我正在嘗試檢索與特定模式匹配的多個資料 txt 檔案，形成我通過 url 訪問的多個壓縮檔案。我撰寫了一個腳本，從 url 下載所需的資料幀檔案，將它們保存在一個串列中，然后將所有資料幀合并在一起。然后我將這個函式應用到一個 url 串列上。
我想要的最終結果是將所有下載的資料從 R 的全域環境中的單個資料幀中的所有 url 中獲取。
但是，目前，單個檔案被下載到我不想要的作業目錄中，并且沒有合并到單個資料幀中。我想知道這個問題是否源于download.file，但我一直無法找到解決方案或有類似問題的帖子。
# list of urls
url_df = data.frame(model = c("rcp26", "rcp45", "rcp85"),
url = c("https://b2share.eudat.eu/api/files/d4850267-3ce2-44f4-b5e3-8391a4f3dc27/LTER_site_data_from_EURO-CORDEX-RCMs_rel1.see_disclaimer.77c127c4-2ebe-453b-b5af-61858ff02e31.huss_historical_rcp26_day_txt.zip",
"https://b2share.eudat.eu/api/files/d4850267-3ce2-44f4-b5e3-8391a4f3dc27/LTER_site_data_from_EURO-CORDEX-RCMs_rel1.see_disclaimer.77c127c4-2ebe-453b-b5af-61858ff02e31.huss_historical_rcp45_day_txt.zip",
"https://b2share.eudat.eu/api/files/d4850267-3ce2-44f4-b5e3-8391a4f3dc27/LTER_site_data_from_EURO-CORDEX-RCMs_rel1.see_disclaimer.77c127c4-2ebe-453b-b5af-61858ff02e31.huss_historical_rcp85_day_txt.zip"))
# create empty dataframe where data will be saved
downloaded_data = data.frame()
# create function to retrieve desired files from a single url
get_data = function(url) {
temp <- tempfile() # create temp file
download.file(url,temp) # download file contained in the url
# get a list of the desired files
file.list <- grep("KNMI-RACMO22E.*txt|MPI-CSC-REMO.*txt|SMHI-RCA4.*txt", unzip(temp, list=TRUE)$Name, ignore.case=TRUE, value=TRUE)
data.list = lapply(unzip(temp, files=file.list), read.table, header=FALSE, comment.char = "", check.names = FALSE)
# bind the dataframes in the list into one single dataframe
bound_data = dplyr::bind_rows(data.list)
downloaded_data = rbind(downloaded_data, bound_data )
return(downloaded_data)
unlink(temp)
}
# apply function over the list of urls
sapply(url_df$url, get_data)
任何幫助將不勝感激！
uj5u.com熱心網友回復：
不能downloaded_data在函式內部參考——函式會分別應用到每個 URL 上，然后你可以將它們系結在一起創建downloaded_data. 對資料的解壓縮和讀入也進行了一些更改，以確保檔案實際被讀入。
# list of urls
url_df = data.frame(model = c("rcp26", "rcp45", "rcp85"),
url = c("https://b2share.eudat.eu/api/files/d4850267-3ce2-44f4-b5e3-8391a4f3dc27/LTER_site_data_from_EURO-CORDEX-RCMs_rel1.see_disclaimer.77c127c4-2ebe-453b-b5af-61858ff02e31.huss_historical_rcp26_day_txt.zip",
"https://b2share.eudat.eu/api/files/d4850267-3ce2-44f4-b5e3-8391a4f3dc27/LTER_site_data_from_EURO-CORDEX-RCMs_rel1.see_disclaimer.77c127c4-2ebe-453b-b5af-61858ff02e31.huss_historical_rcp45_day_txt.zip",
"https://b2share.eudat.eu/api/files/d4850267-3ce2-44f4-b5e3-8391a4f3dc27/LTER_site_data_from_EURO-CORDEX-RCMs_rel1.see_disclaimer.77c127c4-2ebe-453b-b5af-61858ff02e31.huss_historical_rcp85_day_txt.zip"))
# create function to retrieve desired files from a single url
get_data = function(url) {
temp <- tempdir() # create temp file
download.file(url, file.path(temp, "downloaded.zip")) # download file contained in the url
downloaded_files <- unzip(file.path(temp, "downloaded.zip"), exdir = temp)
keep_files <- downloaded_files[grep("KNMI-RACMO22E.*txt|MPI-CSC-REMO.*txt|SMHI-RCA4.*txt",
downloaded_files)]
data.list <- lapply(keep_files, read.table, header=FALSE, comment.char = "", check.names = FALSE)
# bind the dataframes in the list into one single dataframe
bound_data = dplyr::bind_rows(data.list)
return(bound_data)
unlink(temp)
}
# apply function over the list of urls
downloaded_data <- dplyr::bind_rows(lapply(url_df$url, get_data))
dim(downloaded_data)
#> [1] 912962 7
轉載請註明出處，本文鏈接：https://www.uj5u.com/qiye/488434.html