Merge pull request 'fix: randomize hardware fingerprints across sessions' (#74) from feature/71-randomize-fingerprints into main

Reviewed-on: #74

browser_init.go

@@ -74,9 +74,9 @@ func initBrowser(opt BrowserOptions) (*browserInitResult, error) {
 		initScripts = append(initScripts, stealthCommonScripts...)
 		switch opt.Browser {
 		case BrowserChromium:
-			initScripts = append(initScripts, stealthChromiumScripts...)
+			initScripts = append(initScripts, buildChromiumStealthScripts(randomChromiumProfile())...)
 		case BrowserFirefox:
-			initScripts = append(initScripts, stealthFirefoxScripts...)
+			initScripts = append(initScripts, buildFirefoxStealthScripts(randomFirefoxProfile())...)
 		}
 	}
 

stealth.go

@@ -1,5 +1,10 @@
 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",
@@ -39,8 +44,45 @@ var stealthCommonScripts = []string{
 	})()`,
 }
 
-// stealthChromiumScripts are JavaScript snippets specific to Chromium-based browsers.
+// chromiumHWProfile holds hardware fingerprint values for a Chromium browser session.
-var stealthChromiumScripts = []string{
+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: () => {
@@ -88,33 +130,33 @@ var stealthChromiumScripts = []string{
 	})()`,
 
 		// Spoof WebGL renderer to hide SwiftShader (headless GPU) fingerprint with Chromium ANGLE strings.
-	`(function() {
+		fmt.Sprintf(`(function() {
 		const getParam = WebGLRenderingContext.prototype.getParameter;
 		WebGLRenderingContext.prototype.getParameter = function(param) {
-			if (param === 37445) return 'Google Inc. (Intel)';
+			if (param === 37445) return '%s';
-			if (param === 37446) return 'ANGLE (Intel, Intel(R) UHD Graphics 630, OpenGL 4.5)';
+			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 'Google Inc. (Intel)';
+				if (param === 37445) return '%s';
-				if (param === 37446) return 'ANGLE (Intel, Intel(R) UHD Graphics 630, OpenGL 4.5)';
+				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).
-	`(function() {
+		fmt.Sprintf(`(function() {
 		if (!navigator.connection) {
 			Object.defineProperty(navigator, 'connection', {
 				get: function() {
-					return { effectiveType: '4g', rtt: 50, downlink: 10, saveData: false, onchange: null };
+					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() {
@@ -135,9 +177,37 @@ var stealthChromiumScripts = []string{
 		}
 	})()`,
 	}
+}
 
-// stealthFirefoxScripts are JavaScript snippets specific to Firefox.
+// firefoxHWProfile holds hardware fingerprint values for a Firefox browser session.
-var stealthFirefoxScripts = []string{
+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);
@@ -150,40 +220,40 @@ var stealthFirefoxScripts = []string{
 		};
 	})()`,
 
-	// Spoof WebGL renderer with Firefox-appropriate Mesa/Intel strings.
+		// Spoof WebGL renderer with Firefox-appropriate Mesa/driver strings.
-	`(function() {
+		fmt.Sprintf(`(function() {
 		const getParam = WebGLRenderingContext.prototype.getParameter;
 		WebGLRenderingContext.prototype.getParameter = function(param) {
-			if (param === 37445) return 'Intel Open Source Technology Center';
+			if (param === 37445) return '%s';
-			if (param === 37446) return 'Mesa DRI Intel(R) UHD Graphics 630';
+			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 'Intel Open Source Technology Center';
+				if (param === 37445) return '%s';
-				if (param === 37446) return 'Mesa DRI Intel(R) UHD Graphics 630';
+				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.
-	`(function() {
+		fmt.Sprintf(`(function() {
 		if (window.mozInnerScreenX === 0) {
-			Object.defineProperty(window, 'mozInnerScreenX', { get: () => 8 });
+			Object.defineProperty(window, 'mozInnerScreenX', { get: () => %d });
 		}
 		if (window.mozInnerScreenY === 0) {
-			Object.defineProperty(window, 'mozInnerScreenY', { get: () => 51 });
+			Object.defineProperty(window, 'mozInnerScreenY', { get: () => %d });
 		}
-	})()`,
+	})()`, p.MozInnerScreenX, p.MozInnerScreenY),
 
 		// Normalize navigator.hardwareConcurrency (Firefox headless sometimes reports 2).
-	`(function() {
+		fmt.Sprintf(`(function() {
 		if (navigator.hardwareConcurrency <= 2) {
-			Object.defineProperty(navigator, 'hardwareConcurrency', { get: () => 4 });
+			Object.defineProperty(navigator, 'hardwareConcurrency', { get: () => %d });
 		}
-	})()`,
+	})()`, p.HardwareConcurrency),
 
