爬虫爬取公众号文章

import requests
from bs4 import BeautifulSoup
import re

def get_mp_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)
    if response.status_code == 200:
        soup = BeautifulSoup(response.text, 'html.parser')
        title = soup.find('h1', class_='rich_media_title').get_text()
        content = soup.find('div', class_='rich_media_content')
        if content:
            content = content.find_all(style=re.compile("visibility: visible"))
            for p in content:
                print(p.get_text())
        else:
            print("No content found.")
    else:
        print("Failed to retrieve the webpage.")

# 示例公众号文章URL
article_url = 'https://mp.weixin.qq.com/s/YOUR_ARTICLE_URL'
get_mp_article(article_url)