Update ocr.py

ocr.py

@@ -10,6 +10,15 @@ Date: 2024-11-23
 import os
 os.system("bash setup.sh")  # Ensure setup script runs before importing pytesseract
 
+# Check Ghostscript installation
+gs_path = "/usr/bin/gs"  # Default Ghostscript location on Ubuntu
+
+if not os.path.exists(gs_path):
+    raise FileNotFoundError(f"Ghostscript not found at {gs_path}")
+
+# Set Ghostscript path explicitly
+os.environ["OCRMYPDF_GS"] = gs_path
+
 import pytesseract
 from pdf2image import convert_from_path
 from pdf2image.exceptions import PDFPageCountError, PDFSyntaxError