htmlparse.java~11~

来自「这是我当时为了完成毕设」· JAVA~11~ 代码 · 共 66 行

package news;

/**
 * <p>Title: 新闻搜索引擎</p>
 * <p>Description: 毕业设计</p>
 * <p>Copyright: Copyright (c) 2003</p>
 * <p>Company: </p>
 * @author 计算机99630 沈晨
 * @version 1.0
 */

import java.util.Iterator;
import java.util.Vector;

import com.heaton.bot.HTMLPage;
import com.heaton.bot.HTTP;
import com.heaton.bot.Link;

public class HTMLParse {
  HTTP _http = null;
  public HTMLParse(HTTP http) {
    _http = http;
  }

  public void start() {
    try {
      HTMLPage _page = new HTMLPage(_http);
      _page.open(_http.getURL(), null);
      Vector _links = _page.getLinks();
      Index _index = new Index();
      Iterator _it = _links.iterator();
      while (_it.hasNext()) {

        Link _link = (Link) _it.next();

        String _herf = input(_link.getHREF().trim());
        String _title = input(_link.getPrompt().trim());

        //System.out.println("=================================");
        //System.out.println("HREF: " + _herf);
        //System.out.println("TITLE: " + _title);

        //_index.AddNews(_herf,_title);

      }
      //_index.close();
    }
    catch (Exception ex) {
      System.out.println(ex);
    }
  }

  public static String input(String str) {
    String temp = null;
    if (str != null) {
      try {
        temp = new String(str.getBytes("ISO8859_1"));
      }
      catch (Exception e) {
      }
    }
    return temp;
  }

}