Add onion location parsing

author: Rasmus Dahlberg <rasmus@rgdd.se> 2023-03-23 19:33:21 +0100
committer: Rasmus Dahlberg <rasmus@rgdd.se> 2023-03-23 19:33:21 +0100
commit: cdfc220d5df547bc4fbe3157ddfa22c614eb737c (patch)
tree: 61134d9edc0d810f227ef60a9dbbe8357159ea7d
parent: 4bce91550ecf8d426862590dae011298f9e30454 (diff)
4 files changed, 358 insertions, 0 deletions
diff --git a/go.mod b/go.mod
new file mode 100644
index 0000000..ea65ea5
--- /dev/null
+++ b/go.mod
@@ -0,0 +1,5 @@
+module git.cs.kau.se/rasmoste/find-onion
+
+go 1.19
+
+require golang.org/x/net v0.8.0 // indirect
diff --git a/go.sum b/go.sum
new file mode 100644
index 0000000..6c4f79e
--- /dev/null
+++ b/go.sum
@@ -0,0 +1,2 @@
+golang.org/x/net v0.8.0 h1:Zrh2ngAOFYneWTAIAPethzeaQLuHwhuBkuV6ZiRnUaQ=
+golang.org/x/net v0.8.0/go.mod h1:QVkue5JL9kW//ek3r6jTKnTFis1tRmNAW2P1shuFdJc=
diff --git a/internal/onionloc/onionloc.go b/internal/onionloc/onionloc.go
new file mode 100644
index 0000000..63e512a
--- /dev/null
+++ b/internal/onionloc/onionloc.go
@@ -0,0 +1,74 @@
+package onionloc
+
+import (
+	"net/http"
+	"strings"
+
+	"golang.org/x/net/html"
+)
+
+const (
+	HTTPHeaderName = "Onion-Location"
+)
+
+func HTTP(rsp *http.Response) (string, bool) {
+	v, ok := rsp.Header[HTTPHeaderName]
+	if !ok {
+		return "", false
+	}
+	if len(v) != 1 {
+		return "", false
+	}
+	return v[0], true
+}
+
+func HTML(rsp *http.Response) (string, bool) {
+	z := html.NewTokenizer(rsp.Body)
+	for {
+		tt := z.Next()
+		if tt == html.ErrorToken {
+			return "", false // EOF and other errors
+		}
+
+		switch tt {
+		case html.StartTagToken, html.SelfClosingTagToken:
+			t := z.Token()
+
+			// Looking for the html meta tag, see:
+			// https://www.w3schools.com/tags/tag_meta.asp
+			//
+			// We expect two attributes: "key" and "content"
+			if strings.ToLower(t.Data) != "meta" {
+				break
+			}
+			if len(t.Attr) != 2 {
+				break
+			}
+
+			// We're looking for the "http-equiv" key, see:
+			// https://www.w3schools.com/tags/att_meta_http_equiv.asp
+			//
+			// In particular with the value "onion-location", see:
+			// https://community.torproject.org/onion-services/advanced/onion-location/
+			//
+			// If we have all this and a following content
+			// attribute, that is the Onion-Location URL that this
+			// page advertises.  We make no attempt to validate
+			// whether the content value is really an onion address.
