寒假python作业5

powerfulhell2026-02-08 8:49

python 复制代码

import re
#- 匹配陕西省区号 029-12345
print(re.match(pattern=r"^029-\d{5}$", string="029-12345"))
#- 匹配邮政编码 745100
print(re.match(pattern=r"^\d{6}$", string="745100"))
#- 匹配邮箱 lijian@xianoupeng.com
print(re.match(pattern=r"^[a-zA-Z0-9_-]+@[a-zA-Z0-9_-]+\.[a-zA-Z0-9_-]+$", string="lijian@xianoupeng.com"))
#- 匹配身份证号 62282519960504337X
print(re.match(pattern=r"^\d{17}[\dXx]$", string="62282519960504337X"))

python 复制代码

import requests
import re
 
def log_crawl(func):
    def wrapper(url):
        print(f"开始爬取：{url}")
        result = func(url)  # 执行核心爬取函数
        print(f"爬取完成，共提取{len(result)}条图片路径")
        return result
    return wrapper
 
@log_crawl
def get_img_urls(url):
    res = requests.get(url, headers={"User-Agent": "Mozilla/5.0"})
    res.encoding = "utf-8"
    return re.findall(r'<img src="(.*?)"', res.text)
 
if __name__ == "__main__":
    url = "https://www.gsau.edu.cn/"
    img_list = get_img_urls(url)
    with open("学校图片地址.txt", "w", encoding="utf-8") as f:
        f.write("\n".join(img_list))
    print("路径已保存到 学校图片地址.txt")