us.codecraft.webmagic.model.annotation.HelpUrl Maven / Gradle / Ivy

Go to download

Show more of this group Show more artifacts with this name
Show all versions of webmagic-extension Show documentation

The newest version!

package us.codecraft.webmagic.model.annotation;

import java.lang.annotation.ElementType;
import java.lang.annotation.Retention;
import java.lang.annotation.Target;

/**
 * Define the 'help' url patterns for class. 

 * All urls matching the pattern will be crawled and but not extracted for new objects. 

 *
 * @author [email protected] 

 * @since 0.2.0
 */
@Retention(java.lang.annotation.RetentionPolicy.RUNTIME)
@Target({ElementType.TYPE})
public @interface HelpUrl {

    /**
     * The url patterns to crawl. 

     * Use regex expression with some changes: 

     *      "." stand for literal character "." instead of "any character". 

     *      "*" stand for any legal character for url in 0-n length ([^"'#]*) instead of "any length". 

     *
     * @return the url patterns for class
     */
    String[] value();

    /**
     * Define the region for url extracting. 

     * Only support XPath.

     * When sourceRegion is set, the urls will be extracted only from the region instead of entire content. 

     *
     * @return the region for url extracting
     */
    String sourceRegion() default "";
}