read_springer_books_script.Rmd

---
title: "books"
author: "Sarah Van Alsten"
date: "4/27/2020"
output: html_document
---

```{r setup, include=FALSE}
knitr::opts_chunk$set(echo = TRUE)
library(tidyverse)
library(pdftools)
library(readxl)
library(httr)
library(janitor)
library(XML)

```

```{r}


books <- readxl::read_xlsx('Springer.xlsx')
books <- janitor::clean_names(books)
print('Download started.')
  

for (i in 1:nrow(books)){
    r <- httr::GET(books$open_url[i])
    new_url <- r$url
    
    new_url <- stringr::str_replace(new_url, '/book/','/content/pdf/') %>%
      stringr::str_replace('%2F','/') %>% paste0('.pdf')

    final <- stringr::str_split(new_url, '/')[-1]
    final <- stringr::str_replace(books$book_title[i], ',','-') %>%
    stringr::str_replace('.','') %>% stringr::str_replace('/',' ') %>%
    paste0("_")
  
    final2 <- stringr::str_replace(books$author[i],', ','+') %>%
    stringr::str_replace('.','') %>% stringr::str_replace('/',' ') %>%
    paste0('.pdf')
  
    final3 <- paste0(final, final2)
  
    download.file(new_url, final3, mode="wb")
  
}



print('Download finished.')
```