[feature] proof of work scraper deterrence (#4043)

This adds a proof-of-work based scraper deterrence to GoToSocial's middleware stack on profile and status web pages. Heavily inspired by https://github.com/TecharoHQ/anubis, but massively stripped back for our own usecase.

Todo:
- ~~add configuration option so this is disabled by default~~
- ~~fix whatever weirdness is preventing this working with CSP (even in debug)~~
- ~~use our standard templating mechanism going through apiutil helper func~~
- ~~probably some absurdly small performance improvements to be made in pooling re-used hex encode / hash encode buffers~~ the web endpoints aren't as hot a path as API / ActivityPub, will leave as-is for now as it is already very minimal and well optimized
- ~~verify the cryptographic assumptions re: using a portion of token as challenge data~~ this isn't a serious application of cryptography, if it turns out to be a problem we'll fix it, but it definitely should not be easily possible to guess a SHA256 hash from the first 1/4 of it even if mathematically it might make it a bit easier
- ~~theme / make look nice??~~
- ~~add a spinner~~
- ~~add entry in example configuration~~
- ~~add documentation~~

Verification page originally based on https://github.com/LucienV1/powtect

Co-authored-by: tobi <tobi.smethurst@protonmail.com>
Reviewed-on: https://codeberg.org/superseriousbusiness/gotosocial/pulls/4043
Reviewed-by: tobi <tsmethurst@noreply.codeberg.org>
Co-authored-by: kim <grufwub@gmail.com>
Co-committed-by: kim <grufwub@gmail.com>

