download_books.py

import pandas as pd
import requests
from bs4 import BeautifulSoup as bs
from urllib.request import urlretrieve

base_url = 'https://link.springer.com/'

books_path = '/content/drive/My Drive/Springer Books/'

books = pd.read_csv(books_path + 'Springer Free Books - Data, Stats, Math & Tech.csv')

books.head()

links = books['OpenURL']
array_links = links.values

count = 0
for link in links:
    page = requests.get(link)
    soup = bs(page.text, 'html.parser')
    try:
        down_link = base_url + soup.find(class_ = 'cta-button-container__item').a.attrs['href']
    except:
        pass
    finally:
        try: 
            title = soup.find(class_ = 'page-title').h1.text
            if '/' in title:
                title = title.replace('/', ' ')
        except:
            subtitle = ''
    urlretrieve(down_link, books_path + title + '.pdf')
    print(count)
    print(f"Book {title} saved on Google Drive")
    count += 1