Update app.py

app.py

@@ -52,14 +52,14 @@ def get_subdirectory_pages(url, base_url, visited=set(), max_pages=100):
                 parsed_full_url = urlparse(full_url)
                 parsed_base_url = urlparse(base_url)
                 
-                # Check if the URL is one level deeper
+                # Check if the URL is in the same directory or a direct subdirectory
                 if (parsed_full_url.scheme == parsed_base_url.scheme and
                     parsed_full_url.netloc == parsed_base_url.netloc and
                     parsed_full_url.path.startswith(parsed_base_url.path) and
-                    parsed_full_url.path.count('/') == parsed_base_url.path.count('/') + 1):
+                    parsed_full_url.path.count('/') <= parsed_base_url.path.count('/') + 1):
                     
                     if full_url not in visited:
-                        pages.extend(get_subdirectory_pages(full_url, full_url, visited, max_pages))
+                        pages.extend(get_subdirectory_pages(full_url, base_url, visited, max_pages))
                         if len(visited) >= max_pages:
                             break
     except Exception as e:
@@ -101,7 +101,7 @@ def process_url(url):
 
 iface = gr.Interface(
     fn=process_url,
-    inputs=gr.Textbox(label="Enter website URL (e.g., https://www.gradio.app/docs)"),
+    inputs=gr.Textbox(label="Enter website URL (e.g., https://www.gradio.app/docs/gradio)"),
     outputs=gr.File(label="Download PDF"),
     title="Website Subdirectory to PDF Converter",
     description="Enter a website URL to convert its subdirectories into a PDF."