updating readHFCweb and getHFCcountries functions for new HFC website

TR1/HMDHFDplus/R/HFDutils.R

@@ -329,7 +329,7 @@ getHFCcountries <- function(names = FALSE){
 	Codes <-
 	html_table(
 	  html_element(
-	    read_html("http://www.fertilitydata.org/cgi-bin/country_codes.php"), 
+	    read_html("https://www.fertilitydata.org/Codes/CountryCodes/country_codes.php"), 
 	    "table"),
 	  header = TRUE)
 

TR1/HMDHFDplus/R/readHFD.R

@@ -206,70 +206,70 @@ https://www.humanfertility.org/Account/UserAgreement"))
 # readHFCweb()
 ############################################################################
 
-##' @title readHFCweb get HFC data straight from the web into R!
-##' 
-##' @description This concatenates the necessary url and calls \code{read.csv()} with all the necessary defaults to avoid annoying surprises#. \code{Age} is given as an integer, along with an \code{AgeInterval}. The default behavior is to change the \code{AgeInterval} column to #character and produce a logical indicator column, \code{OpenInterval}. \code{Year} is also given as the starting year of a \code{YearInterval}, rather than the original \code{Year1} and \code{Year2} columns. The column \code{Country} is renamed \code{CNTRY}. All #other original columns are maintained. Output is invisibly returned, so you must assign it to take a look. 
-##' 
-##' @param CNTRY character string of the HCD short code. Only one! Run \code{getHFCcountries(FALSE)} to see what the options are.
-##' @param item character string of the data product code, which is the base file name, but excluding the country code and file extension \code{.txt}. For instance, \code{"ASFRstand_TOT"}, \code{"ASFRstand_BO"}, \code{"TFRMAB_TOT"}, \code{"TFRMAB_BO"}. Only one item!
-##' @param fixup logical. Default \code{TRUE}. Should column classes be coerced to those more similar to HFD, HMD?
-##' @param ... optional arguments passed to \code{read.csv()}. Not required.
-##' 
-##' @export
-##' 
-##' @importFrom httr HEAD
-##' @importFrom utils read.csv
-##' 
-##' @examples 
-##' \dontrun{
-##' DF <- readHFCweb("CZE","TFRMAB_TOT")
-##' head(DF)
-##' DF <- readHFCweb("CZE","ASFRstand_BO")
-##' head(DF)
-##' 
-##' # get ASFRstand_BO for all countries where available:
-##' Countries <- getHFCcountries()
-##' # takes a minute to run
-##' 
-##' urls <- paste0("http://www.fertilitydata.org/data/", 
-##'                Countries,"/", Countries, "_",  "ASFRstand_BO", ".txt")
-##' 
-##' HaveBO <- RCurl::url.exists(urls)
-##'  # we grab data for these countries:
-##'  (Countries <- Countries[HaveBO])
-##' 
-##' # Also takes 1-15 min depending on internet connection and machine
-##' # read in one at a time and stick together into long data.frame
-##' allBO <- do.call(rbind,
-##'         # this is the iteration of reading in
-##'         lapply(Countries, function(CNTRY){
-##'             readHFCweb(CNTRY, item = "ASFRstand_BO")
-##'              })) # closes off the meta-rbind thingy
-##' dim(allBO) # [1] 133237     31
-##' unique(allBO$CNTRY)
-##' 
-##' }
-##' 
-## readHFCweb <- function(CNTRY, item, fixup = TRUE, ...){
-## 	# concatenate url:
-## 	fileurl <- paste0("https://www.fertilitydata.org/data/", CNTRY, "/", CNTRY, "_", item, ".txt")
-## 	
-## 	# read in with needed arguments:
-## 	if (httr::HEAD(fileurl)$all_headers[[1]]$status == 200){
-## 		con         <- url(fileurl)
-## 		DF          <- read.csv(url(fileurl), stringsAsFactors = FALSE, na.strings = ".", strip.white = TRUE, ...)
