Download OHLDM

download_book.py

import requests
import re
import time

r = requests.get('https://direct.mit.edu/books/book/5244/The-Open-Handbook-of-Linguistic-Data-Management',
                 stream=True, headers={'User-agent': 'Mozilla/5.0'})
                 
urls = re.findall('href="(.*?.pdf)"', r.text)
base = 'https://direct.mit.edu'
urls = [base + path for path in urls if '/book/' in path]

for i, url in enumerate(urls):
    r = requests.get(urls[0], stream=True, headers={'User-agent': 'Mozilla/5.0'})
    with open(f'{i}.pdf','wb') as f:
        f.write(r.content)
    
    # Be nice to the server:
    time.sleep(2)