import requests
from bs4 import BeautifulSoup
import os

# URL from which pdfs to be downloaded
book_url = input("Book url: ") # e.g. "https://www.degruyterbrill.com/document/doi/10.1515/9781400882540/html"#
pre = book_url[:book_url.find("/document")]

html = requests.get(book_url).content.decode()
parsed_html = BeautifulSoup(html)


title = parsed_html.find("h1", attrs={"class": "title-dgb"}).contents[0]
os.makedirs(f"./{title}", exist_ok=True)

res = parsed_html.find_all('tr',  attrs={"class": "bookTocEntryRow"})
pdf_urls = [tag.find("a")["href"] for tag in res]

for i, pdf_url in enumerate(pdf_urls):
    response = requests.get(pre + pdf_url.replace("html", "pdf"))
    with open(f'{title}/{i}_{pdf_url[-8:-5]}.pdf', 'wb') as f:
        f.write(response.content)
        print(f"saved {i+1} out of {len(pdf_urls)}")