R script to check an HTML document for broken links. Save, source and try the example at the bottom.

checkLinks.R

# checkLinks.R
# Author: Boris Steipe (ORCID: 0000-0002-1134-6758)
# License: (c) Author (2018) + MIT
# Date: 2018-12-29
#
# This R-script installs packages (if needed) and defines a function to access
# all http:// and https:// links referenced in an HTML document and check their
# status code.
#
# Issues:
#  - relative URLs are not expanded with an inferred base-URL but discarded
#  - calls to URLs that don't resolve throw an error. Might use tryCatch()
#        on httr::GET()
#

if (! requireNamespace("xml2", quietly = TRUE)) {
  install.packages("xml2")
}

if (! requireNamespace("rvest", quietly = TRUE)) {
  install.packages("rvest")
}

if (! requireNamespace("httr", quietly = TRUE)) {
  install.packages("httr")
}

checkLinks <- function(URL) {
  # download page and access URLs
  myPage <- xml2::read_html(URL)
  URLs <- rvest::html_attr(rvest::html_nodes(myPage, "a"), "href")

  # remove URLs that don't begin with http:// or https://
  sel <- grepl("^https?://", URLs)
  URLs <- URLs[sel]

  # remove anchor parts (from "#" to end), since absence of internal
  # anchors does not affect the status code
  URLs <- gsub("#[^#]*$", "", URLs)

  # remove duplicates
  URLs <- unique(URLs)

  stati <- matrix(c("category", "reason", "URL"), ncol = 3)
  for (thisURL in URLs) {
    x <- httr::GET(thisURL)
    stati <- rbind(stati, c(httr::http_status(x)$category,
                            httr::http_status(x)$reason,
                            thisURL))
  }
  myOrd <- order(stati[ -1, 1])
  stati <- rbind(stati[1, ], (stati[ -1, ])[myOrd, ])

  return(stati)
}


# try it
if (FALSE) {
  # Use test page URL:
  URL <- "http://steipe.biochemistry.utoronto.ca/abc/assets/testCheckLinks.html"
  checkLinks(URL)
}

# [END]

Hi @hyginn thank yo so much for creating this code!
Do you know what can I do if I get this type of error when running your function?

Error in curl::curl_fetch_memory(url, handle = handle) : Could not resolve host: revistacardus.com