From 2109f34b4f3615004de1f2b2e635cfd61dae3cb7 Mon Sep 17 00:00:00 2001
From: Chad Phillips <chad@apartmentlines.com>
Date: Wed, 15 May 2024 10:22:33 -0400
Subject: [PATCH] support python3.12 from
 https://github.com/deanmalmgren/textract/pull/502

---
 textract/parsers/pdf_parser.py | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/textract/parsers/pdf_parser.py b/textract/parsers/pdf_parser.py
index 9fe74e13..10d488af 100644
--- a/textract/parsers/pdf_parser.py
+++ b/textract/parsers/pdf_parser.py
@@ -8,7 +8,10 @@
 from .utils import ShellParser
 from .image import Parser as TesseractParser
 
-from distutils.spawn import find_executable
+try:
+    from shutil import which
+except ImportError:
+    from distutils.spawn import find_executable as which
 
 class Parser(ShellParser):
     """Extract text from pdf files using either the ``pdftotext`` method
@@ -49,7 +52,7 @@ def extract_pdfminer(self, filename, **kwargs):
         #Nested try/except loops? Not great
         #Try the normal pdf2txt, if that fails try the python3
         # pdf2txt, if that fails try the python2 pdf2txt
-        pdf2txt_path = find_executable('pdf2txt.py')
+        pdf2txt_path = which("pdf2txt.py")
         try:
             stdout, _ = self.run(['pdf2txt.py', filename])
         except OSError: