utils.py

import os
import os.path
import hashlib
import errno


def check_integrity(fpath, md5):
    if not os.path.isfile(fpath):
        return False
    md5o = hashlib.md5()
    with open(fpath, 'rb') as f:
        # read in 1MB chunks
        for chunk in iter(lambda: f.read(1024 * 1024), b''):
            md5o.update(chunk)
    md5c = md5o.hexdigest()
    if md5c != md5:
        return False
    return True


def download_url(url, root, filename, md5):
    from six.moves import urllib

    root = os.path.expanduser(root)
    fpath = os.path.join(root, filename)

    try:
        os.makedirs(root)
    except OSError as e:
        if e.errno == errno.EEXIST:
            pass
        else:
            raise

    # downloads file
    if os.path.isfile(fpath) and check_integrity(fpath, md5):
        print('Using downloaded and verified file: ' + fpath)
    else:
        try:
            print('Downloading ' + url + ' to ' + fpath)
            urllib.request.urlretrieve(url, fpath)
        except:
            if url[:5] == 'https':
                url = url.replace('https:', 'http:')
                print('Failed download. Trying https -> http instead.'
                      ' Downloading ' + url + ' to ' + fpath)
                urllib.request.urlretrieve(url, fpath)


def list_dir(root, prefix=False):
    """List all directories at a given root

    Args:
        root (str): Path to directory whose folders need to be listed
        prefix (bool, optional): If true, prepends the path to each result, otherwise
            only returns the name of the directories found
    """
    root = os.path.expanduser(root)
    directories = list(
        filter(
            lambda p: os.path.isdir(os.path.join(root, p)),
            os.listdir(root)
        )
    )

    if prefix is True:
        directories = [os.path.join(root, d) for d in directories]

    return directories


def list_files(root, suffix, prefix=False):
    """List all files ending with a suffix at a given root

    Args:
        root (str): Path to directory whose folders need to be listed
        suffix (str or tuple): Suffix of the files to match, e.g. '.png' or ('.jpg', '.png').
            It uses the Python "str.endswith" method and is passed directly
        prefix (bool, optional): If true, prepends the path to each result, otherwise
            only returns the name of the files found
    """
    root = os.path.expanduser(root)
    files = list(
        filter(
            lambda p: os.path.isfile(os.path.join(root, p)) and p.endswith(suffix),
            os.listdir(root)
        )
    )

    if prefix is True:
        files = [os.path.join(root, d) for d in files]

    return files