Last active
June 11, 2018 22:54
-
-
Save ryan-hill/a8da86ef36eae86dcf3217fda8f96b02 to your computer and use it in GitHub Desktop.
Batch download StreamCat files for entire US based on desired table
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#FTP location | |
ftpdir <- 'ftp://newftp.epa.gov/EPADataCommons/ORD/NHDPlusLandscapeAttributes/StreamCat/HydroRegions/' | |
#Desired table (change to name of desired table) | |
table <- 'PredictedBioCondition' | |
#Get URL, split returned list, select out only desired tables by name ('table' above) | |
library(RCurl) | |
url_list <- getURL(ftpdir, dirlistonly = TRUE) | |
url_list <- strsplit(url_list, split = '\r\n')[[1]] | |
url_list <- url_list[grep(table, url_list)] | |
#Loop through files on FTP, download, and append | |
for(i in 1:length(url_list)){ | |
print(i) | |
temp <- tempfile() | |
download.file(paste0(ftpdir, url_list[i]), temp) | |
#replace .zip with .csv in file name | |
csv_file <- gsub('.zip', '.csv', url_list[i]) | |
#read in csv | |
tmp_metric <- read.csv(unz(temp, csv_file)) | |
#Append to final table | |
if(i == 1){ | |
outdf <- tmp_metric | |
}else{ | |
outdf <- rbind(outdf, tmp_metric) | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment