Merge branch 'master' of https://github.com/danielquinn/paperless into feature/heuristically-extract-date-from-document-text

2025-10-30 03:56:23 -05:00 · 2018-02-02 22:44:03 +01:00
parent e9fff764cb 5e40227bc3
commit f39c7654a0
4 changed files with 4 additions and 3 deletions
--- a/src/paperless_tesseract/parsers.py
+++ b/src/paperless_tesseract/parsers.py
@@ -260,6 +260,6 @@ def get_text_from_pdf(pdf_file):
        try:
            pdf = pdftotext.PDF(f)
        except pdftotext.Error:
-            return False
+            return ""

    return "\n".join(pdf)