망내(사전에 설치할 패키지 깔아놔야함)
getDepenencies <-function(packs) {
dependencyNames <- unlist (
tools::package_dependencies(packages = packs, db = available.packages(),
which = c("Depends", "Imports"),
recursive = TRUE))
packageNames <-union(packs, dependencyNames)
packageNames
}
packages<-getDependencies(c("tidyverse", "openxlsx", "pdftools", "rvest", "PDFR", "springr", "dplyr"))
pkgInfo<-download.packages(pkgs=packages, destdir = getwe(), type="win.binary")
write.csv(file = "pkgFilenames.csv", basename(pkgInfo[,2]), row.names=FALSE)
---------
망외
pkgFilenames<read.csv("pkgFilenames.csv", stringAsFactors = FALSE)[, 1]
install.packages(pkgFilenames, repos=NULL, type= "win.binary")
library(tidyverse)
library(pdftools)
library(stringr)
library(PDFR)
1)PDFR 이용
df<-pdfpage("C:/...",1)
2)pdftools 이용
text<-pdf_text("C:/....") %>% readr::read_lines()
text_sample1<-str_c(text, collapse ="" )
text_sample1<-text %>% str_squish() %>% strsplit(split="")
MAXlengths=max(sapply(text2,length))
revised<lapply(text2, function(el) { length(el) <-MAXlengths ; el})
df<plyr::ldply(revised)
df$V1=ifelse(, , , )
text_sample2<-str_c(text, collapse ="" )
text_sample3<-strsplit(text, "\n")
한글 문서에 격자 보기 및 설정 (0) | 2021.01.25 |
---|