pipeline_functions.py 文件源码

def download_file(my_URL, my_outfile = ''):
    # function to download a file from a URL
    # !! This will overwrite the output file
    # https://gist.github.com/hughdbrown/c145b8385a2afa6570e2

    import urllib2
    import urlparse
    import os

    URL_basename = os.path.basename(urlparse.urlsplit(my_URL).path)

    # if no output file specified, save to URL filename in current dir
    if my_outfile == '':
        my_outfile = URL_basename

    my_URL = urllib2.urlopen(my_URL)
    with open(my_outfile, 'wb') as output:
        while True:
            data = my_URL.read(4096) # download in chunks
            if data:
                output.write(data)
            else:
                break