us.codecraft.webmagic.model.ModelPipeline 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;

import us.codecraft.webmagic.ResultItems;
import us.codecraft.webmagic.Task;
import us.codecraft.webmagic.model.annotation.ExtractBy;
import us.codecraft.webmagic.pipeline.PageModelPipeline;
import us.codecraft.webmagic.pipeline.Pipeline;

import java.lang.annotation.Annotation;
import java.util.List;
import java.util.Map;
import java.util.concurrent.ConcurrentHashMap;

/**
 * The extension to Pipeline for page model extractor.
 *
 * @author [email protected] 

 * @since 0.2.0
 */
class ModelPipeline implements Pipeline {

    private Map pageModelPipelines = new ConcurrentHashMap();

    public ModelPipeline() {
    }

    public ModelPipeline put(Class clazz, PageModelPipeline pageModelPipeline) {
        pageModelPipelines.put(clazz, pageModelPipeline);
        return this;
    }

    @Override
    public void process(ResultItems resultItems, Task task) {
        for (Map.Entry classPageModelPipelineEntry : pageModelPipelines.entrySet()) {
            Object o = resultItems.get(classPageModelPipelineEntry.getKey().getCanonicalName());
            if (o != null) {
                Annotation annotation = classPageModelPipelineEntry.getKey().getAnnotation(ExtractBy.class);
                if (annotation == null || !((ExtractBy) annotation).multi()) {
                    classPageModelPipelineEntry.getValue().process(o, task);
                } else {
                    List