From fa25698620f54207423c3da40ae1bca567b598fa Mon Sep 17 00:00:00 2001
From: Bryan Newbold <bnewbold@archive.org>
Date: Thu, 25 Jun 2020 23:06:36 -0700
Subject: pdfextract: attributerror with text extraction
---
python/sandcrawler/pdfextract.py | 16 ++++++++++++----
1 file changed, 12 insertions(+), 4 deletions(-)
(limited to 'python')
diff --git a/python/sandcrawler/pdfextract.py b/python/sandcrawler/pdfextract.py
index 98d6861..921c883 100644
--- a/python/sandcrawler/pdfextract.py
+++ b/python/sandcrawler/pdfextract.py
@@ -194,10 +194,18 @@ def process_pdf(blob: bytes, thumb_size=(180,300), thumb_type="JPEG") -> PdfExtr
print(str(e), file=sys.stderr)
page0_thumbnail = None
- full_text = page0.text()
- for n in range(1, pdf.pages):
- pageN = pdf.create_page(n)
- full_text += pageN.text()
+ try:
+ full_text = page0.text()
+ for n in range(1, pdf.pages):
+ pageN = pdf.create_page(n)
+ full_text += pageN.text()
+ except AttributeError as e:
+ return PdfExtractResult(
+ sha1hex=sha1hex,
+ status='parse-error',
+ error_msg=str(e),
+ file_meta=file_meta,
+ )
# Kafka message size limit; cap at about 1 MByte
if len(full_text)> 1000000:
--
cgit v1.2.3