r生成html文件,从R中的许多html文件创建一个语料库

这应该做到这一点.在这里,我的计算机上有一个HTML文件的文件夹(来自SO的随机样本),我用它们创建了一个语料库,然后是一个文档术语矩阵,然后完成了一些简单的文本挖掘任务.

# get data

setwd("C:/Downloads/html") # this folder has your HTML files

html

# 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

# clean out non-ASCII characters

html2txtclean

# make corpus for text mining

corpus

# process text...

skipWords

funcs

a

a

a.dtm1

newstopwords

# remove most frequent words for this corpus

a.dtm2

inspect(a.dtm2)

# carry on with typical things that can now be done,ie. cluster analysis

a.dtm3

a.dtm.df

a.dtm.df.scale

d

fit

plot(fit)

# just for fun...

library(wordcloud)

library(RColorBrewer)

m = as.matrix(t(a.dtm1))

# get word counts in decreasing order

word_freqs = sort(colSums(m),decreasing=TRUE)

# create a data frame with words and their frequencies

dm = data.frame(word=names(word_freqs),freq=word_freqs)

# plot wordcloud

wordcloud(dm$word,dm$freq,random.order=FALSE,colors=brewer.pal(8,"Dark2"))