Java小工具 根据URL的抓取搜索引擎搜索结果数目
效果如下图：
至此Google、百度以及搜狗三大搜索引擎，可根据需要扩展其他搜索引擎。
下面是类图：
通过抽象类SearchEngine实现代码的可扩展性。
下面SearchEngine抽象类的源码：
--------------------------------------------------------------------------------------------------------------------------------------
package com.eyck;
import java.io.BufferedReader;
import java.io.File;
import java.io.FileWriter;
import java.io.IOException;
import java.io.InputStreamReader;
import java.net.URL;
import java.net.URLConnection;
import javax.swing.JOptionPane;
public abstract class SearchEngine {
//由解析网页源码，由子类实现
public abstract void parse(String key);
//进行URL编码，由子类实现
public abstract String UrlEncoder(String key);
//搜索不到相关内容
public void showErrorMessage(String key){
String show = "找不到和您查询的\""+key+"\"相符的内容或信息。\n"
+ "建议：\n"
+ "* 请检查输入字词有无错误。\n"
+ "* 请尝试其他查询词。\n"
+ "* 请改用较常见的字词。";
System.out.println(show);
JOptionPane.showMessageDialog(null, show);
}
//获取网页源码
public String search(String url){
BufferedReader br = null;
StringBuilder sb ;
String result = null;
// FileWriter fw = null;
// File file = null;
try{
sb = new StringBuilder();
System.out.println(url);
URL mUrl = new URL(url);
System.setProperty("http.agent", "Chrome");//支持Google搜索
URLConnection conn = mUrl.openConnection();
String hasRead = "";
// file = new File("G:\\javapractice\\Baidu\\google.html");
// fw = new FileWriter(file);
br = new BufferedReader(new InputStreamReader(conn.getInputStream(),"utf-8"));
while((hasRead=br.readLine())!=null){
sb.append(hasRead);
// fw.write(hasRead);
}
result = sb.toString();
}catch(Exception e){
e.printStackTrace();
}finally{
try {
br.close();
// fw.close();
} catch (IOException e) {
e.printStackTrace();
}
return result;
}
}
}--------------------------------------------------------------------------------------------------------------------------------------
实现类BaiduSearch源码：
package com.eyck;
import java.net.URLEncoder;
import javax.swing.JOptionPane;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.select.Elements;
public class BaiduSearch extends SearchEngine{
@Override
public void parse(String key) {
// TODO Auto-generated method stub
String url = UrlEncoder(key);
String result = search(url);
int start = -1;
int end = -1;
Document doc = Jsoup.parse(result);
Elements elements = doc.getElementsByClass("nums");
String element = elements.toString();
System.out.println(element);
for(int i=0;i<element.length();i++){
if(element.charAt(i)=='百'){
start = i;
}
if(element.charAt(i)=='个'){
end = i+1;
}
}
String finalResult = element.substring(start, end);
if(!finalResult.equals("0")){
System.out.println(finalResult);
JOptionPane.showMessageDialog(null, finalResult);
}else{
showErrorMessage(key);
}
}
@Override
public String UrlEncoder(String key) {
String url = "http://www.baidu.com/s?wd=";
return url += URLEncoder.encode(key);
}
}--------------------------------------------------------------------------------------------------------------------------------------
其他两个实现类GoogleSearch.java和SougouSearch.java与BaiduSearch.java差不多，根据返回的具体源码进行解析即可，这里就不放上来了。
接下来是SearchClient的源码：
package com.eyck;
import java.applet.Applet;
import java.awt.Button;
import java.awt.Choice;
import java.awt.Color;
import java.awt.TextField;
import java.awt.event.ActionEvent;
import java.awt.event.ActionListener;
import java.io.BufferedReader;
import java.io.File;
import java.io.FileOutputStream;
import java.io.FileWriter;
import java.io.IOException;
import java.io.InputStreamReader;
import java.net.URL;
import java.net.URLConnection;
import java.net.URLEncoder;
import java.util.ListIterator;
import javax.swing.JOptionPane;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;
public class SearchClient extends Applet implements ActionListener{
TextField keyword = new TextField(30);
Choice engine ;
Button go = new Button("搜索");
SearchEngine mEngine;
public void init(){
setBackground(Color.white);
keyword = new TextField(20);
engine = new Choice();
engine.addItem("百度");
engine.addItem("Google");
engine.addItem("搜狗");
engine.select(1);
add(keyword);
add(engine);
add(go);
addKeyListener(new MyKeyListener());
go.addActionListener(this);
}
@Override
public void actionPerformed(ActionEvent e) {
// TODO Auto-generated method stub
if(e.getSource() == go){
try{
String key = goSearch();
mEngine.parse(key);
}catch(Exception ex){
ex.printStackTrace();
}
}
}
private String goSearch() throws Exception{
// TODO Auto-generated method stub
String str = keyword.getText();
if(str.equals("")){
JOptionPane.showMessageDialog(null, "请填写搜索的关键词");
return null;
}
String engineName = "";
switch(engine.getSelectedIndex()){
case 0:
engineName = "http://www.baidu.com/";
mEngine = new BaiduSearch();
break;
case 1:
engineName = "https://www.google.com.hk/";
mEngine = new GoogleSearch();
break;
case 2:
engineName = "https://www.sogou.com/";
mEngine = new SougouSearch();
break;
}
//url += URLEncoder.encode(str);
showStatus("正在等待"+engineName+"的响应");
return str;
}
}--------------------------------------------------------------------------------------------------------------------------------------
这里在解析网页源码的时候使用jsoup开源框架 对HTML 文档进行解析和操作，需要导入相关的jar包，笔者使用的是jsoup-1.10.1.jar。
UML类图使用startUML绘制。
小奋斗文章
--------------------------------------------------------------------------------------------------------------------------------------
评论