qichacha.py 文件源码

def generate_firm_content(self, response):
        qitem = YQichachaItem()
        qitem._id = re.search(u'firm_(.*)(\.html)$', response.url).group(1)
        qitem.name = response.xpath("//div[contains(@class, 'company-top-name')]/text()").extract()[0]
        base_info = list()
        base_info.append({"????": self.clean_content(response.xpath(
            "//span[contains(@class, 'm_comInfo')]").extract()[0])})

        qitem.base_info = base_info
        qitem.save()
        chacha_url_pre = self.url_qichacha_pre + '/company_getinfos?unique=' + qitem._id + '&companyname='+qitem.name
        yield scrapy.Request(
            chacha_url_pre +'&tab=base',
            callback=self.generate_firm_base,
            cookies=self.qicha_cookie,
            encoding='utf-8',
            meta={"item": qitem, "chacha_url_pre":chacha_url_pre}
        )