这里我用两个案例来讲解jsoup爬虫

案例1：完整版的爬虫案例（CSDN博客的增量爬取）

涉及到的点有以下几个：

1、httpclient获取网页内容

2、Jsoup解析网页内容

3、要达到增量爬取的效果，那么需要利用缓存ehcache对重复URL判重

4、将爬取到的数据存入数据库

5、为解决某些网站防盗链的问题，那么需要将对方网站的静态资源（这里只处理了图片）本地化

案例2:为了辅助上篇博客Python的学习，我们需要爬取电影网站的数据

以下是案例1的相关代码及结果图：

Pom依赖

<!-- jdbc驱动包 -->
		<dependency>
			<groupId>mysql</groupId>
			<artifactId>mysql-connector-java</artifactId>
			<version>5.1.44</version>
		</dependency>

		<!-- 添加Httpclient支持 -->
		<dependency>
			<groupId>org.apache.httpcomponents</groupId>
			<artifactId>httpclient</artifactId>
			<version>4.5.2</version>
		</dependency>

		<!-- 添加jsoup支持 -->
		<dependency>
			<groupId>org.jsoup</groupId>
			<artifactId>jsoup</artifactId>
			<version>1.10.1</version>
		</dependency>


		<!-- 添加日志支持 -->
		<dependency>
			<groupId>log4j</groupId>
			<artifactId>log4j</artifactId>
			<version>1.2.16</version>
		</dependency>

		<!-- 添加ehcache支持 -->
		<dependency>
			<groupId>net.sf.ehcache</groupId>
			<artifactId>ehcache</artifactId>
			<version>2.10.3</version>
		</dependency>

		<!-- 添加commons io支持 -->
		<dependency>
			<groupId>commons-io</groupId>
			<artifactId>commons-io</artifactId>
			<version>2.5</version>
		</dependency>

		<dependency>
			<groupId>com.alibaba</groupId>
			<artifactId>fastjson</artifactId>
			<version>1.2.47</version>
		</dependency>

crawler.properties

dbUrl=jdbc:mysql://localhost:3306/mybatis_ssm?autoReconnect=true
dbUserName=mybatis_ssm
dbPassword=xiaoli
jdbcName=com.mysql.jdbc.Driver
ehcacheXmlPath=C://blogCrawler/ehcache.xml
blogImages=C://blogCrawler/blogImages/

log4j.properties 

DbUtil.java

package com.javaxl.util;

import java.sql.Connection;
import java.sql.DriverManager;

/**
 * 数据库工具类
 * @author user
 *
 */
public class DbUtil {

	/**
	 * 获取连接
	 * @return
	 * @throws Exception
	 */
	public Connection getCon()throws Exception{
		Class.forName(PropertiesUtil.getValue("jdbcName"));
		Connection con=DriverManager.getConnection(PropertiesUtil.getValue("dbUrl"), PropertiesUtil.getValue("dbUserName"), PropertiesUtil.getValue("dbPassword"));
		return con;
	}
	
	/**
	 * 关闭连接
	 * @param con
	 * @throws Exception
	 */
	public void closeCon(Connection con)throws Exception{
		if(con!=null){
			con.close();
		}
	}
	
	public static void main(String[] args) {
		DbUtil dbUtil=new DbUtil();
		try {
			dbUtil.getCon();
			System.out.println("数据库连接成功");
		} catch (Exception e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
			System.out.println("数据库连接失败");
		}
	}
}

PropertiesUtil.java

package com.javaxl.util;

import java.io.IOException;
import java.io.InputStream;
import java.util.Properties;

/**
 * properties工具类
 * @author user
 *
 */
public class PropertiesUtil {

	/**
	 * 根据key获取value值
	 * @param key
	 * @return
	 */
	public static String getValue(String key){
		Properties prop=new Properties();
		InputStream in=new PropertiesUtil().getClass().getResourceAsStream("/crawler.properties");
		try {
			prop.load(in);
		} catch (IOException e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
		}
		return prop.getProperty(key);
	}
}

BlogCrawlerStarter.java（核心代码）

package com.javaxl.crawler;

import java.io.File;
import java.io.IOException;
import java.sql.Connection;
import java.sql.PreparedStatement;
import java.sql.SQLException;
import java.util.HashMap;
import java.util.List;
import java.util.Map;
import java.util.UUID;

import org.apache.commons.io.FileUtils;
import org.apache.http.HttpEntity;
import org.apache.http.client.ClientProtocolException;
import org.apache.http.client.config.RequestConfig;
import org.apache.http.client.methods.CloseableHttpResponse;
import org.apache.http.client.methods.HttpGet;
import org.apache.http.impl.client.CloseableHttpClient;
import org.apache.http.impl.client.HttpClients;
import org.apache.http.util.EntityUtils;
import org.apache.log4j.Logger;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;

import com.javaxl.util.DateUtil;
import com.javaxl.util.DbUtil;
import com.javaxl.util.PropertiesUtil;

import net.sf.ehcache.Cache;
import net.sf.ehcache.CacheManager;
import net.sf.ehcache.Status;

