1 package us.codecraft.webmagic;
2
3 import us.codecraft.webmagic.utils.Experimental;
4
5 import java.util.Collection;
6
7 /**
8 * Extract an object of more than one pages, such as news and articles.<br>
9 *
10 * @author code4crafter@gmail.com <br>
11 * @since 0.2.0
12 */
13 @Experimental
14 public interface MultiPageModel {
15
16 /**
17 * Page key is the identifier for the object.
18 *
19 * @return page key
20 */
21 public String getPageKey();
22
23 /**
24 * page is the identifier of a page in pages for one object.
25 *
26 * @return page
27 */
28 public String getPage();
29
30 /**
31 * other pages to be extracted.<br>
32 * It is used to judge whether an object contains more than one page, and whether the pages of the object are all extracted.
33 *
34 * @return other pages
35 */
36 public Collection<String> getOtherPages();
37
38 /**
39 * Combine multiPageModels to a whole object.
40 *
41 * @param multiPageModel multiPageModel
42 * @return multiPageModel combined
43 */
44 public MultiPageModel combine(MultiPageModel multiPageModel);
45
46 }