Update app.py

app.py

@@ -92,7 +92,7 @@ def extract_text_from_pptx(pptx_data, clean=True):
         text = clean_text(text)
     return text, len(text)
 
-def read_document(file_path, clean=True):
+def read_document(file_path, clean=True, url=""):
     with open(file_path, "rb") as f:
         file_content = f.read()
 
@@ -159,8 +159,8 @@ def read_document(file_path, clean=True):
             soup = BeautifulSoup(file_content, 'html.parser')
             structured_data = {
                 "Texts": extract_texts(soup),
-                "Links": extract_links(soup, ""), 
-                "Images": extract_images(soup, "")
+                "Links": extract_links(soup, url), 
+                "Images": extract_images(soup, url)
             }
             return format_detailed_output(structured_data), 0
         except Exception as e:
@@ -204,7 +204,7 @@ def download_and_process_file(url, clean=True):
         if kind and kind.mime.startswith('image/'):
             return f"![]({url})", 0  # Return markdown image syntax if it's an image
         else:
-            return read_document(temp_filename, clean)  # Otherwise, process as a document
+            return read_document(temp_filename, clean, url)  # Otherwise, process as a document
 
     except requests.exceptions.MissingSchema:
         return "Error: Invalid URL format. Even after adding 'http://', the URL is still invalid.", 0