go-extractor/stealth.go

package extractor

import (
	"fmt"
	"math/rand/v2"
)

// stealthChromiumArgs are launch arguments that reduce automation detection for Chromium-based browsers.
var stealthChromiumArgs = []string{
	"--disable-blink-features=AutomationControlled",
}

// stealthCommonScripts are JavaScript snippets injected before page scripts on all browser engines.
var stealthCommonScripts = []string{
	// Override navigator.webdriver to return undefined (the real-browser value).
	`Object.defineProperty(navigator, 'webdriver', {get: () => undefined})`,

	// Fix outerWidth/outerHeight which are 0 in headless mode.
	`if (window.outerWidth === 0) {
		Object.defineProperty(window, 'outerWidth',  { get: () => window.innerWidth  });
		Object.defineProperty(window, 'outerHeight', { get: () => window.innerHeight });
	}`,

	// Override navigator.permissions.query to return "denied" for notifications.
	`(function() {
		if (navigator.permissions && navigator.permissions.query) {
			const origQuery = navigator.permissions.query.bind(navigator.permissions);
			navigator.permissions.query = function(desc) {
				if (desc && desc.name === 'notifications') {
					return Promise.resolve({ state: 'denied', onchange: null });
				}
				return origQuery(desc);
			};
		}
	})()`,

	// Stub Notification constructor if missing (headless may lack it).
	`(function() {
		if (typeof Notification === 'undefined') {
			window.Notification = function() {};
			Notification.permission = 'denied';
			Notification.requestPermission = function() { return Promise.resolve('denied'); };
		}
	})()`,
}

// chromiumHWProfile holds hardware fingerprint values for a Chromium browser session.
type chromiumHWProfile struct {
	WebGLVendor   string
	WebGLRenderer string
	ConnRTT       int     // base RTT in ms (jittered ±20 per session)
	ConnDownlink  float64 // base downlink in Mbps (jittered ±2 per session)
}

// chromiumHWProfiles is a pool of realistic Chromium hardware profiles.
// Index 0 matches the original hardcoded values.
var chromiumHWProfiles = []chromiumHWProfile{
	{"Google Inc. (Intel)", "ANGLE (Intel, Intel(R) UHD Graphics 630, OpenGL 4.5)", 50, 10},
	{"Google Inc. (NVIDIA)", "ANGLE (NVIDIA, NVIDIA GeForce GTX 1660 SUPER, D3D11)", 30, 25},
	{"Google Inc. (AMD)", "ANGLE (AMD, AMD Radeon RX 580, D3D11)", 100, 5},
	{"Google Inc. (Intel)", "ANGLE (Intel, Intel(R) UHD Graphics 770, OpenGL 4.5)", 50, 10},
	{"Google Inc. (NVIDIA)", "ANGLE (NVIDIA, NVIDIA GeForce RTX 3060, D3D11)", 25, 50},
	{"Google Inc. (Intel)", "ANGLE (Intel, Intel(R) Iris Xe Graphics, D3D11)", 75, 8},
}

// randomChromiumProfile returns a randomly selected Chromium hardware profile.
func randomChromiumProfile() chromiumHWProfile {
	return chromiumHWProfiles[rand.IntN(len(chromiumHWProfiles))]
}

// buildChromiumStealthScripts returns Chromium stealth init scripts with the given hardware profile
// values templated into the WebGL and connection spoofing scripts. Connection RTT and downlink
// receive per-session jitter (±20ms RTT, ±2 Mbps downlink).
func buildChromiumStealthScripts(p chromiumHWProfile) []string {
	// Apply jitter to connection stats.
	rtt := p.ConnRTT + rand.IntN(41) - 20 // ±20ms
	if rtt < 0 {
		rtt = 0
	}
	downlink := p.ConnDownlink + (rand.Float64()*4 - 2) // ±2 Mbps
	if downlink < 0.5 {
		downlink = 0.5
	}

	return []string{
		// Populate navigator.plugins with realistic Chromium entries so plugins.length > 0.
		`Object.defineProperty(navigator, 'plugins', {
		get: () => {
			const arr = [
				{ name: 'PDF Viewer', filename: 'internal-pdf-viewer', description: 'Portable Document Format' },
				{ name: 'Chrome PDF Plugin', filename: 'internal-pdf-viewer', description: '' },
				{ name: 'Chromium PDF Viewer', filename: 'internal-pdf-viewer', description: '' },
			];
			arr.item = (i) => arr[i] || null;
			arr.namedItem = (n) => arr.find(p => p.name === n) || null;
			arr.refresh = () => {};
			return arr;
		},
	})`,

