chsi.py 文件源码

def parse_jianjie(self, response):

        item = response.meta['item']
        item['intro'] = response.xpath(u'//div[@class="schInfoSubT" and a/@name="2"]/following-sibling::div[1]').extract_first()

        for link in LinkExtractor(restrict_xpaths=u'//ul[@id="topNav"]//a[.="????"]').extract_links(response):
            yield Request(link.url, meta={'item': item}, callback=self.parse_zhuanye)