get-news-r

get_news <- function(link1){
  page1 <- read_html(link1)
  page1 %>% html_nodes(".table")
  tables <- page1 %>% html_nodes(xpath = "//p[@class='table']")
  rubs <- tables[1] %>% html_nodes("a") %>% html_text()
  time <- tables[2] %>% html_nodes("time")
  date <- time %>% html_attr("content")
  date_unix <- time %>% html_attr("data-unix")
  time_human <- time %>% html_node("span") %>% html_text()
  diffc <- tables[3] %>% html_node(".difficult-value") %>% 
    html_text() %>% as.numeric()
  
  parts <- page1 %>% html_nodes(xpath = "//p[not(@*)]") %>% html_text()
  text <- paste(parts, collapse = " ")
  text2 <- str_split(text, "Нашли опечатку?")[[1]][1]
  text_final <- gsub("\\n", " ", text2)
  
  author <- page1 %>% html_nodes(xpath = "//meta[@name='mediator_author']") %>% 
    html_attr("content")
  atitle <- page1 %>% html_nodes(xpath = "//meta[@name='twitter:title']") %>% 
    html_attr("content")
  L <- list(title = atitle, 
            text = text_final,
            author = author,
            date = date, 
            date_unix = date_unix,
            time = time_human,
            dicciculty = diffc)
  return(L)
}