download_all_books from search query in project gutemberg

download_all_books.py

def download_all_books(url, save_path):
    # download the page that lists top books
    data = download_url(url)
    print(f'.downloaded {url}')
    # extract all links from the page
    links = get_urls_from_html(data)
    print(f'.found {len(links)} links on the page')
    # retrieve all unique book ids
    book_ids = get_book_identifiers(links)
    print(f'.found {len(book_ids)} unique book ids')
    # create the save directory if needed
    makedirs(save_path, exist_ok=True)
    # download and save each book in turn
    for book_id in book_ids:
        print(book_id)
        # download and save this book
        result = download_book(book_id, save_path)
        # report result
        print(result)