Reading and Text Mining a PDF File in R

# download pdftotxt from 

# ftp://ftp.foolabs.com/pub/xpdf/xpdfbin-win-3.03.zip

# and extract to your program files folder



# here is a pdf for mining

url <- span=""> "http://www.noisyroom.net/blog/RomneySpeech072912.pdf"

dest <- span=""> tempfile(fileext = ".pdf")

download.file(url, dest, mode = "wb")



# set path to pdftotxt.exe and convert pdf to text

exe <- span=""> "C:\\Program Files\\xpdfbin-win-3.03\\bin32\\pdftotext.exe"

system(paste("\"", exe, "\" \"", dest, "\"", sep = ""), wait = F)



# get txt-file name and open it  

filetxt <- span=""> sub(".pdf", ".txt", dest)

shell.exec(filetxt); shell.exec(filetxt)    # strangely the first try always throws an error..





# do something with it, i.e. a simple word cloud 

library(tm)

library(wordcloud)

library(Rstem)



txt <- span=""> readLines(filetxt) # don't mind warning..



txt <- span=""> tolower(txt)

txt <- span=""> removeWords(txt, c("\\f", stopwords()))



corpus <- span=""> Corpus(VectorSource(txt))

corpus <- span=""> tm_map(corpus, removePunctuation)

tdm <- span=""> TermDocumentMatrix(corpus)

m <- span=""> as.matrix(tdm)

d <- span=""> data.frame(freq = sort(rowSums(m), decreasing = TRUE))



# Stem words

d$stem <- span=""> wordStem(row.names(d), language = "english")



# and put words to column, otherwise they would be lost when aggregating

d$word <- span=""> row.names(d)



# remove web address (very long string):

d <- span=""> d[nchar(row.names(d)) < 20, ]



# aggregate freqeuncy by word stem and

# keep first words..

agg_freq <- span=""> aggregate(freq ~ stem, data = d, sum)

agg_word <- span=""> aggregate(word ~ stem, data = d, function(x) x[1])



d <- span=""> cbind(freq = agg_freq[, 2], agg_word)



# sort by frequency

d <- span=""> d[order(d$freq, decreasing = T), ]



# print wordcloud:

wordcloud(d$word, d$freq)



# remove files

file.remove(dir(tempdir(), full.name=T)) # remove files