write to xlsx

main.py

@@ -74,14 +74,14 @@ black_list = {"eastsheep", "ABB", "BRsanyuan", "JCSTRONG", "TECHNOLOGY",
               }
 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')
     data = df.iloc[:, [0]].values
     ans = []
     result = []
     for i in range(len(data)):
-        if i > 10:
+        if i >= 1000:
            break   # for debug, don't forget to delete this line.
         sku_name_str = data[i][0]
         res_tmp = match_sku(sku_name_str)
@@ -97,6 +97,8 @@ def main():
             if len(tmp_map) != 0:
                 score_in_one_row.append(tmp_map)
         if len(score_in_one_row) == 0:
+            result.append({})
+            print(i, "------", {})
             continue
         else:
             max_score = score_in_one_row[0].get("score")
@@ -106,7 +108,8 @@ def main():
                 max_score = score_in_one_row[k].get("score")
                 index = k
         result.append(score_in_one_row[index])
-    return result
+        print(i, "------", score_in_one_row[index])
+    return result     #返回一个列表，列表中要么为空字典，要么为 {"goods_name": _goods_name, "goods_id": _goods_id, "brand_name": _brand_name, "score": _score} 字典
 
 def match_sku(s: str) -> []:
     # s = "RG58/U射频连接线SMA公头转BNC公头延长线 SMA/BNC-JJ Q9/SMA-JJ RG58/U-SMA/BNC-JJ 2m"
@@ -154,6 +157,25 @@ def process(query_str: dict):
     return {}
 
 
+def write_to_xlsx(info_map_list: list):
+    table = {'goods_name': [], 'goods_id': [], 'brand_name': []}
+    for i in range(len(info_map_list)):
+        if len(info_map_list[i]) != 0:
+            table["goods_name"].append(info_map_list[i]["goods_name"])
+            table["goods_id"].append(str(info_map_list[i]["goods_id"]))
+            table["brand_name"].append(info_map_list[i]["brand_name"])
+        else:
+            table["goods_name"].append('')
+            table["goods_id"].append('')
+            table["brand_name"].append('')
+    df = pd.DataFrame(table)
+    df.to_excel('table.xlsx', sheet_name='Sheet1', index=False, startcol=3)
+
+
+
 if __name__ == '__main__':
     res = main()
-    print(res)
\ No newline at end of file
+    # this is how to write to xlsx file, don't delete it !!
+    # df = pd.DataFrame({'One': ['', 'test123', ''], 'Two': ['qq', 'mr', 'asd']})
+    # df.to_excel('ans.xlsx', sheet_name='Sheet1', index=False, startcol=3)
+    write_to_xlsx(res)
\ No newline at end of file