네이버 실시간 검색어 크롤링하기

먼저 크롬을 열고 네이버데이터랩으로 이동!

remDr$open()
url='https://datalab.naver.com/keyword/realtimeList.naver?where=main'
remDr$navigate(url)

source를 가져온 후 text로 변환

html <- remDr$getPageSource()[[1]] 
html <- read_html(html)
sWords <- html %>% html_nodes("div.rank_inner") %>% html_text()

str_split을 통해 분리
sWords=str_split(sWords,'\n')

n=length(sWords)

단어를 클랜징
sWords2=gsub(' ','',sWords[[i]])
sWords2=sWords2[nchar(sWords2)!=0]

제목 추출
title=sWords2[1]
sWords2=sWords2[-1]

df에 데이터프래임 생성

(옵션에 stringsAsFactors=F를 주면,마지막에 정렬해주지 않아도 된다.)

df=data.frame(rank=sWords2[seq(1,length(sWords2),2)],sWords2[seq(2,length(sWords2),2)])
colnames(df)=c('rank',title)
data=df

반복

for(i in 2:n){
sWords2=gsub(' ','',sWords[[i]])
sWords2=sWords2[nchar(sWords2)!=0]
title=sWords2[1]
sWords2=sWords2[-1]
df=data.frame(rank=sWords2[seq(1,length(sWords2),2)],sWords2[seq(2,length(sWords2),2)])
colnames(df)=c('rank',title)
data=merge(data,df,by='rank')
}

data$rank=as.numeric(data$rank)
data[order(data$rank),]
data

remDr$close()

 

전체 코드

remDr$open()
url='https://datalab.naver.com/keyword/realtimeList.naver?where=main'
remDr$navigate(url)

html <- remDr$getPageSource()[[1]] 
html <- read_html(html)
sWords <- html %>% html_nodes("div.rank_inner") %>% html_text()
sWords=str_split(sWords,'\n')

n=length(sWords)

sWords2=gsub(' ','',sWords[[i]])
sWords2=sWords2[nchar(sWords2)!=0]
title=sWords2[1]
sWords2=sWords2[-1]
df=data.frame(rank=sWords2[seq(1,length(sWords2),2)],sWords2[seq(2,length(sWords2),2)])
colnames(df)=c('rank',title)
data=df

for(i in 2:n){
sWords2=gsub(' ','',sWords[[i]])
sWords2=sWords2[nchar(sWords2)!=0]
title=sWords2[1]
sWords2=sWords2[-1]
df=data.frame(rank=sWords2[seq(1,length(sWords2),2)],sWords2[seq(2,length(sWords2),2)])
colnames(df)=c('rank',title)
data=merge(data,df,by='rank')
}
data$rank=as.numeric(data$rank)
data[order(data$rank),]
data