这段代码的目的是从输入的网址中获取所有以.pdf结尾的链接,然后将这些链接对应的pdf文件下载到本地的D:/download/pdf_files文件夹中。代码中使用了requests库和BeautifulSoup库来获取网页内容和解析网页,使用os库来创建文件夹和保存文件。
import requests
from bs4 import BeautifulSoup
import os
url = input("请输入网址:")
response = requests.get(url)
soup = BeautifulSoup(response.text, 'html.parser')
pdf_links = []
for link in soup.find_all('a'):
if link.get('href').endswith('.pdf'):
pdf_links.append(link.get('href'))
if not os.path.exists('d:/download/pdf_files'):
os.makedirs('d:/download/pdf_files')
for pdf_link in pdf_links:
response = requests.get(pdf_link)
with open(os.path.join('d:/download/pdf_files', pdf_link.split('/')[-1]), 'wb') as f:
f.write(response.content)