modify some content

main.py

@@ -80,13 +80,13 @@ count = 0
 
 # 如果是采用单线程的模式跑这个脚本，解析完4000多行数据恐怕要1个小时了 所以还是采用多进程的方式吧 用四个脚本同时解析一个文件的不同行
 def main():
-    df = pd.read_excel('table.xlsx')
+    df = pd.read_excel('jd.xlsx')
     data = df.iloc[:, [0]].values
     ans = []
     result = []
+    goods_name_list = []
     for i in range(len(data)):
-        if i > 9:
-           break   # for debug, don't forget to delete this line.
+         # for debug, don't forget to delete this line.
         sku_name_str = data[i][0]
         res_tmp = match_sku(sku_name_str)
         ans.append(res_tmp)
@@ -97,7 +97,7 @@ def main():
             tmp_goods_name = ans[i][j]
             tmp_query = query
             tmp_query["query"]["bool"]["must"][0]["match"]["goods_name"] = tmp_goods_name
-            tmp_map = process(tmp_query)
+            tmp_map = process(tmp_query, tmp_goods_name)
             if len(tmp_map) != 0:
                 score_in_one_row.append(tmp_map)
         if len(score_in_one_row) == 0:
@@ -148,7 +148,7 @@ def post_to_elasticsearch(q: dict):
     ans = response.json()
     return ans
 
-def process(query_str: dict):
+def process(query_str: dict, key_word: str):
     res = post_to_elasticsearch(query_str)
     if  res["hits"]["max_score"] is not None and res["hits"]["max_score"] > 80:
         for i in range(len(res["hits"]["hits"])):
@@ -157,7 +157,7 @@ def process(query_str: dict):
                 _goods_name = res["hits"]["hits"][i]["_source"]["goods_name"]
                 _goods_id =  res["hits"]["hits"][i]["_source"]["goods_id"]
                 _brand_name = res["hits"]["hits"][i]["_source"]["brand_name"]
-                return {"goods_name": _goods_name, "goods_id": _goods_id, "brand_name": _brand_name, "score": _score}
+                return {"goods_name": _goods_name, "goods_id": _goods_id, "brand_name": _brand_name, "score": _score, "key_word": key_word}
     return {}
 
 
@@ -179,26 +179,30 @@ def write_to_xlsx(info_map_list: list):
 
 # 追加写
 def write_to_xlsx_append(info_map_list: list):
-    info_map = {'goods_name': [], 'goods_id': [], 'brand_name': []}
+    info_map = {'goods_name': [], 'goods_id': [], 'brand_name': [], 'key_word': []}
     for i in range(len(info_map_list)):
         if len(info_map_list[i]) != 0:
             info_map["goods_name"].append(info_map_list[i]["goods_name"])
             info_map["goods_id"].append(str(info_map_list[i]["goods_id"]))
             info_map["brand_name"].append(info_map_list[i]["brand_name"])
+            info_map["key_word"].append(info_map_list[i]["key_word"])
         else:
             info_map["goods_name"].append('')
             info_map["goods_id"].append('')
             info_map["brand_name"].append('')
-    data = openpyxl.load_workbook('table.xlsx')
+            info_map["key_word"].append('')
+    data = openpyxl.load_workbook('jd.xlsx')
     table = data[data.sheetnames[0]]
-    table.cell(1, 4).value = 'goods_name'
-    table.cell(1, 5).value = 'goods_id'
-    table.cell(1, 6).value = 'brand_name'
+    table.cell(1, 6).value = 'goods_name'
+    table.cell(1, 7).value = 'goods_id'
+    table.cell(1, 8).value = 'brand_name'
+    table.cell(1, 9).value = 'key_word'
     for i in range(2, len(info_map_list)+2):
-        table.cell(i, 4).value = info_map['goods_name'][i-2]
-        table.cell(i, 5).value = info_map['goods_id'][i-2]
-        table.cell(i, 6).value = info_map['brand_name'][i-2]
-    data.save('table.xlsx')
+        table.cell(i, 6).value = info_map['goods_name'][i-2]
+        table.cell(i, 7).value = info_map['goods_id'][i-2]
+        table.cell(i, 8).value = info_map['brand_name'][i-2]
+        table.cell(i, 9).value = info_map['key_word'][i-2]
+    data.save('jd.xlsx')