xuetangx.py 文件源码

def get_book(url):
    """ ????? PDF ??? """
    # ????????
    print('???????……')
    nav_page = CONNECTION.get(url).text
    shelves = set(re.findall(r'/courses/.+/pdfbook/\d/', nav_page))
    for shelf_count, shelf in enumerate(shelves, 1):
        res = CONNECTION.get(BASE_URL + shelf).text
        soup = BeautifulSoup(res, 'lxml')
        save_dir = os.path.join(BASE_DIR, 'Books', str(shelf_count))
        if not os.path.exists(save_dir):
            os.makedirs(save_dir)
        for book_count, book in enumerate(soup.select('#booknav a'), 1):
            print('------>', book.string)
            file_name = REG_FILE.sub(' ', book.string) + '.pdf'
            pdf = CONNECTION.get(BASE_URL + book['rel'][0]).content
            with open(os.path.join(save_dir, file_name), 'wb') as pdf_file:
                pdf_file.write(pdf)