Visits every Wikipedia in every language and grabs the title + subtitle.

wikipedia_multilang_subtitles.R

suppressMessages({
  # Preamble ========================================
  # ======== Web Scraping ===========================
  library(rvest) # install.packages('rvest')
  library(magrittr)
  # ======== I/O ====================================
  library(httr) # install.packages('httr')
})

html <- read_html("https://wikipedia.org")

wikipedias <- html %>%
  html_nodes('div[data-el-section="secondary links"] ul li a') %>%
  { data.frame(href = paste0("https:", html_attr(., "href")), name = html_text(.)) }

subtitles <- do.call(rbind, apply(wikipedias, 1, function(wikipedia) {
  html <- read_html(paste0(wikipedia['href'], "wiki/MediaWiki:Sitesubtitle"))
  
  title <- html %>%
    html_nodes("title") %>%
    html_text()
  
  subtitle <- html %>%
    html_nodes("#mw-content-text p") %>%
    html_text()
  
  return(data.frame(title = title, subtitle = subtitle, stringsAsFactors = FALSE))
}))

subtitles$title %<>%
  sub("MediaWiki:Sitesubtitle.{3}", "\\1", .) %>%
  sub(", .*", "", .)