scrap.py

#!/usr/bin/env python

import requests
import sys
import lxml.html
import urlparse
import posixpath
import os


r = requests.get('http://www.jpl.nasa.gov/spaceimages/')
parsed = lxml.html.fromstring(r.text)
images = parsed.xpath('//img/@src')

if not images:
    sys.exit("found no pictures")
images = [urlparse.urljoin(r.url, url) for url in images if 'wallpaper' in url]
print images

print 'found %s pictures' % len(images)

for url in images:
    path = urlparse.urlsplit(url).path
    filename = posixpath.basename(path)
    if not os.path.exists(filename):
        print "downloading {} to {}".format(url, filename)
        r = requests.get(url)
        with open(filename, 'wb') as image:
            image.write(r.content)
    else:
        print "Skpping {}, already exists".format(filename)