Download best books from ukrlib

ukrlib.py

import time
import urllib.request
from pathlib import Path

from bs4 import BeautifulSoup
from tqdm import trange, tqdm

url_page_template = "https://ukrlib.com.ua/books/rating.php?so=1&page={page_id}"
url_download_template = "https://ukrlib.com.ua/books/getfile.php?tid={tid}&type=3"
BEST_BOOKS_DIR = Path(__file__).parent / "best"
BEST_BOOKS_DIR.mkdir(exist_ok=True)


def download_books_on_page(page_id: int):
    url_page = url_page_template.format(page_id=page_id)
    with urllib.request.urlopen(url_page) as response:
        html = response.read().decode("ISO-8859-1")

    soup = BeautifulSoup(html, 'html.parser')
    prefix_skip_len = len('printit.php?tid=')
    fname_prefix = "attachment; filename="
    for a_href in tqdm(soup.find_all('a', attrs={"class": "sr-author"}), desc=f"Page {page_id:02d}", leave=False):
        tid = a_href.get("href")[prefix_skip_len:]
        url_download = url_download_template.format(tid=tid)
        with urllib.request.urlopen(url_download) as response:
            fname = response.info().get('Content-Disposition', f"{fname_prefix}{tid}.docx")
            content = response.read()
        fname = fname[len(fname_prefix):]
        with open(BEST_BOOKS_DIR / fname, 'wb') as f:
            f.write(content)
        time.sleep(0.01)


if __name__ == "__main__":
    for page_id in trange(1, 21, desc=f"Downloading best books to {BEST_BOOKS_DIR}"):
        download_books_on_page(page_id)