Python第五次作业

原创已于 2026-02-11 16:25:12 修改 · 531 阅读

15 ·

本内容遵循CC 4.0 BY-SA版权协议

GEO检测

于 2026-02-11 16:24:17 首次发布

开发板推荐：天空星STM32F407VET6开发板

超高性价比 STM32主控 | 超高主频 | 一板兼容百芯 | 比赛神器 | 沉金彩色丝印

点击查看

代码：

import re

# 1. 匹配陕西省区号 029-12345
def match_phone(s):
pattern = r'^029-\d+$'
return re.fullmatch(pattern, s) is not None

# 2. 匹配邮政编码 745100
def match_zip(s):
pattern = r'^\d{6}$'
return re.fullmatch(pattern, s) is not None

# 3. 匹配邮箱 lijian@xianoupeng.com
def match_email(s):
pattern = r'^[a-zA-Z0-9_.+-]+@[a-zA-Z0-9-]+\.[a-zA-Z0-9-.]+$'
return re.fullmatch(pattern, s) is not None

# 4. 匹配身份证号 62282519960504337X
def match_id_card(s):
pattern = r'^\d{17}[\dXx]$'
return re.fullmatch(pattern, s) is not None

if __name__ == "__main__":
print("匹配区号 029-12345:", match_phone("029-12345"))
print("匹配邮编 745100:", match_zip("745100"))
print("匹配邮箱 lijian@xianoupeng.com:", match_email("lijian@xianoupeng.com"))
print("匹配身份证 62282519960504337X:", match_id_card("62282519960504337X"))

运行结果

代码：

import urllib.request
import re
import functools
import time

# 装饰器：记录函数执行日志
def log_decorator(func):
    @functools.wraps(func)
    def wrapper(*args, **kwargs):
        print(f"[{time.strftime('%Y-%m-%d %H:%M:%S')}] 开始执行函数: {func.__name__}")
        print(f"参数: args={args}, kwargs={kwargs}")
        try:
            result = func(*args, **kwargs)
            print(f"[{time.strftime('%Y-%m-%d %H:%M:%S')}] 函数 {func.__name__} 执行成功")
            return result
        except Exception as e:
            print(f"[{time.strftime('%Y-%m-%d %H:%M:%S')}] 函数 {func.__name__} 执行失败: {str(e)}")
            raise
    return wrapper

@log_decorator
def crawl_school_images(url, output_file="image_paths.txt"):
    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36"
    }

    try:

        req = urllib.request.Request(url, headers=headers)
        with urllib.request.urlopen(req) as response:
            html = response.read().decode(response.headers.get_content_charset() or 'utf-8')

        img_pattern = re.compile(r'<img[^>]*src=["\']([^"\']+)["\'][^>]*>')
        img_urls = img_pattern.findall(html)

        from urllib.parse import urljoin
        full_img_urls = []
        for src in img_urls:
            if not src.startswith(("http://", "https://")):
                src = urljoin(url, src)
            full_img_urls.append(src)

        #保存到文件
        with open(output_file, "w", encoding="utf-8") as f:
            for img_url in full_img_urls:
                f.write(img_url + "\n")

        print(f"成功爬取 {len(full_img_urls)} 张图片，路径已保存到 {output_file}")
        return full_img_urls

    except Exception as e:
        print(f"执行失败: {e}")
        return []

# 调用
if __name__ == "__main__":
    crawl_school_images("https://www.example.com/")

运行结果：