I need to code something that takes in a URL or PDF and then downloads all the PDFs on that page. So far it works when I put in a webpage but inputting PDFs doesn't work. I have very little Python experience and realize it's because BeautifulSoup only works with HTML and XML files so I was wondering if there was something that did the same thing with PDFs.
import os import requests from urllib.parse import urljoin from bs4 import BeautifulSoup url = input("Please enter the URL ") folder_location = input("Please enter the folder location(ie. C:\ExampleFolder) ") #If there is no such folder, the script will create one automatically if not os.path.exists(folder_location):os.mkdir(folder_location) response = requests.get(url) soup= BeautifulSoup(response.text, "html.parser") for link in soup.select("a[href$='.pdf']"): #Name the pdf files using the last portion of each link which are unique in this case filename = os.path.join(folder_location,link['href'].split('/')[-1]) with open(filename, 'wb') as f: f.write(requests.get(urljoin(url,link['href'])).content)