baiduTopStockSpider.py 文件源码

def parse(self, response):
        # print(response, type(response))
        # from scrapy.http.response.html import HtmlResponse
        item = TopStockItem()
        selector = Selector(response)
        stocks = selector.xpath('//td[@class="keyword"]/a[@class="list-title"]')

        for index, stock in enumerate(stocks):
            item['name'] = stock.xpath('text()').extract()[0]
            item['num'] = index + 1
            item['source'] = "baidu"

            yield item