Update app.py

app.py

@@ -768,21 +768,40 @@ def extract_text_from_receipt(file_path):
         return None, []
     
     try:
-        # Set tesseract path for Hugging Face Spaces
-        pytesseract.pytesseract.tesseract_cmd = '/usr/bin/tesseract'
+        # Try to find tesseract automatically
+        import shutil
+        tesseract_path = shutil.which('tesseract')
+        if tesseract_path:
+            pytesseract.pytesseract.tesseract_cmd = tesseract_path
+        else:
+            # Try common paths
+            for path in ['/usr/bin/tesseract', '/usr/local/bin/tesseract', '/bin/tesseract']:
+                if os.path.exists(path):
+                    pytesseract.pytesseract.tesseract_cmd = path
+                    break
         
         text = ""
         
         if file_path.name.lower().endswith('.pdf'):
-            # Set poppler path for Hugging Face Spaces
-            try:
-                images = convert_from_path(file_path.name, poppler_path='/usr/bin')
-            except Exception as e:
-                # If poppler fails, try without path specification
+            # Try multiple possible poppler paths for Hugging Face
+            poppler_paths = [None, '/usr/bin', '/usr/local/bin', '/bin']
+            images = None
+            last_error = None
+            
+            for poppler_path in poppler_paths:
                 try:
-                    images = convert_from_path(file_path.name)
-                except Exception as e2:
-                    return [[True, f"PDF Error: {str(e2)}", "", ""]], []
+                    if poppler_path:
+                        images = convert_from_path(file_path.name, poppler_path=poppler_path)
+                    else:
+                        images = convert_from_path(file_path.name)
+                    break  # Success! Exit loop
+                except Exception as e:
+                    last_error = str(e)
+                    continue
+            
+            if images is None:
+                # If all paths failed, return helpful error
+                return [[True, f"PDF processing unavailable. Please upload images (PNG/JPG) instead. Error: {last_error}", "", ""]], []
             
             for img in images:
                 text += pytesseract.image_to_string(img) + "\n"