From 254f24ad6566c9d4b5814868911b604802847b58 Mon Sep 17 00:00:00 2001
From: Bryan Newbold <bnewbold@archive.org>
Date: Thu, 25 Jun 2020 23:08:47 -0700
Subject: simpler handling of null PDF text pages

---
 python/sandcrawler/pdfextract.py | 15 ++++-----------
 1 file changed, 4 insertions(+), 11 deletions(-)

diff --git a/python/sandcrawler/pdfextract.py b/python/sandcrawler/pdfextract.py
index 921c883..ed323b9 100644
--- a/python/sandcrawler/pdfextract.py
+++ b/python/sandcrawler/pdfextract.py
@@ -194,18 +194,11 @@ def process_pdf(blob: bytes, thumb_size=(180,300), thumb_type="JPEG") -> PdfExtr
         print(str(e), file=sys.stderr)
         page0_thumbnail = None
 
-    try:
-        full_text = page0.text()
-        for n in range(1, pdf.pages):
-            pageN = pdf.create_page(n)
+    full_text = page0.text()
+    for n in range(1, pdf.pages):
+        pageN = pdf.create_page(n)
+        if pageN:
             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