Download a URI
These functions download one or more URIs (a.k.a. URLs). It uses libcurl under the hood to perform the request and retrieve the response. There are a myriad of options that can be specified using the ... mechanism to control the creation and submission of the request and the processing of the response.
getURLContent has been added as a high-level function
like getURL and getBinaryURL but which
determines the type of the content being downloaded
by looking at the resulting HTTP header's Content-Type
field. It uses this to determine whether the bytes
are binary or "text".
The request supports any of the facilities within the
version of libcurl that was installed.
One can examine these via curlVersion.
getURLContent doesn't perform asynchronous or multiple
concurrent requests at present.
getURL(url, ..., .opts = list(),
write = basicTextGatherer(.mapUnicode = .mapUnicode),
curl = getCurlHandle(), async = length(url) > 1,
.encoding = integer(), .mapUnicode = TRUE)
getURI(url, ..., .opts = list(),
write = basicTextGatherer(.mapUnicode = .mapUnicode),
curl = getCurlHandle(), async = length(url) > 1,
.encoding = integer(), .mapUnicode = TRUE)
getURLContent(url, ..., curl = getCurlHandle(.opts = .opts), .encoding = NA,
binary = NA, .opts = list(...),
header = dynCurlReader(curl, binary = binary,
baseURL = url, isHTTP = isHTTP,
encoding = .encoding),
isHTTP = length(grep('^[[:space:]]*http', url)) > 0)url |
a string giving the URI |
... |
named values that are interpreted as CURL options governing the HTTP request. |
.opts |
a named list or |
write |
if explicitly supplied, this is a function that is called with a single argument each time the the HTTP response handler has gathered sufficient text. The argument to the function is a single string. The default argument provides both a function for cumulating this text and is then used to retrieve it as the return value for this function. |
curl |
the previously initialized CURL context/handle which can be used for multiple requests. |
async |
a logical value that determines whether the download
request should be done via asynchronous, concurrent downloading or a serial
download. This really only arises when we are trying to download
multiple URIs in a single call. There are trade-offs between
concurrent and serial downloads, essentially trading CPU cycles
for shorter elapsed times. Concurrent downloads reduce the overall
time waiting for |
.encoding |
an integer or a string that explicitly identifies the
encoding of the content that is returned by the HTTP server in its
response to our query. The possible strings are
‘UTF-8’ or ‘ISO-8859-1’
and the integers should be specified symbolically
as |
.mapUnicode |
a logical value that controls whether the resulting text is processed to map components of the form \uxxxx to their appropriate Unicode representation. |
binary |
a logical value indicating whether the caller knows
whether the resulting content is binary ( |
header |
this is made available as a parameter of the function
to allow callers to construct different readers for processing
the header and body of the (HTTP) response.
Callers specifying this will typically only adjust the
call to The caller can specify a value of |
isHTTP |
a logical value that indicates whether the request an HTTP request. This is used when determining how to process the response. |
If no value is supplied for write,
the result is the text that is the HTTP response.
(HTTP header information is included if the header option for CURL is
set to TRUE and no handler for headerfunction is supplied in
the CURL options.)
Alternatively, if a value is supplied for the write parameter,
this is returned. This allows the caller to create a handler within
the call and get it back. This avoids having to explicitly create
and assign it and then call getURL and then access the result.
Instead, the 3 steps can be inlined in a single call.
Duncan Temple Lang
Curl homepage http://curl.haxx.se
omegahatExists = url.exists("http://www.omegahat.net")
# Regular HTTP
if(omegahatExists) withAutoprint({
txt = getURL("http://www.omegahat.net/RCurl/")
# Then we could parse the result.
XML::htmlTreeParse(txt, asText = TRUE)
})
# HTTPS. First check to see that we have support compiled into
# libcurl for ssl.
if(interactive() && ("ssl" %in% names(curlVersion()$features))
&& url.exists("https://sourceforge.net/")) {
txt = tryCatch(getURL("https://sourceforge.net/"),
error = function(e) {
getURL("https://sourceforge.net/",
ssl.verifypeer = FALSE)
})
}
# Create a CURL handle that we will reuse.
if(interactive() && omegahatExists) {
curl = getCurlHandle()
pages = list()
for(u in c("http://www.omegahat.net/RCurl/index.html",
"http://www.omegahat.net/RGtk/index.html")) {
pages[[u]] = getURL(u, curl = curl)