/**
 * @author Administrator
 *
 */
public class BlogCrawlerStarter {

	private static Logger logger = Logger.getLogger(BlogCrawlerStarter.class);
	private static String HOMEURL = "https://www.csdn.net/nav/newarticles";
	private static CloseableHttpClient httpClient;
	private static Connection con;
	private static CacheManager cacheManager;
	private static Cache cache;

	/**
	 * httpclient解析首页，获取首页内容
	 */
	public static void parseHomePage() {
		logger.info("开始爬取首页：" + HOMEURL);
		
		cacheManager = CacheManager.create(PropertiesUtil.getValue("ehcacheXmlPath"));
		cache = cacheManager.getCache("cnblog");
		
		httpClient = HttpClients.createDefault();
		HttpGet httpGet = new HttpGet(HOMEURL);
		RequestConfig config = RequestConfig.custom().setConnectTimeout(5000).setSocketTimeout(8000).build();
		httpGet.setConfig(config);
		CloseableHttpResponse response = null;
		try {
			response = httpClient.execute(httpGet);
			if (response == null) {
				logger.info(HOMEURL + ":爬取无响应");
				return;
			}

			if (response.getStatusLine().getStatusCode() == 200) {
				HttpEntity entity = response.getEntity();
				String homePageContent = EntityUtils.toString(entity, "utf-8");
				// System.out.println(homePageContent);
				parseHomePageContent(homePageContent);
			}

		} catch (ClientProtocolException e) {
			logger.error(HOMEURL + "-ClientProtocolException", e);
		} catch (IOException e) {
			logger.error(HOMEURL + "-IOException", e);
		} finally {
			try {
				if (response != null) {
					response.close();
				}

				if (httpClient != null) {
					httpClient.close();
				}
			} catch (IOException e) {
				logger.error(HOMEURL + "-IOException", e);
			}
		}

		if(cache.getStatus() ==  Status.STATUS_ALIVE) {
			cache.flush();
		}
		cacheManager.shutdown();
		logger.info("结束爬取首页：" + HOMEURL);

	}

	/**
	 * 通过网络爬虫框架jsoup，解析网页类容，获取想要数据（博客的连接）
	 * 
	 * @param homePageContent
	 */
	private static void parseHomePageContent(String homePageContent) {
		Document doc = Jsoup.parse(homePageContent);
		Elements aEles = doc.select("#feedlist_id .list_con .title h2 a");
		for (Element aEle : aEles) {
//			这个是首页中的博客列表中的单个链接URL
			String blogUrl = aEle.attr("href");
			if (null == blogUrl || "".equals(blogUrl)) {
				logger.info("该博客未内容，不再爬取插入数据库！");
				continue;
			}
			if(cache.get(blogUrl) != null) {
				logger.info("该数据已经被爬取到数据库中，数据库不再收录！");
				continue;
			}
//			System.out.println("************************"+blogUrl+"****************************");
			
			parseBlogUrl(blogUrl);
		}
	}

	/**
	 * 通过博客地址获取博客的标题，以及博客的类容
	 * 
	 * @param blogUrl
	 */
	private static void parseBlogUrl(String blogUrl) {

		logger.info("开始爬取博客网页：" + blogUrl);
		httpClient = HttpClients.createDefault();
		HttpGet httpGet = new HttpGet(blogUrl);
		RequestConfig config = RequestConfig.custom().setConnectTimeout(5000).setSocketTimeout(8000).build();
		httpGet.setConfig(config);
		CloseableHttpResponse response = null;
		try {
			response = httpClient.execute(httpGet);
			if (response == null) {
				logger.info(blogUrl + ":爬取无响应");
				return;
			}

			if (response.getStatusLine().getStatusCode() == 200) {
				HttpEntity entity = response.getEntity();
				String blogContent = EntityUtils.toString(entity, "utf-8");
				parseBlogContent(blogContent, blogUrl);
			}

