179 lines
7.0 KiB
Groff
179 lines
7.0 KiB
Groff
.\" **************************************************************************
|
|
.\" * _ _ ____ _
|
|
.\" * Project ___| | | | _ \| |
|
|
.\" * / __| | | | |_) | |
|
|
.\" * | (__| |_| | _ <| |___
|
|
.\" * \___|\___/|_| \_\_____|
|
|
.\" *
|
|
.\" * Copyright (C) Daniel Stenberg, <daniel@haxx.se>, et al.
|
|
.\" *
|
|
.\" * This software is licensed as described in the file COPYING, which
|
|
.\" * you should have received as part of this distribution. The terms
|
|
.\" * are also available at https://curl.se/docs/copyright.html.
|
|
.\" *
|
|
.\" * You may opt to use, copy, modify, merge, publish, distribute and/or sell
|
|
.\" * copies of the Software, and permit persons to whom the Software is
|
|
.\" * furnished to do so, under the terms of the COPYING file.
|
|
.\" *
|
|
.\" * This software is distributed on an "AS IS" basis, WITHOUT WARRANTY OF ANY
|
|
.\" * KIND, either express or implied.
|
|
.\" *
|
|
.\" * SPDX-License-Identifier: curl
|
|
.\" *
|
|
.\" **************************************************************************
|
|
.TH curl_url_get 3 "6 Aug 2018" "libcurl" "libcurl"
|
|
.SH NAME
|
|
curl_url_get - extract a part from a URL
|
|
.SH SYNOPSIS
|
|
.nf
|
|
#include <curl/curl.h>
|
|
|
|
CURLUcode curl_url_get(const CURLU *url,
|
|
CURLUPart part,
|
|
char **content,
|
|
unsigned int flags);
|
|
.fi
|
|
.SH DESCRIPTION
|
|
Given a \fIurl\fP handle of a URL object, this function extracts an individual
|
|
piece or the full URL from it.
|
|
|
|
The \fIpart\fP argument specifies which part to extract (see list below) and
|
|
\fIcontent\fP points to a 'char *' to get updated to point to a newly
|
|
allocated string with the contents.
|
|
|
|
The \fIflags\fP argument is a bitmask with individual features.
|
|
|
|
The returned content pointer must be freed with \fIcurl_free(3)\fP after use.
|
|
.SH FLAGS
|
|
The flags argument is zero, one or more bits set in a bitmask.
|
|
.IP CURLU_DEFAULT_PORT
|
|
If the handle has no port stored, this option makes \fIcurl_url_get(3)\fP
|
|
return the default port for the used scheme.
|
|
.IP CURLU_DEFAULT_SCHEME
|
|
If the handle has no scheme stored, this option makes \fIcurl_url_get(3)\fP
|
|
return the default scheme instead of error.
|
|
.IP CURLU_NO_DEFAULT_PORT
|
|
Instructs \fIcurl_url_get(3)\fP to not return a port number if it matches the
|
|
default port for the scheme.
|
|
.IP CURLU_URLDECODE
|
|
Asks \fIcurl_url_get(3)\fP to URL decode the contents before returning it. It
|
|
does not decode the scheme, the port number or the full URL.
|
|
|
|
The query component also gets plus-to-space conversion as a bonus when this
|
|
bit is set.
|
|
|
|
Note that this URL decoding is charset unaware and you get a zero terminated
|
|
string back with data that could be intended for a particular encoding.
|
|
|
|
If there are byte values lower than 32 in the decoded string, the get
|
|
operation returns an error instead.
|
|
.IP CURLU_URLENCODE
|
|
If set, \fIcurl_url_get(3)\fP URL encodes the host name part when a full URL
|
|
is retrieved. If not set (default), libcurl returns the URL with the host name
|
|
"raw" to support IDN names to appear as-is. IDN host names are typically using
|
|
non-ASCII bytes that otherwise gets percent-encoded.
|
|
|
|
Note that even when not asking for URL encoding, the '%' (byte 37) is URL
|
|
encoded to make sure the host name remains valid.
|
|
.IP CURLU_PUNYCODE
|
|
If set and \fICURLU_URLENCODE\fP is not set, and asked to retrieve the
|
|
\fBCURLUPART_HOST\fP or \fBCURLUPART_URL\fP parts, libcurl returns the host
|
|
name in its punycode version if it contains any non-ASCII octets (and is an
|
|
IDN name).
|
|
|
|
If libcurl is built without IDN capabilities, using this bit makes
|
|
\fIcurl_url_get(3)\fP return \fICURLUE_LACKS_IDN\fP if the host name contains
|
|
anything outside the ASCII range.