+			attr := t.Attr[0]
+			if strings.ToLower(attr.Key) != "http-equiv" {
+				break
+			}
+			if strings.ToLower(attr.Val) != "onion-location" {
+				break
+			}
+			attr = t.Attr[1]
+			if strings.ToLower(attr.Key) != "content" {
+				break
+			}
+
+			return attr.Val, true
+		default:
+		}
+	}
+}
diff --git a/internal/onionloc/onionloc_test.go b/internal/onionloc/onionloc_test.go
new file mode 100644
index 0000000..4d20876
--- /dev/null
+++ b/internal/onionloc/onionloc_test.go
@@ -0,0 +1,277 @@
+package onionloc
+
+import (
+	"io"
+	"net/http"
+	"strings"
+	"testing"
+)
+
+func TestHTML(t *testing.T) {
+	for _, table := range []struct {
+		desc string
+		html string
+		want string
+	}{
+		{"onion location set", htmlNoOnionLocation, ""},
+		{"onion location unset", htmlOnionLocation, htmlOnionLocationValue},
+	} {
+		var r http.Response
+		r.Body = io.NopCloser(strings.NewReader(table.html))
+
+		v, ok := HTML(&r)
+		if got, want := ok, table.want != ""; got != want {
+			t.Errorf("%s: got ok %v but wanted %v", table.desc, got, want)
+			continue
+		}
+		if !ok {
+			continue
+		}
+		if got, want := v, table.want; got != want {
+			t.Errorf("%s: got %s but wanted %s", table.desc, got, want)
+		}
+	}
+}
+
+// curl -s https://www.rgdd.se/
+const htmlNoOnionLocation = `<!DOCTYPE html>
+<html lang=""><head>
+	<meta name="generator" content="Hugo 0.105.0">
+    <meta charset="utf-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1, shrink-to-fit=no">
+
+    <title>rgdd.se</title>
+    <meta name="description" content="A simple monospaced resume theme for Hugo.">
+    <meta name="author" content='Rasmus Dahlberg'>
+
+    <link rel="stylesheet" href="/cdnjs/bootstrap.min.css">
+    <link rel="stylesheet" href="/cdnjs/all.min.css">
+    <link rel="stylesheet" href="/fontawesome/all.css">
+
+    
+    <link rel="stylesheet" href="/sass/researcher.min.css">
+
+    
+
+    <link rel="alternate" type="application/rss+xml" href="https://www.rgdd.se/index.xml" title="rgdd.se" />
+    
+        
+    
+</head>
+
+    <body><div class="container mt-5">
+    <nav class="navbar navbar-expand-sm flex-column flex-sm-row text-nowrap p-0">
+        <a class="navbar-brand mx-0 mr-sm-auto" href="https://www.rgdd.se" title="rgdd.se">
+          
+          rgdd.se
+        </a>
+        <div class="navbar-nav flex-row flex-wrap justify-content-center">
+            
+                
+                
+                    <a class="nav-item nav-link" href="/post" title="Blog">
+                        Blog
+                    </a>
+                    
+                
+            
+        </div>
+    </nav>
+</div>
+<hr>
+<div id="content">
+<div class="container">
+    <figure class="avatar"><img src="img/author.jpg"
+         alt="avatar"/>
+</figure>
+
+<p>PhD student at <a href="https://www.kau.se/en/">Karlstad University</a>.  Software engineer at <a href="https://www.glasklarteknik.se/">Glasklar Teknik</a>.
+I am passionate about transparency logs, anonymity networks, and Linux.  I have
+a keen interest for the overlap between research, engineering, and operations.
+Off-work I cook, walk, socialize, lift weights, and spoil my cat.</p>
+<h1 id="project-involvement">Project involvement</h1>
+<p>I am a core member of the following projects:</p>
+<ul>
+<li><a href="https://www.sigsum.org/">Sigsum</a>: a free and open source software project that makes a signer&rsquo;s
+key-usage transparent.  It can be used as a building block to secure the
+supply chain and more.</li>
+<li><a href="https://www.system-transparency.org/">System Transparency</a>: an open source project that provides a security
+architecture for bare metal servers.  A system&rsquo;s entire boot chain becomes
+protected and auditable.</li>
+<li><a href="https://www.torproject.org/">Tor</a>: a 501(c)(3) US nonprofit that advance human rights and defend online
+privacy through free software and open networks.</li>
+</ul>
+<h1 id="selected-publications">Selected publications</h1>
+<ul>
+<li>Rasmus Dahlberg, Tobias Pulls.
+<a href="https://www.usenix.org/conference/usenixsecurity23/presentation/dahlberg">Timeless Timing Attacks and Preload Defenses in Tor&rsquo;s DNS Cache</a>.
+USENIX Security (2023)</li>
+<li>Rasmus Dahlberg, Tobias Pulls, Tom Ritter, and Paul Syverson.
+<a href="https://petsymposium.org/2021/files/papers/issue2/popets-2021-0024.pdf">Privacy-Preserving &amp; Incrementally-Deployable Support for Certificate Transparency in Tor</a>.
+PETS (2021)</li>
+<li>Tobias Pulls and Rasmus Dahlberg.
+<a href="https://petsymposium.org/2020/files/papers/issue1/popets-2020-0013.pdf">Website Fingerprinting with Website Oracles</a>.
+PETS (2020)</li>
+<li>Rasmus Dahlberg, Tobias Pulls, Jonathan Vestin, Toke Høiland-Jørgensen, and Andreas Kassler.
+<a href="https://arxiv.org/pdf/1806.08817.pdf">Aggregation-Based Certificate Transparency Gossip</a>.
