Fetch free Springer ebooks.

fetch_springer_ebooks.py

#!/usr/bin/env python3

"""
Download free Springer ebooks.

Examples:

  python fetch_springer_ebooks python
  python fetch_springer_ebooks --dest my/ebooks math
  python fetch_springer_ebooks
  python fetch_springer_ebooks -h

Dependencies:
  - Firefox
  - geckodriver
  - requests
  - selenium
  - python-slugify
"""


import argparse
import os

import requests
from selenium import webdriver
from selenium.webdriver.firefox.options import Options
from slugify import slugify


def download(args):
    dest = args.dest
    query = args.query

    options = Options()
    options.headless = True
    driver = webdriver.Firefox(options=options, executable_path='geckodriver')
    url = "https://springer.com"
    driver.get(url)
    url = "https://link.springer.com/search?facet-content-type=%22Book%22&package=mat-covid19_textbooks"
    driver.get(url)
    input_el = driver.find_element_by_xpath('//*[@id="query"]')
    input_el.clear()
    input_el.send_keys(query)
    button_el = driver.find_element_by_xpath('//*[@id="search"]').click()

    page = 0
    i = 0
    while True:
        print(f"page {page}")
        for book in driver.find_elements_by_xpath('//h2/a[@class="title"]'):
            link = book.get_attribute("href")
            url = link.replace("springer.com/book", "springer.com/content/pdf") + ".pdf"
            text = book.text
            base, ext = os.path.splitext(os.path.basename(url))
            fname = "%s-%s%s" % (base, slugify(text), ext)
            path = os.path.join(dest, fname)
            print(i, fname)
            if not os.path.exists(path):
                with open(path, "wb") as f:
                    f.write(requests.get(url).content)
            i += 1
        try:
            next = driver.find_element_by_xpath('//a[@class="next"]')
            next.click()
        except:
            break
        page += 1

    driver.close()


if __name__ == "__main__":
    desc = "Download free Springer ebooks."
    p = argparse.ArgumentParser(description=desc)

    p.add_argument('query', metavar="TEXT", default="",
        help='Query to search books, example: "python", default: "".')
    p.add_argument('--dest', metavar='PATH', default=".",
        help='Existing destination folder, default: "."')

    args = p.parse_args()
    download(args)