go-extractor/stealth.go

package extractor

// 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'); };
		}
	})()`,
}

// stealthChromiumScripts are JavaScript snippets specific to Chromium-based browsers.
var stealthChromiumScripts = []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.
	`(function() {
		const getParam = WebGLRenderingContext.prototype.getParameter;
		WebGLRenderingContext.prototype.getParameter = function(param) {
			if (param === 37445) return 'Google Inc. (Intel)';
			if (param === 37446) return 'ANGLE (Intel, Intel(R) UHD Graphics 630, OpenGL 4.5)';
			return getParam.call(this, param);
		};
		if (typeof WebGL2RenderingContext !== 'undefined') {
			const getParam2 = WebGL2RenderingContext.prototype.getParameter;
			WebGL2RenderingContext.prototype.getParameter = function(param) {
				if (param === 37445) return 'Google Inc. (Intel)';
				if (param === 37446) return 'ANGLE (Intel, Intel(R) UHD Graphics 630, OpenGL 4.5)';
				return getParam2.call(this, param);
			};
		}
	})()`,

	// Stub navigator.connection (Network Information API) if missing (Chrome-only API).
	`(function() {
		if (!navigator.connection) {
			Object.defineProperty(navigator, 'connection', {
				get: function() {
					return { effectiveType: '4g', rtt: 50, downlink: 10, saveData: false, onchange: null };
				},
			});
		}
	})()`,

	// 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'); },
			});
		}
	})()`,
}

// stealthFirefoxScripts are JavaScript snippets specific to Firefox.
var stealthFirefoxScripts = []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/Intel strings.
	`(function() {
		const getParam = WebGLRenderingContext.prototype.getParameter;
		WebGLRenderingContext.prototype.getParameter = function(param) {
			if (param === 37445) return 'Intel Open Source Technology Center';
			if (param === 37446) return 'Mesa DRI Intel(R) UHD Graphics 630';
			return getParam.call(this, param);
		};
		if (typeof WebGL2RenderingContext !== 'undefined') {
			const getParam2 = WebGL2RenderingContext.prototype.getParameter;
			WebGL2RenderingContext.prototype.getParameter = function(param) {
				if (param === 37445) return 'Intel Open Source Technology Center';
				if (param === 37446) return 'Mesa DRI Intel(R) UHD Graphics 630';
				return getParam2.call(this, param);
			};
		}
	})()`,

	// Spoof mozInnerScreenX/mozInnerScreenY which are 0 in headless Firefox.
	`(function() {
		if (window.mozInnerScreenX === 0) {
			Object.defineProperty(window, 'mozInnerScreenX', { get: () => 8 });
		}
		if (window.mozInnerScreenY === 0) {
			Object.defineProperty(window, 'mozInnerScreenY', { get: () => 51 });
		}
	})()`,

	// Normalize navigator.hardwareConcurrency (Firefox headless sometimes reports 2).
	`(function() {
		if (navigator.hardwareConcurrency <= 2) {
			Object.defineProperty(navigator, 'hardwareConcurrency', { get: () => 4 });
		}
	})()`,

	// 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;
		},
	})`,
}