scrap.py

from urllib2 import urlopen
import urllib
import requests 
import urllib2
import urllib
import pdb
import os
import sys
import time
import lxml.html
from lxml.cssselect import CSSSelector
from lxml.html import parse
import urlparse


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]
#pdb.set_trace()
def  getImages(r):
	print 'found %s pictures' % len(images)
	print "test"
	for url in images:
		
		urllib.urlretrieve(url)
		
		print "downloading!!"
getImages(r)