From 6b46b5e9ce6aa1bdc61a76e7778ec79afeb5691e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E9=B9=BF=E9=B9=BF=E9=B9=BF=E9=B2=A8?= <1243101939@qq.com>
Date: Wed, 19 Jun 2024 11:02:46 +0800
Subject: [PATCH] community: add **request_kwargs and expect TimeError
 AsyncHtmlLoader (#23068)

- **Description:** add `**request_kwargs` and expect `TimeError` in
`_fetch` function for AsyncHtmlLoader. This allows you to fill in the
kwargs parameter when using the `load()` method of the `AsyncHtmlLoader`
class.

Co-authored-by: Yucolu <yucolu@tencent.com>
---
 .../langchain_community/document_loaders/async_html.py         | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/libs/community/langchain_community/document_loaders/async_html.py b/libs/community/langchain_community/document_loaders/async_html.py
index 1bd40aff5e5..97039cffd72 100644
--- a/libs/community/langchain_community/document_loaders/async_html.py
+++ b/libs/community/langchain_community/document_loaders/async_html.py
@@ -137,6 +137,7 @@ class AsyncHtmlLoader(BaseLoader):
                         url,
                         headers=self.session.headers,
                         ssl=None if self.session.verify else False,
+                        **self.requests_kwargs,
                     ) as response:
                         try:
                             text = await response.text()
@@ -144,7 +145,7 @@ class AsyncHtmlLoader(BaseLoader):
                             logger.error(f"Failed to decode content from {url}")
                             text = ""
                         return text
-                except aiohttp.ClientConnectionError as e:
+                except (aiohttp.ClientConnectionError, TimeoutError) as e:
                     if i == retries - 1 and self.ignore_load_errors:
                         logger.warning(f"Error fetching {url} after {retries} retries.")
                         return ""