1 package us.codecraft.webmagic.model.samples;
2
3 import us.codecraft.webmagic.Page;
4 import us.codecraft.webmagic.Site;
5 import us.codecraft.webmagic.model.*;
6 import us.codecraft.webmagic.model.annotation.ExtractBy;
7 import us.codecraft.webmagic.model.annotation.HelpUrl;
8 import us.codecraft.webmagic.model.annotation.TargetUrl;
9
10
11
12
13 @TargetUrl("http://www.oschina.net/question/\\d+_\\d+*")
14 @HelpUrl("http://www.oschina.net/question/*")
15 @ExtractBy(value = "//ul[@class='list']/li[@class='Answer']", multi = true)
16 public class OschinaAnswer implements AfterExtractor{
17
18 @ExtractBy("//img/@title")
19 private String user;
20
21 @ExtractBy("//div[@class='detail']")
22 private String content;
23
24 public static void main(String[] args) {
25 OOSpider.create(Site.me(), OschinaAnswer.class).addUrl("http://www.oschina.net/question/567527_120597").run();
26 }
27
28 @Override
29 public void afterProcess(Page page) {
30
31 }
32 }