def Crawl_Community_Title(response): _title = [] _link = [] item = DmozItem() hxs = HtmlXPathSelector(response) item['title'] = hxs.select("//div[@class=\"newsList\"]//ul//li//a/text()").extract() item['link'] = hxs.select("//div[@class=\"newsList\"]//ul//li//a/@href").extract() dataOptionGet = DataOptionGet() latest_link = dataOptionGet.get_Last_Link_CO() for i in range(len(item['title'])): if str(item['link'][i]) == latest_link: break _title.append(item['title'][i]) _link.append(item['link'][i]) if len(_link) > 0: dataOptionSave = DataOptionSave() dataOptionSave.Comu_Title_Save(_link,_title)