		} catch (ClientProtocolException e) {
			logger.error(blogUrl + "-ClientProtocolException", e);
		} catch (IOException e) {
			logger.error(blogUrl + "-IOException", e);
		} finally {
			try {
				if (response != null) {
					response.close();
				}
			} catch (IOException e) {
				logger.error(blogUrl + "-IOException", e);
			}
		}

		logger.info("结束爬取博客网页：" + HOMEURL);

	}

	/**
	 * 解析博客类容，获取博客中标题以及所有内容
	 * 
	 * @param blogContent
	 */
	private static void parseBlogContent(String blogContent, String link) {
		Document doc = Jsoup.parse(blogContent);
		Elements titleEles = doc
				.select("#mainBox main .blog-content-box .article-header-box .article-header .article-title-box h1");
		if (titleEles.size() == 0) {
			logger.info("博客标题为空，不插入数据库！");
			return;
		}
		String title = titleEles.get(0).html();

		Elements blogContentEles = doc.select("#content_views");
		if (blogContentEles.size() == 0) {
			logger.info("博客内容为空，不插入数据库！");
			return;
		}
		String blogContentBody = blogContentEles.get(0).html();
		
//		Elements imgEles = doc.select("img");
//		List<String> imgUrlList = new LinkedList<String>();
//		if(imgEles.size() > 0) {
//			for (Element imgEle : imgEles) {
//				imgUrlList.add(imgEle.attr("src"));
//			}
//		}
//		
//		if(imgUrlList.size() > 0) {
//			Map<String, String> replaceUrlMap = downloadImgList(imgUrlList);
//			blogContent = replaceContent(blogContent,replaceUrlMap);
//		}

		String sql = "insert into `t_jsoup_article` values(null,?,?,null,now(),0,0,null,?,0,null)";
		try {
			PreparedStatement pst = con.prepareStatement(sql);
			pst.setObject(1, title);
			pst.setObject(2, blogContentBody);
			pst.setObject(3, link);
			if(pst.executeUpdate() == 0) {
				logger.info("爬取博客信息插入数据库失败");
			}else {
				cache.put(new net.sf.ehcache.Element(link, link));
				logger.info("爬取博客信息插入数据库成功");
			}
		} catch (SQLException e) {
			logger.error("数据异常-SQLException：",e);
		}
	}

	/**
	 * 将别人博客内容进行加工，将原有图片地址换成本地的图片地址
	 * @param blogContent
	 * @param replaceUrlMap
	 * @return
	 */
	private static String replaceContent(String blogContent, Map<String, String> replaceUrlMap) {
		for(Map.Entry<String, String> entry: replaceUrlMap.entrySet()) {
			blogContent = blogContent.replace(entry.getKey(), entry.getValue());
		}
		return blogContent;
	}

	/**
	 * 别人服务器图片本地化
	 * @param imgUrlList
	 * @return
	 */
	private static Map<String, String> downloadImgList(List<String> imgUrlList) {
		Map<String, String> replaceMap = new HashMap<String, String>();
		for (String imgUrl : imgUrlList) {
			CloseableHttpClient httpClient = HttpClients.createDefault();
			HttpGet httpGet = new HttpGet(imgUrl);
			RequestConfig config = RequestConfig.custom().setConnectTimeout(5000).setSocketTimeout(8000).build();
			httpGet.setConfig(config);
			CloseableHttpResponse response = null;
			try {
				response = httpClient.execute(httpGet);
				if (response == null) {
					logger.info(HOMEURL + ":爬取无响应");
				}else {
					if (response.getStatusLine().getStatusCode() == 200) {
						HttpEntity entity = response.getEntity();
						String blogImagesPath = PropertiesUtil.getValue("blogImages");
						String dateDir = DateUtil.getCurrentDatePath();
						String uuid = UUID.randomUUID().toString();
						String subfix = entity.getContentType().getValue().split("/")[1];
						String fileName = blogImagesPath + dateDir + "/" + uuid + "." + subfix;
						
						FileUtils.copyInputStreamToFile(entity.getContent(), new File(fileName));
						replaceMap.put(imgUrl, fileName);
					}
				}
			} catch (ClientProtocolException e) {
				logger.error(imgUrl + "-ClientProtocolException", e);
			} catch (IOException e) {
				logger.error(imgUrl + "-IOException", e);
			} catch (Exception e) {
				logger.error(imgUrl + "-Exception", e);
			} finally {
				try {
					if (response != null) {
						response.close();
					}
				} catch (IOException e) {
					logger.error(imgUrl + "-IOException", e);
				}
			}
		
