1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
|
library(XML)
doc = htmlTreeParse("http://finance.yahoo.com/bonds/composite_bond_rates?bypass=true", useInternalNodes = TRUE)
# Use XPath expression to find the nodes
# <div><table class="yfirttbl">..
# as these are the ones we want.
o = getNodeSet(doc, "//div/table[@class='yfirttbl']")
# Write a function that will extract the information out of a given table node.
readHTMLTable =
function(tb)
{
# get the header information.
colNames = sapply(tb[["thead"]][["tr"]]["th"], xmlValue)
vals = sapply(tb[["tbody"]]["tr"], function(x) sapply(x["td"], xmlValue))
matrix(as.numeric(vals[-1,]),
nrow = ncol(vals),
dimnames = list(vals[1,], colNames[-1]),
byrow = TRUE
)
}
# Now process each of the table nodes in the o list.
tables = lapply(o, readHTMLTable)
names(tables) = lapply(o, function(x) xmlValue(x[["caption"]]))
|
