downloading all cdc vital stats public use microdata files

cdc_bulk_download.R

library(tidyverse)
library(rvest)
library(httr)
options(timeout = 1e6)
cdc_url <- "https://www.cdc.gov/nchs/data_access/vitalstatsonline.htm"
pg <- read_html(cdc_url)


test <- html_attr(html_nodes(pg, "a"), "href")
pdfs <- test[grepl(test, pattern = ".pdf")]
zips <- test[grepl(test, pattern = ".zip")]
zips <- zips[!grepl(zips,pattern = "winzip")]


dir.create("zips")
# I manually opened 4 R sessions for downloading the zips
for (z in zips[2:99]){
  filename <- z |> str_split(pattern = "/") %>% '[['(1) |> rev() %>% '[['(1)
  destfile <- file.path("zips", filename)
  download.file(url = z, destfile = destfile, timeout = 10000)
}
for (z in zips[100:199]){
  filename <- z |> str_split(pattern = "/") %>% '[['(1) |> rev() %>% '[['(1)
  destfile <- file.path("zips", filename)
  download.file(url = z, destfile = destfile, timeout = 10000)
}
for (z in zips[200:299]){
  filename <- z |> str_split(pattern = "/") %>% '[['(1) |> rev() %>% '[['(1)
  destfile <- file.path("zips", filename)
  download.file(url = z, destfile = destfile, timeout = 10000)
}
 for (z in zips[300:354]){
   filename <- z |> str_split(pattern = "/") %>% '[['(1) |> rev() %>% '[['(1)
   destfile <- file.path("zips", filename)
   download.file(url = z, destfile = destfile, timeout = 10000)
 }


dir.create("pdfs")
i = 0
for (p in pdfs){
  i <- i + 1
  filename <- p |> str_split(pattern = "/") %>% '[['(1) |> rev() %>% '[['(1)
  filename = paste0(i, filename)
  destfile <- file.path("pdfs", filename)
  download.file(url = p, destfile = destfile, timeout = 10000)
}