script_download_springer_free_ML_books

download_springer_free_ML_books.py

import requests
from bs4 import BeautifulSoup
import os
import re

### Requirements ###
# requests
# beautifulsoup4


source_url = 'https://techgrabyte.com/springer-released-65-machine-learning-data-science-books-free/'
page = requests.get(source_url)
books = BeautifulSoup(page.content, 'html.parser').find_all('a')
save_folder = 'springer_ML_free_books'
os.makedirs(save_folder, exist_ok=True)
base_url = 'https://link.springer.com/content/pdf/'

for book in books:
    try:
        book_url = book.attrs['href']
        if 'springer.com' in book_url:
            book_url += '#authorsandaffiliationsbook'
            pdf_url = book_url.replace('book', 'content/pdf')
            pdf_url += '.pdf'

            page = requests.get(book_url)
            title_ = BeautifulSoup(page.content, 'html.parser').find_all('h1')[0].text
            title = title_.replace(' ', '_')
            title = title.replace(':', '_')
            title = title.replace(',', '')

            print(f'Downloading... {title_}')

            regex = r"doi\.org/(.*)<"
            x = re.search(regex, page.text)[0]
            x = x.split('/')[1:]
            x = '/'.join(x)
            x = x.replace('/', '%2F')[0:-1]

            pdf_url = base_url + x
            s = requests.Session()
            r = s.get(pdf_url)

            with open(f'{os.path.join(save_folder, title)}.pdf', 'wb') as f:
                f.write(r.content)
    except:
        continue