官方文档地址：

http://webmagic.io/docs/zh/posts/ch1-overview/

代码github地址：

https://github.com/code4craft/webmagic

使用案例

1、加载maven依赖

<dependency>
    <groupId>us.codecraft</groupId>
    <artifactId>webmagic-core</artifactId>
    <version>0.7.3</version>
</dependency>
<dependency>
    <groupId>us.codecraft</groupId>
    <artifactId>webmagic-extension</artifactId>
    <version>0.7.3</version>
</dependency>

2、抓取案例

package com.qingfeng.test.WebMagic;

import us.codecraft.webmagic.Page;
import us.codecraft.webmagic.Site;
import us.codecraft.webmagic.Spider;
import us.codecraft.webmagic.processor.PageProcessor;

/**
 * @author code4crafter@gmail.com <br>
 */
public class SinaBlogProcessor implements PageProcessor {

    public static final String URL_LIST = "http://blog\\.sina\\.com\\.cn/s/articlelist_1586578693_0_\\d+\\.html";

    public static final String URL_POST = "http://blog\\.sina\\.com\\.cn/s/blog_\\w+\\.html";

    private Site site = Site
            .me()
            .setDomain("blog.sina.com.cn")
            .setSleepTime(3000)
            .setUserAgent(
                    "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_2) AppleWebKit/537.31 (KHTML, like Gecko) Chrome/26.0.1410.65 Safari/537.31");

    @Override
    public void process(Page page) {
        //列表页
        if (page.getUrl().regex(URL_LIST).match()) {
            page.addTargetRequests(page.getHtml().xpath("//div[@class=\"articleList\"]").links().regex(URL_POST).all());
            page.addTargetRequests(page.getHtml().links().regex(URL_LIST).all());
            //文章页
        } else {
            page.putField("title", page.getHtml().xpath("//div[@class='articalTitle']/h2"));
            page.putField("content", page.getHtml().xpath("//div[@id='articlebody']//div[@class='articalContent']"));
            page.putField("date",
                    page.getHtml().xpath("//div[@id='articlebody']//span[@class='time SG_txtc']").regex("\\((.*)\\)"));
        }
    }

    @Override
    public Site getSite() {
        return site;
    }

    public static void main(String[] args) {
        Spider.create(new SinaBlogProcessor()).addUrl("http://blog.sina.com.cn/s/articlelist_1586578693_0_1.html").addPipeline(new ConsolePipeline())
                .run();
    }
}