Script to download all Springer books released for free during the 2020 COVID-19 pandemic

springer_dl.R

library(tidyverse)
library(httr)
library(fs)
library(here)

titles_url <- "https://resource-cms.springernature.com/springer-cms/rest/v1/content/17858272/data/v4"

dl_folder <- "downloads"

# Save Excel table to tmp folder
GET(titles_url, write_disk(tmp_table <- tempfile(fileext = ".xlsx")))

titles <- readxl::read_xlsx(tmp_table) %>%
  janitor::clean_names()

titles <- titles %>%
  mutate(
    book_url = map_chr(open_url, ~ GET(.)$url),
    pdf_url = book_url %>%
      str_replace_all(c("/book/" = "/content/pdf/", "%2F" = "/")) %>%
      str_c(".pdf")
  ) %>%
  separate(author,
    into = c("author1", "author2", "author3"), sep = ", ",
    extra = "drop", fill = "right"
  ) %>%
  mutate(
    author1 = map_chr(str_split(author1, " "), tail, 1),
    author2 = map_chr(str_split(author2, " "), tail, 1),
    author3 = map_chr(str_split(author3, " "), tail, 1),
    file_name = case_when(
      # One author:
      is.na(author2) ~ str_c(author1, copyright_year, book_title, sep = "_"),
      # More than two authors:
      !is.na(author3) ~ str_c(author1, "et_al", copyright_year, book_title, sep = "_"),
      # Two authors:
      TRUE ~ str_c(author1, author2, copyright_year, book_title, sep = "_")
    ) %>%
      str_replace_all(c(":" = ".", "/" = "_")) %>%
      str_c(".pdf")
  )

titles %>%
  distinct(english_package_name) %>%
  map(~ dir_create(here(dl_folder, .)))

titles %$%
  map(pdf_url, ~ GET(., write_disk(here(
    dl_folder,
    english_package_name[pdf_url == .],
    file_name[pdf_url == .]
  ))))