Hadoop学习之网络爬虫+分词+倒排索引实现搜索引擎案例

汤高

发布于 2018-01-11 16:23:30

1.1K0

发布于 2018-01-11 16:23:30

本项目实现的是：自己写一个网络爬虫，对搜狐(或者csdn)爬取新闻(博客)标题,然后把这些新闻标题和它的链接地址上传到hdfs多个文件上，一个文件对应一个标题和链接地址，然后通过分词技术对每个文件中的标题进行分词，分词后建立倒排索引以此来实现搜索引擎的功能，建立倒排索引不熟悉的朋友可以看看我上篇博客

Hadoop–倒排索引过程详解

首先要自己写一个网络爬虫

由于我开始写爬虫的时候用了htmlparser，把所有搜到的链接存到队列，并且垂直搜索，这个工作量太大，爬了一个小时还没爬完造成了我电脑的死机，所以，现在我就去掉了垂直搜索，只爬搜狐的主页的新闻文章链接

不多说，看代码

首先看下载工具类，解释看注释

package com.yc.spider;

import java.io.BufferedInputStream;
import java.io.BufferedOutputStream;
import java.io.File;
import java.io.FileOutputStream;
import java.io.IOException;
import java.net.HttpURLConnection;
import java.net.MalformedURLException;
import java.net.URL;
import java.text.DateFormat;
import java.text.SimpleDateFormat;
import java.util.Date;
import java.util.List;
import java.util.Random;
import java.util.Scanner;
import java.util.Set;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
/**
 * 下载工具类
 * @author 汤高 
 *
 */
public class DownLoadTool {
    /**
     * 下载页面的内容
     * 就是根据地址下载整个html标签
     * 
     * @param addr
     * @return
     */
    public String downLoadUrl(final String addr) {
        StringBuffer sb = new StringBuffer();
        try {
            URL url;
            if(addr.startsWith("http://")==false){
                String urladdr=addr+"http://";
                 url = new URL(urladdr);
            }else{
            System.out.println(addr);
            url = new URL(addr);
            }
            HttpURLConnection con = (HttpURLConnection) url.openConnection();
            con.setConnectTimeout(5000);
            con.connect();
            if (con.getResponseCode() == 200) {
                BufferedInputStream bis = new BufferedInputStream(con
                        .getInputStream());
                Scanner sc = new Scanner(bis,"gbk");
                while (sc.hasNextLine()) {
                    sb.append(sc.nextLine());
                }
            }
        } catch (IOException e) {
            e.printStackTrace();
        }
        return sb.toString();
    }

}

然后看一个文章链接的匹配类

package com.yc.spider;

import java.io.BufferedInputStream;
import java.io.IOException;
import java.net.HttpURLConnection;
import java.net.URL;
import java.util.ArrayList;
import java.util.HashSet;
import java.util.List;
import java.util.Scanner;
import java.util.Set;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

/**
 * 文章下载类
 * 
 * @author 汤高
 *        
 *         
 */
public class ArticleDownLoad {
    /**
     * 取出文章的a标记href
     */
    static String ARTICLE_URL = "<a\\s+[^<>]*\\s+href=\"?(http[^<>\"]*)\"[^<>]*>([^<]*)</a>";


    static Set<String> getImageLink(String html) {
        Set<String> result = new HashSet<String>();
        // 创建一个Pattern模式类，编译这个正则表达式
        Pattern p = Pattern.compile(ARTICLE_URL, Pattern.CASE_INSENSITIVE);
        // 定义一个匹配器的类
        Matcher matcher = p.matcher(html);
        while (matcher.find()) {
            System.out.println("======="+matcher.group(1)+"\t"+matcher.group(2));
            result.add(matcher.group(1)+"\t"+matcher.group(2));
        }
        return result;

    }


}

下面看爬虫类

package com.yc.spider;

import java.io.IOException;
import java.net.URI;
import java.net.URISyntaxException;
import java.util.List;
import java.util.Set;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

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.htmlparser.util.ParserException;
/**
 * 把爬到的内容上传到hdfs
 * @author 汤高
 * 
 *
 */
public class Spider {
    private DownLoadTool dlt = new DownLoadTool();
    private ArticleDownLoad pdl = new ArticleDownLoad();
    public void crawling(String url) {
        try {
            Configuration conf = new Configuration();
            URI uri = new URI("hdfs://192.168.52.140:9000");
            FileSystem hdfs = FileSystem.get(uri, conf);

            String html = dlt.downLoadUrl(url);
            Set<String> allneed = pdl.getImageLink(html);
            for (String addr : allneed) {
                //生成文件路径
                Path p1 = new Path("/myspider/" + System.currentTimeMillis());
                FSDataOutputStream dos = hdfs.create(p1);
                String a = addr + "\n";
                //把内容写入文件
                dos.write(a.getBytes());
            }
        } catch (IllegalArgumentException e) {
            e.printStackTrace();
        } catch (URISyntaxException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        }
    }
}

最后看测试类来爬内容

package com.yc.spider;

import java.io.FileNotFoundException;

import org.htmlparser.util.ParserException;

public class Test {
    public static void main(String[] args) throws ParserException {
        Spider s=new Spider();
        //  s.crawling("http://blog.csdn.net");
        s.crawling("http://www.sohu.com");

