Java应用开源框架实现简易web搜索引擎

引言

应用 Java 的开源库，编写一个搜索引擎，这个引擎能爬取一个网站的内容。并根据网页内容进行深度爬取，获取所有相关的网页地址和内容，用户可以通过关键词，搜索所有相关的网址。

具体功能

(1) 用户可以指定爬取一个url对应的网页的内容。
(2) 对网页内容进行解析，并获取其中所有的url链接地址。
(3) 用户可以设定爬取深度，代表着从初始url对应的页面开始，可以爬取其中所有的url对应的网页内的url，以此类推。深度越大，能爬取到的网站越多。
(4) 对爬取到的url内容进行保存、建立索引。建立索引的内容是url地址本身，和url对应的网页标题。
(5) 用户可以通过关键词对网址进行搜索，找出有该关键词的url地址。
(6) 建立索引和搜索索引的过程能智能识别中文关键词，能对关键词进行分词操作。
(7) 用户可以指定保存索引的地址、初始url、爬取深度、进行搜索的关键词和最大匹配项。

开源框架

Lucene
Jsoup

源码

爬虫部分：Spider.java

package webCrawler.Spider;

import java.io.IOException;
import java.util.ArrayList;
import java.util.HashSet;
import java.util.Scanner;

import org.jsoup.Jsoup;
import org.jsoup.nodes.document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;

import webCrawler.Index.BuildIndex;



public class Spider {
  ArrayList URLs;
  private String startURL;
  private int digLevel;

  
  public Spider(String startURL, int digLevel){
    this.startURL = startURL;
    this.digLevel = digLevel;
    this.URLs = new ArrayList<>();
  }

  
  public ArrayList getLevelURLs(int level, ArrayList arrayList) 
      throws IOException{
    ArrayList total = null;
    if(level>0){      
      total = new ArrayList<>();
      for(String url: arrayList){
 
 for(String each: getBarelinks(url)){
   total.add(each);
 }
      }
      
      HashSet hashSet = new HashSet<>(total);
      total = new ArrayList<>(hashSet);
    }
    return total;
  }

  
  public void getAll() throws IOException{
    ArrayList newURLs;
    ArrayList currentURLs = new ArrayList<>();
    
    currentURLs.add(startURL);
    for(int i=digLevel; i>0; i--){
      
      System.out.println("Dig into level: " + (digLevel-i+1));
      newURLs = getLevelURLs(i, currentURLs);
      for(String each: currentURLs){
 URLs.add(each);
      }
      currentURLs = newURLs;
    }
    for(String each:currentURLs){
      URLs.add(each);
    }
    HashSet hashSet = new HashSet<>(URLs);
    URLs = new ArrayList<>(hashSet);
  }

  
  public void storeURLsAndInfo(String path) throws IOException{
    BuildIndex build = new BuildIndex(path);
    
    for(String each:URLs){
      String text = getlinkText(each);
      if(text!=null){
 build.addField("url", each);
 build.addField("text", text);
 
 build.pushIndex();
      }
    }
    build.close();
  }

  
  public String getlinkText(String url) throws IOException{
    document document = null;
    try {
      
      document = Jsoup.connect(url).timeout(3000).get();
    } catch (Exception e) {
      System.out.println("[TIMEOUT]Get title of url:"+url);
      return null;
    }
    String title = document.title();
    return title;
  }


  
  public ArrayList getBarelinks(String url) throws IOException{
    ArrayList linksList = new ArrayList<>();
    document document;

    try {
      document = Jsoup.connect(url).timeout(2000).get();
    } catch (Exception e) {
      return linksList;
    }
    
    Elements links = document.select("body").select("a[href]");

    for(Element link: links){
      
      String href = link.attr("abs:href").replaceAll("#", "");
      
      if(href.contains("zju.edu.cn")){
 if (href.endsWith("/")){
   href = href.substring(0, href.length()-1);
 }
 linksList.add(href);
      }
    }
    HashSet hashSet = new HashSet<>(linksList);
    ArrayList arrayList = new ArrayList<>(hashSet);

    return arrayList;
  }

  public static void main(String[] args) {
    Scanner in = new Scanner(System.in);
    System.out.println("Enter url:");
    String url = in.nextLine().trim();
    while(!url.startsWith("http://")){
      System.out.println("http:// is needed!");
      System.out.println("Enter url:");
      url = in.nextLine().trim();
    }
    System.out.println("Enter depth to dig more urls[<=3 recommended]：");
    int depth = in.nextInt();
    Spider spider = new Spider(url, depth);
    System.out.println("Enter path you want to save[default=d:/index-spider]:");
    String path = in.nextLine().trim();
    if(path.length()==0){
      path = "d:/index-spider";
    }
    try {
      System.out.println("Start fetching...");
      spider.getAll();
      System.out.println("Urls got success!");
      spider.storeURLsAndInfo(path);
      System.out.println("Stored success!");
    } catch (IOException e) {
      e.printStackTrace();
    }
  }

