jsoup使用例子（仅作参考）

package com.gxzhuangxing.seed.modules.release.service;

import java.io.File;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.OutputStream;
import java.net.HttpURLConnection;
import java.net.MalformedURLException;
import java.net.URL;
import java.text.SimpleDateFormat;
import java.util.Date;
import java.util.Random;

import javax.servlet.ServletContext;

import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;
import org.quartz.Scheduler;
import org.springframework.transaction.annotation.Transactional;
import org.springframework.web.context.ContextLoader;
import org.springframework.web.context.WebApplicationContext;

import com.gxzhuangxing.seed.modules.release.entity.Release;

public class Test {	

    //线程锁
    private int releaseLock = 0;
	//这个是总管理类   
	private Scheduler scheduler;
	/**
	 * 监测预警：定时器（二）保存网络数据    逐条执行
	 * @param oneHtml
	 * @return
	 */
	public void saveSpider(){
		System.out.println("----------------------------------------------");
		if(releaseLock!=0)return;
		releaseLock=1;
		String oneHtmlURL="http://www.gxny.gov.cn/news/ncpzlyaq/";
		if(this.getOneHtml(oneHtmlURL)==true){
	    	Document doc;
	    	Element elt;
			try {
				//获取整个页面
				doc = Jsoup.connect(oneHtmlURL).timeout(1800000).get();
				//获取需要的部分
		    	elt=doc.getElementsByClass("subright1concon").get(0);
		    	//分页的获取
		    	Elements pages = elt.getElementsByTag("script");
		    	String scriptOne = pages.get(0).toString();
		    	scriptOne=scriptOne.substring(scriptOne.indexOf("(")+1, scriptOne.lastIndexOf(")"));
		    	String[] pageCont=scriptOne.split(",");
		    	int pageAll =Integer.parseInt(pageCont[0]);
		    	String pageUrl="";
		    	for(int i=0;i<pageAll;i++){
		    		try{
			    		pageUrl=oneHtmlURL+pageCont[2].replace("\"", "").trim()+"_"+i+"."+pageCont[3].replace("\"", "").trim();
			    		if(i==0)pageUrl=oneHtmlURL;
			    		if(this.getOneHtml(pageUrl)==false)continue;
						doc = Jsoup.connect(pageUrl).timeout(1800000).get();
						//获取需要的部分
				    	elt=doc.getElementsByClass("subright1concon").get(0);
				    	//获取节点连接
				    	Elements links = elt.getElementsByTag("a");
				    	for (Element link : links) {
				    		try{
					            String content="";
					            String imageUrl="";
					            String imageUrls="";
					            Element contentOne=null;
					            //获取节点url
					            String url=oneHtmlURL+link.attr("href");
					            //获取title
					            String title=link.attr("title").toString();
					            //线程休眠；防止访问频繁造成访问不了页面现象
					            this.threadSleep();
					            //验证是否已存在数据库内
//					            boolean isExists = this.uriTitle(url, title);
//					            if(isExists==true)continue;
					            System.out.println(title);
					            //获取内容
						    	Elements contentAll=Jsoup.connect(url).timeout(1800000).get().getElementsByClass("TRS_Editor");
						    	if(contentAll==null||contentAll.size()==0){
						    		contentOne=Jsoup.connect(url).timeout(1800000).get().getElementById("mcontent");
						    	}else{
						    		contentOne=contentAll.get(0);
						    	}
				            	content=contentOne.toString();
					            //内容中图片处理
					            Elements images=contentOne.getElementsByTag("img");
					            if(images!=null){
					            	for(Element image : images){
					            		//判断连接是否存在
					            		String isUrl=image.attr("src");
					            		if(isUrl==null||isUrl.trim().equals("")||isUrl.trim().equals("#")){
					            			continue;
					            		}
					            		imageUrl=url.toString().substring(0, url.toString().lastIndexOf("/"))+isUrl.substring(1, isUrl.length());
					            		//图片验证,过滤掉url网址上不正确的图片路径
					            		if(this.getOneHtml(imageUrl)==false)imageUrl="";
					            		//下载图片
					            		imageUrls+=imageUrl+",";
					            		/**
					            		 * 保存数据时验证后再处理下载（需优化逻辑）
					            		 */
		//			            		this.inputImages(imageUrl);
					            		//文件名
				        	            String fileName=imageUrl.substring(imageUrl.lastIndexOf("/")+1, imageUrl.length());
					            		//将内容图片路径替换成服务器图片路径
				        				String filePath=this.savePath("${ctxStatic}/../upload/release/");
				        				String fileUrl=filePath+fileName;
				        				content=content.replace(isUrl, fileUrl);
					            	}
					            }
					            this.saveSpider(url, title, content, imageUrls);
				    		}catch (Exception e){
				                System.out.println("获取本‘条’数据,出现异常："+e);
				    			continue;
				    		}
				    	}
		    		}catch (Exception e){
		                System.out.println("获取本‘页’数据,出现异常："+e);
		    			continue;
		    		}
		    	}
			} catch (IOException e) {
				e.printStackTrace();
			}
		}
		releaseLock=0;
	}
	public Scheduler getScheduler() {  
        return scheduler;  
    }  
    public void setScheduler(Scheduler scheduler) {  
        this.scheduler = scheduler;  
    } 

