import urllib2 as url def getBetween(s, e, searched): sInd = searched.find(s) return searched[sInd + len(s):searched.find(e, sInd)] def get(url): isHards = [] isbns = [] done = False for pg in xrange(1, 5000): html = url.urlopen(url + '?PG=%d' % pg).read() eInd = 0 while True: sInd = html.find("(", eInd) if sInd == -1: if eInd == 0: done = True break eInd = html.find("\n", sInd) foo = html[sInd + len("("):eInd] isHards.append('Hardback' in foo) isbns.append(getBetween('ISBN10: ', ';', foo)) if done: break return results print get('http://www.textbooks.com/Catalog/KMG/Geometry-for-K-12.php') ###### http://www.chartwellyorke.com/fathom/fathomdemos.html http://isbndb.com/