Print HTML to PDF using chromote

chromote-print-to-pdf.R

library("promises")
library("chromote")

#' Print HTML to PDF using chromote
#'
#' @param url Input URL
#' @param filename Output file name
#' @param wait_ If TRUE, run in synchronous mode,
#' otherwise, run in asynchronous mode.
#' @param ... Additional parameters for Page.printToPDF, see
#' <https://chromedevtools.github.io/devtools-protocol/tot/Page/#method-printToPDF>
#' for possible options.
print_to_pdf <- function(url, filename = NULL, wait_ = FALSE, ...) {
  if (is.null(filename)) {
    filename <- url |>
      gsub("^.*://", "", x = _) |>
      gsub("/$", "", x = _) |>
      fs::path_sanitize(replacement = "_") |>
      paste0(".pdf")
  }

  b <- ChromoteSession$new()

  p <-
    {
      b$Page$navigate(url, wait_ = FALSE)
    } %...>%
    {
      b$Page$loadEventFired(wait_ = FALSE)
    } %...>%
    {
      b$Page$printToPDF(..., wait_ = FALSE)
    } %...>%
    {
      .$data
    } %...>%
    {
      outfile <- file(filename, "wb")
      base64enc::base64decode(., output = outfile)
      close(outfile)
    } %...>%
    {
      message(filename)
    } %>%
    finally(~ b$close())

  if (wait_) {
    b$wait_for(p)
  } else {
    p
  }

  invisible(filename)
}

# ioslides presentation and pagedown book
urls <- c(
  "https://nanx.me/talks/reimagine-rpkgs/",
  "https://pagedown.rbind.io/"
)

fn <- lapply(urls, print_to_pdf, printBackground = TRUE)

fn[[1]] |>
  pdftools::pdf_info() |>
  str()
fn[[2]] |>
  pdftools::pdf_info() |>
  str()

# Also supports file:// URLs
# (but only after running remote URLs like above AND using `wait_ = TRUE`)
f <- "https://nanx.me/blog/post/r-readability-parser/example.html" |>
  curl::curl_download(tempfile(fileext = ".html"))

print_to_pdf(
  paste0("file://", normalizePath(f, winslash = "/")),
  filename = "example.pdf",
  wait_ = TRUE
) |>
  pdftools::pdf_info() |>
  str()