+SECUREWARE (2019)</li>
+<li>Tobias Pulls and Rasmus Dahlberg.
+<a href="https://eprint.iacr.org/2018/737.pdf">Steady: A Simple End-to-End Secure Logging System</a>.
+NordSec (2018)</li>
+</ul>
+<h1 id="contact">Contact</h1>
+<p>Feel free to reach out on email or other platforms as you see fit.</p>
+
+</div>
+
+        </div><div id="footer" class="mb-5">
+    <hr>
+    
+    <div class="container text-center">
+        
+            <a href="https://www.instagram.com/__rgdd" class="fab fa-instagram fa-1x" title="Instagram"></a>
+        
+            <a href="https://mastodon.social/@rgdd" class="fab fa-mastodon fa-1x" title="Mastodon"></a>
+        
+            <a href="https://github.com/rgdd" class="fab fa-github fa-1x" title="GitHub"></a>
+        
+            <a href="https://gitlab.torproject.org/rgdd" class="fab fa-gitlab fa-1x" title="GitLab"></a>
+        
+            <a href="https://git.glasklar.is/rgdd" class="fab fa-gitlab fa-1x" title="GitLab"></a>
+        
+            <a href="mailto:rasmus@rgdd.se" class="fas fa-envelope fa-1x" title="E-mail"></a>
+        
+    </div>
+    
+    
+        <div class="container text-center">
+            <a href="http://cyigahm4clwlimo6mfl4yjie5fwfbhlbuag57xo3kimk6invht6ffrad.onion" title="cyigahm4clwlimo6mfl4yjie5fwfbhlbuag57xo3kimk6invht6ffrad.onion"><small>cyigahm4clwlimo6mfl4yjie5fwfbhlbuag57xo3kimk6invht6ffrad.onion</small></a>
+        </div>
+    
+</div>
+</body>
+</html>`
+
+const htmlOnionLocationValue = "http://cyigahm4clwlimo6mfl4yjie5fwfbhlbuag57xo3kimk6invht6ffrad.onion/"
+
+// curl -s https://www.rgdd.se/
+// then add <meta http-equiv="onion-location" content="http://cyigahm4clwlimo6mfl4yjie5fwfbhlbuag57xo3kimk6invht6ffrad.onion/" />
+// somewhere in the head portion
+const htmlOnionLocation = `<!DOCTYPE html>
+<html lang=""><head>
+	<meta name="generator" content="Hugo 0.105.0">
+    <meta charset="utf-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1, shrink-to-fit=no">
+
+    <title>rgdd.se</title>
+    <meta name="description" content="A simple monospaced resume theme for Hugo.">
+    <meta name="author" content='Rasmus Dahlberg'>
+    <meta http-equiv="onion-location" content="http://cyigahm4clwlimo6mfl4yjie5fwfbhlbuag57xo3kimk6invht6ffrad.onion/" />
+
+    <link rel="stylesheet" href="/cdnjs/bootstrap.min.css">
+    <link rel="stylesheet" href="/cdnjs/all.min.css">
+    <link rel="stylesheet" href="/fontawesome/all.css">
+
+    
+    <link rel="stylesheet" href="/sass/researcher.min.css">
+
+    
+
+    <link rel="alternate" type="application/rss+xml" href="https://www.rgdd.se/index.xml" title="rgdd.se" />
+    
+        
+    
+</head>
+
+    <body><div class="container mt-5">
+    <nav class="navbar navbar-expand-sm flex-column flex-sm-row text-nowrap p-0">
+        <a class="navbar-brand mx-0 mr-sm-auto" href="https://www.rgdd.se" title="rgdd.se">
+          
+          rgdd.se
+        </a>
+        <div class="navbar-nav flex-row flex-wrap justify-content-center">
+            
+                
+                
+                    <a class="nav-item nav-link" href="/post" title="Blog">
+                        Blog
+                    </a>
+                    
+                
+            
+        </div>
+    </nav>
+</div>
+<hr>
+<div id="content">
+<div class="container">
+    <figure class="avatar"><img src="img/author.jpg"
+         alt="avatar"/>
+</figure>
+
+<p>PhD student at <a href="https://www.kau.se/en/">Karlstad University</a>.  Software engineer at <a href="https://www.glasklarteknik.se/">Glasklar Teknik</a>.
+I am passionate about transparency logs, anonymity networks, and Linux.  I have
+a keen interest for the overlap between research, engineering, and operations.
