Download every file linked on a page

snatch.py

from bs4 import BeautifulSoup
import urllib.request
import sys
import argparse


parser = argparse.ArgumentParser(description='Scrape a page for all the files and download them to the current directory.')
parser.add_argument('root', metavar='url', type=str, help='URL you want to download files from')

args = parser.parse_args()


if not args.root.endswith('/'):
	print("[+] You forgot to add a / to the end of your url. Snatch is adding it for you.")
	args.root = args.root+"/"
if not args.root.startswith('http'):
	print("[+] You forgot to add http:// to the beginning of your url. Snatch is adding it for you.")
	args.root = "http://" + args.root

print()
print ("[+] URL: " + args.root)


request = urllib.request.urlopen(args.root)
website = BeautifulSoup(request, features="html.parser", from_encoding=request.info().get_param('charset'))

for link in website.find_all('a', href=True):
	file = urllib.parse.quote(link['href'])
	filePath = args.root + file
	try:
		print("[+] Downloading " + filePath)
		urllib.request.urlretrieve(filePath, file)
	except:
		print ("[-] Failed to download file at " + filePath)