R/url.R

In tonyelhabr/misterchiefdata: R package for pro Halo data

#' Check if URL exists
#'
#' @param x a single URL
#' @param non_2xx_return_value what to do if the site exists but the
#'        HTTP status code is not in the `2xx` range. Default is to return `FALSE`.
#' @param quiet if not `FALSE`, then every time the `non_2xx_return_value` condition
#'        arises a warning message will be displayed. Default is `FALSE`.
#' @param ... other params (`timeout()` would be a good one) passed directly
#'        to `httr::HEAD()` and/or `httr::GET()`
#' @source https://stackoverflow.com/questions/52911812/check-if-url-exists-in-r
url_exists <- function(x, non_2xx_return_value = FALSE, quiet = FALSE,...) {
  
  sHEAD <- purrr::safely(httr::HEAD)
  sGET <- purrr::safely(httr::GET)
  
  # Try HEAD first since it's lightweight
  res <- sHEAD(x, ...)
  
  if (is.null(res$result) || 
      ((httr::status_code(res$result) %/% 200) != 1)) {
    
    res <- sGET(x, ...)
    
    if (is.null(res$result)) return(NA) # or whatever you want to return on "hard" errors
    
    if (((httr::status_code(res$result) %/% 200) != 1)) {
      if (!quiet) warning(sprintf("Requests for [%s] responded but without an HTTP status code in the 200-299 range", x))
      return(non_2xx_return_value)
    }
    
    return(TRUE)
    
  } else {
    return(TRUE)
  }
  
}