mirror of
https://github.com/danswer-ai/danswer.git
synced 2025-07-28 13:53:28 +02:00
Thanks for your contribution!
This commit is contained in:
@@ -308,7 +308,10 @@ def extract_text(file: dict[str, str], service: discovery.Resource) -> str:
|
||||
response = service.files().get_media(fileId=file["id"]).execute()
|
||||
pdf_stream = io.BytesIO(response)
|
||||
pdf_reader = PdfReader(pdf_stream)
|
||||
return "\n".join(page.extract_text() for page in pdf_reader.pages)
|
||||
if pdf_reader.is_encrypted:
|
||||
logger.warning(f"Google drive file: {file['name']} is encrypted danswer will ignore it's content")
|
||||
else:
|
||||
return "\n".join(page.extract_text() for page in pdf_reader.pages)
|
||||
|
||||
|
||||
class GoogleDriveConnector(LoadConnector, PollConnector):
|
||||
|
Reference in New Issue
Block a user