Last active
April 5, 2020 00:58
-
-
Save tcostam/1dba9d4ba4e615133a8a4c468d535881 to your computer and use it in GitHub Desktop.
Download free springer books from a specific spreadsheet
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
""" | |
There are books available for free download from springer editor | |
According to the following blog, it put together a spreadsheet with | |
all available books: | |
https://marcusnunes.me/posts/livros-gratuitos-da-springer/ | |
This script requires python3, pandas, xlrd and wget | |
Steps: | |
1. Put spreadsheet on the same folder as this script | |
2. Populate var file_name with the spreadsheet name | |
3. Populate var extension with pdf or epub | |
""" | |
import pandas as pd | |
import requests | |
import re | |
import wget | |
file_name = "FreeEnglishTextbooks.xlsx" | |
dfs = pd.read_excel(file_name, sheet_name="eBook list") | |
extension = "epub" | |
errors = [] | |
for index, row in dfs.iterrows(): | |
item = dict(row) | |
title = item["Book Title"] | |
author = item["Author"] | |
url = item["OpenURL"] | |
print('Downloding "{} - {}" from {}'.format(title, author, url)) | |
book_page = requests.get(url) | |
base_url = "http://link.springer.com" | |
file_urls = re.findall( | |
'(?<=<a\shref=")[A-z0-9_@\-^!#$%&+={}.\/\\\[\]]+\.' + extension + "+", | |
str(book_page._content), | |
) | |
if file_urls: | |
wget.download( | |
base_url + file_urls[0], "{} - {}.{}".format(title, author, extension) | |
) | |
else: | |
error_msg = "Can't find a {} file for book {} - {}: {}".format( | |
extension, title, author, url | |
) | |
errors.append(error_msg) | |
print(error_msg) | |
for error_msg in errors: | |
print("The following errors occurred:") | |
print(error_msg) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment