def test1(): obj = HtmlContent.objects.get(pk=46) key, sum, cls = summarize(obj.content) key2 = key_rank(obj.content) sents = list(cut_sentence(obj.content)) docs = [list(Tokenize(sent)) for sent in sents] sum2 = summarize4(sents) print 'key1', key, cls print 'key2', ', '.join(key2) print 'sum1', sum print 'sum2', sum2
def test1(): obj = HtmlContent.objects.get(pk=46) key,sum,cls = summarize(obj.content) key2 = key_rank(obj.content) sents = list(cut_sentence(obj.content)) docs = [list(Tokenize(sent)) for sent in sents] sum2 = summarize4(sents) print 'key1', key, cls print 'key2',', '.join(key2) print 'sum1',sum print 'sum2',sum2
def test5(): for obj in HtmlContent.objects.filter(~Q(content='')): sents = list(cut_sentence(obj.content)) docs = [list(Tokenize(sent)) for sent in sents] obj.summerize = summarize4(sents, docs)[0:400] obj.save()