فهرست منبع

提取标题品类信息

luojunhui 3 ماه پیش
والد
کامیت
2b228ff4a0
2فایلهای تغییر یافته به همراه6 افزوده شده و 2 حذف شده
  1. 1 1
      applications/tasks/data_recycle_tasks/recycle_daily_publish_articles.py
  2. 5 1
      dev/crontab_back.txt

+ 1 - 1
applications/tasks/data_recycle_tasks/recycle_daily_publish_articles.py

@@ -307,7 +307,7 @@ class UpdateRootSourceIdAndUpdateTimeTask(Const):
     async def get_article_list(self) -> list[dict]:
         query = """select ContentUrl, wx_sn from official_articles_v2 where publish_timestamp in %s;"""
         article_list = await self.pool.async_fetch(
-            query=query, db_name="piaoquan_crawler", params=(tuple([0, -1]),)
+            query=query, db_name="piaoquan_crawler", params=(tuple([0, -1, -3]),)
         )
         return article_list
 

+ 5 - 1
dev/crontab_back.txt

@@ -118,7 +118,11 @@
 13 3,4,5 * * * curl -X POST http://192.168.142.66:6060/api/run_task -H "Content-Type: application/json" -d '{"task_name": "mini_program_detail_process"}'
 
 
-# */8 * * * * curl -X POST http://192.168.142.66:6060/api/run_task -H "Content-Type: application/json" -d '{"task_name": "extract_title_features", "batch_size": 10}'
+*/8 * * * * curl -X POST http://192.168.142.66:6060/api/run_task -H "Content-Type: application/json" -d '{"task_name": "extract_title_features", "batch_size": 10, "version": 2}'
+
+0 9,16 * * * curl -X POST http://192.168.142.66:6060/api/run_task -H "Content-Type: application/json" -d '{"task_name": "recycle_outside_account_articles"}'
+
+# 35 16 * * * curl -X POST http://192.168.142.66:6060/api/run_task -H "Content-Type: application/json" -d '{"task_name": "update_outside_account_article_root_source_id"}'
 
 # 候选账号质量分析
 0 5,10,15,20 * * * curl -X POST http://192.168.142.66:6060/api/run_task -H "Content-Type: application/json" -d '{"task_name": "candidate_account_quality_analysis"}'