		// Populate navigator.mimeTypes to match the fake Chromium plugins above.
		`Object.defineProperty(navigator, 'mimeTypes', {
		get: () => {
			const arr = [
				{ type: 'application/pdf', suffixes: 'pdf', description: 'Portable Document Format' },
			];
			arr.item = (i) => arr[i] || null;
			arr.namedItem = (n) => arr.find(m => m.type === n) || null;
			return arr;
		},
	})`,

		// Provide window.chrome runtime stub (Chromium-only signal).
		`if (!window.chrome) {
		window.chrome = { runtime: {} };
	}`,

		// Add chrome.app, chrome.csi, and chrome.loadTimes stubs missing in headless.
		`(function() {
		if (!window.chrome) window.chrome = {};
		if (!window.chrome.app) {
			window.chrome.app = { isInstalled: false, InstallState: { DISABLED: 'disabled', INSTALLED: 'installed', NOT_INSTALLED: 'not_installed' }, RunningState: { CANNOT_RUN: 'cannot_run', READY_TO_RUN: 'ready_to_run', RUNNING: 'running' } };
		}
		if (!window.chrome.csi) {
			window.chrome.csi = function() { return { startE: Date.now(), onloadT: Date.now(), pageT: 0, tran: 15 }; };
		}
		if (!window.chrome.loadTimes) {
			window.chrome.loadTimes = function() { return { commitLoadTime: Date.now() / 1000, connectionInfo: 'h2', finishDocumentLoadTime: Date.now() / 1000, finishLoadTime: Date.now() / 1000, firstPaintAfterLoadTime: 0, firstPaintTime: Date.now() / 1000, navigationType: 'Other', npnNegotiatedProtocol: 'h2', requestTime: Date.now() / 1000, startLoadTime: Date.now() / 1000, wasAlternateProtocolAvailable: false, wasFetchedViaSpdy: true, wasNpnNegotiated: true }; };
		}
	})()`,

		// Spoof WebGL renderer to hide SwiftShader (headless GPU) fingerprint with Chromium ANGLE strings.
		fmt.Sprintf(`(function() {
		const getParam = WebGLRenderingContext.prototype.getParameter;
		WebGLRenderingContext.prototype.getParameter = function(param) {
			if (param === 37445) return '%s';
			if (param === 37446) return '%s';
			return getParam.call(this, param);
		};
		if (typeof WebGL2RenderingContext !== 'undefined') {
			const getParam2 = WebGL2RenderingContext.prototype.getParameter;
			WebGL2RenderingContext.prototype.getParameter = function(param) {
				if (param === 37445) return '%s';
				if (param === 37446) return '%s';
				return getParam2.call(this, param);
			};
		}
	})()`, p.WebGLVendor, p.WebGLRenderer, p.WebGLVendor, p.WebGLRenderer),

		// Stub navigator.connection (Network Information API) if missing (Chrome-only API).
		fmt.Sprintf(`(function() {
		if (!navigator.connection) {
			Object.defineProperty(navigator, 'connection', {
				get: function() {
					return { effectiveType: '4g', rtt: %d, downlink: %.1f, saveData: false, onchange: null };
				},
			});
		}
	})()`, rtt, downlink),

		// Remove CDP artifacts (window.cdc_* globals injected by Chrome DevTools Protocol).
		`(function() {
		for (var key in window) {
			if (key.match(/^cdc_/)) {
				delete window[key];
			}
		}
	})()`,

		// Strip "HeadlessChrome" from navigator.userAgent if present.
		`(function() {
		var ua = navigator.userAgent;
		if (ua.indexOf('HeadlessChrome') !== -1) {
			Object.defineProperty(navigator, 'userAgent', {
				get: function() { return ua.replace('HeadlessChrome', 'Chrome'); },
			});
		}
	})()`,
	}
}

