是否有R函数可以从多个pdf中提取特定单词？

Question

我已经学习R一周了，但是我一直在尝试从多个pdf中提取特定单词。有人对此有任何解决方案吗？我一直在到处寻找它。

  library(tidyverse) 
  library(pdftools) 
  library(dplyr) 
  library(tm) library(RWeka) 
  library(magrittr) 
  library(slam) 
  library(quanteda) 
  library(SnowballC)

read in all the .pdf files

files <- list.files("C:../Desktop/pdfs",full.names = TRUE, pattern='.pdf')

files_text <- lapply(files, pdf_text)

length(files_text[7])

head(files_text[7])

lapply(files_text,length)

Create a document matrix

corp <- Corpus(URISource(files),readerControl = list(reader = readPDF))

corp <- tm_map(corp, removePunctuation, ucp = TRUE)

files_text.tdm <- TermDocumentMatrix(corp,control =list(stopwords = TRUE,tolower = TRUE,stemming = TRUE,removeNumbers = TRUE,bounds = list(global = c(3, Inf)))) 

Search for specific words

corp <- corpus(files_text)

files_text <- tokens(corp, what="sentence")

grep ("risk|upside|downside", files_text, value= TRUE)