diff options
| author | Bryan Newbold <bnewbold@archive.org> | 2022-09-14 12:00:59 -0700 |
|---|---|---|
| committer | Bryan Newbold <bnewbold@archive.org> | 2022-09-14 12:01:01 -0700 |
| commit | 2c19b7180e83c70411516c63b8dced5429b450f4 (patch) | |
| tree | 8f7e4c9237f9bd9c84af9d226aa0a48eb49b7c3d /python | |
| parent | a283b054dc98620046dff28cbb16663564b8320b (diff) | |
| download | sandcrawler-2c19b7180e83c70411516c63b8dced5429b450f4.tar.gz sandcrawler-2c19b7180e83c70411516c63b8dced5429b450f4.zip | |
catch poppler 'ValueError' when parsing PDFs
Seeing a spike in bad PDFs in the past week or so, while processing old
failed ingests. Should really switch from poppler to muPDF.
Diffstat (limited to 'python')
| -rw-r--r-- | python/sandcrawler/pdfextract.py | 3 |
1 files changed, 2 insertions, 1 deletions
diff --git a/python/sandcrawler/pdfextract.py b/python/sandcrawler/pdfextract.py index 2441891..5f2dc1a 100644 --- a/python/sandcrawler/pdfextract.py +++ b/python/sandcrawler/pdfextract.py @@ -340,7 +340,8 @@ def process_pdf( ) # this call sometimes fails an returns an AttributeError page0rect = page0.page_rect() - except (AttributeError, poppler.document.LockedDocumentError) as e: + # NOTE: poppler sometimes throws a 'ValueError', but this is pretty broad to catch + except (AttributeError, poppler.document.LockedDocumentError, ValueError) as e: # may need to expand the set of exceptions caught here over time, but # starting with a narrow set return PdfExtractResult( |