update

output/output_article_distribution_0917.py

@@ -130,6 +130,9 @@ tags_v3_count_dict = {'颧骨修复': 38, '焕肤美白': 2, '玻尿酸垫下巴
 print(second_demands_count_dict,tags_v3_count_dict)
 time.sleep(10)
 
+
+second_demands_tag_count = {}
+projects_demands_tag_count = {}
 for redis_count,spark_res in enumerate(sql_res):
     # if redis_count >= 50:break
     second_demands = []
@@ -146,12 +149,21 @@ for redis_count,spark_res in enumerate(sql_res):
         second_demands = res.get("second_demands")
         # print(count_res)
         for tag in second_demands:
+            if tag in second_demands_tag_count:
+                second_demands_tag_count[tag] += 1
+            else:
+                second_demands_tag_count[tag] = 1
             if tag in second_demands_count_dict:
                 total_tractate_content_num += second_demands_count_dict[tag]
     if res.get("projects"):
         projects = res.get("projects")
         # print(count_res)
         for tag in projects:
+            if tag in projects_demands_tag_count:
+                projects_demands_tag_count[tag] += 1
+            else:
+                projects_demands_tag_count[tag] = 1
+
             if tag in tags_v3_count_dict:
                 total_tractate_content_num += tags_v3_count_dict[tag]
     # print(total_answer_content_num, total_tractate_content_num, total_diary_content_num)
@@ -174,10 +186,13 @@ for redis_count,spark_res in enumerate(sql_res):
         bulk_dict[1000][1] += 1
 
     if redis_count % 5000 == 0:
-        print(bulk_dict)
+        print(redis_count,bulk_dict)
 
 
 print(bulk_dict)
 
+print("second_demands_tag_count",second_demands_tag_count)
+print("projects_demands_tag_count",projects_demands_tag_count)
+