[R] 利用Graph API 製作FB朋友文字雲

一.首先要先在Facebook申請 AccessToken
網址如下:

Facebook開發人員網址

(1)進入網址後點Tools&Support => 進入 Graph API Explorer

(2)之後點選 Get AccessToken

(3)勾選這些權限允許

二.確定R的版本與各項packages安裝

(1)我這邊R的版本是R version 3.0.2 (2013-09-25)
(2)有些package沒辦法自動下載完，需自行編譯

install.packages("rJava")
install.packages("RCurl")
install.packages("rjson")
install.packages("tm", repos="http://R-Forge.R-project.org", type = "source")
install.packages("tmcn", repos="http://R-Forge.R-project.org", type = "source")
install.packages("Rwordseg", repos = "http://R-Forge.R-project.org", type = "source")
install.packages("RColorBrewer")
install.packages("wordcloud")
install.packages("rJava")

三.執行程式碼

(1)程式碼部分如下:

require(RCurl)
require(rjson)


setwd('/home/lock/')              #設定工作環境位置1
if(!file.exists('/home/lock/somedir')){dir.create('somedir')}
wdname ="/home/lock/somedir"    #設定工作環境位置2
setwd(wdname)

token = "CAACEdEose0cBAHHZBR0qbBrZC21IVWIz3pheMDTv7YhrJHI4GpzreZCjWwltHxlZBKob4g91i8N48ovVDDYnftLqw4jWQ1YPOeXjZARi2GiSF9iwBZA1CCJRy4zktdUS1fQ2BHZA8s1jCZBhLrsHvD2m7ryC1Kpz8sJZAOX10tSfZAjcOqjKNwZApjTiE7pAvof1JHyxfFofsi3Wzk40NUbLGNsjPtjaIjt6mIZD"

###############
#Function start
###############
facebook =  function( path = "me?fields=posts.limit(200)", access_token = token, options){
  if( !missing(options) ){
    options = sprintf( "?%s", paste( names(options), "=", unlist(options), collapse = "&", sep = "" ) )
  } else {
    options = ""
  }
  data = getURL( sprintf( "https://graph.facebook.com/%s%s&access_token=%s", path, options, access_token )  
                  , .opts = list(ssl.verifypeer = FALSE),encoding='UTF-8')
  fromJSON( data )
}
###################################################################
facebook2 = function(urlcode){
  data =getURL (urlcode,.opts = list(ssl.verifypeer = FALSE))
  fromJSON( data )
}
###################################################################
is.defined = function(x)!is.null(x)
###################################################################
fb_like_next = function(tmp_like2, urlcode){
  
  posts2=facebook2( urlcode )
  for(i in 1 : length(posts2$data)){
    tmp_like2 = c(tmp_like2,posts2$data[i]$name)
  } 
  if(is.defined(posts2$paging$`next`)){
    tmp_like2 = c( fb_like_next(tmp_like2,posts2$paging$`next`),posts2$data[i]$name)
  }
  return(tmp_like2)
}

###################################################################
###############
#Function end
###############
posts = facebook()
tmp_like = list()
for(i in 1:length(posts[1]$posts$data)){
  if(is.defined(posts[1]$posts$data[[i]]$likes)){
    for(j in 1:length(posts[1]$posts$data[[i]]$likes$data)){
         
      ddname =c(posts[1]$posts$data[[i]]$likes$data[[j]]$name)     
      tmp_like = c( tmp_like,ddname)

      if(is.defined(posts[1]$posts$data[[i]]$likes$paging$`next`)){
        dda = fb_like_next(tmp_like,posts[1]$posts$data[[i]]$likes$paging$`next`)
      }
    }
  }
}
tmp_like = c(tmp_like,dda)
lapply(tmp_like, write, "fb_friends.txt", append=TRUE, ncolumns=1000)

library(tm)
library(tmcn)
library(Rwordseg)

d.corpus = Corpus(DirSource(wdname), list(language=NA))
d.corpus = tm_map(d.corpus, stripWhitespace)
d.corpus = tm_map(d.corpus, removePunctuation)
d.corpus = tm_map(d.corpus, removeWords, stopwordsCN())
d.corpus = tm_map(d.corpus, PlainTextDocument)
d.corpus = tm_map(d.corpus,function(x){gsub(" ", "", x)})  #把空白去



tdm = TermDocumentMatrix(d.corpus, control = list(wordLengths = c(2,Inf)))


library(RColorBrewer)
library(wordcloud)

m1 = as.matrix(tdm)
v = sort(rowSums(m1), decreasing = TRUE)
d = data.frame(word = names(v), freq = v)


pal2 = brewer.pal(8,"Dark2")
png("wordcloud_fb_like.png", width=60,height=30, units='in', res=300)
wordcloud(d$word[1:50], d$freq, scale=c(15,.2),min.freq=2,
          max.words=Inf, random.order=FALSE, rot.per=.15, colors=pal2)
dev.off()

四、開啟圖片

五、完成

參考:

講題分享 - 用 R 進行中文 text Mining (作者:陳嘉葳@Taiwan R User Group)