Преглед изворни кода

Merge branch '2025-03-11-bugfix' of luojunhui/LongArticlesJob into master

luojunhui пре 4 месеци
родитељ
комит
2791ffe3d7
1 измењених фајлова са 3 додато и 1 уклоњено
  1. 3 1
      coldStartTasks/crawler/weixin_video_crawler.py

+ 3 - 1
coldStartTasks/crawler/weixin_video_crawler.py

@@ -87,7 +87,8 @@ class WeixinVideoCrawler(object):
         select_sql = f"""
             SELECT gh_id, account_name, latest_crawler_timestamp
             FROM weixin_account_for_videos
-            WHERE status = {const.ACCOUNT_CRAWL_STATUS};
+            WHERE status = {const.ACCOUNT_CRAWL_STATUS}
+            ORDER BY latest_crawler_timestamp;
         """
         response = self.db_client.select(select_sql, DictCursor)
         return response
@@ -158,6 +159,7 @@ class WeixinVideoCrawler(object):
                     url_unique = functions.generateGzhId(article_url)
                     # 判断该视频链接是否下载,若已经下载则直接跳过
                     if self.is_downloaded(url_unique):
+                        print("url exists")
                         continue
 
                     title = article.get("Title", None)