// firefoxHWProfile holds hardware fingerprint values for a Firefox browser session.
type firefoxHWProfile struct {
	WebGLVendor         string
	WebGLRenderer       string
	MozInnerScreenX     int
	MozInnerScreenY     int
	HardwareConcurrency int
}

// firefoxHWProfiles is a pool of realistic Firefox hardware profiles.
// Index 0 matches the original hardcoded values.
var firefoxHWProfiles = []firefoxHWProfile{
	{"Intel Open Source Technology Center", "Mesa DRI Intel(R) UHD Graphics 630", 8, 51, 4},
	{"Intel Open Source Technology Center", "Mesa DRI Intel(R) HD Graphics 530", 0, 71, 8},
	{"X.Org", "AMD Radeon RX 580 (polaris10, LLVM 15.0.7, DRM 3.49, 6.1.0-18-amd64)", 8, 51, 8},
	{"Intel Open Source Technology Center", "Mesa DRI Intel(R) UHD Graphics 770", 0, 51, 16},
	{"nouveau", "NV167", 8, 71, 4},
	{"Intel", "Mesa Intel(R) Iris(R) Xe Graphics", 0, 51, 8},
}

// randomFirefoxProfile returns a randomly selected Firefox hardware profile.
func randomFirefoxProfile() firefoxHWProfile {
	return firefoxHWProfiles[rand.IntN(len(firefoxHWProfiles))]
}

// buildFirefoxStealthScripts returns Firefox stealth init scripts with the given hardware profile
// values templated into the WebGL, mozInnerScreen, and hardwareConcurrency spoofing scripts.
func buildFirefoxStealthScripts(p firefoxHWProfile) []string {
	return []string{
		// Harden navigator.webdriver for Firefox: ensure Object.getOwnPropertyDescriptor also returns undefined.
		`(function() {
		const proto = Object.getPrototypeOf(navigator);
		const origGetOwnPropDesc = Object.getOwnPropertyDescriptor;
		Object.getOwnPropertyDescriptor = function(obj, prop) {
			if ((obj === navigator || obj === proto) && prop === 'webdriver') {
				return undefined;
			}
			return origGetOwnPropDesc.call(this, obj, prop);
		};
	})()`,

		// Spoof WebGL renderer with Firefox-appropriate Mesa/driver strings.
		fmt.Sprintf(`(function() {
		const getParam = WebGLRenderingContext.prototype.getParameter;
		WebGLRenderingContext.prototype.getParameter = function(param) {
			if (param === 37445) return '%s';
			if (param === 37446) return '%s';
			return getParam.call(this, param);
		};
		if (typeof WebGL2RenderingContext !== 'undefined') {
			const getParam2 = WebGL2RenderingContext.prototype.getParameter;
			WebGL2RenderingContext.prototype.getParameter = function(param) {
				if (param === 37445) return '%s';
				if (param === 37446) return '%s';
				return getParam2.call(this, param);
			};
		}
	})()`, p.WebGLVendor, p.WebGLRenderer, p.WebGLVendor, p.WebGLRenderer),

		// Spoof mozInnerScreenX/mozInnerScreenY which are 0 in headless Firefox.
		fmt.Sprintf(`(function() {
		if (window.mozInnerScreenX === 0) {
			Object.defineProperty(window, 'mozInnerScreenX', { get: () => %d });
		}
		if (window.mozInnerScreenY === 0) {
			Object.defineProperty(window, 'mozInnerScreenY', { get: () => %d });
		}
	})()`, p.MozInnerScreenX, p.MozInnerScreenY),

		// Normalize navigator.hardwareConcurrency (Firefox headless sometimes reports 2).
		fmt.Sprintf(`(function() {
		if (navigator.hardwareConcurrency <= 2) {
			Object.defineProperty(navigator, 'hardwareConcurrency', { get: () => %d });
		}
	})()`, p.HardwareConcurrency),

		// Override navigator.plugins with Firefox-appropriate PDF.js entry.
		`Object.defineProperty(navigator, 'plugins', {
		get: () => {
			const arr = [
				{ name: 'PDF.js', filename: 'internal-pdf-viewer', description: 'Portable Document Format' },
			];
			arr.item = (i) => arr[i] || null;
			arr.namedItem = (n) => arr.find(p => p.name === n) || null;
			arr.refresh = () => {};
			return arr;
		},
	})`,
	}
}