+Off-work I cook, walk, socialize, lift weights, and spoil my cat.</p>
+<h1 id="project-involvement">Project involvement</h1>
+<p>I am a core member of the following projects:</p>
+<ul>
+<li><a href="https://www.sigsum.org/">Sigsum</a>: a free and open source software project that makes a signer&rsquo;s
+key-usage transparent.  It can be used as a building block to secure the
+supply chain and more.</li>
+<li><a href="https://www.system-transparency.org/">System Transparency</a>: an open source project that provides a security
+architecture for bare metal servers.  A system&rsquo;s entire boot chain becomes
+protected and auditable.</li>
+<li><a href="https://www.torproject.org/">Tor</a>: a 501(c)(3) US nonprofit that advance human rights and defend online
+privacy through free software and open networks.</li>
+</ul>
+<h1 id="selected-publications">Selected publications</h1>
+<ul>
+<li>Rasmus Dahlberg, Tobias Pulls.
+<a href="https://www.usenix.org/conference/usenixsecurity23/presentation/dahlberg">Timeless Timing Attacks and Preload Defenses in Tor&rsquo;s DNS Cache</a>.
+USENIX Security (2023)</li>
+<li>Rasmus Dahlberg, Tobias Pulls, Tom Ritter, and Paul Syverson.
+<a href="https://petsymposium.org/2021/files/papers/issue2/popets-2021-0024.pdf">Privacy-Preserving &amp; Incrementally-Deployable Support for Certificate Transparency in Tor</a>.
+PETS (2021)</li>
+<li>Tobias Pulls and Rasmus Dahlberg.
+<a href="https://petsymposium.org/2020/files/papers/issue1/popets-2020-0013.pdf">Website Fingerprinting with Website Oracles</a>.
+PETS (2020)</li>
+<li>Rasmus Dahlberg, Tobias Pulls, Jonathan Vestin, Toke Høiland-Jørgensen, and Andreas Kassler.
+<a href="https://arxiv.org/pdf/1806.08817.pdf">Aggregation-Based Certificate Transparency Gossip</a>.
+SECUREWARE (2019)</li>
+<li>Tobias Pulls and Rasmus Dahlberg.
+<a href="https://eprint.iacr.org/2018/737.pdf">Steady: A Simple End-to-End Secure Logging System</a>.
+NordSec (2018)</li>
+</ul>
+<h1 id="contact">Contact</h1>
+<p>Feel free to reach out on email or other platforms as you see fit.</p>
+
+</div>
+
+        </div><div id="footer" class="mb-5">
+    <hr>
+    
+    <div class="container text-center">
+        
+            <a href="https://www.instagram.com/__rgdd" class="fab fa-instagram fa-1x" title="Instagram"></a>
+        
+            <a href="https://mastodon.social/@rgdd" class="fab fa-mastodon fa-1x" title="Mastodon"></a>
+        
+            <a href="https://github.com/rgdd" class="fab fa-github fa-1x" title="GitHub"></a>
+        
+            <a href="https://gitlab.torproject.org/rgdd" class="fab fa-gitlab fa-1x" title="GitLab"></a>
+        
+            <a href="https://git.glasklar.is/rgdd" class="fab fa-gitlab fa-1x" title="GitLab"></a>
+        
+            <a href="mailto:rasmus@rgdd.se" class="fas fa-envelope fa-1x" title="E-mail"></a>
+        
+    </div>
+    
+    
+        <div class="container text-center">
+            <a href="http://cyigahm4clwlimo6mfl4yjie5fwfbhlbuag57xo3kimk6invht6ffrad.onion" title="cyigahm4clwlimo6mfl4yjie5fwfbhlbuag57xo3kimk6invht6ffrad.onion"><small>cyigahm4clwlimo6mfl4yjie5fwfbhlbuag57xo3kimk6invht6ffrad.onion</small></a>
+        </div>
+    
+</div>
+</body>
+</html>`
author	Rasmus Dahlberg <rasmus@rgdd.se>	2023-03-23 19:33:21 +0100
committer	Rasmus Dahlberg <rasmus@rgdd.se>	2023-03-23 19:33:21 +0100
commit	cdfc220d5df547bc4fbe3157ddfa22c614eb737c (patch)
tree	61134d9edc0d810f227ef60a9dbbe8357159ea7d
parent	4bce91550ecf8d426862590dae011298f9e30454 (diff)