def parse(self, response): sel = Selector(response) sites = sel.xpath('//div[@id="navsecond"]/div[@id="course"]/ul[1]/li') items = [] for site in sites: item = W3schoolItem() response = HtmlXPathSelector(response) title = response.select('a/text()').extract() link = response.select('a/@href').extract() desc = response.select('a/@title').extract() item['title'] = [t.encode('utf-8') for t in title] item['link'] = [l.encode('utf-8') for l in link] item['desc'] = [d.encode('utf-8') for d in desc] response.append(item) #信息记录函数 log.msg("Appending item...",level='INFO') log.msg("Append done.",level='INFO') return items