python抓取百度企业信用

本文主要是介绍python抓取百度企业信用，希望对大家解决编程问题提供一定的参考价值，需要的开发者们随着小编来一起学习吧！

1.抓取百度企业信用的企业信息（基本信息、股东信息、主要人员等）
在这里插入图片描述
2.难点分析，在于解析数据和通过一个爬虫全部解析入库，我自己用的scrapy，代码如下：

    def parse(self,response):detail_url = response.xpath("//h3/a/@href").extract()[0]# 拼接详情页urldetail_url = "https://xin.baidu.com" + detail_urltry:yield scrapy.Request(detail_url,callback=self.parse_details,dont_filter=True)except Exception as e:logger.error(e)# 详情页解析def parse_details(self, response):# 营业执照的itemitem = QccItem()try:# 法定代表人item["legal_person"] = \response.xpath("//table[@class='zx-detail-basic-table']//tr[2]/td[2]//text()").extract()[0]# print(item["legal_person"])except:item["legal_person"] = " "try:# 注册资本item["money"] = \int(response.xpath("//table[@class='zx-detail-basic-table']//tr[1]/td[2]//text()").extract()[0].strip().split("万")[0])# print(item["money"])if item["money"] == "-":item["money"] = Noneexcept:item["money"] = Nonetry:# 成立日期item["establish_date"] = response.xpath("//table[@class='zx-detail-basic-table']//tr[6]/td[4]//text()").extract()[0].strip()if item["establish_date"] == '-' or item["establish_date"] == '正常' or item["establish_date"] == '暂无':item["establish_date"] = Noneexcept:item["establish_date"] = Nonetry:# 登记状态item["register_status"] = response.xpath("//table[@class='zx-detail-basic-table']//tr[2]/td[4]//text()").extract()[0].strip()except:item["register_status"] = " "try:# 统一社会信用代码item["code_or_registration_no"] = \response.xpath("//table[@class='zx-detail-basic-table']//tr[4]/td[2]//text()").extract()[0].strip()except:item["code_or_registration_no"] = " "try:# 企业类型item["type"] = response.xpath("//table[@class='zx-detail-basic-table']//tr[7]/td[2]//text()").extract()[0].strip()except:item["type"] = " "try:# 核准日期item["approval_date"] = response.xpath("//table[@class='zx-detail-basic-table']//tr[8]/td[4]//text()").extract()[0].strip()if item["approval_date"] == "-":item["approval_date"] = Noneexcept:item["approval_date"] = Nonetry:# 登记机关item["register_organization"] = \response.xpath("//table[@class='zx-detail-basic-table']//tr[6]/td[2]//text()").extract()[0].strip()except:item["register_organization"] = " "try:# 所属区域item["area_id"] = response.xpath("//table[@class='zx-detail-basic-table']//tr[8]/td[2]//text()").extract()[0].strip()except:item["area_id"] = " "try:# 营业期限自item["operating_period_start"] = \response.xpath("//section[@id='Cominfo']//table//tr[7]/td[4]//text()").extract()[0].strip().split("至")[0].replace(" ", "")if item["operating_period_start"] == "***":item["operating_period_start"] = Noneexcept:item["operating_period_start"] = Nonetry:# 营业期限至item["operating_period_end"] = \response.xpath("//table[@class='zx-detail-basic-table']//tr[7]/td[4]//text()").extract()[0].strip().split("至")[1].replace(" ", "")if item["operating_period_end"] == "无固定期限":item["operating_period_end"] = Noneexcept:item["operating_period_end"] = Nonetry:# 住所item["address"] = response.xpath("//table[@class='zx-detail-basic-table']//tr[9]/td[2]//text()").extract()[0].strip().split("查")[0]except:item["address"] = " "try:# 经营范围item["business_scope"] = response.xpath("//table[@class='zx-detail-basic-table']//tr[10]/td[2]//text()").extract()[0].strip()except:item["business_scope"] = " "item["name"] = response.xpath("//span[@class='entName']//text()").extract()[0]# 注册资本（币种）item["money_currency"] = None# 经营者item["business_ower"] = None# 组成形式item["establish_form"] = None# 创建时间item["create_date"] = time.strftime('%Y-%m-%d', time.localtime(time.time()))# 修改时间item["update_date"] = time.strftime('%Y-%m-%d', time.localtime(time.time()))# 空置率item['empty_ratio'] = None# 注销日期item["logout_date"] = None# 吊销日期item["revoke_date"] = None# 注册日期item["register_date"] = None# 数据当前状态item["data_status"] = 1# print(item)yield item在这里插入代码片