python正则表达式进行翻页爬取页面内容

import requests
import re


def parse_age(pares_url):
    header={'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.88 Safari/537.36',
            'Cookie':'GANJISESSID=vq7552fkp302vtu2dpddirfkv2; use_https=1; lg=1; ganji_uuid=2022531570871833990967; __utma=32156897.921022363.1577171825.1577171825.1577171825.1; __utmc=32156897; __utmz=32156897.1577171825.1.1.utmcsr=baidu|utmccn=(organic)|utmcmd=organic; __utmt=1; ganji_xuuid=fb30c20a-5e57-414b-f322-8d745424db93.1577171825268; _gl_tracker=%7B%22ca_source%22%3A%22www.baidu.com%22%2C%22ca_name%22%3A%22-%22%2C%22ca_kw%22%3A%22-%22%2C%22ca_id%22%3A%22-%22%2C%22ca_s%22%3A%22seo_baidu%22%2C%22ca_n%22%3A%22-%22%2C%22ca_i%22%3A%22-%22%2C%22sid%22%3A55025296960%7D; gj_footprint=%5B%5B%22%5Cu79df%5Cu623f%22%2C%22http%3A%5C%2F%5C%2Fsh.ganji.com%5C%2Ffang1%5C%2F%22%5D%5D; citydomain=sh; ganji_login_act=1577172070870; __utmb=32156897.5.10.1577171825'}

    res=requests.get(pares_url,headers=header)
    text=res.text
    res=re.findall(r"""
    
    # 获取房源的标题
    <div.+?ershoufang-list".+?<a.+?js-title.+?>(.+?)</a>
    # 获取房源的户型
    .+?<dd.+?dd-item.+?<span>(.+?)</span>
    # 获取房源的面积
    .+?<span.+?<span>(.+?)</span>
    # 获取房源的朝向
    .+?<span.+?<span>(.+?)</span>
     # 获取房源是否精装修
    .+?<span.+?<span.+?>(.+?)</span>
    # 获取房源的地址
    .+?<dd.+?dd-item.+?<span.+?<span.+?>(.+?)</span>
     # 获取房源的经纪人
     .+?<dd.+?dd-item.+?<span.+?<span.+?>(.+?)</span>
    # 获取房源的价格
    .+?<div.+?price.+?<span.+?>(.+?)</span>
    
    """,text,re.VERBOSE|re.DOTALL)
    # 上面re.VERBOSE是为了使正则表达式可以添加注释，不加的话添加注释会报错
    # re.DOTALL则可以使“.”匹配包括换行符的任意字符，因为html文件内容包含一层
    for resss in res :
             print(resss)


def main():
    # 进行翻页，我这里选了1，5页进行爬取，记得锚点后面要加{}
    base_url="http://sh.ganji.com/zufang/pn{}/"
    for x in range(1,5):
        url = base_url.format(x)
        parse_age(url)



if __name__ == '__main__':
    main()