linux获取整站源码

wget --mirror --convert-links --adjust-extension --page-requisites --no-parent http://example.com

import requests
from bs4 import BeautifulSoup
import os

def download_page(url, folder):
    response = requests.get(url)
    if response.status_code == 200:
        soup = BeautifulSoup(response.text, 'html.parser')
        for link in soup.find_all('a', href=True):
            href = link['href']
            if href.startswith('http'):
                download_page(href, folder)
            elif href.startswith('/'):
                download_page(url + href, folder)
            else:
                file_path = os.path.join(folder, href)
                if not os.path.exists(os.path.dirname(file_path)):
                    os.makedirs(os.path.dirname(file_path))
                with open(file_path, 'wb') as f:
                    f.write(requests.get(url + href).content)

if __name__ == '__main__':
    download_page('http://example.com', 'website_source')