m

databaseConn/__init__.py

@@ -38,13 +38,13 @@ mysql_info={
     "8066_27":{
         "name":"real_data_test",
         "pwd":"qpRBSarm$Tv*YO!n",
-        "host":"172.30.5.27",
+        "host":"off-line-db.quantgroups.com",
         "port":"8066"
     },
     "7438_27":{
         "name":"xyqb_recommender_system_w",
         "pwd":"Qa6pxybKE8KgsUGV",
-        "host":"172.30.5.27",
+        "host":"off-line-db.quantgroups.com",
         "port":"7438"
     },
     "nearly":{
@@ -53,6 +53,13 @@ mysql_info={
         "host":"recommend-nearline-prod-5-7.cr22rydq7l0o.rds.cn-north-1.amazonaws.com.cn",
         "port":"3306"
     },
+    "89":{
+        "name":"root",
+        "pwd":"123456",
+        "host":"172.16.9.89",
+        "port":"3306"
+    }
+    ,
     "usergroup":{
         "name":"tjzimuali_test",
         "pwd":"bYut032QgkJ7ElMXwW",

databaseConn/mysqlOperation.py

@@ -42,6 +42,7 @@ def execmysl(namespace,sql):
     if 'select' not in sql or 'from' not in sql:
         raise Exception('在mysql看来不是有效的sql',sql)
     try:
+        print(sql)
         df=pd.read_sql(sql,con=mysql_universal(namespace))
         return df
     except Exception as e:
@@ -72,5 +73,5 @@ def concatSql(sql,**kwargs):
     return sql+' where '+temp[:-4]
 
 if __name__ == '__main__':
-    #print(mysqlInfo('test1'))
-    print(execmysl('qa',"select * from kdsp.t_brands limit 1"))
+    print(mysqlInfo('test1'))
+    #print(execmysl('test1',"select key_word as word,key_word_url as jumpUrl,icon_url as iconUrl from t_app_config_search_keyword where status=1 and DATE_FORMAT(end_time,'%Y-%m-%d') >= DATE_FORMAT('2022-06-14 15:38:50','%Y-%m-%d') and DATE_FORMAT('2022-06-14 15:38:50','%Y-%m-%d') >= DATE_FORMAT(start_time,'%Y-%m-%d') order by sort"))
\ No newline at end of file

recommend/__init__.py

@@ -9,3 +9,5 @@ from recommend.publicSql import *
 
 cur_dir=os.path.dirname(os.path.abspath(__file__))
 file_path=os.path.join(cur_dir,'tempFile')
+nearline_url_aws="http://aws-online-recommend-parent.ec-test.qg-rc.net"
+nearline_url_aliyun="http://172.16.9.90:19999"
\ No newline at end of file

recommend/product_result_page_less.py

+import requests
+
+from recommend import *
+
+def preconditions(content,uuid,gid):
+    from search.abSearch import requestsend
+    try:
+        _, spu_nos,*_=requestsend(uuid,gid,content,selectedActivitie=1,page=1,searchtype='txt',env='test')
+        temp_spu_nos=spu_nos.split(',')
+        if len(temp_spu_nos)>5:
+            return 0
+        return temp_spu_nos
+    except:
+        return 0
+
+def diwenci(uuid=None,gid=None):
+    url=nearline_url_aliyun+"/recommend/searchShadingWords"
+    body={
+        "position":1,
+        "userUuid":uuid or "",
+        "deviceId":gid or ""
+    }
+    temp=requests.get(url,params=body)
+    word=jsonpath.jsonpath(temp.json(),'$..word')
+    return word
+
+def searchTopic(content):
+    #uuid,gid=genUuidDeviceid()
+    uuid=""
+    gid="4205df9318c69521"
+    print("uuid:",uuid,"====>","gid",gid)
+    #diwenci_result=diwenci(uuid,gid)
+    result_skus=preconditions(content,uuid,gid)
+    diwenci_result=diwenci(uuid,gid)
+    print("搜索结果的skus,",result_skus)
+    #query+similar_query
+    similar_temp=[]
+    similar_change_sql=recommend_hot_query_similar_info_sql+" where hot_query="+"'"+str(content)+"'" +" order by rank asc"
+    similar_df=execmysl('89',similar_change_sql)
+    similar_query_word=similar_df['hot_query_similar'].to_list() if   not similar_df.empty else []
+    similar_temp+=similar_query_word
+    print("相似热词结果:",similar_temp)
+    ##sku+query
+    if not result_skus:
+        print("底纹词,",diwenci_result)
+        ##如果搜索没有商品数，则结果=相似搜索词+底纹词,并去重
+        return removeRepeat(similar_temp+diwenci_result[:3])
+
+
+    sku_match_change_sql=concatSql(recommend_sku_query_match_info_sql,**{"sku_no":result_skus}) +'order by rank asc'
+    sku_match_df=execmysl('89',sku_match_change_sql)
+    sku_match_change_df=sku_match_df.astype(str)[['sku_no','query']]. \
+            groupby(by='query')['sku_no'].count().reset_index(name='count') \
+        if not  sku_match_df.empty else []
+    ##通过query分组拿到skuno，如果3个元素的值都小于1，则空列表
+    try:
+        sku_match_temp=sku_match_change_df[sku_match_change_df['count']>1].sort_values(by='count',ascending=False)['query'].to_list()
+    except:
+        sku_match_temp=[]
+
+    finally:
+        if not (similar_temp and sku_match_temp):
+            return removeRepeat(diwenci_result)
+        print("商品相关词:",sku_match_temp)
+        ##从sku的query结果中，去掉相似query，然后2边交叉排序
+        sku_match_temp_remove_from_similar=bingji(sku_match_temp,similar_temp)
+        ##因为随机取不好弄，所以拿到所有数据交叉的
+        return listCross(similar_temp,sku_match_temp_remove_from_similar)
+
+
+
+
+
+
+
+if __name__ == '__main__':
+    print(searchTopic('苹果耳机'))
+

