well that was easy

    def wordCounts(self, revision=-1):
        pageCrap = NOTAGRE.sub("", self.getHTML(revision))
        ret = collections.defaultdict(int)

        for word in pageCrap:
            per = set()

            for i in range(len(word)):
                for j in range(i+1, len(word)+1):
                    per |= {word[i:j]}

            for i in per:
                ret[i] += 1

        return dict(ret)