How to extract text into a dataframe from pdf files

In this guide, I will show you how to extract text from pdf files. LinkedIn created a short time ago a guide on how to write successful job descriptions. Click here to download their pdf.

setwd("~/Documents/job descriptions/")

library(officer)
library(dplyr)
library(stringr)
library(tidyr)
library(stringi)

path = "23 Job descriptions/" #folder in which I downloaded the 23 job descriptions

data<-list() # start with an empty list
file.names <- dir(path, pattern =".docx")

# run through your loop, adding each vector to the list
for(i in 1:length(file.names)){
  file <- read_docx(paste0("23 Job descriptions/",file.names[i]))
  content <- docx_summary(file)
  r <- paste(content[1,4])
  s <- paste(content[2,4])
  combined  <- paste0(content$text, collapse=",") # result of iteration of loop added to combined data frame
  t <- as.data.frame(regmatches(combined, regexpr("OVERALL SUMMARY,\\s*\\K.*?(?=\\s*RESPONSIBILITIES)", combined, perl=TRUE)))
  x <- as.data.frame(regmatches(combined, regexpr("RESPONSIBILITIES,\\s*\\K.*?(?=\\s*,REQUIREMENTS)", combined, perl=TRUE)))
  y <- as.data.frame(regmatches(combined, regexpr("REQUIREMENTS,\\s*\\K.*?(?=\\s*,ABOUT)", combined, perl=TRUE)))
  data <- rbind(data, data.frame(r, s, t, x, y))
  }

colnames(data) <- c("Role","Job description title", "Overall summary", "Responsibilities", "Requirements")

data$Role <- stri_trans_totitle(data$Role)

write.csv(data, file = "job decriptions data.csv",row.names=FALSE)