import requests
from bs4 import BeautifulSoup
def fetch_article(url):
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',
'Referer': url
}
response = requests.get(url, headers=headers)
if response.status_code == 200:
return response.text
else:
return None
def parse_article(html):
soup = BeautifulSoup(html, 'html.parser')
content = soup.find('div', class_='rich_media_content').get_text()
# Browsing count and comments extraction would be more complex and may need specific HTML structure inspection
return content
def main():
url = 'https://mp.weixin.qq.com/s/I3hVi4znBgunzqDGLGLg_w'
html = fetch_article(url)
if html:
content = parse_article(html)
print(content)
else:
print("Failed to retrieve article.")
if __name__ == '__main__':
main()
04-21
4544
09-06