update

tasks/crawler_week_report.py

@@ -317,8 +317,8 @@ def get_count_hot_crawler_data_from_mysql(start_ts: int) -> Dict:
         data = cur_mimas.fetchall()
         match_all_num = data[0][0]
         # print(match_all_num)
-        oneline_sql = """select count(id) as nums from api_tractate where create_time >= '{time}' and is_online = 1 and platform = {platfrom}""".format(
-            time=str(start_date), platfrom=platform_id)
+        oneline_sql = """select count(id) as nums from api_tractate where create_time >= '{time}' and is_online = 1 and pgc_type = 1""".format(
+            time=str(start_date))
         cur_mimas.execute(oneline_sql)
         data = cur_mimas.fetchall()
         match_oneline_num = data[0][0]

tasks/from_sparksql_to_mysql.py

@@ -95,7 +95,7 @@ for res in sql_res:
     self_wel_click_pv = res.self_wel_click_pv
     partition_day = res.PARTITION_DAY
     pid = hashlib.md5((day_id + device_os_type + active_type + grey_type + page_name).encode("utf8")).hexdigest()
-    sql = """INSERT INTO conent_detail_page_grayscale_ctr(
+    instert_sql = """INSERT INTO conent_detail_page_grayscale_ctr(
     day_id,device_os_type,active_type,grey_type,page_name,content_pv,content_uv,wel_exp_pv,
     content_exp_pv,wel_click_pv,content_click_pv,slide_wel_click_pv,self_wel_click_pv,partition_day,pid
     ) VALUES('{day_id}','{device_os_type}','{active_type}','{grey_type}','{page_name}',{content_pv},{content_uv},
@@ -105,8 +105,10 @@ for res in sql_res:
         content_click_pv=content_click_pv,slide_wel_click_pv=slide_wel_click_pv,self_wel_click_pv=self_wel_click_pv,
         partition_day=partition_day, pid=pid
     )
-    print(sql)
-    res = cursor.execute(sql)
+    print(instert_sql)
+    cursor.execute("set names 'UTF8'")
+    res = cursor.execute(instert_sql)
+
     print(res)
 # cursor.executemany()
 db.close()
\ No newline at end of file