rvest html_table() 产生错误

Question

我正在尝试从 https://finance.yahoo.com/screener/predefined/small_cap_gainers?offset=0&count=100

获取 table

require('rvest')

url <- 'https://finance.yahoo.com/screener/predefined/small_cap_gainers?offset=0&count=100'
TABLA <- read_html(url)
TABLA %>% html_nodes(xpath='//*[@id="scr-res-table"]/div[1]/table') %>% `[[`(1) %>% html_table(fill = TRUE)

这会产生以下错误： Error in if (length(p) > 1 & maxp * n != sum(unlist(nrows)) & maxp * n != : missing value where TRUE/FALSE needed

我尝试了以下 link：

但我似乎无法弄清楚。

Answer 1

问题是 html_table 试图读取 table 单元格的 colspan 属性，但它们在您的网页中被设置为空字符串。这可以通过更改 html_table 函数来解决：

html_table_fix <- function(x, header = NA, trim = TRUE,
                                fill = FALSE, dec = ".") {

  stopifnot(html_name(x) == "table")

  # Throw error if any rowspan/colspan present
  rows <- html_nodes(x, "tr")
  n <- length(rows)
  cells <- lapply(rows, "html_nodes", xpath = ".//td|.//th")

  ncols <- lapply(cells, html_attr, "colspan", default = "1")
  # Replace empty values of colspan with "1"
  ncols <- lapply(ncols, function(x) {x[x==""] <- "1"; x})
  ncols <- lapply(ncols, as.integer)
  nrows <- lapply(cells, html_attr, "rowspan", default = "1")
  nrows <- lapply(nrows, as.integer)

  p <- unique(vapply(ncols, sum, integer(1)))
  maxp <- max(p)

  if (length(p) > 1 & maxp * n != sum(unlist(nrows)) &
      maxp * n != sum(unlist(ncols))) {
    # then malformed table is not parsable by smart filling solution
    if (!fill) { # fill must then be specified to allow filling with NAs
      stop("Table has inconsistent number of columns. ",
           "Do you want fill = TRUE?", call. = FALSE)
    }
  }

  values <- lapply(cells, html_text, trim = trim)
  out <- matrix(NA_character_, nrow = n, ncol = maxp)

  # fill colspans right with repetition
  for (i in seq_len(n)) {
    row <- values[[i]]
    ncol <- ncols[[i]]
    col <- 1
    for (j in seq_len(length(ncol))) {
      out[i, col:(col+ncol[j]-1)] <- row[[j]]
      col <- col + ncol[j]
    }
  }

  # fill rowspans down with repetition
  for (i in seq_len(maxp)) {
    for (j in seq_len(n)) {
      rowspan <- nrows[[j]][i]; colspan <- ncols[[j]][i]
      if (!is.na(rowspan) & (rowspan > 1)) {
        if (!is.na(colspan) & (colspan > 1)) {
          # special case of colspan and rowspan in same cell
          nrows[[j]] <- c(utils::head(nrows[[j]], i),
                          rep(rowspan, colspan-1),
                          utils::tail(nrows[[j]], length(rowspan)-(i+1)))
          rowspan <- nrows[[j]][i]
        }
        for (k in seq_len(rowspan - 1)) {
          l <- utils::head(out[j+k, ], i-1)
          r <- utils::tail(out[j+k, ], maxp-i+1)
          out[j + k, ] <- utils::head(c(l, out[j, i], r), maxp)
        }
      }
    }
  }

  if (is.na(header)) {
    header <- all(html_name(cells[[1]]) == "th")
  }
  if (header) {
    col_names <- out[1, , drop = FALSE]
    out <- out[-1, , drop = FALSE]
  } else {
    col_names <- paste0("X", seq_len(ncol(out)))
  }

  # Convert matrix to list to data frame
  df <- lapply(seq_len(maxp), function(i) {
    utils::type.convert(out[, i], as.is = TRUE, dec = dec)
  })
  names(df) <- col_names
  class(df) <- "data.frame"
  attr(df, "row.names") <- .set_row_names(length(df[[1]]))

  if (length(unique(col_names)) < length(col_names)) {
    warning('At least two columns have the same name')
  }

  df
}

这只是原始实现的副本，但添加了行 ncols <- lapply(ncols, function(x) {x[x==""] <- "1"; x})，它将这些空字符串设置为字符串 "1".

rvest html_table() 产生错误

rvest html_table() produces errors

r

rvest