How to use gdown - 10 common examples

To help you get started, we’ve selected a few gdown examples, based on popular ways it is used in public projects.

Secure your code as it's written. Use Snyk Code to scan source code in minutes - no build needed - and fix issues immediately.

github wkentaro / gdown / tests / test_download.py View on Github external
def test_download():
    url = "https://raw.githubusercontent.com/wkentaro/gdown/3.1.0/gdown/__init__.py"  # NOQA
    output = "/tmp/gdown_r"

    # Usage before https://github.com/wkentaro/gdown/pull/32
    assert download(url, output, quiet=False) == output
    os.remove(output)
github wkentaro / gdown / tests / test_parse_url.py View on Github external
(file_id, False),
            True,
        ),
        (
            "https://drive.google.com/a/jsk.imi.i.u-tokyo.ac.jp/uc?id={}&export=download".format(  # NOQA
                file_id
            ),
            (file_id, True),
            False,
        ),
    ]

    for url, expected, check_warn in urls:
        if check_warn:
            with pytest.warns(UserWarning):
                assert parse_url(url) == expected
        else:
            assert parse_url(url) == expected
github tofunlp / lineflow / lineflow / datasets / text_classification.py View on Github external
def list_creator(path):
        dataset = {}
        archive_path = gdown.cached_download(url)

        maxsize = sys.maxsize
        while True:
            try:
                csv.field_size_limit(maxsize)
                break
            except OverflowError:
                maxsize = int(maxsize / 10)
        csv.field_size_limit(maxsize)

        with tarfile.open(archive_path, 'r') as archive:
            for split in ('train', 'test'):
                filename = f'{key}_csv/{split}.csv'
                print(f'Processing {filename}...')
                reader = csv.reader(
                    io.TextIOWrapper(archive.extractfile(filename), encoding='utf-8'))
github snorkel-team / snorkel-tutorials / recsys / utils.py View on Github external
def maybe_download_files(data_dir: str = "data") -> None:
    if not os.path.exists(data_dir):
        os.makedirs(data_dir, exist_ok=True)
        if IS_TEST:
            # Sample data pickle
            gdown.download(SMALL_DATA_URL, output=SAMPLE_DATA, quiet=None)
        else:
            # Books
            gdown.download(YA_BOOKS_URL, output=BOOK_DATA, quiet=None)
            # Interactions
            gdown.download(YA_INTERACTIONS_URL, output=INTERACTIONS_DATA, quiet=None)
            # Reviews
            gdown.download(YA_REVIEWS_URL, output=REVIEWS_DATA, quiet=None)
github monologg / hashtag-prediction-pytorch / server / app.py View on Github external
def download(url, filename, cachedir='~/hashtag/'):
    f_cachedir = os.path.expanduser(cachedir)
    os.makedirs(f_cachedir, exist_ok=True)
    file_path = os.path.join(f_cachedir, filename)
    if os.path.isfile(file_path):
        print('Using cached model')
        return file_path
    gdown.download(url, file_path, quiet=False)
    return file_path
github huangzhii / FCN-3D-pytorch / main3d.py View on Github external
def cached_download(url, path, md5=None, quiet=False):

    def check_md5(path, md5):
        print('[{:s}] Checking md5 ({:s})'.format(path, md5))
        return md5sum(path) == md5

    if osp.exists(path) and not md5:
        print('[{:s}] File exists ({:s})'.format(path, md5sum(path)))
        return path
    elif osp.exists(path) and md5 and check_md5(path, md5):
        return path
    else:
        dirpath = osp.dirname(path)
        if not osp.exists(dirpath):
            os.makedirs(dirpath)
        return gdown.download(url, path, quiet=quiet)
def md5sum(filename, blocksize=65536):
github snorkel-team / snorkel-tutorials / recsys / utils.py View on Github external
def maybe_download_files(data_dir: str = "data") -> None:
    if not os.path.exists(data_dir):
        os.makedirs(data_dir, exist_ok=True)
        if IS_TEST:
            # Sample data pickle
            gdown.download(SMALL_DATA_URL, output=SAMPLE_DATA, quiet=None)
        else:
            # Books
            gdown.download(YA_BOOKS_URL, output=BOOK_DATA, quiet=None)
            # Interactions
            gdown.download(YA_INTERACTIONS_URL, output=INTERACTIONS_DATA, quiet=None)
            # Reviews
            gdown.download(YA_REVIEWS_URL, output=REVIEWS_DATA, quiet=None)
github wkentaro / fcn / fcn / data.py View on Github external
def cached_download(url, path, md5=None, quiet=False, postprocess=None):

    def check_md5(path, md5):
        print('[{:s}] Checking md5 ({:s})'.format(path, md5))
        return md5sum(path) == md5

    if osp.exists(path) and not md5:
        print('[{:s}] File exists ({:s})'.format(path, md5sum(path)))
    elif osp.exists(path) and md5 and check_md5(path, md5):
        pass
    else:
        dirpath = osp.dirname(path)
        if not osp.exists(dirpath):
            os.makedirs(dirpath)
        gdown.download(url, path, quiet=quiet)

    if postprocess is not None:
        postprocess(path)

    return path
github KaiyangZhou / deep-person-reid / torchreid / models / osnet.py View on Github external
torch_home = _get_torch_home()
    model_dir = os.path.join(torch_home, 'checkpoints')
    try:
        os.makedirs(model_dir)
    except OSError as e:
        if e.errno == errno.EEXIST:
            # Directory already exists, ignore.
            pass
        else:
            # Unexpected OSError, re-raise.
            raise
    filename = key + '_imagenet.pth'
    cached_file = os.path.join(model_dir, filename)

    if not os.path.exists(cached_file):
        gdown.download(pretrained_urls[key], cached_file, quiet=False)

    state_dict = torch.load(cached_file)
    model_dict = model.state_dict()
    new_state_dict = OrderedDict()
    matched_layers, discarded_layers = [], []

    for k, v in state_dict.items():
        if k.startswith('module.'):
            k = k[7:] # discard module.

        if k in model_dict and model_dict[k].size() == v.size():
            new_state_dict[k] = v
            matched_layers.append(k)
        else:
            discarded_layers.append(k)
github ckiplab / ckiptagger / src / data_utils.py View on Github external
def download_data_gdown(path):
    import gdown
    
    file_id = "1efHsY16pxK0lBD2gYCgCTnv1Swstq771"
    url = f"https://drive.google.com/uc?id={file_id}"
    data_zip = os.path.join(path, "data.zip")
    gdown.download(url, data_zip, quiet=False)
    
    with zipfile.ZipFile(data_zip, "r") as zip_ref:
        zip_ref.extractall(path)
    return

gdown

Google Drive direct download of big files.

MIT
Latest version published 2 days ago

Package Health Score

85 / 100
Full package analysis