인프런 커뮤니티 질문&답변

Error in which(str_detect(b, "id=\"newEndContents\">")):which(str_detect(b,  : 

  argument of length 0

위 에러 메세지가 발생하는데 무엇인지 못찾겠네요. 아래는 코드 입니다. 

final_data <-NULL

i<-1

j<-1

for(j in 1:5) {

  

for(i in 1:2) {

  date<-Sys.Date()-j

  date2<-gsub("-","",date)

url <- paste0("https://sports.news.naver.com/kbaseball/news/list?isphoto=N&date=",date2,"&page=", i)

b<-readLines(url, encoding = "utf-8")

library(RJSONIO)

b2<-fromJSON(b)

b2$list[[1]]

a1<-sapply(b2$list, function(x){x$oid})

a2<-sapply(b2$list, function(x){x$aid})

a3<-sapply(b2$list, function(x){x$title})

final_data<-rbind(final_data,cbind(a1, a2, a3))

cat("\n", date2, "-", i, "데이터 수집 중" )

}

}

setwd("/Users/??/Workspace/R/Projects/CrawlingPro/05")

write.csv(final_data, "baseball_news.csv", row.names = F)

final_data[,1]

final_data[,2]

con_url<-paste0("https://sports.news.naver.com/news?oid=", final_data[,1], "&aid=", final_data[,2])

library(stringr)

con_url

k<-1

con<-c()

for (k in 1:length(con_url)) {

  b<-readLines(con_url[k], encoding="utf-8")

  b2<-b[which(str_detect(b, "id=\"newEndContents\">")):which(str_detect(b, "news_end_btn"))]

  b3<-paste(b2, collapse = " ")

  b3

  b3<-gsub("<.*?>", "",b3)

  b3<-gsub("\t|&gt;|&#160;|&lt;", "",b3)

  

  con[k] <- b3

  cat("\n", k)  

}

baseball_data<-cbind(final_data, con)

colnames(baseball_data) <- c("oid", "aid", "head", "cont")

write.csv(baseball_data, "baseball.csv", row.names=F)