requests库爬取拉勾网，session()实现cookie共享，以及list index out of range错误解决

遇到了许多问题，最终在一次次尝试下终于成功。
一开始没有没有意识到拉勾网的cookie在变化，总是不能正常爬取。查资料发现session可以共享信息，这才爬取到了一点正常信息。
爬取一半出现list index out of range，也发现错误的网页每次也不相同，猜测拉勾网后台数据在变化，返回了一个空的列表，使用if else能够继续爬取但同时也丢失了几条数据（大佬指点指点）。

import requests
from lxml import etree
import re

#使用session共享cookie
s = requests.session()

headers_1 = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.86 Safari/537.36'
        }

def main():
    #使用开始网址来实现cookie的共享
    ref_url = 'https://www.lagou.com/jobs/list_python?labelWords=&fromSearch=true&suginput='
    data_url='https://www.lagou.com/jobs/positionAjax.json?needAddtionalResult=false'

    data = {
        'first': 'false',
        'pn': 1,
        'kd': 'python',
        'sid': '15fc1c7c57184b6ab5137cb384bfa498'
    }
    for x in range(1,11):
        data['pn'] = x
        res = s.get(ref_url,headers=headers_1)
        
        headers_2= {
        'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.86 Safari/537.36',
        'Referer':ref_url
        }
        get_data(data_url,headers_2,data)
#先爬取一页
        break
        
#获取职位详细页面的url
def get_data(url,headers,data):
    resp = s.post(url,headers=headers,data=data)
    html = resp.json()
    results = html['content']['positionResult']['result']
    for result in results:
        id = result['positionId']
        data_detail_url = 'https://www.lagou.com/jobs/{}.html?show=ab8107555dd04359ad1490655d0066e3'.format(id)
        detail_data(data_detail_url)


def detail_data(url):
    res = s.get(url,headers = headers_1)
    text = res.text
    html = etree.HTML(text)
    a = html.xpath("//h2[@class='name']/text()")
    b = html.xpath("//dd[@class='job_request']//span/text()")
#没有if时出现list index out of range错误，猜测可能是一个空的列表
    if a==[]:
        pass
    else:
        name = a[0]
        print(name)
    if b==[]:
        pass
    else:
        salary = b[0]
        city = re_sub(b[1])
        education = re_sub(b[3])
        print(salary,city,education)
#职位详细信息
    c = html.xpath("//div[@class='job-detail']/p/text()")
    for d in c:
        print(d)



def re_sub(data):
    data = re.sub(r'[\s/]','',data)
    return data

if __name__ == '__main__':
    main()