    }
}

看看结果

爬到的内容上传到hdfs上了

下面进行分词和建倒排索引

看分词所用到的包

我的分词用了lucenne5.5.1版本

中文分词用到了IKAnalyzer-5.0.1版本，但是与我的lucenne5.5.1不兼容，所以我做了一下兼容，然后自己打成了一个tanggao-IkAnalyzer.jar包，大家可以用现在最新的IKAnalyzer2012版本，应该可以兼容lucenne5.5.1版本

看代码

package com.tg.hadoop;

import java.io.IOException;
import java.io.StringReader;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
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.KeyValueTextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.tokenattributes.OffsetAttribute;

import com.tg.Ik.IKAnalyzer5x;

public class AriticleInvertedIndex {
    /**
     * 
     * @author 汤高
     *
     */
    public static class ArticleInvertedIndexMapper extends Mapper<Text, Text, Text, Text>{

        private Text keyInfo = new Text();  // 存储单词和URI的组合
        private Text valueInfo = new Text(); //存储词频
        @Override
        protected void map(Text key, Text value, Mapper<Text, Text, Text, Text>.Context context)
                throws IOException, InterruptedException {

            //把标题分词
             Analyzer analyzer = new IKAnalyzer5x(true);
               TokenStream ts = analyzer.tokenStream("field", new StringReader( value.toString().trim()  ));

                OffsetAttribute offsetAtt = ts.addAttribute(OffsetAttribute.class);
                try {
                    ts.reset();
                    while (ts.incrementToken()) {
                        System.out.println(offsetAtt.toString().trim());
                        keyInfo.set( offsetAtt.toString()+":"+key);
                        valueInfo.set("1");
                        System.out.println("key"+keyInfo);
                        System.out.println("value"+valueInfo);
                        context.write(keyInfo, valueInfo);
                    }
                    ts.end();
                } finally {
                    ts.close();
                }
        }
    }

    public static class ArticleInvertedIndexCombiner extends Reducer<Text, Text, Text, Text>{
        private Text info = new Text();
        @Override
        protected void reduce(Text key, Iterable<Text> values, Reducer<Text, Text, Text, Text>.Context context)
                throws IOException, InterruptedException {

            //统计词频
            int sum = 0;
            for (Text value : values) {
                sum += Integer.parseInt(value.toString() );
            }

            int splitIndex = key.toString().indexOf(":");

            //重新设置value值由URI和词频组成
            info.set( key.toString().substring( splitIndex + 1) +":"+sum );

            //重新设置key值为单词
            key.set( key.toString().substring(0,splitIndex));

            context.write(key, info);
            System.out.println("key"+key);
            System.out.println("value"+info);
        }
    }


    public static class ArticleInvertedIndexReducer extends Reducer<Text, Text, Text, Text>{

        private Text result = new Text();

        @Override
        protected void reduce(Text key, Iterable<Text> values, Reducer<Text, Text, Text, Text>.Context context)
                throws IOException, InterruptedException {

            //生成文档列表
            String fileList = new String();
            for (Text value : values) {
                fileList += value.toString()+";";
            }
            result.set(fileList);

            context.write(key, result);
        }

    }

    public static void main(String[] args) {
        try {
            Configuration conf = new Configuration();

            Job job = Job.getInstance(conf,"InvertedIndex");
            job.setJarByClass(AriticleInvertedIndex.class);
            job.setInputFormatClass(KeyValueTextInputFormat.class);
            //实现map函数，根据输入的<key,value>对生成中间结果。
            job.setMapperClass(ArticleInvertedIndexMapper.class);

            job.setMapOutputKeyClass(Text.class);
            job.setMapOutputValueClass(Text.class);

            job.setCombinerClass(ArticleInvertedIndexCombiner.class);
            job.setReducerClass(ArticleInvertedIndexReducer.class);

            job.setOutputKeyClass(Text.class);
            job.setOutputValueClass(Text.class);


            FileInputFormat.addInputPath(job, new Path("hdfs://192.168.52.140:9000/myspider/"));
            FileOutputFormat.setOutputPath(job, new Path("hdfs://192.168.52.140:9000/myspider_outindex"+System.currentTimeMillis()+"/"));

            System.exit(job.waitForCompletion(true) ? 0 : 1);
        } catch (IllegalStateException e) {
            e.printStackTrace();
        } catch (IllegalArgumentException e) {
            e.printStackTrace();
        } catch (ClassNotFoundException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        } catch (InterruptedException e) {
            e.printStackTrace();
        }

    }
}

结果：

转载请指明出处：https://cloud.tencent.com/developer/article/1018569

         $(function () {                 $('pre.prettyprint code').each(function () {                     var lines = $(this).text().split('\n').length;                     var $numbering = $('<ul/>').addClass('pre-numbering').hide();                     $(this).addClass('has-numbering').parent().append($numbering);                     for (i = 1; i <= lines; i++) {                         $numbering.append($('<li/>').text(i));                     };                     $numbering.fadeIn(1700);                 });             });

本文参与腾讯云自媒体分享计划，分享自作者个人站点/博客。

原始发表：2016-05-12 ，如有侵权请联系 cloudcommunity@tencent.com 删除

爬虫