		}
		return replaceMap;
	}

	public static void start() {
		while(true) {
			DbUtil dbUtil = new DbUtil();
			try {
				con = dbUtil.getCon();
				parseHomePage();
			} catch (Exception e) {
				logger.error("数据库连接势失败！");
			} finally {
				try {
					if (con != null) {
						con.close();
					}
				} catch (SQLException e) {
					logger.error("数据关闭异常-SQLException：",e);
				}
			}
			try {
				Thread.sleep(1000*60);
			} catch (InterruptedException e) {
				logger.error("主线程休眠异常-InterruptedException：",e);
			}
		}
	}

	public static void main(String[] args) {
		start();
	}
}

ehcache.xml 

控制台效果图：

以下是案例2的相关代码及结果图：

package com.javaxl.crawler;

import java.io.IOException;
import java.sql.Connection;
import java.sql.PreparedStatement;
import java.sql.SQLException;
import java.util.LinkedList;
import java.util.List;
import java.util.UUID;

import org.apache.http.HttpEntity;
import org.apache.http.client.ClientProtocolException;
import org.apache.http.client.config.RequestConfig;
import org.apache.http.client.methods.CloseableHttpResponse;
import org.apache.http.client.methods.HttpGet;
import org.apache.http.impl.client.CloseableHttpClient;
import org.apache.http.impl.client.HttpClients;
import org.apache.http.util.EntityUtils;
import org.apache.log4j.Logger;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;

import com.zking.util.DbUtil;
import com.zking.util.PropertiesUtil;

import net.sf.ehcache.Cache;
import net.sf.ehcache.CacheManager;
import net.sf.ehcache.Status;

/**
 * 第一页 http://www.8gw.com/8gli/index8.html 第二页
 * http://www.8gw.com/8gli/index8_2.html 图片地址
 * http://img.dphydh.com/uploadimg/2013-3/20105141822720399.jpg
 * 
 * @author Administrator
 *
 */
public class MovieCrawlerStarter {
	private static Logger logger = Logger.getLogger(MovieCrawlerStarter.class);
	private static String URL = "http://www.8gw.com/";
	private static String PROJECT_URL = "http://www.8gw.com";

	private static Connection con;
	private static CacheManager manager;
	private static Cache cache;
	private static CloseableHttpClient httpClient;
	private static long total = 0;

	/**
	 * 等待爬取的52个链接的数据
	 * 
	 * @return
	 */
	private static List<String> getUrls() {
		List<String> list = new LinkedList<String>();
		list.add("http://www.8gw.com/8gli/index8.html");
		for (int i = 2; i < 53; i++) {
			list.add("http://www.8gw.com/8gli/index8_" + i + ".html");
		}
		return list;
	}

	/**
	 * 获取URL主体类容
	 * 
	 * @param url
	 */
	private static void parseUrl(String url) {

		logger.info("开始爬取系列列表：：" + url);

		HttpGet httpGet = new HttpGet(url);
		RequestConfig config = RequestConfig.custom().setConnectTimeout(5000).setSocketTimeout(8000).build();
		httpGet.setConfig(config);
		CloseableHttpResponse response = null;
		try {
			response = httpClient.execute(httpGet);
			if (response == null) {
				logger.info("链接超时！");
			} else {
				if (response.getStatusLine().getStatusCode() == 200) {
					HttpEntity entity = response.getEntity();
					String pageContent = EntityUtils.toString(entity, "GBK");
					parsePageContent(pageContent, url);
				}
			}
		} catch (ClientProtocolException e) {
			logger.error(url + "-解析异常-ClientProtocolException", e);
		} catch (IOException e) {
			logger.error(url + "-解析异常-IOException", e);
		} finally {
			try {
				if (response != null) {
					response.close();
				}
			} catch (IOException e) {
				logger.error(url + "-解析异常-IOException", e);
			}
		}
		logger.info("结束爬取系列列表：：" + url);

	}

	/**
	 * 获取当前页中的具体影片的链接
	 * @param pageContent
	 * @param url
	 */
	private static void parsePageContent(String pageContent, String url) {
//		System.out.println("****************" + url + "***********************");
		Document doc = Jsoup.parse(pageContent);
		Elements liEles = doc.select(".span_2_800 #list_con li");
		for (Element liEle : liEles) {
			
			String movieUrl = liEle.select(".info a").attr("href");
			if (null == movieUrl || "".equals(movieUrl)) {
				logger.info("该影片未内容，不再爬取插入数据库！");
				continue;
			}
			if(cache.get(movieUrl) != null) {
				logger.info("该数据已经被爬取到数据库中，数据库不再收录！");
				continue;
			}
			parseSingleMovieUrl(PROJECT_URL+movieUrl);
		}
		