	/**
	 * 下载url上的图片到本地
	 * @param imageUrl  下载地址
	 * @param filePath  保存文件夹地址
	 * @return
	 */
	@Transactional(readOnly = false)
	public void inputImages(String imageUrl,String filePath){
		try {
			// 构造URL
            String fileName=imageUrl.substring(imageUrl.lastIndexOf("/")+1, imageUrl.length());
			String fileUrl=filePath+fileName;
			URL url = new URL(imageUrl);   
			System.out.println(imageUrl);
			System.out.println(fileUrl);
			// 打开连接   
			HttpURLConnection con = (HttpURLConnection) url.openConnection();   
			//设置请求超时为10s   
			con.setConnectTimeout(180*1000);   
			// 输入流   
			InputStream is = con.getInputStream();
			// 1K的数据缓冲   
			byte[] bs = new byte[1024];   
			// 读取到的数据长度   
			int len;   
			// 输出的文件流   
			File sf=new File(filePath);
			if(sf.isDirectory()&&!sf.exists()){   
				sf.mkdirs();   
			}   
			OutputStream os = new FileOutputStream(fileUrl);   
			// 开始读取   
			while ((len = is.read(bs)) != -1) {   
				
			    os.write(bs, 0, len);   
			}   
			// 完毕，关闭所有链接   
			os.close();   
			is.close();
		} catch (MalformedURLException e) {
            System.out.println("不是正确的URL"+e);
			e.printStackTrace();
		} catch (IOException e) {
            System.out.println("获取不到URL,出现异常："+e);
			e.printStackTrace();
		}
		
	}

	/**
	 * 本地存储图片路径 处理器（按天区分）
	 * @param url
	 * @return
	 */
	@Transactional(readOnly = false)
	public String savePath(String url){
		Date date =new Date();
		SimpleDateFormat sdf=new SimpleDateFormat("yyyyMMdd");
		String dateNow =sdf.format(date);
		String filePath=url+dateNow+"/";
		File file = new File(filePath);
		if(!file.exists()&&!file.isDirectory())file.mkdir();
		return filePath;
	}
	/**
	 * 线程休眠；防止访问过于频繁造成访问不了页面现象
	 */
	public void threadSleep(){
		Thread t =Thread.currentThread();
        int max=1000;
        int min=100;
        Random random = new Random();
        int s = random.nextInt(max)%(max-min+1) + min;
        try {
			t.sleep(s);
		} catch (InterruptedException e) {
			e.printStackTrace();
		}
	}

	
	/**
	 * 验证url
	 * @param oneHtmlURL
	 * @return
	 */
	@Transactional(readOnly = false)
	public boolean getOneHtml(String oneHtmlURL){
		URL url;
        int responsecode;
        HttpURLConnection urlConnection;
        try{
            //生成一个URL对象，要获取源代码的网页地址为：http://www.sina.com.cn
            url=new URL(oneHtmlURL);
            //打开URL
            urlConnection = (HttpURLConnection)url.openConnection();
            //获取服务器响应代码
            responsecode=urlConnection.getResponseCode();
            if(responsecode==200){
            	return true;
            }
            else{
                System.out.println("获取不到网页的源码，服务器响应代码为："+responsecode);
                return false;
            }
        }
        catch(Exception e){
            System.out.println("获取不到网页的源码,出现异常："+e);
            return false;
        }
	}
	/**
	 * 保存数据
	 * @param  String url, String title, String content, String imagesURL(文章路径，文章题目，文章内容，文章内容中的图片)
	 */
	@Transactional(readOnly = false)
	public void saveSpider(String url, String title, String content, String imagesURL){
		Release release = new Release();
		String fileUrl="";
		//下载图片
		if(imagesURL!=null&&!imagesURL.trim().equals("")){
			String[] imageUrls = imagesURL.split(",");
			for(int i=0;i<imageUrls.length;i++){
				if(imageUrls[i]==null||imageUrls[i].trim().equals(""))continue;
	            String fileName=imageUrls[i].substring(imageUrls[i].lastIndexOf("/")+1, imageUrls[i].length());
	            WebApplicationContext webApplicationContext = ContextLoader.getCurrentWebApplicationContext();
	            ServletContext servletContext = webApplicationContext.getServletContext(); 
	            String filePath=this.savePath(servletContext.getRealPath("/").replace("\\", "/")+"upload/release/");
				fileUrl+=filePath+fileName+",";
				this.inputImages(imageUrls[i],filePath);
			}
		}
		release.setCopyfrom(url);
		release.setTitle(title);
		release.setContent(content);
		release.setImagesUrl(fileUrl==null?"":fileUrl);
		release.setInputImagesUrl(imagesURL==null?"":imagesURL);
//		releaseDao.save(release);
	}
	
	public static void main(String[] arg){  
       Test ss=new Test();  
       ss.saveSpider();  
    }  

}