API Access

library(httr2) # Get urls base_url <- "https://data.opm.gov/api/v1/files" list_url<- paste0(base_url, "/separations") # Get current files list_payload<- request(list_url) |> req_url_query(current = TRUE) |> req_timeout(30) |> req_perform() |> resp_body_json() print(list_payload)

library(httr2) # Specify starting year, month and dataset year <- "2020" month <- "09" dataset <- "employment" # Get urls base_url <- "https://data.opm.gov/api/v1/files" list_url <- paste0(base_url, "/", dataset) # Create output directory output_dir <- "fwd_downloads" if (!dir.exists(output_dir)) { dir.create(output_dir, recursive = TRUE) } # Get current files list_payload <- request(list_url) |> req_url_query(current = TRUE, month = month) |> req_timeout(30) |> req_perform() |> resp_body_json() # Get files after specified year and month filtered_list <- Filter( function(x) as.numeric(x$year) >= as.numeric(year), list_payload ) # Download the files for (file in filtered_list) { file_name <- paste0(file$filename, ".parquet") output_path <- file.path(output_dir, file_name) download_url <- paste0( base_url, "/", dataset, "/", file$year, "/", file$month, "/", file$version, "/download" ) download_response <- request(download_url) |> req_timeout(120) |> req_perform(path = output_path) cat(sprintf("Downloaded file to %s\n", output_path)) }