Update scrape_3gpp.py

scrape_3gpp.py

@@ -67,7 +67,8 @@ def scrape(url, excel_file, folder_name, status_list, progress=gr.Progress()):
     status_filenames = []
     df = pd.DataFrame()  # Initialize df to ensure it's always defined
 
-    if os.path.exists(excel_file):
+    # Only proceed if excel_file is not None and it exists
+    if excel_file and os.path.exists(excel_file):
         try:
             df = pd.read_excel(excel_file)
             print(f"Initial DataFrame size: {len(df)}")
@@ -76,7 +77,6 @@ def scrape(url, excel_file, folder_name, status_list, progress=gr.Progress()):
                 df = df[df['TDoc Status'].isin(status_list)]
                 print(f"Filtered DataFrame size: {len(df)}")
             else:
-                # If status_list is empty, consider all statuses
                 print("No filtering applied based on TDoc Status")
 
             if not df.empty:
@@ -86,13 +86,15 @@ def scrape(url, excel_file, folder_name, status_list, progress=gr.Progress()):
                     status_filenames = df['URL'].tolist()
                 else:
                     print("No valid 'TDoc' or 'URL' entries found.")
-                
+
                 print(f"Filenames: {status_filenames}")
             else:
                 print("DataFrame is empty after filtering.")
 
         except Exception as e:
             print(f"Error reading Excel file: {e}")
+    else:
+        print("No valid excel_file path provided.")
 
     download_directory = folder_name
     if not os.path.exists(download_directory):
@@ -109,8 +111,7 @@ def scrape(url, excel_file, folder_name, status_list, progress=gr.Progress()):
         filename = os.path.basename(file_url)
         save_path = os.path.join(download_directory, filename)
         progress(pourcentss, desc='Downloading')
-        # Adjust progress calculation based on actual number of files
-        pourcentss += 0.4 / len(status_filenames)
+        pourcentss += 0.4 / len(status_filenames) if status_filenames else 1  # Adjust to prevent division by zero
         try:
             with requests.get(file_url, stream=True) as r:
                 r.raise_for_status()
@@ -119,14 +120,13 @@ def scrape(url, excel_file, folder_name, status_list, progress=gr.Progress()):
                         f.write(chunk)
         except requests.exceptions.HTTPError as e:
             print(f"HTTP error occurred: {file_url}: {e}")
-            # Decide how you want to handle HTTP errors (e.g., skip this file, stop the process, etc.)
 
-    # Ensure correct return value, especially if the function should indicate success/failure and the number of processed files
     return True, len(status_filenames)
 
 
 
 
+
 def extractZip(url):
     # Répertoire où les fichiers zip sont déjà téléchargés
     nom_extract = url.split("/")[-3] + "_extraction"