A short script to download files from a webpage you saved in your browser. Currently set to download PDFs.

download-files-in-html-file-links.py

import re
from urllib.request import urlretrieve
from bs4 import BeautifulSoup

page = open('index.html', 'r')
page_text = page.read()
soup = BeautifulSoup(page_text, 'html.parser')
zipfiles = soup.find_all('a', href=re.compile('\.pdf'))
for z in zipfiles:
    url = z['href']
    parts = url.split('/')
    dst = parts[-1]
    print("Retrieving " + dst + ": " + url)
    try:
        urlretrieve(url, dst)
    except:
        print("Error, skipping.")