java爬虫Gecco工具抓取新闻实例

   com.geccocrawler
   gecco
   1.0.8

@Gecco(matchUrl = "http://zj.zjol.com.cn/home.html?pageIndex={pageIndex}&pageSize={pageSize}",pipelines = "zJNewsListPipelines")
public class ZJNewsGeccoList implements HtmlBean {
  @Request
  private HttpRequest request;
  @RequestParameter
  private int pageIndex;
  @RequestParameter
  private int pageSize;
  @HtmlField(cssPath = "#content > div > div > div.con_index > div.r.main_mod > div > ul > li > dl > dt > a")
  private List newList;
}

@PipelineName("zJNewsListPipelines")
public class ZJNewsListPipelines implements Pipeline {
  public void process(ZJNewsGeccoList zjNewsGeccoList) {
    HttpRequest request=zjNewsGeccoList.getRequest();
    for (HrefBean bean:zjNewsGeccoList.getNewList()){
      //进入祥情页面抓取
    SchedulerContext.into(request.subRequest("http://zj.zjol.com.cn"+bean.getUrl()));
    }
    int page=zjNewsGeccoList.getPageIndex()+1;
    String nextUrl = "http://zj.zjol.com.cn/home.html?pageIndex="+page+"&pageSize=100";
    //抓取下一页
    SchedulerContext.into(request.subRequest(nextUrl));
  }
}

@Gecco(matchUrl = "http://zj.zjol.com.cn/news/[code].html" ,pipelines = "zjNewsDetailPipeline")
public class ZJNewsDetail implements HtmlBean {

  @Text
  @HtmlField(cssPath = "#headline")
  private String title ;

  @Text
  @HtmlField(cssPath = "#content > div > div.news_con > div.news-content > div:nth-child(1) > div > p.go-left.post-time.c-gray")
  private String createTime;
}

@PipelineName("zjNewsDetailPipeline")
public class ZJNewsDetailPipeline implements Pipeline {
  public void process(ZJNewsDetail zjNewsDetail) {
    System.out.println(zjNewsDetail.getTitle()+" "+zjNewsDetail.getCreateTime());
  }
}

public class Main {
  public static void main(String [] rags){
    GeccoEngine.create()
        //工程的包路径
        .classpath("com.zhaochao.gecco.zj")
        //开始抓取的页面地址
        .start("http://zj.zjol.com.cn/home.html?pageIndex=1&pageSize=100")
        //开启几个爬虫线程
        .thread(10)
        //单个爬虫每次抓取完一个请求后的间隔时间
        .interval(10)
        //使用pc端userAgent
        .mobile(false)
        //开始运行
        .run();
  }
}