luojunhui 3 months ago
parent
commit
57e80ad345
1 changed files with 6 additions and 4 deletions
  1. 6 4
      applications/tasks/crawler_tasks/crawler_account_manager.py

+ 6 - 4
applications/tasks/crawler_tasks/crawler_account_manager.py

@@ -5,6 +5,7 @@ from datetime import datetime
 from typing import Optional, List, Dict
 from typing import Optional, List, Dict
 from pandas import DataFrame
 from pandas import DataFrame
 from scipy import stats
 from scipy import stats
+from tqdm.asyncio import tqdm
 
 
 
 
 class CrawlerAccountManagerConst:
 class CrawlerAccountManagerConst:
@@ -94,8 +95,8 @@ class WeixinAccountManager(CrawlerAccountManager):
                 history_info["ci_lower"],
                 history_info["ci_lower"],
                 recently_info["publish_frequency"],
                 recently_info["publish_frequency"],
                 recently_info["ci_lower"],
                 recently_info["ci_lower"],
-                account_id,
                 datetime.today().strftime("%Y-%m-%d"),
                 datetime.today().strftime("%Y-%m-%d"),
+                account_id,
             ),
             ),
         )
         )
 
 
@@ -128,13 +129,13 @@ class WeixinAccountManager(CrawlerAccountManager):
             "ci_upper": self.safe_float(ci_upper),
             "ci_upper": self.safe_float(ci_upper),
         }
         }
 
 
-    async def analysis_single_account(self, account_id: str) -> None:
+    async def analysis_single_account(self, account_id: str) -> int:
         dataframe = await self.get_account_crawler_articles_info(account_id)
         dataframe = await self.get_account_crawler_articles_info(account_id)
         history_articles_analysis = self.analysis_dataframe(dataframe)
         history_articles_analysis = self.analysis_dataframe(dataframe)
         thirty_days_before = int(time.time()) - self.THIRTY_DAYS_TIMESTAMP
         thirty_days_before = int(time.time()) - self.THIRTY_DAYS_TIMESTAMP
         recent_30_days_df = dataframe[dataframe["publish_time"] >= thirty_days_before]
         recent_30_days_df = dataframe[dataframe["publish_time"] >= thirty_days_before]
         recent_30_days_analysis = self.analysis_dataframe(recent_30_days_df)
         recent_30_days_analysis = self.analysis_dataframe(recent_30_days_df)
-        await self.update_account_stat_detail(
+        return await self.update_account_stat_detail(
             account_id, history_articles_analysis, recent_30_days_analysis
             account_id, history_articles_analysis, recent_30_days_analysis
         )
         )
 
 
@@ -143,5 +144,6 @@ class WeixinAccountManager(CrawlerAccountManager):
         if not account_id_list:
         if not account_id_list:
             account_id_list = await self.get_crawling_accounts(platform=platform)
             account_id_list = await self.get_crawling_accounts(platform=platform)
 
 
-        for account_id in account_id_list:
+        for account_id in tqdm(account_id_list):
             await self.analysis_single_account(account_id)
             await self.analysis_single_account(account_id)
+