python代码实战wx实现壁纸一键下载

原创已于 2025-10-24 10:30:58 修改 · 259 阅读

5 ·

CC 4.0 BY-SA版权

文章标签：

#1024程序员节 #python

于 2025-10-24 10:24:44 首次发布

Python 专栏收录该内容

7 篇文章

订阅专栏

思路：

1.通过输入的网页链接进行下载源码，比如这个链接

https:/xxxx/s/PZMAOvbgmnJUdjAQ3E9xig?scene=1&click_id=2

2.然后根据源码是否对应上面图片的格式来提取图片链接，然后下载到当前脚本文件所在的文件夹image中（自己新建）

3.最后下载保存在有日期命名的文件中，名称用1.2.3这样的命名。后缀格式为.png

效果：

代码：

""" 
@Project ：test 
@File ：download.py
@IDE ：PyCharm 
@Author ：随风万里无云
@Date ：2025/10/24 10:04
"""

import os
import re
import requests
from datetime import datetime
from urllib.parse import urljoin, urlparse
import time
import json


class WeixinImageDownloader:
    def __init__(self):
        self.session = requests.Session()
        self.session.headers.update({
            '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',
            'Referer': 'https://mp.weixin.qq.com/'
        })

    def get_html_content(self, url):
        
        try:
            response = self.session.get(url, timeout=10)
            response.raise_for_status()

            
            if response.encoding == 'ISO-8859-1':
                response.encoding = response.apparent_encoding or 'utf-8'

            return response.text
        except Exception as e:
            raise Exception(f"获取网页内容失败: {e}")

    def extract_image_urls(self, html_content):
        
        
        weixin_patterns = [
            r'data-src="(https?://mmbiz\.qpic\.cn/[^"]+)"',
            r'src="(https?://mmbiz\.qpic\.cn/[^"]+)"',
            r'data-src="(https?://[^"]*wx_fmt=[^"]*)"',
        ]

        all_urls = []
        for pattern in weixin_patterns:
            matches = re.findall(pattern, html_content)
            all_urls.extend(matches)

        
        return list(set(all_urls))

    def download_image(self, url, filepath):
        
        try:
            response = self.session.get(url, timeout=15, stream=True)
            response.raise_for_status()

            
            content_type = response.headers.get('content-type', '')
            if not content_type.startswith('image/'):
                return False, f"不是图片类型: {content_type}"

            
            with open(filepath, 'wb') as f:
                for chunk in response.iter_content(chunk_size=8192):
                    f.write(chunk)

            return True, "下载成功"

        except Exception as e:
            return False, str(e)

    def run(self, url):
        
        print(f"开始处理: {url}")

        
        today = datetime.now().strftime("%Y%m%d_%H%M%S")
        save_dir = os.path.join("image", today)
        os.makedirs(save_dir, exist_ok=True)

        try:
            
            html_content = self.get_html_content(url)
            print("✓ 网页源码获取成功")

            
            image_urls = self.extract_image_urls(html_content)
            if not image_urls:
                print("✗ 未找到符合格式的图片链接")
                return

            print(f"✓ 找到 {len(image_urls)} 个图片链接")

            
            success_count = 0
            download_log = []

            for i, img_url in enumerate(image_urls, 1):
                filename = f"{i}.png"
                filepath = os.path.join(save_dir, filename)

                print(f"下载中 [{i}/{len(image_urls)}]: {filename}")

                success, message = self.download_image(img_url, filepath)

                if success:
                    print(f"  ✓ 成功: {filename}")
                    success_count += 1
                else:
                    print(f"  ✗ 失败: {message}")

                download_log.append({
                    'index': i,
                    'url': img_url,
                    'filename': filename,
                    'success': success,
                    'message': message
                })

                
                time.sleep(0.5)

            
            log_file = os.path.join(save_dir, "download_log.json")
            with open(log_file, 'w', encoding='utf-8') as f:
                json.dump(download_log, f, ensure_ascii=False, indent=2)

            
            print(f"\n{'=' * 50}")
            print(f"下载完成！")
            print(f"成功: {success_count}/{len(image_urls)}")
            print(f"保存路径: {os.path.abspath(save_dir)}")
            print(f"{'=' * 50}")

        except Exception as e:
            print(f"处理失败: {e}")


def main():
    
    downloader = WeixinImageDownloader()

    
    url = input("请输入微信公众号文章链接: ").strip()

    if not url:
        print("使用示例链接...")
        url = "https://mp.weixin.qq.com/s/PZMAOvbgmnJUdjAQ3E9xig?scene=1&click_id=2"

    
    if not url.startswith(('http://', 'https://')):
        print("错误：请输入有效的URL")
        return

    
    downloader.run(url)


if __name__ == "__main__":
    main()