第五次作业

第一题

代码：

import re
print(re.match("\d*-\d*","029-12345"))
print(re.match("\d+","745100"))
print(re.match(".*","lijian@xianouoeng.com"))
print(re.match("\d{17}[x|\d|X]$", "62282519960504337x"))

第二题（借鉴了豆包）

代码：

#1.定义需要爬取的网站
url = "https://nhjcxy.edu.cn/"
#2.导入爬虫库
import requests
from bs4 import BeautifulSoup
#3.爬取数据
def log(func):
    def wrap(url):
        print(f"爬取中...{url}")
        func(url)
        print("爬取完成！")
    return wrap

@log
def get_imgs(url):
    resp = requests.get(url)
    for img in BeautifulSoup(resp.text, "html.parser").find_all("img"):
        with open("img_paths.txt", "a") as f:
            f.write(img["src"] + "\n")
get_imgs(url)