 
}

建立索引：BuildIndex.java

package webCrawler.Index;

import java.io.*;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.document.document;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.TextField;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.util.Version;
import org.wltea.analyzer.lucene.IKAnalyzer;


public class BuildIndex {
  private File file;
  private Directory directory;
  private IndexWriter indexWriter;
  private IndexWriterConfig config;
  private Analyzer analyzer;
  private document document;

  
  public BuildIndex(String path) {
    try {
      file = new File(path);
      directory = FSDirectory.open(file);
      document = new document();
      analyzer = new IKAnalyzer();    
      config = new IndexWriterConfig(Version.LUCENE_4_10_0, analyzer);
      indexWriter = new IndexWriter(directory, config);      

    } catch (Exception e) {
      e.printStackTrace();
    }
  }

  
  public void addField(String fieldName, String fieldText){
    try{
      Field field = new TextField(fieldName, fieldText, Field.Store.YES);
      document.add(field);
    }catch (Exception e) {
      e.printStackTrace();
    }
  }

  
  public void pushIndex(){
    try {
      indexWriter.adddocument(document);
      document = new document();
    } catch (Exception e) {
      e.printStackTrace();
    }
  }

  
  public void addoneIndex(String url, String text){
    this.addField("url", url);
    this.addField("text", text);
    this.pushIndex();
  }

  
  public void close(){
    try {
      indexWriter.close();
    } catch (Exception e) {
      e.printStackTrace();
    }
  }

}

搜索索引

package webCrawler.Index;

import java.io.File;
import java.util.Scanner;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.document.document;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.queryparser.classic.QueryParser;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.store.FSDirectory;
import org.wltea.analyzer.lucene.IKAnalyzer;


public class SearchIndex {
  private IndexSearcher indexSearcher;
  private Analyzer analyzer;
  private QueryParser parser;
  private Query query;
  private TopDocs hits;
  private DirectoryReader reader;

  
  public SearchIndex(String path){
    try {
      reader = DirectoryReader.open(FSDirectory.open(new File(path)));
      indexSearcher = new IndexSearcher(reader);
      analyzer = new IKAnalyzer();
    } catch (Exception e) {
      e.printStackTrace();
    }
  }

  
  public int search(String fieldName, String text, int matchNumber){
    try {
      parser = new QueryParser(fieldName, analyzer);
      query = parser.parse(text);
      hits = indexSearcher.search(query, matchNumber);

      return hits.totalHits;
    } catch (Exception e) {
      e.printStackTrace();
    }
    return -1;
  }
  
  public void printHits(){
    try{
      System.out.println("Total hits number:"+hits.totalHits);
      for(ScoreDoc doc: hits.scoreDocs){
 document document = indexSearcher.doc(doc.doc);
 System.out.println(document.get("url"));
 System.out.println(document.get("text"));
      }
      reader.close();
    }catch (Exception e) {
      e.printStackTrace();
    }
  }
  public static void main(String[] args) {
    
    Scanner in = new Scanner(System.in);
    System.out.println("Enter path of the index:");
    String path = in.nextLine().trim();
    while(path.length()==0){
      System.out.println("Enter path of the index:");
      path = in.nextLine().trim();
    }

    System.out.println("Enter max hit number:");
    int max = in.nextInt();
    while(max<0){
      System.out.println("Enter max hit number:");
      max = in.nextInt();
    }
    in.nextLine();
    System.out.print("Search>>> ");
    String text = in.nextLine().trim();
    
    while(!text.equals("q")){
      if(text.length()>0){
 SearchIndex search = new SearchIndex(path);
 int hits = search.search("text", text, max);
 if(hits!=-1){
   search.printHits();
 }
      }
      System.out.print("Search>>> ");
      text = in.nextLine().trim();
    }
  }
}

UI界面（这里为了方便只是命令行的形式，可以根据需求写一个GUI界面）

package webCrawler.UI;

import java.util.Scanner;

import webCrawler.Index.SearchIndex;


public class UI {
  public static void main(String[] args) {
    
    Scanner in = new Scanner(System.in);
    System.out.print("Search>>> ");
    String text = in.nextLine().trim();
    
    while(!text.equals("q") && text.length()>0){
      SearchIndex search = new SearchIndex("d:/index-spider2");
      int hits = search.search("text", text, 20);
      if(hits!=-1){
 search.printHits();
      }
      System.out.print("Search>>> ");
      text = in.nextLine().trim();
    }
  }
}

以上就是本文的全部内容，希望对大家的学习有所帮助，也希望大家多多支持考高分网。

Java应用开源框架实现简易web搜索引擎

Java相关栏目本月热门文章