From a4de486bdd28b71562ae65d7ce6c8c741e5056b3 Mon Sep 17 00:00:00 2001
From: Bryan Newbold <bnewbold@archive.org>
Date: Thu, 25 Jun 2020 23:05:06 -0700
Subject: catch UnicodeDecodeError in pdfextract

---
 python/sandcrawler/pdfextract.py | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

(limited to 'python/sandcrawler/pdfextract.py')

diff --git a/python/sandcrawler/pdfextract.py b/python/sandcrawler/pdfextract.py
index d1b060e..98d6861 100644
--- a/python/sandcrawler/pdfextract.py
+++ b/python/sandcrawler/pdfextract.py
@@ -215,7 +215,16 @@ def process_pdf(blob: bytes, thumb_size=(180,300), thumb_type="JPEG") -> PdfExtr
             file_meta=file_meta,
         )
 
-    pdf_info = pdf.infos()
+    try:
+        pdf_info = pdf.infos()
+    except UnicodeDecodeError:
+        return PdfExtractResult(
+            sha1hex=sha1hex,
+            status='bad-unicode',
+            error_msg="in infos()",
+            file_meta=file_meta,
+        )
+
     # TODO: is this actually needed? or does json marshalling work automatically?
     for k in pdf_info.keys():
         if isinstance(pdf_info[k], datetime.datetime):
-- 
cgit v1.2.3