searcher.java

来自「一个入门的lucene例子」· Java 代码 · 共 52 行

package com.ou;

/**
 * <p>Title: 搜索引擎</p>
 * <p>Description: </p>
 * <p>Copyright: Copyright (c) 2003</p>
 * <p>Company: </p>
 * @author 欧阳凯
 * @version 1.0
 */

import com.heaton.bot.HTTP;
import com.heaton.bot.HTTPSocket;
import com.heaton.bot.ISpiderReportable;
import com.heaton.bot.IWorkloadStorable;
import com.heaton.bot.Spider;
import com.heaton.bot.SpiderInternalWorkload;

public class Searcher
    implements ISpiderReportable {
  public static void main(String[] args) throws Exception {
    IWorkloadStorable wl = new SpiderInternalWorkload();
    Searcher _searcher = new Searcher();
    //我理解获取指定网站的链接
    Spider _spider
        = new Spider(_searcher, "http://www.baidu.com/s?wd=java",
                     new HTTPSocket(), 100, wl);
    _spider.setMaxBody(100);
    _spider.start();
  }
  public boolean foundInternalLink(String url) {
    return false;
  }
  public boolean foundExternalLink(String url) {
    return false;
  }
  public boolean foundOtherLink(String url) {
    return false;
  }
  public void processPage(HTTP http) {
    System.out.println("扫描网页：" + http.getURL());
    new HTMLParse(http).start();
  }
  public void completePage(HTTP http, boolean error) {
  }
  public boolean getRemoveQuery() {
    return true;
  }
  public void spiderComplete() {
  }
}