-## 		# close(con)
-## 		# optionally use standard columns:
-## 		if (fixup){
-## 			DF      <- HFCparse(DF)
-## 		}
-## 		return(invisible(DF))
-## 	} else {
-## 		cat("Either the CNTRY code or data item are not available\nCheck names.\nNULL returned\n")
-## 		NULL
-## 	}
-## 	
-## }
+#' @title readHFCweb get HFC data straight from the web into R!
+#'
+#' @description This concatenates the necessary url and calls \code{read.csv()} with all the necessary defaults to avoid annoying surprises#. \code{Age} is given as an integer, along with an \code{AgeInterval}. The default behavior is to change the \code{AgeInterval} column to #character and produce a logical indicator column, \code{OpenInterval}. \code{Year} is also given as the starting year of a \code{YearInterval}, rather than the original \code{Year1} and \code{Year2} columns. The column \code{Country} is renamed \code{CNTRY}. All #other original columns are maintained. Output is invisibly returned, so you must assign it to take a look.
+#'
+#' @param CNTRY character string of the HCD short code. Only one! Run \code{getHFCcountries(FALSE)} to see what the options are.
+#' @param item character string of the data product code, which is the base file name, but excluding the country code and file extension \code{.txt}. For instance, \code{"ASFRstand_TOT"}, \code{"ASFRstand_BO"}, \code{"TFRMAB_TOT"}, \code{"TFRMAB_BO"}. Only one item!
+#' @param fixup logical. Default \code{TRUE}. Should column classes be coerced to those more similar to HFD, HMD?
+#' @param ... optional arguments passed to \code{read.csv()}. Not required.
+#'
+#' @export
+#'
+#' @importFrom httr HEAD
+#' @importFrom utils read.csv
+#'
+#' @examples
+#' \dontrun{
+#' DF <- readHFCweb("CZE","TFRMAB_TOT")
+#' head(DF)
+#' DF <- readHFCweb("CZE","ASFRstand_BO")
+#' head(DF)
+#'
+#' # get ASFRstand_BO for all countries where available:
+#' Countries <- getHFCcountries()
+#' # takes a minute to run
+#'
+#' urls <- paste0("http://www.fertilitydata.org/data/",
+#'                Countries,"/", Countries, "_",  "ASFRstand_BO", ".txt")
+#'
+#' HaveBO <- RCurl::url.exists(urls)
+#'  # we grab data for these countries:
+#'  (Countries <- Countries[HaveBO])
+#'
+#' # Also takes 1-15 min depending on internet connection and machine
+#' # read in one at a time and stick together into long data.frame
+#' allBO <- do.call(rbind,
+#'         # this is the iteration of reading in
+#'         lapply(Countries, function(CNTRY){
+#'             readHFCweb(CNTRY, item = "ASFRstand_BO")
+#'              })) # closes off the meta-rbind thingy
+#' dim(allBO) # [1] 133237     31
+#' unique(allBO$CNTRY)
+#'
+#' }
+#'
+readHFCweb <- function(CNTRY, item, fixup = TRUE, ...){
+  # concatenate url:
+  fileurl <- paste0("https://www.fertilitydata.org/File/GetFile/Country/", CNTRY, "/", CNTRY, "_", item, ".txt")
+  
+  # read in with needed arguments:
+  if (httr::GET(fileurl)$all_headers[[1]]$status == 200){
+    con         <- url(fileurl)
+    DF          <- read.csv(url(fileurl), stringsAsFactors = FALSE, na.strings = ".", strip.white = TRUE)
+    # close(con)
+    # optionally use standard columns:
+    if (fixup){
+      DF      <- HFCparse(DF)
+    }
+    return(invisible(DF))
+  } else {
+    cat("Either the CNTRY code or data item are not available\nCheck names.\nNULL returned\n")
+    NULL
+  }
+  
+}
 
 
 # end