gistfile1.py

import urllib, sys
from BeautifulSoup import BeautifulSoup

if __name__ == '__main__':
    if len(sys.argv) != 2:
        print "usage: %s <amazon s3 url>" % sys.argv[0]
        sys.exit(1)
    base_url = sys.argv[1]
    xml = urllib.urlopen(base_url).read()
    soup = BeautifulSoup(xml)
    for content in soup.findAll("contents"):
        if content.key.string.find("$folder$") == -1:
            file_url = base_url + "/" + content.key.string
            print "downloading: %s" % file_url
            urllib.urlretrieve(file_url, content.key.string.replace("/", "_"))