今天第一次做Springboot項目整合webMagic項目時。剛剛創建的一個新的項目啟動時突然發現報錯了!!!
報錯如下:
java.lang.IncompatibleClassChangeError: null at us.codecraft.webmagic.scheduler.DuplicateRemovedScheduler.push(DuplicateRemovedScheduler.java:35) ~[classes/:na] at us.codecraft.webmagic.Spider.setScheduler(Spider.java:197) ~[classes/:na] at com.itheima.utils.JobProcessor.startSpider(JobProcessor.java:106) ~[classes/:na] at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) ~[na:1.8.0_131] at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62) ~[na:1.8.0_131] at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) ~[na:1.8.0_131] at java.lang.reflect.Method.invoke(Method.java:498) ~[na:1.8.0_131] at org.springframework.scheduling.support.ScheduledMethodRunnable.run(ScheduledMethodRunnable.java:84) ~[spring-context-5.1.4.RELEASE.jar:5.1.4.RELEASE] at org.springframework.scheduling.support.DelegatingErrorHandlingRunnable.run(DelegatingErrorHandlingRunnable.java:54) ~[spring-context-5.1.4.RELEASE.jar:5.1.4.RELEASE] at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:511) [na:1.8.0_131] at java.util.concurrent.FutureTask.runAndReset(FutureTask.java:308) [na:1.8.0_131] at java.util.concurrent.ScheduledThreadPoolExecutor$ScheduledFutureTask.access$301(ScheduledThreadPoolExecutor.java:180) [na:1.8.0_131] at java.util.concurrent.ScheduledThreadPoolExecutor$ScheduledFutureTask.run(ScheduledThreadPoolExecutor.java:294) [na:1.8.0_131] at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142) [na:1.8.0_131] at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617) [na:1.8.0_131] at java.lang.Thread.run(Thread.java:748) [na:1.8.0_131]
我瘋狂百度呀,找資料呀也找不出個所以然來。
異步任務的代碼:
package com.wangjie.crawlerjob.task; import org.springframework.scheduling.annotation.Scheduled; import org.springframework.stereotype.Component; import us.codecraft.webmagic.Page; import us.codecraft.webmagic.Site; import us.codecraft.webmagic.Spider; import us.codecraft.webmagic.processor.PageProcessor; import us.codecraft.webmagic.scheduler.BloomFilterDuplicateRemover; import us.codecraft.webmagic.scheduler.QueueScheduler; import us.codecraft.webmagic.selector.Html; /** * @author 落魄書生 * @data 2020/9/23 - 10:50 */ @Component public class JobProcessor implements PageProcessor { private String url = "https://search.51job.com/list/000000,000000,0000,01%252c32,9,99,java,2,1.html?lang=c&postchannel=0000&workyear=99&cotype=99°reefrom=99&jobterm=99&companysize=99&ord_field=0&dibiaoid=0&line=&welfare="; @Override public void process(Page page) { Html html = page.getHtml(); System.out.println(html.toString()); } private Site site = Site.me() .setCharset("gbk") // 設置編碼 .setTimeOut(10000) // 設置超時時間 .setRetrySleepTime(3000) // 設置 重試的間隔時間 .setRetryTimes(3); // 設置重試的次數 @Override public Site getSite() { return site; } /** * initialDelay: 當項目啟動之后 隔多久運行這個定時任務 * fixedDelay: 每隔多久執行這個方法 */ @Scheduled(initialDelay = 1000, fixedDelay = 100 * 1000) public void process() { Spider.create(new JobProcessor()) .addUrl(url) .setScheduler(new QueueScheduler().setDuplicateRemover(new BloomFilterDuplicateRemover(100000))) .thread(10) .run(); } }
后來我就試試換了一個SpringBoot的版本。和把一些亂七八糟的依賴刪掉。把版本降低到2.0.2版本。然后抱着試試的心態竟然成功了!神奇
我又嘗試把版本換回2.3.4版本。發現它又行了。然后就解決。問題是啥我一臉懵逼,解決后我還是一臉懵。自己技術還是太菜了,努力學習吧,騷年~