Update app.py

app.py

@@ -85,11 +85,17 @@ def get_pdf_links_from_dataset(url):
         response = requests.get(url)
         response.raise_for_status()
         soup = BeautifulSoup(response.text, 'html.parser')
-        pdf_links = [link.get('href') for link in soup.find_all('a') if '.pdf' in link.get('href')]
+        
+        # Define the base URL
+        base_url = "https://huggingface.co"
+        
+        # Extract and construct absolute URLs
+        pdf_links = [base_url + link.get('href') for link in soup.find_all('a') if '.pdf' in link.get('href')]
         return pdf_links
     except requests.HTTPError as e:
         logging.error(f"Failed to get PDF links from dataset. Error: {e}")
         return []
+
         
 #train_directory = r'C:\Users\writa\Downloads\Crypto'
 url = "https://huggingface.co/datasets/Writo/realestate_data/tree/main"