定时爬虫系统(以爬取[百度7日关注]为例)

1、web.xml加载servlet

 1 <?xml version="1.0" encoding="UTF-8"?>
 2 <web-app xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns="http://java.sun.com/xml/ns/javaee" xsi:schemaLocation="http://java.sun.com/xml/ns/javaee http://java.sun.com/xml/ns/javaee/web-app_2_5.xsd" id="WebApp_ID" version="2.5">
 3   <display-name>TaskSchedule</display-name>
 4   <welcome-file-list>
 5     <welcome-file>index.html</welcome-file>
 6     <welcome-file>index.htm</welcome-file>
 7     <welcome-file>index.jsp</welcome-file>
 8     <welcome-file>default.html</welcome-file>
 9     <welcome-file>default.htm</welcome-file>
10     <welcome-file>default.jsp</welcome-file>
11   </welcome-file-list>
12   <servlet>
13       <servlet-name>hotword</servlet-name>
14       <servlet-class>com.richinfo.asynctask.servlet.TaskScheduleServlet</servlet-class>
15       <load-on-startup>1</load-on-startup>
16   </servlet>
17 </web-app>

2、TaskScheduleServlet初始化init

 1 public class TaskScheduleServlet extends HttpServlet{
 2     private static final Log logger = LogFactory.getLog(TaskScheduleServlet.class);
 3     private static final long serialVersionUID = 9089148097823231232L;
 4     
 5     @Override
 6     public void init() throws ServletException {
 7         super.init();
 8         logger.info("TaskScheduleServlet init!");
 9         System.setProperty("sun.net.client.defaultConnectTimeout", "30000");
10         System.setProperty("sun.net.client.defaultReadTimeout", "30000");
11         TaskRegister.getInstance().start();
12         printLocalHost();
13         logger.info("TaskScheduleServlet start!");
14     }
15     private void printLocalHost() {
16         try {
17             InetAddress local = InetAddress.getLocalHost();
18             String ip = local.getHostAddress();
19             String host = local.getHostName();
20             logger.info("服务器信息:ip=" + ip + ", host=" + host);
21         } catch (UnknownHostException e) {
22             logger.error(e.getMessage());
23         }
24     }
25 
26     @Override
27     public void destroy() {
28         super.destroy();
29         TaskRegister.getInstance().shutdown();
30         logger.info("TaskScheduleServlet destroy!");
31     }
32 }

3、TaskRegister.getInstance().start()

4、定时任务的设置,这里不做赘述(有兴趣可以看我的另一篇有关定时任务配置的文章http://www.cnblogs.com/zhuziyu/p/7704661.html)

5、爬虫具体实现

(1)调用任务

 1 public class BaiduDayHotFocusGrabJob implements Job{
 2     private final static Log logger = LogFactory.getLog(BaiduDayHotFocusGrabJob.class);
 3     private UnifiedPosMgrPlatService service = new UnifiedPosMgrPlatSeviceImpl();
 4     @Override
 5     public void execute(JobExecutionContext context)
 6             throws JobExecutionException {
 7         JobKey key = context.getJobDetail().getKey();
 8         logger.info("开始任务["+key.getGroup()+"."+key.getName()+"]");
 9         
10         try {
11             resolve();
12         } catch (Exception e) {
13             logger.error(Tools.getStackInfo(e));
14         }
15     }
16     
17     public void resolve() throws IOException {
18         Document doc = Jsoup.connect("http://top.baidu.com/").timeout(10000).get();
19         Element attentionDiv = doc.select("#main div.tab-bd div.tab-box:eq(1)").first();
20         Elements attentionEles = attentionDiv.select("ul li a.list-title");
21         // 七日关注
22         
23         List<HotSpot> attentionList = new ArrayList<HotSpot>();
24         int len = attentionEles.size();
25         for (int i = 0; i < len; i++) {
26             Element ele = attentionEles.get(i);
27             String name = ele.text().trim();
28             String uri = ele.attr("href").trim();
29             attentionList.add(new HotSpot(Source.BAIDU_TOP, uri, name, i));
30         }
31         HotFocus focus = new HotFocus(Type.DAILY, Source.BAIDU_TOP, attentionList);
32         int ret = service.addHotFocus(focus);
33         if (ret != 1) {
34             logger.warn("更新七日关注失败!");
35         }
36         else {
37             logger.info("更新七日关注成功!");
38         }
39     }
40 }

(2)具体实现

 1 public class UnifiedPosMgrPlatSeviceImpl implements UnifiedPosMgrPlatService {
 2     private static final Logger logger = Logger.getLogger(UnifiedPosMgrPlatSeviceImpl.class);
 3     
 4     @Override
 5     public int addHotFocus(HotFocus focus) throws IOException {
 6         if (focus == null) return -1;
 7         List<HotSpot> spots = focus.getHots();
 8         if (spots == null || spots.isEmpty()) return -1;
 9         String uri = getAddHotWordInvokeUrl();
10         String requestXml = requestAddHotWord(focus);
11         String responseXml = invokeAddHotWords(uri, requestXml);
12         return responseAddHotWords(responseXml);
13     }
14 }

对应要调用的接口系统:本人的是http://127.0.0.1:8080/接口系统/方法

6、对应系统的接口实现这里不赘述,最终执行数据库操作,将爬取内容写入数据库表

posted @ 2018-04-23 17:09  不是植物  阅读(370)  评论(0编辑  收藏  举报