Function download_url

monai/apps/utils.py:191–274

Download file from specified URL link, support process bar and hash check. Args: url: source URL link to download file. filepath: target filepath to save the downloaded file (including the filename). If undefined, `os.path.basename(url)` will be used. ha

(
    url: str,
    filepath: PathLike = "",
    hash_val: str | None = None,
    hash_type: str = "md5",
    progress: bool = True,
    **gdown_kwargs: Any,
)

def download_url(
    url: str,
    filepath: PathLike = "",
    hash_val: str | None = None,
    hash_type: str = "md5",
    progress: bool = True,
    **gdown_kwargs: Any,
) -> None:
    """
    Download file from specified URL link, support process bar and hash check.

    Args:
        url: source URL link to download file.
        filepath: target filepath to save the downloaded file (including the filename).
            If undefined, `os.path.basename(url)` will be used.
        hash_val: expected hash value to validate the downloaded file.
            if None, skip hash validation.
        hash_type: 'md5' or 'sha1', defaults to 'md5'.
        progress: whether to display a progress bar.
        gdown_kwargs: other args for `gdown` except for the `url`, `output` and `quiet`.
            these args will only be used if download from google drive.
            details of the args of it:
            https://github.com/wkentaro/gdown/blob/main/gdown/download.py

    Raises:
        RuntimeError: When the hash validation of the ``filepath`` existing file fails.
        RuntimeError: When a network issue or denied permission prevents the
            file download from ``url`` to ``filepath``.
        URLError: See urllib.request.urlretrieve.
        HTTPError: See urllib.request.urlretrieve.
        ContentTooShortError: See urllib.request.urlretrieve.
        IOError: See urllib.request.urlretrieve.
        RuntimeError: When the hash validation of the ``url`` downloaded file fails.

    """
    if not filepath:
        filepath = Path(".", _basename(url)).resolve()
        logger.info(f"Default downloading to '{filepath}'")
    filepath = Path(filepath)
    if filepath.exists():
        if not check_hash(filepath, hash_val, hash_type):
            raise RuntimeError(
                f"{hash_type} check of existing file failed: filepath={filepath}, expected {hash_type}={hash_val}."
            )
        logger.info(f"File exists: {filepath}, skipped downloading.")
        return
    try:
        with tempfile.TemporaryDirectory() as tmp_dir:
            tmp_name = Path(tmp_dir, _basename(filepath))
            if urlparse(url).netloc == "drive.google.com":
                if not has_gdown:
                    raise RuntimeError("To download files from Google Drive, please install the gdown dependency.")
                if "fuzzy" not in gdown_kwargs:
                    gdown_kwargs["fuzzy"] = True  # default to true for flexible url
                gdown.download(url, f"{tmp_name}", quiet=not progress, **gdown_kwargs)
            elif urlparse(url).netloc == "cloud-api.yandex.net":
                with urlopen(url) as response:
                    code = response.getcode()