	}

	/**
	 * 解析单个影片链接
	 * @param movieUrl
	 */
	private static void parseSingleMovieUrl(String movieUrl) {
		logger.info("开始爬取影片网页：" + movieUrl);
		httpClient = HttpClients.createDefault();
		HttpGet httpGet = new HttpGet(movieUrl);
		RequestConfig config = RequestConfig.custom().setConnectTimeout(5000).setSocketTimeout(8000).build();
		httpGet.setConfig(config);
		CloseableHttpResponse response = null;
		try {
			response = httpClient.execute(httpGet);
			if (response == null) {
				logger.info(movieUrl + ":爬取无响应");
				return;
			}

			if (response.getStatusLine().getStatusCode() == 200) {
				HttpEntity entity = response.getEntity();
				String blogContent = EntityUtils.toString(entity, "GBK");
				parseSingleMovieContent(blogContent, movieUrl);
			}

		} catch (ClientProtocolException e) {
			logger.error(movieUrl + "-ClientProtocolException", e);
		} catch (IOException e) {
			logger.error(movieUrl + "-IOException", e);
		} finally {
			try {
				if (response != null) {
					response.close();
				}
			} catch (IOException e) {
				logger.error(movieUrl + "-IOException", e);
			}
		}

		logger.info("结束爬取影片网页：" + movieUrl);

			
	}

	/**
	 * 解析页面主体类容（影片名字、影片描述、影片地址）
	 * @param pageContent
	 * @param movieUrl
	 */
	private static void parseSingleMovieContent(String pageContent, String movieUrl) {
//		System.out.println("****************" + movieUrl + "***********************");
		Document doc = Jsoup.parse(pageContent);
		Elements divEles = doc.select(".wrapper .main .moviedteail");
//		.wrapper .main .moviedteail .moviedteail_tt h1
//		.wrapper .main .moviedteail .moviedteail_list .moviedteail_list_short a
//		.wrapper .main .moviedteail .moviedteail_img img	
		
		Elements h1Eles = divEles.select(".moviedteail_tt h1");
		if (h1Eles.size() == 0) {
			logger.info("影片名字为空，不插入数据库！");
			return;
		}
		String mname = h1Eles.get(0).html();
		
		Elements aEles = divEles.select(".moviedteail_list .moviedteail_list_short a");
		if (aEles.size() == 0) {
			logger.info("影片描述为空，不插入数据库！");
			return;
		}
		String mdesc = aEles.get(0).html();
		
		Elements imgEles = divEles.select(".moviedteail_img img");
		if (null == imgEles || "".equals(imgEles)) {
			logger.info("影片描述为空，不插入数据库！");
			return;
		}
		String mimg = imgEles.attr("src");
		String sql = "insert into movie(mname,mdesc,mimg,mlink) values(?,?,?,99)";
		
		try {
			System.out.println("****************" + mname + "***********************");
			System.out.println("****************" + mdesc + "***********************");
			System.out.println("****************" + mimg + "***********************");
			
			PreparedStatement pst = con.prepareStatement(sql);
			pst.setObject(1, mname);
			pst.setObject(2, mdesc);
			pst.setObject(3, mimg);
			if(pst.executeUpdate() == 0) {
				logger.info("爬取影片信息插入数据库失败");
			}else {
				cache.put(new net.sf.ehcache.Element(movieUrl, movieUrl));
				logger.info("爬取影片信息插入数据库成功");
			}
		} catch (SQLException e) {
			logger.error("数据异常-SQLException：",e);
		}
	}

	public static void main(String[] args) {
		manager = CacheManager.create(PropertiesUtil.getValue("ehcacheXmlPath"));
		cache = manager.getCache("8gli_movies");
		httpClient = HttpClients.createDefault();
		DbUtil dbUtil = new DbUtil();
		
		try {
			con = dbUtil.getCon();
			List<String> urls = getUrls();
			for (String url : urls) {
				try {
					parseUrl(url);
				} catch (Exception e) {
//					urls.add(url);
				}
			} 
		} catch (Exception e1) {
			logger.error("数据库连接势失败！");
		} finally {
			try {
				if (httpClient != null) {
					httpClient.close();
				}
				if (con != null) {
					con.close();
				}
			} catch (IOException e) {
				logger.error("网络连接关闭异常-IOException：",e);
			} catch (SQLException e) {
				logger.error("数据关闭异常-SQLException：",e);
			}
		}
		// 最终将数据缓存到硬盘中
		if (cache.getStatus() == Status.STATUS_ALIVE) {
			cache.flush();
		}
		manager.shutdown();
	}

}

over......