from os import path
from urllib import urlopen
from urlparse import urlsplit
from BeautifulSoup import BeautifulSoup
from httplib import InvalidURL
 
savedir = 'E:\Documents and Settings\Mark-James McDougall\Desktop\DTA'
 
url = 'http://bombingscience.com/graffitiforum/index.php?showtopic=4900&st=%s'
 
main_url = 'http://bombingscience.com/'
 
 
for i in range(0, 526):
 
  this_url = url % i
 
  try:
    soup = BeautifulSoup(urlopen(this_url))
 
  except InvalidURL, e:
    print 'url <%s> did not open: %s' % (this_url, e)
    print sys.exit(1)
 
  for img in soup.findAll('img'):
    src = img['src']
 
    # if it's from the ad server, let's ignore this image
    if 'adserver' in src:
      print 'This looks like an ad, skipping: %s' % src
      continue
 
    if not src.startswith('http://'):
      image_url = main_url + src.strip('/')
    else:
      image_url = src
 
    try:
      image = urlopen(image_url).read()
      relative_path = urlsplit(src)[2]
 
      filename = relative_path.split('/')[-1]
 
      open(path.join(savedir, filename), 'wb').write(image)
      print 'got %s successfully' % image_url
 
    except IOError, e:
      print 'could not open this image: <%s>' % image_url