From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <l.stechauner@proxmox.com>
Received: from firstgate.proxmox.com (firstgate.proxmox.com [212.224.123.68])
 (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits)
 key-exchange X25519 server-signature RSA-PSS (2048 bits))
 (No client certificate requested)
 by lists.proxmox.com (Postfix) with ESMTPS id 3EF4B72548
 for <pve-devel@lists.proxmox.com>; Tue, 15 Jun 2021 16:09:41 +0200 (CEST)
Received: from firstgate.proxmox.com (localhost [127.0.0.1])
 by firstgate.proxmox.com (Proxmox) with ESMTP id 263E22F2D6
 for <pve-devel@lists.proxmox.com>; Tue, 15 Jun 2021 16:09:11 +0200 (CEST)
Received: from proxmox-new.maurer-it.com (proxmox-new.maurer-it.com
 [94.136.29.106])
 (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits)
 key-exchange X25519 server-signature RSA-PSS (2048 bits))
 (No client certificate requested)
 by firstgate.proxmox.com (Proxmox) with ESMTPS id 2C64D2F297
 for <pve-devel@lists.proxmox.com>; Tue, 15 Jun 2021 16:09:09 +0200 (CEST)
Received: from proxmox-new.maurer-it.com (localhost.localdomain [127.0.0.1])
 by proxmox-new.maurer-it.com (Proxmox) with ESMTP id 05D4344096
 for <pve-devel@lists.proxmox.com>; Tue, 15 Jun 2021 16:09:09 +0200 (CEST)
From: Lorenz Stechauner <l.stechauner@proxmox.com>
To: pve-devel@lists.proxmox.com
Date: Tue, 15 Jun 2021 16:08:37 +0200
Message-Id: <20210615140841.117933-5-l.stechauner@proxmox.com>
X-Mailer: git-send-email 2.20.1
In-Reply-To: <20210615140841.117933-1-l.stechauner@proxmox.com>
References: <20210615140841.117933-1-l.stechauner@proxmox.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
X-SPAM-LEVEL: Spam detection results:  0
 AWL 0.947 Adjusted score from AWL reputation of From: address
 BAYES_00                 -1.9 Bayes spam probability is 0 to 1%
 KAM_DMARC_STATUS 0.01 Test Rule for DKIM or SPF Failure with Strict Alignment
 SPF_HELO_NONE           0.001 SPF: HELO does not publish an SPF Record
 SPF_PASS               -0.001 SPF: sender matches SPF record
 URIBL_BLOCKED 0.001 ADMINISTRATOR NOTICE: The query to URIBL was blocked. See
 http://wiki.apache.org/spamassassin/DnsBlocklists#dnsbl-block for more
 information. [nodes.pm]
Subject: [pve-devel] [PATCH v8 manager 1/5] api: nodes: add
 query_url_metadata method
X-BeenThere: pve-devel@lists.proxmox.com
X-Mailman-Version: 2.1.29
Precedence: list
List-Id: Proxmox VE development discussion <pve-devel.lists.proxmox.com>
List-Unsubscribe: <https://lists.proxmox.com/cgi-bin/mailman/options/pve-devel>, 
 <mailto:pve-devel-request@lists.proxmox.com?subject=unsubscribe>
List-Archive: <http://lists.proxmox.com/pipermail/pve-devel/>
List-Post: <mailto:pve-devel@lists.proxmox.com>
List-Help: <mailto:pve-devel-request@lists.proxmox.com?subject=help>
List-Subscribe: <https://lists.proxmox.com/cgi-bin/mailman/listinfo/pve-devel>, 
 <mailto:pve-devel-request@lists.proxmox.com?subject=subscribe>
X-List-Received-Date: Tue, 15 Jun 2021 14:09:41 -0000

metadata is gained using a HEAD request.

Due to the ability of this api endpoint to request files on internal
networks (which would not be visible/accessible from outside) it is
restricted to users with permissions `Sys.Audit` and `Sys.Modify` on
`/`. Users with these permissions are able to alter node (network)
config anyway, so this should not create any further security risk.

