script.py

"""
aajjbb

python3 script based on ricbit script to dowload all books from computer science section of Springer

It has BeautifulSoup as dependency, easy installed with 'pip install beautifulsoup4'

"""

import re, subprocess, time, sys

from urllib.request import urlopen
from bs4 import BeautifulSoup

pmax = 456
target_file = open("test.txt", "w")

ROOT_URL = 'http://link.springer.com/search/page/%d?facet-discipline="Computer+Science"&showAll=false&facet-language="En"&facet-content-type="Book'

def getBookInfo(url):
  info = BeautifulSoup(str(url), "html.parser").a

  book_title = info.string
  page_url = info['href']

  return { 'book_title': book_title if book_title else page_url, 'page_url': page_url } 

def getDownloadUrl(url):
  page = BeautifulSoup(urlopen(url), "html.parser")

  name = page.find("h1", id="title").string
  pdf = page.find_all("a")

  for link in pdf:
    link_data = BeautifulSoup(str(link), "html.parser").a

    try:
      tag_id = str(link_data['id'])

      if tag_id.startswith("toc-download-book-pdf"):
        pdf = str(link_data['href'])
        break
    except:
      pass

  return None if type(pdf) != str else "http://link.springer.com" + pdf

for i in range(1, pmax):
  index = ROOT_URL % i
  page = urlopen(index)

  soup = BeautifulSoup(page, 'html.parser')
  urls = soup.find_all("a", class_="title")

  for url in urls:
    book_info = getBookInfo(url)
      
    download_url = getDownloadUrl('http://link.springer.com' + book_info['page_url'])

    if download_url:
      ret = subprocess.Popen(str("wget %s -O %s" % (download_url, str(book_info['book_title']).replace(' ', '-'))).split())
      ret.wait()