匯入資料，抓文章

##設定自己jre位置

Sys.setenv(JAVA_HOME='C:/Program Files/Java/jdk1.8.0_121/jre')

library(rJava)

library(xlsx)





sd_content <- read.xlsx("sd_content.xlsx",header = TRUE,sheetIndex=1,encoding = "UTF-8")

class(sd_content$ar_ID)



library(openxlsx) ##檔案過大時，使用openxlsx

sd_ofile <- read.xlsx("sd_of_new_1.xlsx",sheet = 1)

ar_id_df <- read.xlsx("ar_id_df.xlsx",sheet = 1)

##check第一列第一個欄位，匯入時的多編碼

nchar(sd_content$ar_ID[1])

sd_content$ar_ID[1] <- c("1928")

nchar(sd_content$ar_ID[1])



## weblog與content結合，輸出有被點擊的文章

count <- nrow(ar_id_df)

for(i in 1:count){

  ar_sit <- which((ar_id_df$Document[i]==sd_content$ar_ID)==TRUE)

  ar_con <- sd_content$ar_content[c(ar_sit)]

  write.table(ar_con,file=sprintf("sd_articles/sd_%s.utf8",ar_id_df$Document[i]),fileEncoding = "UTF-8",quote = F,row.names = F,col.names = F)

}