Python从网站递归下载所有PDF

import requests
from bs4 import BeautifulSoup
import os

def download_pdf(url, save_dir):
    response = requests.get(url)
    soup = BeautifulSoup(response.text, 'html.parser')
    
    # 创建保存PDF文件的目录
    if not os.path.exists(save_dir):
        os.makedirs(save_dir)
    
    # 解析HTML页面，提取出所有的链接
    for link in soup.find_all('a'):
        href = link.get('href')
        
        # 筛选出以".pdf"结尾的链接
        if href.endswith('.pdf'):
            pdf_url = url + href
            pdf_name = href.split('/')[-1]
            
            # 下载PDF文件并保存到本地
            response = requests.get(pdf_url)
            with open(os.path.join(save_dir, pdf_name), 'wb') as f:
                f.write(response.content)
            
            print(f"下载成功：{pdf_name}")
        
        # 如果链接指向的是一个网页，递归调用下载函数
        elif href.startswith(url):
            download_pdf(href, save_dir)

# 调用下载函数
url = "https://example.com"  # 网站的URL
save_dir = "pdfs"  # 保存PDF文件的目录
download_pdf(url, save_dir)