From 5cc23dbf2413ec2a296d3af58f70a8ed85e7d410 Mon Sep 17 00:00:00 2001 From: "James R. Barlow" Date: Wed, 4 Jul 2018 17:12:30 -0700 Subject: [PATCH] pdfinfo: more robustness --- src/ocrmypdf/pdfinfo.py | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/src/ocrmypdf/pdfinfo.py b/src/ocrmypdf/pdfinfo.py index 4e36207c..5a025557 100644 --- a/src/ocrmypdf/pdfinfo.py +++ b/src/ocrmypdf/pdfinfo.py @@ -521,7 +521,13 @@ def _page_get_textblocks(infile, pageno): # are only generated as innermost self-closing tags. gstext = regex_remove_char_tags.sub(b' ', gstext) - root = ET.fromstring(gstext) + if gstext.strip() == '': + return [] + + try: + root = ET.fromstring(gstext) + except ET.ParseError as e: + return [] # If we can't parse, assume none... def blocks(): for span in root.findall('.//span'):