1 package us.codecraft.webmagic.model.annotation;
2
3 import java.lang.annotation.ElementType;
4 import java.lang.annotation.Retention;
5 import java.lang.annotation.Target;
6
7 /**
8 * Define the extractor for field or class.<br>
9 *
10 * @author code4crafter@gmail.com <br>
11 * @since 0.2.0
12 */
13 @Retention(java.lang.annotation.RetentionPolicy.RUNTIME)
14 @Target({ElementType.FIELD, ElementType.TYPE})
15 public @interface ExtractBy {
16
17 /**
18 * Extractor expression, support XPath, CSS Selector and regex.
19 *
20 * @return extractor expression
21 */
22 String value();
23
24 /**
25 * types of extractor expressions
26 */
27 public static enum Type {XPath, Regex, Css, JsonPath}
28
29 /**
30 * Extractor type, support XPath, CSS Selector and regex.
31 *
32 * @return extractor type
33 */
34 Type type() default Type.XPath;
35
36 /**
37 * Define whether the field can be null.<br>
38 * If set to 'true' and the extractor get no result, the entire class will be discarded. <br>
39 *
40 * @return whether the field can be null
41 */
42 boolean notNull() default false;
43
44 /**
45 * types of source for extracting.
46 */
47 public static enum Source {
48 /**
49 * extract from the content extracted by class extractor
50 */
51 SelectedHtml,
52 /**
53 * extract from the raw html
54 */
55 RawHtml,
56 RawText
57 }
58
59 /**
60 * The source for extracting. <br>
61 * It works only if you already added 'ExtractBy' to Class. <br>
62 *
63 * @return the source for extracting
64 */
65 Source source() default Source.SelectedHtml;
66
67 /**
68 * Define whether the extractor return more than one result.
69 * When set to 'true', the extractor return a list of string (so you should define the field as List). <br>
70 *
71 * Deprecated since 0.4.2. This option is determined automatically by the class of field.
72 * @deprecated since 0.4.2
73 * @return whether the extractor return more than one result
74 */
75 boolean multi() default false;
76
77 }