From 4cb49d000d7f6c880995ddd5fc2d4b142e7c4f7e Mon Sep 17 00:00:00 2001 From: Bryan Newbold Date: Wed, 20 May 2020 21:10:22 -0700 Subject: skip pdftotext loading on unicode error --- fatcat_scholar/work_pipeline.py | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fatcat_scholar/work_pipeline.py b/fatcat_scholar/work_pipeline.py index 5bfc1b6..7100b32 100644 --- a/fatcat_scholar/work_pipeline.py +++ b/fatcat_scholar/work_pipeline.py @@ -125,6 +125,8 @@ class WorkPipeline(): ) except FileNotFoundError: pass + except except UnicodeDecodeError: + pass return None def lookup_sim(self, release: ReleaseEntity) -> Optional[SimIssueRow]: -- cgit v1.2.3