This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
library(XML) | |
library(RCurl) | |
library(tm) | |
library(tmcn) | |
library(Rwordseg) | |
setwd("C:/test") | |
d.corpus <-Corpus(DirSource("/test/doc"), readerControl = list(language="UTF-8")) | |
#上兩行為抓取本機文字檔, 餘皆同網路上說明文字 |