Python爬虫 selenium抓取企查查招投标

企查查最新中标企业抓取

 网站链接:标找找 - 企查查旗下一站式标讯服务平台
 

需要使用的python包

selenium

在未付费的情况下只能抓取最新50条数据

解析代码如下：

# -*- coding: utf-8 -*-
from selenium.webdriver import Chrome


def main():
    driver = Chrome()
    driver.get('https://www.biaozhaozhao.com/?tab=wtb_company')
    for _ in range(10):
        lis = driver.find_elements_by_xpath("//div[@class='tc_list_item tc_list_hover']")
        for row in lis:
            item = dict()
            # 企业名称
            item['ent_name'] = row.find_element_by_xpath("div/div/div[@class='FpwufnYn']/div/a/span").text
            # 企业状态
            item['ent_state'] = row.find_element_by_xpath("div/div[@class='_0aDOKXj6']/span").text
            # 企业标签
            item['tag'] = [i.text for i in row.find_elements_by_xpath("div/div/span[@class='ant-tag awpCsC3X']")]
            # 招投标数
            item['num'] = row.find_element_by_xpath("div/div/div[@class='WMSbIy8X']/span").text
            # 法定代表人
            item['name'] = row.find_element_by_xpath("div/div/div/ul[@class='ozeTtOeS']/li/a").text
            # 注册资金
            item['regcap'] = row.find_element_by_xpath("div/div/div/ul[@class='ozeTtOeS']/li[2]/span[2]").text
            # 成立日期
            item['date'] = row.find_element_by_xpath("div/div/div/ul[@class='ozeTtOeS']/li[3]/span[2]").text
            # 公示
            item['title'] = row.find_element_by_xpath("div/div/div/div/div[@class='lZ9dQcZO']/a").text
            # 公示链接
            item['url'] = row.find_element_by_xpath("div/div/div/div/div[@class='lZ9dQcZO']/a").get_attribute('href')
            print(item)

        driver.find_element_by_xpath("//i[@class='anticon anticon-right']").click()
        #  点击下一页
    driver.close()


if __name__ == '__main__':
    main()

只解析了部分字段

结果：