webmagic爬取分页列表数据

webmagic是java爬虫框架中比较简单易上手的一个。官网链接：http://webmagic.io/

下面的例子是使用这个框架来爬取工商银行的私人理财推荐分页列表数据。页面链接为：https://mybank.icbc.com.cn/se...$17$TJ&Area_code=0200&requestChannel=302

1.引入webmagic：maven配置

us.codecraft
webmagic-core
0.7.3


us.codecraft
webmagic-extension
0.7.3

如果项目已经引入slf4j记录日志，则需要在webmagic-extension中排除slf4j-log4j12。如下：

us.codecraft
webmagic-extension
0.7.3
    
     
         org.slf4j
         slf4j-log4j12
     
     

2.日志文件配置如下：

log4j.rootLogger=info, ServerDailyRollingFile, stdout
log4j.appender.ServerDailyRollingFile=org.apache.log4j.DailyRollingFileAppender
log4j.appender.ServerDailyRollingFile.DatePattern='.'yyyy-MM-dd
log4j.appender.ServerDailyRollingFile.File=/home/myfile/log/mps.log  //日志文件路径配置
log4j.appender.ServerDailyRollingFile.layout=org.apache.log4j.PatternLayout
log4j.appender.ServerDailyRollingFile.layout.ConversionPattern=%d - %m%n
log4j.appender.ServerDailyRollingFile.Append=true
log4j.appender.stdout=org.apache.log4j.ConsoleAppender
log4j.appender.stdout.layout=org.apache.log4j.PatternLayout
log4j.appender.stdout.layout.ConversionPattern=%d{yyyy-MM-dd HH\:mm\:ss} %p [%c] %m%n

3.爬虫代码

import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import us.codecraft.webmagic.Page;
import us.codecraft.webmagic.Site;
import us.codecraft.webmagic.Spider;
import us.codecraft.webmagic.pipeline.ConsolePipeline;
import us.codecraft.webmagic.processor.PageProcessor;
import us.codecraft.webmagic.selector.Selectable;
import java.util.ArrayList;
import java.util.List;
/**
 *私行推荐理财
 */
public class PrivateRecommendFinanceSpider implements PageProcessor {
   private Logger log = LoggerFactory.getLogger(PrivateRecommendFinanceSpider.class);
// 定义连接失败时，重试机制
   private static Site site = Site.me().setRetryTimes(3).setSleepTime(100);
   public Site getSite() {
   return site;
  }
  @Override
  public void process(Page page) {
  log.info("私行推荐理财爬虫开始====");
   String pageNum=page.getHtml().xpath("//*[@id=pageturn]/ul/li[3]/span[2]/b/text()").get();
   int pageNumInt=Integer.parseInt(pageNum);
   for (int i = 1; i < pageNumInt; i++) {
//获取下一页的链接，将当前页数拼接到url上
   String nextUrl="https://mybank.icbc.com.cn/servlet/ICBCBaseReqServletNoSession?dse_operationName=per_FinanceCurProListP3NSOp&p3bank_error_backid=120103&pageFlag=0&menuLabel=10$17$TJ&Area_code=0200&requestChannel=302&nowPageNum_turn="+(i+1);
//将下一页链接添加到爬虫队列中
   page.addTargetRequest(nextUrl);
   }
   List nodes = page.getHtml().xpath("//*[@id=datatableModel]/div").nodes(); //获取列表的条数
int length=nodes.size();
System.out.println(length);
List