How to download .gz files from FTP server in R? - r

Question

I am trying to download all .gz files from this link:
ftp://ftp.ncbi.nih.gov/snp/organisms/human_9606_b151_GRCh38p7/BED/
So far I tried this and I am not getting any results:
require(RCurl)
url= "ftp://ftp.ncbi.nih.gov/snp/organisms/human_9606_b151_GRCh38p7/BED/"
filenames = getURL(url, ftp.use.epsv = FALSE, dirlistonly = TRUE)
filenames <- strsplit(filenames, "\r\n")
filenames = unlist(filenames)
I am getting this error:
Error in function (type, msg, asError = TRUE) :
Operation timed out after 300552 milliseconds with 0 out of 0 bytes received
Can someone please help with this?
Thanks
EDIT:
I tried to run with with filenames provided to me bellow so in my r script I have:
require(RCurl)
my_url <-"ftp://ftp.ncbi.nih.gov/snp/organisms/human_9606_b151_GRCh38p7/BED/"
my_filenames= c("bed_chr_11.bed.gz", ..."bed_chr_9.bed.gz.md5")
my_filenames <- strsplit(my_filenames, "\r\n")
my_filenames = unlist(my_filenames)
for(my_file in my_filenames){
download.file(paste0(my_url, my_file), destfile = file.path('/mydir', my_file))
}
And when I run the script I get these warnings:
trying URL 'ftp://ftp.ncbi.nih.gov/snp/organisms/human_9606_b151_GRCh38p7/BED/bed_chr_11.bed.gz'
Error in download.file(paste0(my_url, my_file), destfile = file.path("/mydir", :
cannot open URL 'ftp://ftp.ncbi.nih.gov/snp/organisms/human_9606_b151_GRCh38p7/BED/bed_chr_11.bed.gz'
In addition: Warning message:
In download.file(paste0(my_url, my_file), destfile = file.path("/mydir", :
URL 'ftp://ftp.ncbi.nih.gov/snp/organisms/human_9606_b151_GRCh38p7/BED/bed_chr_11.bed.gz': status was 'Timeout was reached'
Execution halted

Answer 1

The file names you're trying to access are
filenames <- c("bed_chr_11.bed.gz", "bed_chr_11.bed.gz.md5", "bed_chr_12.bed.gz",
"bed_chr_12.bed.gz.md5", "bed_chr_13.bed.gz", "bed_chr_13.bed.gz.md5",
"bed_chr_14.bed.gz", "bed_chr_14.bed.gz.md5", "bed_chr_15.bed.gz",
"bed_chr_15.bed.gz.md5", "bed_chr_16.bed.gz", "bed_chr_16.bed.gz.md5",
"bed_chr_17.bed.gz", "bed_chr_17.bed.gz.md5", "bed_chr_18.bed.gz",
"bed_chr_18.bed.gz.md5", "bed_chr_19.bed.gz", "bed_chr_19.bed.gz.md5",
"bed_chr_20.bed.gz", "bed_chr_20.bed.gz.md5", "bed_chr_21.bed.gz",
"bed_chr_21.bed.gz.md5", "bed_chr_22.bed.gz", "bed_chr_22.bed.gz.md5",
"bed_chr_AltOnly.bed.gz", "bed_chr_AltOnly.bed.gz.md5", "bed_chr_MT.bed.gz",
"bed_chr_MT.bed.gz.md5", "bed_chr_Multi.bed.gz", "bed_chr_Multi.bed.gz.md5",
"bed_chr_NotOn.bed.gz", "bed_chr_NotOn.bed.gz.md5", "bed_chr_PAR.bed.gz",
"bed_chr_PAR.bed.gz.md5", "bed_chr_Un.bed.gz", "bed_chr_Un.bed.gz.md5",
"bed_chr_X.bed.gz", "bed_chr_X.bed.gz.md5", "bed_chr_Y.bed.gz",
"bed_chr_Y.bed.gz.md5", "bed_chr_1.bed.gz", "bed_chr_1.bed.gz.md5",
"bed_chr_10.bed.gz", "bed_chr_10.bed.gz.md5", "bed_chr_2.bed.gz",
"bed_chr_2.bed.gz.md5", "bed_chr_3.bed.gz", "bed_chr_3.bed.gz.md5",
"bed_chr_4.bed.gz", "bed_chr_4.bed.gz.md5", "bed_chr_5.bed.gz",
"bed_chr_5.bed.gz.md5", "bed_chr_6.bed.gz", "bed_chr_6.bed.gz.md5",
"bed_chr_7.bed.gz", "bed_chr_7.bed.gz.md5", "bed_chr_8.bed.gz",
"bed_chr_8.bed.gz.md5", "bed_chr_9.bed.gz", "bed_chr_9.bed.gz.md5"
)
The files are big, so I didn't check that this whole loop, but this worked at least for the first file. Add this to the end of your code.
my_url <- 'ftp://ftp.ncbi.nih.gov/snp/organisms/human_9606_b151_GRCh38p7/BED/'
for(my_file in filenames){ # loop over the files
# download each file, saving in a directory that you need to create on your own computer
download.file(paste0(my_url, my_file), destfile = file.path('c:/users/josep/Documents/', my_file))
}