Take a folder of HTML files and convert them to a document term matrix for text mining. Includes removal of non-ASCII characters and iterative removal of stopwords

HTML2DTM.r

# get data
setwd("C:/Downloads/html") # this folder has only the HTML files
html <- list.files()

# load packages
library(tm)
library(RCurl)
library(XML)
# get some code from github to convert HTML to text
writeChar(con="htmlToText.R", (getURL(ssl.verifypeer = FALSE, "https://raw.github.com/tonybreyal/Blog-Reference-Functions/master/R/htmlToText/htmlToText.R")))
source("htmlToText.R")
# convert HTML to text
html2txt <- lapply(html, htmlToText)
# clean out non-ASCII characters
html2txtclean <- sapply(html2txt, function(x) iconv(x, "latin1", "ASCII", sub=""))

# make corpus for text mining
corpus <- Corpus(VectorSource(html2txtclean))

# process text...
skipWords <- function(x) removeWords(x, stopwords("english"))
funcs <- list(tolower, removePunctuation, removeNumbers, stripWhitespace, skipWords)
a <- tm_map(corpus, FUN = tm_reduce, tmFuns = funcs)
a.dtm1 <- TermDocumentMatrix(a, control = list(wordLengths = c(3,10))) 
newstopwords <- findFreqTerms(a.dtm1, lowfreq=10) # get most frequent words
# remove most frequent words for this corpus
a.dtm2 <- a.dtm1[!(a.dtm1$dimnames$Terms) %in% newstopwords,] 
inspect(a.dtm2)