Python 爬虫 招聘信息并存入数据库

新学习了selenium,啪一下腾讯招聘

 from lxml import etree
 from selenium import webdriver
 import pymysql
 def Geturl(fullurl):#获取每个招聘网页的链接
     browser.get(fullurl)
     shouye_html_text = browser.page_source
     shouye_ele = etree.HTML(shouye_html_text)
     zp_list = shouye_ele.xpath('//*[@id="position"]/div[1]/table/tbody/tr/td/a/@href')#链接url
     zp_url_list  = []
     for zp_url_lost in zp_list:
         zp_url  = 'https://hr.tencent.com/'+zp_url_lost
         zp_url_list.append(zp_url)
     return zp_url_list
 def Getinfo(zp_url_list):#获取每个招聘链接内部的内容
     for zp_url in zp_url_list:
         browser.get(zp_url)
         zp_info_html = browser.page_source
         zp_ele = etree.HTML(zp_info_html)
         zp_info_title = str(zp_ele.xpath('//*[@id="sharetitle"]/text()')[0])
         zp_info_location = str(zp_ele.xpath('//*[@id="position_detail"]/div/table/tbody/tr[2]/td[1]/text()')[0])
         zp_info_type = str(zp_ele.xpath('//*[@id="position_detail"]/div/table/tbody/tr[2]/td[2]/text()')[0])
         zp_info_num = str(zp_ele.xpath('//*[@id="position_detail"]/div/table/tbody/tr[2]/td[3]/text()')[0])
         zp_info_need = str(zp_ele.xpath('//*[@id="position_detail"]/div/table/tbody/tr[3]/td/ul/li/text()'))
         connection = pymysql.connect(host='localhost', user='root', password='', db='txzp', )
         try:
             with connection.cursor() as cursor:
                 sql = "INSERT INTO `txzp_info` (`title`, `location`,`type`,`num`,`need`) VALUES (%s,%s,%s,%s, %s)"
                 cursor.execute(sql, (zp_info_title,zp_info_location,zp_info_type,zp_info_num,zp_info_need))
             connection.commit()
         finally:
             connection.close()
         print(zp_info_title,zp_info_location,zp_info_type,zp_info_num,zp_info_need)
 if __name__ == '__main__':
     browser = webdriver.Chrome()
     pags = int(input('需要几页?'))
     for i in range(0,pags):
         url = 'https://hr.tencent.com/position.php?keywords=&tid=0&start={}'
         fullurl = url.format(str(i*10))
         zp_url_list = Geturl(fullurl)
         Getinfo(zp_url_list)
     browser.close()