diff --git a/dsLightRag/WxGzh/T2_CollectArticle.py b/dsLightRag/WxGzh/T2_CollectArticle.py index 23b89728..8aa7476a 100644 --- a/dsLightRag/WxGzh/T2_CollectArticle.py +++ b/dsLightRag/WxGzh/T2_CollectArticle.py @@ -67,7 +67,7 @@ async def is_article_exist(pool, article_url): return False # 出错时默认返回False,避免影响正常流程 -async def save_article_to_db(pool, article_title, account_name, article_url, publish_time, content, id): +async def save_article_to_db(pool, article_title, account_name, article_url, publish_time, content, source_id): # 先检查文章是否已存在 if await is_article_exist(pool, article_url): logger.info(f"文章已存在,跳过保存: {article_url}") @@ -80,7 +80,7 @@ async def save_article_to_db(pool, article_title, account_name, article_url, pub (title, source, url, publish_time, content, source_id) VALUES ($1, $2, $3, $4, $5, $6) ''', article_title, account_name, article_url, - publish_time, content, id) + publish_time, content, source_id) except Exception as e: logging.error(f"保存文章失败: {e}") @@ -198,7 +198,10 @@ if __name__ == '__main__': continue logger.info(f"正在处理文章: {article_title} ({publish_time})") + + logger.info(f"正在获取文章: {article_title}内容...") content = get_article_content(article_url) + logger.info(f"成功获取文章: {article_title}内容。") loop = asyncio.new_event_loop() asyncio.set_event_loop(loop)