Update app.py

app.py

@@ -158,18 +158,18 @@ def identify_headers_with_openrouter(pdf_path, model, LLM_prompt, pages_to_check
         
                 # Use first span to check vertical position
                 y0 = spans[0]["bbox"][1]
-                y1 = spans[0]["bbox"][3]
-        
+                y1 = spans[0]['bbox'][3]
                 # if y0 < top_margin or y1 > (page_height - bottom_margin):
                 #     continue
-        
-                for span in spans:
-                    text = span.get("text", "").strip()
-                    if not text:
-                        continue
-        
-                    lines_for_prompt.append(f"PAGE {pno + 1}: {text}")
+                text = " ".join(s.get('text','') for s in spans).strip()
+                if text:
+
+
+                    # prefix with page for easier mapping back
+                    lines_for_prompt.append(f"PAGE {pno+1}: {text}")
                     lines_on_page += 1
+        
+        # if lines_on_page > 0:
 
         # page = doc.load_page(pno)
         # page_height = page.rect.height