Signed-off-by: Lorenz Stechauner <l.stechauner@proxmox.com>
---
 PVE/API2/Nodes.pm | 96 +++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 96 insertions(+)

diff --git a/PVE/API2/Nodes.pm b/PVE/API2/Nodes.pm
index e58d9c10..77fa710a 100644
--- a/PVE/API2/Nodes.pm
+++ b/PVE/API2/Nodes.pm
@@ -11,6 +11,7 @@ use JSON;
 use POSIX qw(LONG_MAX);
 use Time::Local qw(timegm_nocheck);
 use Socket;
+use IO::Socket::SSL;
 
 use PVE::API2Tools;
 use PVE::APLInfo;
@@ -238,6 +239,7 @@ __PACKAGE__->register_method ({
 	    { name => 'netstat' },
 	    { name => 'network' },
 	    { name => 'qemu' },
+	    { name => 'query-url-metadata' },
 	    { name => 'replication' },
 	    { name => 'report' },
 	    { name => 'rrd' }, # fixme: remove?
@@ -1595,6 +1597,100 @@ __PACKAGE__->register_method({
 	return $rpcenv->fork_worker('download', undef, $user, $worker);
     }});
 
+__PACKAGE__->register_method({
+    name => 'query_url_metadata',
+    path => 'query-url-metadata',
+    method => 'GET',
+    description => "Query metadata of an URL: file size, file name and mime type.",
+    proxyto => 'node',
+    permissions => {
+	check => ['perm', '/', [ 'Sys.Audit', 'Sys.Modify' ]],
+    },
+    parameters => {
+	additionalProperties => 0,
+	properties => {
+	    node => get_standard_option('pve-node'),
+	    url => {
+		description => "The URL to query the metadata from.",
+		type => 'string',
+		pattern => 'https?://.*',
+	    },
+	    'verify-certificates' => {
+		description => "If false, no SSL/TLS certificates will be verified.",
+		type => 'boolean',
+		optional => 1,
+		default => 1,
+	    }
+	},
+    },
+    returns => {
+	type => "object",
+	properties => {
+	    filename => {
+		type => 'string',
+		optional => 1,
+	    },
+	    size => {
+		type => 'integer',
+		renderer => 'bytes',
+		optional => 1,
+	    },
+	    mimetype => {
+		type => 'string',
+		optional => 1,
+	    },
+	},
+    },
+    code => sub {
+	my ($param) = @_;
+
+	my $url = $param->{url};
+
+	my $ua = LWP::UserAgent->new();
+
+	my $dccfg = PVE::Cluster::cfs_read_file('datacenter.cfg');
+	if ($dccfg->{http_proxy}) {
+	    $ua->proxy('http', $dccfg->{http_proxy});
+	}
+
+	my $verify = $param->{'verify-certificates'} // 1;
+	if (!$verify) {
+	    $ua->ssl_opts(
+		verify_hostname => 0,
+		SSL_verify_mode => IO::Socket::SSL::SSL_VERIFY_NONE,
+	    );
+	}
+
+	my $req = HTTP::Request->new(HEAD => $url);
+	my $res = $ua->request($req);
+
+	die "invalid server response: '" . $res->status_line() . "'\n" if ($res->code() != 200);
+
+	my $size = $res->header("Content-Length");
+	my $disposition = $res->header("Content-Disposition");
+	my $type = $res->header("Content-Type");
+
+	my $filename;
+
+	if ($disposition && ($disposition =~ m/filename="([^"]*)"/ || $disposition =~ m/filename=([^;]*)/)) {
+	    $filename = $1;
+	} elsif ($url =~ m!^[^?]+/([^?/]*)(?:\?.*)?$!) {
+	    $filename = $1;
+	}
+
+	# Content-Type: text/html; charset=utf-8
+	if ($type && $type =~ m/^([^;]+);/) {
+	    $type = $1;
+	}
+
+	my $ret = {};
+	$ret->{filename} = $filename if $filename;
+	$ret->{size} = $size + 0 if $size;
+	$ret->{mimetype} = $type if $type;
+
+	return $ret;
+    }});
+
 __PACKAGE__->register_method({
     name => 'report',
     path => 'report',
-- 
2.20.1