监测被删文章，加上root_source_id_list

published_articles_monitor.py

@@ -22,7 +22,7 @@ def monitor_article(article):
     """
     校验单篇文章是否
     """
-    gh_id, account_name, title, url, wx_sn, publish_date = article
+    gh_id, account_name, title, url, wx_sn, publish_date, root_source_id_list = article
     try:
         response = spider.get_article_text(url, is_cache=False)
         response_code = response["code"]
@@ -30,13 +30,13 @@ def monitor_article(article):
             error_detail = response.get("msg")
             insert_sql = f"""
                 INSERT IGNORE INTO illegal_articles 
-                (gh_id, account_name, title, wx_sn, publish_date, illegal_reason)
+                (gh_id, account_name, title, wx_sn, publish_date, illegal_reason, root_source_id_list) 
                 VALUES 
-                (%s, %s, %s, %s, %s, %s);
+                (%s, %s, %s, %s, %s, %s, %s);
                 """
             affected_rows = long_articles_db_client.save(
                 query=insert_sql,
-                params=(gh_id, account_name, title, wx_sn, publish_date, error_detail),
+                params=(gh_id, account_name, title, wx_sn, publish_date, error_detail, root_source_id_list),
             )
             if affected_rows:
                 bot(
@@ -71,7 +71,7 @@ def get_article_list(run_date):
             int(datetime.strptime(run_date, "%Y-%m-%d").timestamp()) - const.MONITOR_PERIOD
     )
     select_sql = f"""
-        SELECT ghId, accountName, title, ContentUrl, wx_sn, from_unixtime(publish_timestamp) AS publish_timestamp
+        SELECT ghId, accountName, title, ContentUrl, wx_sn, from_unixtime(publish_timestamp) AS publish_timestamp, root_source_id_list
         FROM official_articles_v2
         WHERE publish_timestamp >= {monitor_start_timestamp}
         ORDER BY publish_timestamp DESC;