}
}
# Set additional fields in the header of the HTTP request.
# verbose option allows us to see that they were included.
if(omegahatExists)
getURL("http://www.omegahat.net", httpheader = c(Accept = "text/html",
MyField = "Duncan"),
verbose = TRUE)
# Arrange to read the header of the response from the HTTP server as
# a separate "stream". Then we can break it into name-value
# pairs. (The first line is the HTTP/1.1 200 Ok or 301 Moved Permanently
# status line)
if(omegahatExists) withAutoprint({
h = basicTextGatherer()
txt = getURL("http://www.omegahat.net/RCurl/index.html",
header= TRUE, headerfunction = h$update,
httpheader = c(Accept="text/html", Test=1), verbose = TRUE)
print(paste(h$value(NULL)[-1], collapse=""))
con <- textConnection(paste(h$value(NULL)[-1], collapse=""))
read.dcf(con)
close(con)
})
# Test the passwords.
if(omegahatExists) withAutoprint({
x = getURL("http://www.omegahat.net/RCurl/testPassword/index.html", userpwd = "bob:duncantl")
# Catch an error because no authorization
# We catch the generic HTTPError, but we could catch the more specific "Unauthorized" error
# type.
x = tryCatch(getURLContent("http://www.omegahat.net/RCurl/testPassword/index.html"),
HTTPError = function(e) {
cat("HTTP error: ", e$message, "\n")
})
})
## Not run:
# Needs specific information from the cookie file on a per user basis
# with a registration to the NY times.
x = getURL("http://www.nytimes.com",
header = TRUE, verbose = TRUE,
cookiefile = "/home/duncan/Rcookies",
netrc = TRUE,
maxredirs = as.integer(20),
netrc.file = "/home2/duncan/.netrc1",
followlocation = TRUE)
## End(Not run)
if(interactive() && omegahatExists) {
d = debugGatherer()
x = getURL("http://www.omegahat.net", debugfunction = d$update, verbose = TRUE)
d$value()
}
#############################################
# Using an option set in R
if(interactive() && omegahatExists) {
opts = curlOptions(header = TRUE, userpwd = "bob:duncantl", netrc = TRUE)
getURL("http://www.omegahat.net/RCurl/testPassword/index.html", verbose = TRUE, .opts = opts)
# Using options in the CURL handle.
h = getCurlHandle(header = TRUE, userpwd = "bob:duncantl", netrc = TRUE)
getURL("http://www.omegahat.net/RCurl/testPassword/index.html", verbose = TRUE, curl = h)
}
# Use a C routine as the reader. Currently gives a warning.
if(interactive() && omegahatExists) {
routine = getNativeSymbolInfo("R_internalWriteTest", PACKAGE = "RCurl")$address
getURL("http://www.omegahat.net/RCurl/index.html", writefunction = routine)
}
# Example
if(interactive() && omegahatExists) {
uris = c("http://www.omegahat.net/RCurl/index.html",
"http://www.omegahat.net/RCurl/philosophy.xml")
txt = getURI(uris)
names(txt)
nchar(txt)
txt = getURI(uris, async = FALSE)
names(txt)
nchar(txt)
routine = getNativeSymbolInfo("R_internalWriteTest", PACKAGE = "RCurl")$address
txt = getURI(uris, write = routine, async = FALSE)
names(txt)
nchar(txt)
# getURLContent() for text and binary
x = getURLContent("http://www.omegahat.net/RCurl/index.html")
class(x)
x = getURLContent("http://www.omegahat.net/RCurl/data.gz")
class(x)
attr(x, "Content-Type")
x = getURLContent("http://www.omegahat.net/Rcartogram/demo.jpg")
class(x)
attr(x, "Content-Type")
curl = getCurlHandle()
dd = getURLContent("http://www.omegahat.net/RJSONIO/RJSONIO.pdf",
curl = curl,
header = dynCurlReader(curl, binary = TRUE,
value = function(x) {
print(attributes(x))
x}))
}
# FTP
# Download the files within a directory.
if(interactive() && url.exists('ftp://ftp.wcc.nrcs.usda.gov')) {
url = 'ftp://ftp.wcc.nrcs.usda.gov/data/snow/snow_course/table/history/idaho/'
filenames = getURL(url, ftp.use.epsv = FALSE, dirlistonly = TRUE)
# Deal with newlines as \n or \r\n. (BDR)
# Or alternatively, instruct libcurl to change \n's to \r\n's for us with crlf = TRUE
# filenames = getURL(url, ftp.use.epsv = FALSE, ftplistonly = TRUE, crlf = TRUE)
filenames = paste(url, strsplit(filenames, "\r*\n")[[1]], sep = "")
con = getCurlHandle( ftp.use.epsv = FALSE)
# there is a slight possibility that some of the files that are
# returned in the directory listing and in filenames will disappear
# when we go back to get them. So we use a try() in the call getURL.
contents = sapply(filenames[1:5], function(x) try(getURL(x, curl = con)))
names(contents) = filenames[1:length(contents)]
}Please choose more modern alternatives, such as Google Chrome or Mozilla Firefox.