## 'raise_for_status' parameter of WebBaseLoader works in sync load but
not in async load.
In webBaseLoader:
Sync load is calling `_scrape` and has `raise_for_status` properly
handled.
```
def _scrape(
self,
url: str,
parser: Union[str, None] = None,
bs_kwargs: Optional[dict] = None,
) -> Any:
from bs4 import BeautifulSoup
if parser is None:
if url.endswith(".xml"):
parser = "xml"
else:
parser = self.default_parser
self._check_parser(parser)
html_doc = self.session.get(url, **self.requests_kwargs)
if self.raise_for_status:
html_doc.raise_for_status()
if self.encoding is not None:
html_doc.encoding = self.encoding
elif self.autoset_encoding:
html_doc.encoding = html_doc.apparent_encoding
return BeautifulSoup(html_doc.text, parser, **(bs_kwargs or {}))
```
Async load is calling `_fetch` but missing `raise_for_status` logic.
```
async def _fetch(
self, url: str, retries: int = 3, cooldown: int = 2, backoff: float = 1.5
) -> str:
async with aiohttp.ClientSession() as session:
for i in range(retries):
try:
async with session.get(
url,
headers=self.session.headers,
ssl=None if self.session.verify else False,
cookies=self.session.cookies.get_dict(),
) as response:
return await response.text()
```
Co-authored-by: kefan.you <darkfss@sina.com>
24b5c27bb1