如何使用R登录网站并检查登录是否成功？

Question

我只需要在网页登录页面进行简单的登录，如何检查登录是否成功？

library(httr)
library(jsonlite)
library(tictoc)
library(data.table)
library(properties)
library(futile.logger)
library(crayon)
library(XML)
library(methods)
library(compare)
library(tictoc)
args = commandArgs(trailingOnly=TRUE)

server.name <- "lgloz050.lss.emc.com"
port.no <- "58443"
default.path <- "/APG/lookup/"

set_config(config(ssl_verifypeer = 0L))

config.s3 <- fread("Configuration_modify.csv")
config.s3$bc <- config.s3$testReport
config.s3$testReport <- gsub(">>","/", config.s3$testReport)
config.s3$testReport <- gsub(" ","%20", config.s3$testReport)

config.s3$link <- paste("https://",server.name,":",port.no,default.path,config.s3$testReport,"/report.csv", sep = "")

properties = read.csv2("Configuration.properties",sep = "=", blank.lines.skip = TRUE,header = FALSE,stringsAsFactors = FALSE  )
colnames(properties) <- c("key", "value")

config.s3$link <- gsub("$","PH_", config.s3$link)
#config.s3$link

for(i in 1:nrow(properties)){
  if(startsWith(properties[i,1],"$")){
    print(properties[i,1])
    for (j in 1: nrow(config.s3)) {
      config.s3[j]$link = gsub(paste("PH_",substring(trimws(properties[i,1]),2),sep = "")
                           ,trimws(properties[i,2]),config.s3[j]$link,ignore.case = TRUE)
    }
  }

}

result <- config.s3[, list(bc,TestCaseID,link),]

auth <- function(link,user.name="*****", password="******"){
  res <- GET(link,add_headers("accept"="text/json"))
  res <- POST('https://lgloz050.lss.emc.com:58443/APG/j_security_check'
              ,set_cookies=res$cookies
              ,body = "j_username=*****&j_password=******"
              ,add_headers("Content-Type" ="application/x-www-form-linkencoded" ))
  return(res)
}


fetch <- function(link,save.location,cookies){
  fetch.success = TRUE
  res <- GET(link
             ,add_headers("Authorization"="Basic **************")
             ,set_cookies=cookies)
  tryCatch({repot_data <- fread(content(res,"text"),header = TRUE);
  fwrite(data.frame(repot_data),save.location,row.names = FALSE);
  flog.info(green("'\u2713' - Fetch Completed successfully ..."))
  flog.info(paste("link : ",link))},
  error = function(e){fetch.success= FALSE; flog.error(paste("\u2715 - Not able to fetch data,file not created "))})

  return(fetch.success)
}

config.s3$save.location = sub("TruthData","testData",config.s3$truthReport,ignore.case = T)
response = auth(config.s3[1]$link)

# Function Call - fetch all the report data
result[,fetch:=FALSE]
result[,fetch.time:=0]
pb <- winProgressBar(title="Fetching Reports... ", label="0%", min=0, max=100, initial=0,width = 500)
for (i in 1:nrow(config.s3)) {
  tic()
  getWinProgressBar(pb)
  setWinProgressBar(pb, i*(100/nrow(config.s3)), label =paste(round(i*(100/nrow(config.s3)))," % \n",config.s3[i]$testReport))
  flog.info(paste("report",i,"started",config.s3[i]$link))
  fetch.success = fetch(config.s3[i]$link,config.s3[i]$save.location,response$cookies)
  t <- toc()
  t$toc
  result[i]$fetch <- fetch.success
  result[i]$fetch.time <- t$toc / 10000
}
close(pb)

result[,-c("link"),with=FALSE]

这是获取 CSV 文件的代码，但该文件包含登录页面的 HTML 内容。请告诉我哪里做错了，以及我必须纠正和修改哪些内容才能获得正确的数据。

建议一些程序。预先感谢。

Answer 1

我得到的解决方案如下：

library(httr) 
library(rvest)
url <- "https://lgloz050.lss.emc.com:58443/APG/"
dn_url <- "https://lgloz050.lss.emc.com:58443/APG/lookup/Report%20Library/Amazon%20S3/Inventory/Accounts/report.csv"
session <-  html_session(url)
form <- html_form(session)[[1]]
fl_fm <- set_values(form,
                        j_username = "*****",
                        j_password = "********")
main_page <- submit_form(session, fl_fm) 
download <- jump_to(main_page,dn_url)
writeBin(download$response$content, basename(dn_url))

执行此代码后，它将成功登录并下载报告，并且下载的报告具有所需的相同内容。我对一个文件执行此操作，接下来我尝试在一次执行中下载多个文件。

感谢大家的支持。让我知道上面的代码是否有任何其他可能的解决方案或需要任何类型的修改。