在python中通过爬取子URL下载文件

import requests
from bs4 import BeautifulSoup
import urllib.parse

# 定义爬取子URL的函数
def get_sub_urls(url):
    response = requests.get(url)
    soup = BeautifulSoup(response.text, 'html.parser')
    sub_urls = []
    for link in soup.find_all('a'):
        sub_url = link.get('href')
        if sub_url.startswith('http'):
            sub_urls.append(sub_url)
        else:
            sub_urls.append(urllib.parse.urljoin(url, sub_url))
    return sub_urls

# 定义下载文件的函数
def download_file(url, save_path):
    response = requests.get(url)
    with open(save_path, 'wb') as file:
        file.write(response.content)

# 主函数
def main(url):
    sub_urls = get_sub_urls(url)
    for sub_url in sub_urls:
        if sub_url.endswith('.pdf') or sub_url.endswith('.docx'):
            file_name = sub_url.split('/')[-1]
            download_file(sub_url, file_name)

# 调用主函数
main('https://example.com')