我正在尝试刮擦这张桌子 http://www.hko.gov.hk/cis/dailyExtract_e.htm?y=1999&m=1
这是我所有的尝试。他们都没有接近提取任何信息。我想念什么吗?
library("rvest")
library("tidyverse")
# METHOD 1
url <- "http://www.hko.gov.hk/cis/dailyExtract_e.htm?y=1999&m=1"
data <- url %>%
read_html() %>%
html_nodes(xpath='//*[@id="t1"]/tbody/tr[1]') %>%
html_table()
data <- data[[1]]
# METHOD 2
library(XML)
library(RCurl)
library(rlist)
theurl <- getURL("http://www.hko.gov.hk/cis/dailyExtract_e.htm?y=1999&m=1",.opts = list(ssl.verifypeer = FALSE) )
tables <- readHTMLTable(theurl)
tables <- list.clean(tables, fun = is.null, recursive = FALSE)
n.rows <- unlist(lapply(tables, function(t) dim(t)[1]))
tables[[which.max(n.rows)]]
# METHOD 3
library(htmltab)
tab <- htmltab("http://www.hko.gov.hk/cis/dailyExtract_e.htm?y=1999&m=1",
which = '//*[@id="t1"]/tbody/tr[4]',
header = '//*[@id="t1"]/tbody/tr[3]',
rm_nodata_cols = TRUE)
# METHOD 4
website <-read_html("http://www.hko.gov.hk/cis/dailyExtract_e.htm?y=1999&m=1")
scraped <- website %>%
html_nodes("table") %>%
.[(2)] %>%
html_table(fill = TRUE) %>%
`[[`(1)
# METHOD 5
getHrefs <- function(node, encoding)
if (!is.null(xmlChildren(node)$a)) {
paste(xpathSApply(node, './a', xmlGetAttr, "href"), collapse = ",")
} else {
return(xmlValue(xmlChildren(node)$text))
}
data <- ( readHTMLTable("http://www.hko.gov.hk/cis/dailyExtract_e.htm?y=1999&m=1", which = 1, elFun = getHrefs) )
预期结果应为表中的12个别名以及下面的数据