wrap confluence attachment processing with a try-except block (#11503)

Prevents document loading from erroring out when an attachment is not
found at the url.

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
pull/11498/head^2
April 11 months ago committed by GitHub
parent 17439daa6a
commit c14a8df2ee
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23

@ -541,6 +541,7 @@ class ConfluenceLoader(BaseLoader):
media_type = attachment["metadata"]["mediaType"]
absolute_url = self.base_url + attachment["_links"]["download"]
title = attachment["title"]
try:
if media_type == "application/pdf":
text = title + self.process_pdf(absolute_url, ocr_languages)
elif (
@ -561,6 +562,12 @@ class ConfluenceLoader(BaseLoader):
else:
continue
texts.append(text)
except requests.HTTPError as e:
if e.response.status_code == 404:
print(f"Attachment not found at {absolute_url}")
continue
else:
raise
return texts

Loading…
Cancel
Save