5 files changed, 204 insertions, 0 deletions

diff --git a/web/source/css/nollamas.css b/web/source/css/nollamas.css
new file mode 100644
index 000000000..2f6671a62
--- /dev/null
+++ b/web/source/css/nollamas.css
@@ -0,0 +1,27 @@
+/*
+	GoToSocial
+	Copyright (C) GoToSocial Authors admin@gotosocial.org
+	SPDX-License-Identifier: AGPL-3.0-or-later
+
+	This program is free software: you can redistribute it and/or modify
+	it under the terms of the GNU Affero General Public License as published by
+	the Free Software Foundation, either version 3 of the License, or
+	(at your option) any later version.
+
+	This program is distributed in the hope that it will be useful,
+	but WITHOUT ANY WARRANTY; without even the implied warranty of
+	MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+	GNU Affero General Public License for more details.
+
+	You should have received a copy of the GNU Affero General Public License
+	along with this program.  If not, see <http://www.gnu.org/licenses/>.
+*/
+
+.nollamas {
+	display: flex;
+	flex-direction: column;
+
+	.nollamas-solving {
+		align-self: center;
+	}
+}
diff --git a/web/source/index.js b/web/source/index.js
index 6a218cd08..b9d608318 100644
--- a/web/source/index.js
+++ b/web/source/index.js
@@ -73,6 +73,24 @@ skulk({
 				["babelify", { global: true }]
 			],
 		},
+		nollamas: {
+			entryFile: "nollamas",
+			outputFile: "nollamas.js",
+			preset: ["js"],
+			prodCfg: prodCfg,
+			transform: [
+				["babelify", { global: true }]
+			],
+		},
+		nollamasworker: {
+			entryFile: "nollamasworker",
+			outputFile: "nollamasworker.js",
+			preset: ["js"],
+			prodCfg: prodCfg,
+			transform: [
+				["babelify", { global: true }]
+			],
+		},
 		settings: {
 			entryFile: "settings",
 			outputFile: "settings.js",
diff --git a/web/source/nollamas/index.js b/web/source/nollamas/index.js
new file mode 100644
index 000000000..792a5c7f5
--- /dev/null
+++ b/web/source/nollamas/index.js
@@ -0,0 +1,63 @@
+/*
+	GoToSocial
+	Copyright (C) GoToSocial Authors admin@gotosocial.org
+	SPDX-License-Identifier: AGPL-3.0-or-later
+
+	This program is free software: you can redistribute it and/or modify
+	it under the terms of the GNU Affero General Public License as published by
+	the Free Software Foundation, either version 3 of the License, or
+	(at your option) any later version.
+
+	This program is distributed in the hope that it will be useful,
+	but WITHOUT ANY WARRANTY; without even the implied warranty of
+	MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+	GNU Affero General Public License for more details.
+
+	You should have received a copy of the GNU Affero General Public License
+	along with this program.  If not, see <http://www.gnu.org/licenses/>.
+*/
+
+document.addEventListener('DOMContentLoaded', function() {
+	// Get the nollamas section container.
+	const nollamas = document.querySelector(".nollamas");
+
+	// Add some "loading" text to show that
+	// a proof-of-work captcha is being done.
+	const p = this.createElement("p");
+	p.className = "nollamas-explanation";
+	p.appendChild(document.createTextNode("Your browser is currently solving a proof-of-work challenge designed to deter \"ai\" scrapers. This should take no more than a few seconds..."));
+	nollamas.appendChild(p);
+
+	// Add a loading spinner as well if motion is allowed.
+	if (!window.matchMedia('(prefers-reduced-motion: reduce)').matches) {
+		const i = this.createElement("i");
+		i.className = "fa fa-2x fa-spin fa-refresh nollamas-solving";
+		i.setAttribute("title","Solving...");
+		nollamas.appendChild(i);
+	}
+
+	// Read the challenge and difficulty from
+	// data attributes on the nollamas section.
+	const challenge = nollamas.dataset.nollamasChallenge;
+	const difficulty = nollamas.dataset.nollamasDifficulty;
+
+	console.log('challenge:', challenge);   // eslint-disable-line no-console
+	console.log('difficulty:', difficulty); // eslint-disable-line no-console
+
+	// Prepare the worker with task function.
+	const worker = new Worker("/assets/dist/nollamasworker.js");
+	worker.postMessage({
+		challenge: challenge,
+		difficulty: difficulty,
+	});
+
+	// Set the main worker function.
+	worker.onmessage = function (e) {
+		if (e.data.done) {
+			console.log('solution found for:', e.data.nonce); // eslint-disable-line no-console
+			let url = new URL(window.location.href);
+			url.searchParams.set('nollamas_solution', e.data.nonce);
+			window.location.href = url.toString();
+		}
+	};
+});
diff --git a/web/source/nollamasworker/index.js b/web/source/nollamasworker/index.js
new file mode 100644
index 000000000..b95ec0917
--- /dev/null
+++ b/web/source/nollamasworker/index.js
@@ -0,0 +1,53 @@
+/*
+	GoToSocial
+	Copyright (C) GoToSocial Authors admin@gotosocial.org
+	SPDX-License-Identifier: AGPL-3.0-or-later
+
+	This program is free software: you can redistribute it and/or modify
+	it under the terms of the GNU Affero General Public License as published by
+	the Free Software Foundation, either version 3 of the License, or
+	(at your option) any later version.
+
+	This program is distributed in the hope that it will be useful,
+	but WITHOUT ANY WARRANTY; without even the implied warranty of
+	MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+	GNU Affero General Public License for more details.
+
+	You should have received a copy of the GNU Affero General Public License
+	along with this program.  If not, see <http://www.gnu.org/licenses/>.
+*/
+
+onmessage = async function(e) {
+	console.log('worker started'); // eslint-disable-line no-console
+
+	const challenge = e.data.challenge;
+	const textEncoder = new TextEncoder();
+
+	// Get difficulty and generate the expected
+	// zero ASCII prefix to check for in hashes.
+	const difficultyStr = e.data.difficulty;
+	const difficulty = parseInt(difficultyStr, 10);
+	const zeroPrefix = '0'.repeat(difficulty);
+
+	let nonce = 0;
+	while (true) { // eslint-disable-line no-constant-condition
+
+		// Create possible solution string from challenge + nonce.
+		const solution = textEncoder.encode(challenge + nonce.toString());
+
+		// Generate SHA256 hashsum of solution string and hex encode the result.
+		const hashBuffer = await crypto.subtle.digest('SHA-256', solution);
+		const hashArray = Array.from(new Uint8Array(hashBuffer));
+		const hashHex = hashArray.map(b => b.toString(16).padStart(2, '0')).join('');
+
+		// Check if the hex encoded hash has
+		// difficulty defined zeroes prefix.
+		if (hashHex.startsWith(zeroPrefix)) {
+			postMessage({ nonce: nonce, done: true });
+			break;
+		}
+
+		// Iter.
+		nonce++;
+	}
+};
diff --git a/web/template/nollamas.tmpl b/web/template/nollamas.tmpl
new file mode 100644
index 000000000..a02fd92f7
--- /dev/null
+++ b/web/template/nollamas.tmpl
@@ -0,0 +1,43 @@
+{{- /*
+// GoToSocial
+// Copyright (C) GoToSocial Authors admin@gotosocial.org
+// SPDX-License-Identifier: AGPL-3.0-or-later
+//
+// This program is free software: you can redistribute it and/or modify
+// it under the terms of the GNU Affero General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+//
+// This program is distributed in the hope that it will be useful,
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+// GNU Affero General Public License for more details.
+//
+// You should have received a copy of the GNU Affero General Public License
+// along with this program.  If not, see <http://www.gnu.org/licenses/>.
+*/ -}}
+
+{{- with . }}
+<main>
+    <section class="nollamas"
+        data-nollamas-challenge="{{ .challenge }}"
+        data-nollamas-difficulty="{{ .difficulty }}"
+    >
+        <h1>Checking you're not a creepy crawler...</h1>
+        <noscript>
+            <p>
+                The page you're visiting is guarded from "ai" scrapers
+                and other crawlers by a proof-of-work challenge.
+            </p>
+            <p>
+                Unfortunately, this means that Javascript is required.
+                To see the page, <b>please enable Javascript and try again</b>.
+            </p>
+            <aside>
+                Once your browser has completed the challenge, you can turn
+                Javascript off again if you like. Revalidation is done once per hour.
+            </aside>
+        </noscript>
+    </section>
+</main>
+{{- end }}
\ No newline at end of file