DownloadData.py

import os
import sys
from six.moves.urllib.request import urlretrieve

# GTZAN genre collection.
url = 'http://opihi.cs.uvic.ca/sound/genres.tar.gz'
last_percent_reported = None
data_root = '.'  # Change me to store data elsewhere


def download_progress_hook(count, blockSize, totalSize):
    """A hook to report the progress of a download. This is mostly intended for users with
    slow internet connections. Reports every 5% change in download progress.
    """
    global last_percent_reported
    percent = int(count * blockSize * 100 / totalSize)

    if last_percent_reported != percent:
        if percent % 5 == 0:
            sys.stdout.write("%s%%" % percent)
            sys.stdout.flush()
        else:
            sys.stdout.write(".")
            sys.stdout.flush()

        last_percent_reported = percent


def maybe_download(filename, expected_bytes, force=False):
    """Download a file if not present, and make sure it's the right size."""
    dest_filename = os.path.join(data_root, filename)
    if force or not os.path.exists(dest_filename):
        print('Attempting to download:', filename)
        filename, _ = urlretrieve(url + filename, dest_filename, reporthook=download_progress_hook)
        print('\nDownload Complete!')
    statinfo = os.stat(dest_filename)
    if statinfo.st_size == expected_bytes:
        print('Found and verified', dest_filename)
    else:
        raise Exception(
            'Failed to verify ' + dest_filename + '. Can you get to it with a browser?')
    return dest_filename


train_filename = maybe_download('genres.tar.gz', 1225573614)