在研究文学的过程中,我真的需要删除所有来自英特尔的新闻标题。
但英特尔新闻编辑室(https://newsroom.intel.com/news-releases/)中有“更多内容”
帮帮我..
install.packages('rvest')
install.packages('RCurl')
library(rvest)
library(RCurl)
url2 <- "https://newsroom.intel.com/news-releases/#"
N_pages2 <- 1
#.post-title/.post-timestamp
A2 <- NULL
for ( j in 1: N_pages2){
EVTDT2 <- read_html(paste0(url2, j))
B2 <- cbind(EVTDT2 %>%
html_nodes(".post-title") %>%
html_text(), EVTDT2 %>%
html_nodes(".post-timestamp") %>%
html_text() )
A2 <- rbind(A2,B2)}
A2
write.csv(A2,"INT_NEWS_EVT.CSV")