1、爬虫任务类中url常量抽出一个常量类

2、其他类注解相关修改

xjs-business/xjs-business-common/src/main/java/com/xjs/consts/ApiWarnHandleConst.java

@@ -1,9 +1,9 @@
 package com.xjs.consts;
 
 /**
+ * api预警处理常量
  * @author xiejs
- * @desc api预警处理常量
+ * @since  2022-01-07
- * @create 2022-01-07
  */
 public class ApiWarnHandleConst {
     //已处理

xjs-business/xjs-business-common/src/main/java/com/xjs/consts/CopyWritingConst.java

@@ -1,9 +1,9 @@
 package com.xjs.consts;
 
 /**
+ * 各个数据平台常量类
  * @author xiejs
- * @desc  各个数据平台常量类
+ * @since  2021-12-28
- * @create 2021-12-28
  */
 public class CopyWritingConst {
 

xjs-business/xjs-business-common/src/main/java/com/xjs/consts/EnglishWordConst.java

@@ -1,9 +1,9 @@
 package com.xjs.consts;
 
 /**
+ * 英语单词常量类
  * @author xiejs
- * @desc 英语单词常量类
+ * @since  2021-12-31
- * @create 2021-12-31
  */
 public class EnglishWordConst {
 

xjs-business/xjs-business-common/src/main/java/com/xjs/consts/RegexConst.java

@@ -27,4 +27,9 @@ public class RegexConst {
      * ip地址v4、v6正则
      */
     public static final String IP_REGEX ="^((2[0-4]\\d|25[0-5]|[01]?\\d\\d?)\\.){3}(2[0-4]\\d|25[0-5]|[01]?\\d\\d?)$";
+
+    /**
+     * 数字校验正则
+     */
+    public static final String NUMBER_REGEX= "[0-9]*";
 }

xjs-business/xjs-business-common/src/main/java/com/xjs/consts/ReptileUrlConst.java

@@ -0,0 +1,24 @@
+package com.xjs.consts;
+
+/**
+ * 爬虫网址常量类
+ * @author xiejs
+ * @since 2022-02-16
+ */
+public class ReptileUrlConst {
+
+    /**
+     * 新浪新闻网站
+     */
+    public static final String SINA_NEWS_URL = "https://news.sina.com.cn/";
+
+    /**
+     * 文案网网址
+     */
+    public static final String COPY_WRITING_NETWORK_URL = "https://www.wenanwang.com/";
+
+
+
+
+
+}

xjs-business/xjs-business-common/src/main/java/com/xjs/consts/ReqConst.java

@@ -1,9 +1,9 @@
 package com.xjs.consts;
 
 /**
+ * 请求是否成功常量
  * @author xiejs
- * @desc  请求是否成功常量
+ * @since  2021-12-26
- * @create 2021-12-26
  */
 public class ReqConst {
     public static final Integer SUCCESS = 1;

xjs-business/xjs-business-webmagic/src/main/java/com/xjs/copywritingNetwork/task/CopyWritingNetworkTask.java

@@ -18,6 +18,9 @@ import java.util.HashMap;
 import java.util.Map;
 import java.util.regex.Pattern;
 
+import static com.xjs.consts.RegexConst.NUMBER_REGEX;
+import static com.xjs.consts.ReptileUrlConst.COPY_WRITING_NETWORK_URL;
+
 /**
  * 文案网爬虫任务   url:https://www.wenanwang.com/
  *
@@ -34,23 +37,21 @@ public class CopyWritingNetworkTask {
     private CopyWritingNetworkService copyWritingNetworkService;
 
 
-    public static final String URL = "https://www.wenanwang.com/";
+    private static final Pattern pattern = Pattern.compile(NUMBER_REGEX);
 
-    private static Pattern pattern = Pattern.compile("[0-9]*");
+    @Scheduled(fixedDelay = 1000 * 5 * 60 * 10)
-
-    @Scheduled(fixedDelay = 1000 * 5)
     public void reptileCopyWriting() {
         try {
-            String html = httpUtils.doGetHtml(URL);
+            String html = httpUtils.doGetHtml(COPY_WRITING_NETWORK_URL);
 
             Document document = Jsoup.parse(html);
 
             this.parseHtmlGetUrl(document);
         } catch (Exception e) {
             e.printStackTrace();
-        }finally {
+        } finally {
             int i = copyWritingNetworkService.deleteRepeatData();
-            log.info("删除文案网数据重复数："+i);
+            log.info("删除文案网数据重复数：" + i);
         }
     }
 
@@ -92,7 +93,7 @@ public class CopyWritingNetworkTask {
             for (Element element : a) {
 
                 String href = element.attr("href");
-                String newUrl = URL + href;
+                String newUrl = COPY_WRITING_NETWORK_URL + href;
 
                 String cw = httpUtils.doGetHtml(newUrl);
                 Document cwDocument = Jsoup.parse(cw);

xjs-business/xjs-business-webmagic/src/main/java/com/xjs/sina/task/SinaNewsTask.java

@@ -16,6 +16,8 @@ import org.springframework.stereotype.Component;
 import java.util.*;
 import java.util.stream.Collectors;
 
+import static com.xjs.consts.ReptileUrlConst.SINA_NEWS_URL;
+
 /**
  * 新浪新闻爬虫任务
  * @author xiejs
@@ -30,11 +32,12 @@ public class SinaNewsTask {
     @Autowired
     private SinaNewsService sinaNewsService;
 
+
+
     public void reptileSinaNews() {
         try {
-            String url = "https://news.sina.com.cn/";
 
-            String html = httpUtils.doGetHtml(url);
+            String html = httpUtils.doGetHtml(SINA_NEWS_URL);
 
             Document document = Jsoup.parse(html);