使用rvest从Yahoo finance获取基金数据

你可以拿到整张桌子,考虑一下这个

result <- html_nodes(webpage, "#quote-summary")
result <- html_nodes(result, "table") %>% html_table()

我补充道,很难弄清楚 rvest 并选择Orgadget。更聪明的人可以使用CSS选择器,但我必须使用XPATH选择器。以下是一些用于完成任务的函数。请记住,这些输出是字符,需要转换为数字。

library(rvest)

get_url <- function(sym) {
  out <- paste0("https://finance.yahoo.com/quote/", sym, "/profile?p=", sym)
}

get_name <- function(sym) {
  url <- get_url(sym)
  name <- read_html(url) %>%
    html_nodes(xpath = 
      '//*[contains(concat( " ", @class, " " ), concat( " ", "Mend(40px)", " " ))]') %>%
    html_text()
  return(name)
}

get_ratio <- function(sym) {
  url <- get_url(sym)
  out <- read_html(url) %>%
    html_nodes(xpath = 
      '//*[contains(concat( " ", @class, " " ), concat( " ", "Ta(e)", " " ))]') %>%
    html_text()
  return(out[4])
}

get_assets <- function(sym) {
  url <- get_url(sym)
  out <- read_html(url) %>%
    html_nodes(xpath = 
      '//*[contains(concat( " ", @class, " " ), concat( " ", "Fl(end)", " " ))]') %>%
    html_text()
  return(out[6])
}