瀏覽代碼

排除爬虫

huangzhiguo 2 年之前
父節點
當前提交
4ebfe70fee

+ 1 - 1
src/main/java/com/caimei365/tools/service/impl/CmBehaviorRecordServiceImpl.java

@@ -505,7 +505,7 @@ public class CmBehaviorRecordServiceImpl implements CmBehaviorRecordService {
     private boolean boolReptiles(String userAgent) {
         if (userAgent.contains("serpstatbot") || userAgent.contains("spider") || userAgent.contains("Googlebot") || userAgent.contains("bingbot")
                 || userAgent.contains("SeznamBot") || userAgent.contains("YisouSpider") || userAgent.contains("petalbot") || userAgent.contains("YandexBot")
-                || userAgent.contains("AhrefsBot")) {
+                || userAgent.contains("AhrefsBot") || userAgent.contains("BingPreview/1.0b")) {
             return true;
         }
         return false;

+ 3 - 1
src/main/resources/mapper/CmBehaviorRecordMapper.xml

@@ -236,7 +236,8 @@
                  LEFT JOIN club c ON b.userID = c.userID
                  LEFT JOIN shop s ON b.userID = s.userID
         WHERE  b.IP != '106.55.202.118' AND b.delFlag = 0  AND b.accessDate = #{accessDate}
-        GROUP BY b.IP, b.accessDate,b.userID, b.behaviorType ORDER BY b.accessTime DESC
+          AND b.region NOT LIKE '%美国Microsoft公司%' AND b.region NOT LIKE '%亚马逊(Amazon)公司%'
+        GROUP BY b.IP, b.accessDate,b.userID ORDER BY b.accessTime DESC
     </select>
     <select id="insertYesterdayList">
         INSERT INTO cm_behavior_record_index (
@@ -333,6 +334,7 @@
                  LEFT JOIN club c ON b.userID = c.userID
                  LEFT JOIN shop s ON b.userID = s.userID
         WHERE  b.IP != '106.55.202.118' AND b.delFlag = 0  AND b.accessDate = #{accessDate}
+          AND b.region NOT LIKE '%美国Microsoft公司%' AND b.region NOT LIKE '%亚马逊(Amazon)公司%'
         GROUP BY b.IP, b.accessDate,b.userID ORDER BY b.accessTime DESC
     </select>
     <select id="selDataList" resultType="com.caimei365.tools.model.po.CmBehaviorRecordPo">