recommend/publicSql.py

@@ -110,3 +110,14 @@ cate_brand_intention_score_sql="""
 select * from 
 offline_recommend.cate_brand_intention_score 
 """
+
+
+###query热词的相似表
+recommend_hot_query_similar_info_sql="""
+select * from online_recommend.recommend_hot_query_similar_info
+"""
+
+###商品和关键词的匹配度
+recommend_sku_query_match_info_sql="""
+select * from online_recommend.recommend_sku_query_match_info
+"""

search/abSearch.py

@@ -254,7 +254,7 @@ if __name__ == '__main__':
     isexec=0
     ishotwordrand=0
     if isexec:
-        allRun(1000,isFirstPage=1,sheetname=3,ishotwordrand=ishotwordrand)
+        allRun(1,isFirstPage=1,sheetname=3,ishotwordrand=ishotwordrand)
     else:
         print(analysis())
     # a=[['236473224274432', '7188063'],['236473224274432', '7188063']]

search/abSearch_script.py

@@ -129,7 +129,7 @@ def requestsend(uuid,deviceid,searchContent,selectedActivitie,page=1,searchtype=
         total_skus=jsonpath.jsonpath(t.json(), '$..totalCount')[0]
         request_time = t.elapsed.total_seconds()
         #tttt=','.join(spu_nos)
-        print(sku_nos)
+        #print(sku_nos)
         # with open('sku_result_3.txt', 'a+') as file:
         #     file.write('搜索词:' + searchContent + ";result:" + ','.join(sku_names) + "\n")
         return page_size,sku_nos , str(request_time), search_id,','.join(sku_names),searchContent,total_skus
@@ -225,7 +225,7 @@ def totalrun(selectedActivitie=1, type='txt', num=0,isFirstPage=False,sheetname=
             temp.append(result_temp)
             flag+=1
     #filename=genReportName('searchResult')
-        print(temp)
+        print('搜索接口响应处理后的结果：',temp)
         return temp
     except:
         traceback.print_exc(limit=2)

tools/changeLXQpassword.py

@@ -28,4 +28,4 @@ def modifyPasseord(name,namespace):
         print("this is update")
 
 if __name__ == '__main__':
-    modifyPasseord('dong.chao','qa')
+    modifyPasseord('haiyuan.wen','test1')
\ No newline at end of file

tools/listOperation.py

@@ -66,11 +66,35 @@ def listSubgroup(tt,size=6):
     return temp
 
 
+def countlist(a,num=0):
+    from collections import Counter
+    '''
+    :param a:
+    :param num:如果num不为空，则按num取前num个
+    :return: 重复元素计数
+    '''
+    temp=Counter(a)
+    if num:
+        return dict(temp.most_common(num))
+    return dict(temp.most_common(len(a)))
+
+def bingji(a,b):
+    """
+    :param a:
+    :param b:
+    :return: 并集
+    """
+    temp=list(set(a).difference(set(b)))
+    temp.sort(key=a.index)
+    return temp
+
+
 if __name__ == '__main__':
-    a=[1,2,4,3,5,6,7,8]
-    #print(listGroup(a))
+    a=[2,2,4,3,5,6,7,8]
+    b=[10,2,4,3,9]
+    print(bingji(b,a))
 
     #a=[[1,2],[2,3]]
     #print(mergelist(a))
 
-    print(listSubgroup(a,6))
+    #print(listSubgroup(a,6))

tools/publicFun.py

@@ -5,7 +5,7 @@ def genUuidDeviceid():
     :return:
     """
     uuid,deviced=codeuuid.uuid4().urn.split(':')[-1],codeuuid.uuid4().urn.split(':')[-1]
-    uuid='87f491d2-527f-4386-9bb1-3d67017cb6d8'
+    #uuid='87f491d2-527f-4386-9bb1-3d67017cb6d8'
     deviced='guiqiuyue_'+str(deviced)
     return uuid,deviced