webMagic静态页面的爬取

 

一：java maven依赖：

<dependency>
    <groupId>us.codecraft</groupId>
    <artifactId>webmagic-core</artifactId>
    <version>0.7.4</version>
</dependency>
<dependency>
    <groupId>us.codecraft</groupId>
    <artifactId>webmagic-extension</artifactId>
    <version>0.7.4</version>
</dependency>

二：示例代码：

import us.codecraft.webmagic.Page;
import us.codecraft.webmagic.Site;
import us.codecraft.webmagic.Spider;
import us.codecraft.webmagic.pipeline.JsonFilePipeline;
import us.codecraft.webmagic.processor.PageProcessor;
import us.codecraft.webmagic.selector.Selectable;

public class GithubRepoPageProcessor implements PageProcessor {

    // 部分一：抓取网站的相关配置，包括编码、抓取间隔、重试次数等
    private Site site = Site.me().setRetryTimes(3).setSleepTime(1000);

    @Override
    // process是定制爬虫逻辑的核心接口，在这里编写抽取逻辑
    public void process(Page page) {
        // 部分二：定义如何抽取页面信息，并保存下来
        String titleXpath = "//div[@class='postTitle']/a/span/text()";
        String date_xpath = "//div[@class='dayTitle']/a/text()";
        String detailUrlsXpath="//div[@class='postTitle']/a[@class='postTitle2 vertical-middle']/@href";
        String nextPageXpath="//div[@class='pager']/a/@href";
        String nextPageCss = "#homepage_top_pager > div:nth-child(1) > a:nth-child(8)";
        page.putField("title", page.getHtml().xpath(titleXpath).toString());
        if (page.getResultItems().get("title") == null) {
            //skip this page
            page.setSkip(true);
        }
        page.putField("date",page.getHtml().xpath(date_xpath).toString());

         // 部分三：从页面发现后续的url地址来抓取
        if(page.getHtml().xpath(detailUrlsXpath).match()){
            Selectable detailUrls = page.getHtml().xpath(detailUrlsXpath);
            page.addTargetRequests(detailUrls.all());
        }
        if(page.getHtml().xpath(nextPageXpath).match()){
            Selectable nextPageUrl = page.getHtml().xpath(nextPageXpath);
            page.addTargetRequests(nextPageUrl.all());
        }
        if(page.getHtml().css(nextPageCss).match()){
            Selectable nextPageUrl = page.getHtml().xpath(nextPageXpath);
            page.addTargetRequests(nextPageUrl.all());
        }

        //page.addTargetRequests(page.getHtml().links().regex("http://www.cnblogs.com/dick159/default.html?page=1").all());
    }

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

    public static void main(String[] args) {

        Spider.create(new GithubRepoPageProcessor())
                //从"http://www.cnblogs.com/dick159/default.html?page=1"开始抓
                .addUrl("http://www.cnblogs.com/dick159/default.html?page=1")
                // 输出到D盘webmagic文件夹
                .addPipeline(new JsonFilePipeline("D:\\webmagic\\"))
                //开启1个线程抓取
                .thread(1)
                //启动爬虫
                .run();
    }
}