Python正则表达式爬取 Python怎样利用正则表达式爬取网页信息及图片

<div class="province-box"> ...... </div>

import requests
import re

url = "https://yyk.99.com.cn/sanjia/shanghai/"
# 模拟浏览器的访问
headers ={'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:87.0) '
                        'Gecko/20100101 Firefox/87.0'}
res = requests.get(url,headers=headers)

if res.status_code == 200:
	#1.获取网页源代码
    raw_text = res.text
    
    #2.正则表达式书写:
    #2.2注意:正则表达式默认匹配的是一行  我们的源代码是多行匹配的要加另一个参数 re.DOTALL
	#2.3正则法一:
		#re.findall() 返回的是lsit集合 一次过滤
    re_res = re.findall(r'<div class="province-box">(.*)<div class="wrap-right">', raw_text,re.DOTALL)
    	#re_res[0] 获取下标是的数据    二次过滤
    res=re.findall(r'title="(.*[院心部]）*)"',re_res[0])
    	#检查打印获取到的信息
	print(res)
	
	#2.4正则法二:
		#(优化)不用二次过滤 一次过滤就解决了
    # re_list = re.findall(r'<li><a href="/[^/].*/" rel="external nofollow"  rel="external nofollow"  target="_blank" title="(.*)">', res.text)
    #print(re_list)

    # 写入文件中
    read = open("上海医院名单", "w", encoding='utf-8')
    for i in res:
        read.write(i)
        read.write("\n")
    read.close()
else:
    print("error")

import os,sys,time,json,time
import socket,random,hashlib
import requests,configparser
import json,re
from datetime import datetime
from multiprocessing.dummy import Pool as ThreadPool


def getpicurl(url):
    url = "http://www.mzitu.com/zipai/comment-page-352"
    html = requests.get(url).text
    pic_url = re.findall('img src="(.*?)"',html,re.S)
    for key in pic_url:
        print(key + "\r\n")
    #print(pic_url)
    
getpicurl("http://www.mzitu.com/zipai/comment-pag.e-352")