电商实战
项目需求
根据电商日志文件,分析:
-
统计页面浏览量(每行记录就是一次浏览)
-
统计各个省份的浏览量 (需要解析IP)
-
日志的ETL操作,本项目中需要解析出:ip、url、pageId(topicId对应的页面Id)、country、province、city
本篇文章完成问题3
实现思路
- Extract(抽取): 同上,将日志文件上传到HDFS(即第1问时上传的文件)
- Transform(转换):
- Mapper:
读取日志文件的每一行,解析出所需的字段,包括ip、url。对于pageId,可能需要从url中提取特定的部分(如/products/123中的123),或者使用正则表达式匹配。对于country、province、city,同样可以通过IP地址库进行查找。Mapper将解析出的字段作为键值对输出。- Reducer:
如果Mapper的输出已经满足需求(即每个key对应唯一的记录),则可能不需要Reducer。但如果有需要合并或进一步处理的记录,可以使用Reducer。
- Load(加载): 将转换后的数据加载到目标存储中,如HDFS、HBase、Hive或关系型数据库等。如果目标存储是HBase或Hive,还需要定义相应的表结构或模式。
实现代码
LogETLMapper.java
import com.bigdata.hadoop.project.utils.GetPageId;
import com.bigdata.hadoop.project.utils.LogParser;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import java.io.IOException;
import java.util.Map;
public class LogETLMapper extends Mapper<LongWritable, Text, Text, IntWritable> {
private static final IntWritable one = new IntWritable(1);
private Text outputKey = new Text();
private LogParser logParser = new LogParser();
private Logger logger = LoggerFactory.getLogger(LogETLMapper.class);
@Override
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
// 解析日志记录
Map<String, String> logInfo = logParser.parse(value.toString());
if (logInfo == null) {
logger.error("日志记录的格式不正确或解析失败:" + value.toString());
return;
}
// 获取需要的字段
String ip = logInfo.get("ip");
String url = logInfo.get("url");
String country = logInfo.get("country");
String province = logInfo.get("province");
String city = logInfo.get("city");
// 调用 GetPageId 获取 topicId
String topicId = GetPageId.getPageId(url);
logInfo.put("pageId", topicId);
// 检查所有字段是否全部为空
if (ip != null || url != null || topicId != null || country != null || province != null || city != null) {
StringBuilder sb = new StringBuilder();
if (ip != null && !ip.isEmpty()) sb.append("IP: ").append(ip).append(", ");
if (url != null && !url.isEmpty()) sb.append("URL: ").append(url).append(", ");
if (topicId != null && !topicId.isEmpty()) sb.append("PageId: ").append(topicId).append(", ");
if (country != null && !country.isEmpty()) sb.append("Country: ").append(country).append(", ");
if (province != null && !province.isEmpty()) sb.append("Province: ").append(province).append(", ");
if (city != null && !city.isEmpty()) sb.append("City: ").append(city);
// 移除末尾的逗号和空格
String outputString = sb.toString().replaceAll(", $", "");
outputKey.set(outputString);
context.write(outputKey, one);
} else {
logger.error("所有字段为空,日志记录:" + value.toString());
}
}
}
LogETLReducer.java
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
import java.io.IOException;
public class LogETLReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
private IntWritable result = new IntWritable();
@Override
protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
int sum = 0;
for (IntWritable val : values) {
sum += val.get();
}
result.set(sum);
context.write(key, result);
}
}
LogETLDriver.java
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
public class LogETLDriver {
public static void main(String[] args) throws Exception {
if (args.length != 2) {
System.err.println("Usage: LogETLDriver <input path> <output path>");
System.exit(-1);
}
Configuration conf = new Configuration();
Job job = Job.getInstance(conf, "Log ETL");
job.setJarByClass(LogETLDriver.class);
job.setMapperClass(LogETLMapper.class);
job.setCombinerClass(LogETLReducer.class);
job.setReducerClass(LogETLReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
FileInputFormat.addInputPath(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}
运行结果
将java项目打包后,在Hadoop上运行jar包