|
|
|
|
(Added in curl 7.88.0)
|
|
.IP CURLU_PUNY2IDN
|
|
If set and asked to retrieve the \fBCURLUPART_HOST\fP or \fBCURLUPART_URL\fP
|
|
parts, libcurl returns the host name in its IDN (International Domain Name)
|
|
UTF-8 version if it otherwise is a punycode version. If the punycode name
|
|
cannot be converted to IDN correctly, libcurl returns
|
|
\fICURLUE_BAD_HOSTNAME\fP.
|
|
|
|
If libcurl is built without IDN capabilities, using this bit makes
|
|
\fIcurl_url_get(3)\fP return \fICURLUE_LACKS_IDN\fP if the host name is using
|
|
punycode.
|
|
|
|
(Added in curl 8.3.0)
|
|
.SH PARTS
|
|
.IP CURLUPART_URL
|
|
When asked to return the full URL, \fIcurl_url_get(3)\fP returns a normalized
|
|
and possibly cleaned up version using all available URL parts.
|
|
|
|
We advise using the \fICURLU_PUNYCODE\fP option to get the URL as "normalized"
|
|
as possible since IDN allows host names to be written in many different ways
|
|
that still end up the same punycode version.
|
|
.IP CURLUPART_SCHEME
|
|
Scheme cannot be URL decoded on get.
|
|
.IP CURLUPART_USER
|
|
.IP CURLUPART_PASSWORD
|
|
.IP CURLUPART_OPTIONS
|
|
The options field is an optional field that might follow the password in the
|
|
userinfo part. It is only recognized/used when parsing URLs for the following
|
|
schemes: pop3, smtp and imap. The URL API still allows users to set and get
|
|
this field independently of scheme when not parsing full URLs.
|
|
.IP CURLUPART_HOST
|
|
The host name. If it is an IPv6 numeric address, the zone id is not part of it
|
|
but is provided separately in \fICURLUPART_ZONEID\fP. IPv6 numerical addresses
|
|
are returned within brackets ([]).
|
|
|
|
IPv6 names are normalized when set, which should make them as short as
|
|
possible while maintaining correct syntax.
|
|
.IP CURLUPART_ZONEID
|
|
If the host name is a numeric IPv6 address, this field might also be set.
|
|
.IP CURLUPART_PORT
|
|
A port cannot be URL decoded on get. This number is returned in a string just
|
|
like all other parts. That string is guaranteed to hold a valid port number in
|
|
ASCII using base 10.
|
|
.IP CURLUPART_PATH
|
|
The \fIpart\fP is always at least a slash ('/') even if no path was supplied
|
|
in the URL. A URL path always starts with a slash.
|
|
.IP CURLUPART_QUERY
|
|
The initial question mark that denotes the beginning of the query part is a
|
|
delimiter only. It is not part of the query contents.
|
|
|
|
A not-present query returns \fIpart\fP set to NULL.
|
|
A zero-length query returns \fIpart\fP as a zero-length string.
|
|
|
|
The query part gets pluses converted to space when asked to URL decode on get
|
|
with the CURLU_URLDECODE bit.
|
|
.IP CURLUPART_FRAGMENT
|
|
The initial hash sign that denotes the beginning of the fragment is a
|
|
delimiter only. It is not part of the fragment contents.
|
|
.SH EXAMPLE
|
|
.nf
|
|
int main(void)
|
|
{
|
|
CURLUcode rc;
|
|
CURLU *url = curl_url();
|
|
rc = curl_url_set(url, CURLUPART_URL, "https://example.com", 0);
|
|
if(!rc) {
|
|
char *scheme;
|
|
rc = curl_url_get(url, CURLUPART_SCHEME, &scheme, 0);
|
|
if(!rc) {
|
|
printf("the scheme is %s\\n", scheme);
|
|
curl_free(scheme);
|
|
}
|
|
curl_url_cleanup(url);
|
|
}
|
|
}
|
|
.fi
|
|
.SH AVAILABILITY
|
|
Added in 7.62.0. CURLUPART_ZONEID was added in 7.65.0.
|
|
.SH RETURN VALUE
|
|
Returns a CURLUcode error value, which is CURLUE_OK (0) if everything went
|
|
fine. See the \fIlibcurl-errors(3)\fP man page for the full list with
|
|
descriptions.
|
|
|
|
If this function returns an error, no URL part is returned.
|
|
.SH "SEE ALSO"
|
|
.BR curl_url (3),
|
|
.BR curl_url_cleanup (3),
|
|
.BR curl_url_dup (3),
|
|
.BR curl_url_set (3),
|
|
.BR curl_url_strerror (3),
|
|
.BR CURLOPT_CURLU (3)
|