瀏覽代碼

update jhs task modify 9.25.1

lei.chen 2 月之前
父節點
當前提交
70d782aa5d
共有 1 個文件被更改,包括 7 次插入7 次删除
  1. 7 7
      jihuanshe_spider/jhs_new_daily_spider.py

+ 7 - 7
jihuanshe_spider/jhs_new_daily_spider.py

@@ -278,16 +278,16 @@ def jhs_main(log):
         raise Exception("MySQL数据库连接失败")
 
     try:
-        # max_sql_id = sql_pool.select_one("select max(product_id) from jhs_product_record")
-        # if max_sql_id:
-        #     max_sql_id = max_sql_id[0]
-        # else:
-        #     max_sql_id = 422342
-        # log.debug(f"当前数据库中最大的 product_id max_sql_id:{max_sql_id}")
+        max_sql_pid = sql_pool.select_one("select max(product_id) from jhs_product_record")
+        if max_sql_pid:
+            max_sql_pid = max_sql_pid[0]
+        else:
+            max_sql_pid = 568835
+        log.debug(f"当前数据库中最大的 product_id max_sql_id:{max_sql_pid}")
 
         # 从数据库获取需要爬取的 product_id  从最大的id max_sql_id 开始
         product_id_list = sql_pool.select_all(
-            "SELECT id, product_id FROM jhs_task WHERE task_state != 1 AND id > 522769 LIMIT 10000")
+            f"SELECT id, product_id FROM jhs_task WHERE task_state != 1 AND id > '{max_sql_pid}' LIMIT 5000")
             # "SELECT id, product_id FROM jhs_task WHERE task_state IN (0, 2) AND id > 420107 LIMIT 10000")
         # "SELECT id, product_id FROM jhs_task WHERE task_state IN (0, 2) AND id > %s LIMIT 6000", (max_sql_id,))
         # "SELECT id, product_id FROM jhs_task WHERE task_state IN (0, 2) AND id < 376575 ORDER BY id DESC")