From fe29f997b43d502fda3353b6c59894e962de48f9 Mon Sep 17 00:00:00 2001
From: Bryan Newbold <bnewbold@archive.org>
Date: Thu, 25 Jun 2020 21:14:25 -0700
Subject: pdfextract: catch poppler.LockedDocumentError
---
python/sandcrawler/pdfextract.py | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
(limited to 'python')
diff --git a/python/sandcrawler/pdfextract.py b/python/sandcrawler/pdfextract.py
index 97c2f3b..e7bfa43 100644
--- a/python/sandcrawler/pdfextract.py
+++ b/python/sandcrawler/pdfextract.py
@@ -167,7 +167,7 @@ def process_pdf(blob: bytes, thumb_size=(180,300), thumb_type="JPEG") -> PdfExtr
)
# this call sometimes fails an returns an AttributeError
page0rect = page0.page_rect()
- except AttributeError as e:
+ except (AttributeError, poppler.LockedDocumentError) as e:
# may need to expand the set of exceptions caught here over time, but
# starting with a narrow set
return PdfExtractResult(
--
cgit v1.2.3