update

utils/portary_div_exposure.py

@@ -3,6 +3,7 @@
 # @File  : portary_div_exposure.py
 # @email : litao@igengmei.com
 # @author : litao
+import datetime
 import json
 import traceback
 
@@ -10,6 +11,7 @@ import redis
 import pymysql
 from elasticsearch import Elasticsearch
 from meta_base_code.utils.func_get_pv_card_id import get_card_id
+import pandas as pd
 
 redis_client = redis.StrictRedis.from_url("redis://:ReDis!GmTx*0aN6@172.16.40.133:6379")
 redis_client2 = redis.StrictRedis.from_url("redis://:ReDis!GmTx*0aN9@172.16.40.173:6379")
@@ -27,6 +29,7 @@ es = Elasticsearch([
 
 
 def user_portrait_scan_info():
+    res_dict = {}
     try:
         round = 0
         all_count = 0
@@ -52,7 +55,11 @@ def user_portrait_scan_info():
                 # just_projects_count += 1
 
                 # user_portrait_get_empty_candidates(device_id)
-                yield get_user_portrait_tag3_from_redis(device_id)
+                res_dic = get_user_portrait_tag3_from_redis(device_id)
+                print(res_dic)
+                # for data_list in res_dic:
+                #     for data in data_list:
+
 
         print("all count: " + str(all_count))
         print("empty portrait: " + str(empty_count))
@@ -447,7 +454,7 @@ def from_id_get_tag(card_id_dict):
             doc_type = 'tractate'
         for card_id in card_id_dict[card_type]:
             res = es.get_source(index,doc_type,card_id)
-            print(res)
+            # print(res)
             first_demands = res.get("first_demands") if res.get("first_demands") else []
             second_demands = res.get("second_demands") if res.get("second_demands") else []
             first_solutions = res.get("first_solutions") if res.get("first_solutions") else []
@@ -464,19 +471,32 @@ def from_id_get_tag(card_id_dict):
     return query_count
 
 
+# def save_data_to_csv(all_tags, word_count_exposure):
+#     all_data = []
+#
+#     data = pd.DataFrame(all_dic)
+#     s = datetime.datetime.now()
+#     ss = str(s)[0:19].replace(' ', '-').replace(':', '-')
+#     data.to_csv('%s%sall_s2.csv' % (d, monthly_doc_type_name), encoding='gb18030',
+#                 # columns=columns
+#                 )
 
 def parse_data():
     demands_num = {}
+    # 获取画像数
+    user_portrait_scan_info()
     # 获取全部标签
     all_tags = get_channel_tags_info()
     print(all_tags)
     # 获取标签对应的日记帖子回答数
-    article_num_dict = get_es_article_num(all_tags)
+    # article_num_dict = get_es_article_num(all_tags)
     # 获取曝光的id
     card_id_dict = get_card_id()
     print(card_id_dict)
     # 获取曝光id对应的标签
     word_count_exposure = from_id_get_tag(card_id_dict)
+    print(word_count_exposure)
+    save_data_to_csv(all_tags, word_count_exposure)
 
 if __name__ == "__main__":
     parse_data()