原时间格式 public static final SimpleDateFormat dateformat1 = new SimpleDateFormat("yyyy-MM-dd");//现时间格式 private Date parseDateFormat(String string) { //转换时间格式 Date parse = null; try { parse = FORMAT.parse(string); } catch (Exception e) { e.printStackTrace(); } return parse; } //将一行数据清洗整合到一个字符串数组里 public String[] parse(String line) { String ip = parseIP(line); //ip String time = parseTime(line); //时间 String url = parseURL(line); //url String status = parseStatus(line); //状态 String traffic = parseTraffic(line);//流量 return new String[] { ip, time, url, status, traffic }; } private String parseTraffic(String line) { //流量 final String trim = line.substring(line.lastIndexOf("\"") + 1) .trim(); String traffic = trim.split(" ")[1]; return traffic; } private String parseStatus(String line) { //状态 final String trim = line.substring(line.lastIndexOf("\"") + 1) .trim(); String status = trim.split(" ")[0]; return status; } private String parseURL(String line) { //url final int first = line.indexOf("\""); final int last = line.lastIndexOf("\""); String url = line.substring(first + 1, last); return url; } //解析Time private String parseTime(String line) { //时间 final int first = line.indexOf("[");//查找一个字符串中,第一次出现指定字符串的位置。 final int last = line.indexOf("+0800]"); String time = line.substring(first + 1, last).trim();//"hamburger".substring(3,8) returns "burge" Date date = parseDateFormat(time); return dateformat1.format(date); } private String parseIP(String line) { //ip String ip = line.split("- -")[0].trim(); return ip; } public static class Map extends Mapper<LongWritable, Text, Text, IntWritable> { public void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException { // 将输入的纯文本文件的数据转化成String Text outputValue = new Text(); String line = value.toString(); Result aa=new Result(); StringTokenizer tokenizerArticle = new StringTokenizer(line, "\n"); // 分别对每一行进行处理 while (tokenizerArticle.hasMoreElements()) { // 每行按空格划分 String stra=tokenizerArticle.nextToken().toString(); String [] Newstr=aa.parse(stra); if (Newstr[2].startsWith("GET /")) { //过滤开头字符串 Newstr[2] = Newstr[2].substring("GET /".length()); } else if (Newstr[2].startsWith("POST /")) { Newstr[2] = Newstr[2].substring("POST /".length()); } if (Newstr[2].endsWith(" HTTP/1.1")) { //过滤结尾字符串 Newstr[2] = Newstr[2].substring(0, Newstr[2].length() - " HTTP/1.1".length()); } String[] words = Newstr[2].split("/"); if(words.length==4){ outputValue.set(Newstr[0] + "\t" + Newstr[1] + "\t" + words[0]+"\t"+words[1]+"\t"+words[2]+"\t"+words[3]+"\t"+"0"); context.write(outputValue,new IntWritable(1)); } } } } public static class Reduce extends Reducer<Text, IntWritable, Text, IntWritable> { // 实现reduce函数 public void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException { int sum = 0; Iterator<IntWritable> iterator = values.iterator(); while (iterator.hasNext()) { sum += iterator.next().get(); } context.write(key, new IntWritable(sum)); } } public static void main(String[] args) throws Exception { Configuration conf = new Configuration(); // conf.set("mapred.jar","Namecount.jar"); // // String[] ioArgs = new String[] { "name", "name_out" }; // // String[] otherArgs = new GenericOptionsParser(conf, ioArgs).getRemainingArgs();//输入输出路径 // // //验证输入输出路径是否存在 // if (otherArgs.length != 2) { // System.err.println("Usage: Score Average <in> <out>"); // System.exit(2); // } Job job = Job.getInstance(); job.setJarByClass(Result.class); // 设置Map、Combine和Reduce处理类 job.setMapperClass(Map.class); job.setCombinerClass(Reduce.class); job.setReducerClass(Reduce.class); // 设置输出类型 job.setOutputKeyClass(Text.class); job.setOutputValueClass(IntWritable.class); // 将输入的数据集分割成小数据块splites,提供一个RecordReder的实现 job.setInputFormatClass(TextInputFormat.class); // 提供一个RecordWriter的实现,负责数据输出 job.setOutputFormatClass(TextOutputFormat.class); // 设置输入和输出目录 FileInputFormat.addInputPath(job, new Path("hdfs://192.168.57.128:9000/MyMapReduce/classtest3/name.txt")); FileOutputFormat.setOutputPath(job, new Path("hdfs://192.168.57.128:9000/MyMapReduce/classtest3/test1result")); System.exit(job.waitForCompletion(true) ? 0 : 1); } }
导入Hive语句:
load data inpath '/MyMapReduce/classtest3/test1result/part-r-00000' into table acc_log;