def download_url()

in url_utils.py [0:0]

• 27 lines of code
• 8 McCabe index (conditional complexity)

def download_url(url, destination_filename=None, progress_updater=None, 
                 force_download=False):
    """
    Download a URL to a file.  If no file is specified, creates a temporary file, 
    with a semi-best-effort to avoid filename collisions.
    
    Prints some diagnostic information and makes sure to omit SAS tokens from printouts.
    
    progress_updater can be "None", "True", or a specific callback.
    """
    
    if progress_updater is not None and isinstance(progress_updater,bool):
        if not progress_updater:
            progress_updater = None
        else:
            progress_updater = DownloadProgressBar()
            
    url_no_sas = url.split('?')[0]
        
    if destination_filename is None:
        target_folder = get_temp_folder()
        url_without_sas = url.split('?', 1)[0]
        
        # This does not guarantee uniqueness, hence "semi-best-effort"
        url_as_filename = re.sub(r'\W+', '', url_without_sas)
        n_folder_chars = len(ai4e_utils_temp_dir)
        if len(url_as_filename) + n_folder_chars > max_path_len:
            print('Warning: truncating filename target to {} characters'.format(max_path_len))
            url_as_filename = url_as_filename[-1*(max_path_len-n_folder_chars):]
        destination_filename = \
            os.path.join(target_folder,url_as_filename)
        
    if (not force_download) and (os.path.isfile(destination_filename)):
        print('Bypassing download of already-downloaded file {}'.format(os.path.basename(url_no_sas)))
    else:
        print('Downloading file {} to {}'.format(os.path.basename(url_no_sas),destination_filename),end='')
        urllib.request.urlretrieve(url, destination_filename, progress_updater)  
        assert(os.path.isfile(destination_filename))
        nBytes = os.path.getsize(destination_filename)
        print('...done, {} bytes.'.format(nBytes))
        
    return destination_filename