import requests
from bs4 import BeautifulSoup
import re

def get_article(url):
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3'}
    response = requests.get(url, headers=headers)
    soup = BeautifulSoup(response.text, 'html.parser')

    # 去除不需要的标签
    for tag in soup(['style', 'script']):
        tag.decompose()

    # 提取文章内容
    content = soup.find('div', {'class': 'rich_media_content'})
    if content:
        for p in content.find_all('p'):
            # 去除图片标签
            for img in p.find_all('img'):
                img.decompose()
            # 去除【style="visibility: hidden; opacity: 0;】
            p['style'] = ''
        # 保存到本地txt文件
        with open('article.txt', 'w', encoding='utf-8') as f:
            f.write(str(content))
    else:
        print("未找到文章内容")

if __name__ == '__main__':
    url = input("请输入微信公众号文章链接：")
    get_article(url)