 		// Override navigator.plugins with Firefox-appropriate PDF.js entry.
 		`Object.defineProperty(navigator, 'plugins', {
@@ -198,3 +268,4 @@ var stealthFirefoxScripts = []string{
 		},
 	})`,
 	}
+}

stealth_test.go

@@ -129,14 +129,16 @@ func TestStealthCommonScripts_Notification(t *testing.T) {
 // --- Chromium scripts ---
 
 func TestStealthChromiumScripts_Count(t *testing.T) {
-	if len(stealthChromiumScripts) != 8 {
+	scripts := buildChromiumStealthScripts(chromiumHWProfiles[0])
-		t.Fatalf("expected 8 chromium stealth scripts, got %d", len(stealthChromiumScripts))
+	if len(scripts) != 8 {
+		t.Fatalf("expected 8 chromium stealth scripts, got %d", len(scripts))
 	}
 }
 
 func TestStealthChromiumScripts_Plugins(t *testing.T) {
+	scripts := buildChromiumStealthScripts(chromiumHWProfiles[0])
 	found := false
-	for _, s := range stealthChromiumScripts {
+	for _, s := range scripts {
 		if strings.Contains(s, "Chrome PDF Plugin") && strings.Contains(s, "navigator") && strings.Contains(s, "plugins") {
 			found = true
 			break
@@ -148,8 +150,9 @@ func TestStealthChromiumScripts_Plugins(t *testing.T) {
 }
 
 func TestStealthChromiumScripts_MimeTypes(t *testing.T) {
+	scripts := buildChromiumStealthScripts(chromiumHWProfiles[0])
 	found := false
-	for _, s := range stealthChromiumScripts {
+	for _, s := range scripts {
 		if strings.Contains(s, "mimeTypes") && strings.Contains(s, "application/pdf") {
 			found = true
 			break
@@ -161,8 +164,9 @@ func TestStealthChromiumScripts_MimeTypes(t *testing.T) {
 }
 
 func TestStealthChromiumScripts_WindowChrome(t *testing.T) {
+	scripts := buildChromiumStealthScripts(chromiumHWProfiles[0])
 	found := false
-	for _, s := range stealthChromiumScripts {
+	for _, s := range scripts {
 		if strings.Contains(s, "window.chrome") && strings.Contains(s, "runtime") {
 			found = true
 			break
@@ -174,8 +178,9 @@ func TestStealthChromiumScripts_WindowChrome(t *testing.T) {
 }
 
 func TestStealthChromiumScripts_ChromeApp(t *testing.T) {
+	scripts := buildChromiumStealthScripts(chromiumHWProfiles[0])
 	found := false
-	for _, s := range stealthChromiumScripts {
+	for _, s := range scripts {
 		if strings.Contains(s, "chrome.app") && strings.Contains(s, "chrome.csi") && strings.Contains(s, "chrome.loadTimes") {
 			found = true
 			break
@@ -187,8 +192,9 @@ func TestStealthChromiumScripts_ChromeApp(t *testing.T) {
 }
 
 func TestStealthChromiumScripts_WebGLSpoof(t *testing.T) {
+	scripts := buildChromiumStealthScripts(chromiumHWProfiles[0])
 	found := false
-	for _, s := range stealthChromiumScripts {
+	for _, s := range scripts {
 		if strings.Contains(s, "37446") && strings.Contains(s, "ANGLE") {
 			found = true
 			break
@@ -200,8 +206,9 @@ func TestStealthChromiumScripts_WebGLSpoof(t *testing.T) {
 }
 
 func TestStealthChromiumScripts_NavigatorConnection(t *testing.T) {
+	scripts := buildChromiumStealthScripts(chromiumHWProfiles[0])
 	found := false
-	for _, s := range stealthChromiumScripts {
+	for _, s := range scripts {
 		if strings.Contains(s, "connection") && strings.Contains(s, "effectiveType") {
 			found = true
 			break
@@ -213,8 +220,9 @@ func TestStealthChromiumScripts_NavigatorConnection(t *testing.T) {
 }
 
 func TestStealthChromiumScripts_CDPCleanup(t *testing.T) {
+	scripts := buildChromiumStealthScripts(chromiumHWProfiles[0])
 	found := false
-	for _, s := range stealthChromiumScripts {
+	for _, s := range scripts {
 		if strings.Contains(s, "cdc_") && strings.Contains(s, "delete") {
 			found = true
 			break
@@ -226,8 +234,9 @@ func TestStealthChromiumScripts_CDPCleanup(t *testing.T) {
 }
 
 func TestStealthChromiumScripts_UserAgentStrip(t *testing.T) {
+	scripts := buildChromiumStealthScripts(chromiumHWProfiles[0])
 	found := false
-	for _, s := range stealthChromiumScripts {
+	for _, s := range scripts {
 		if strings.Contains(s, "HeadlessChrome") && strings.Contains(s, "userAgent") {
 			found = true
 			break
@@ -241,14 +250,16 @@ func TestStealthChromiumScripts_UserAgentStrip(t *testing.T) {
 // --- Firefox scripts ---
 
 func TestStealthFirefoxScripts_Count(t *testing.T) {
-	if len(stealthFirefoxScripts) != 5 {
+	scripts := buildFirefoxStealthScripts(firefoxHWProfiles[0])
-		t.Fatalf("expected 5 firefox stealth scripts, got %d", len(stealthFirefoxScripts))
+	if len(scripts) != 5 {
+		t.Fatalf("expected 5 firefox stealth scripts, got %d", len(scripts))
 	}
 }
 
 func TestStealthFirefoxScripts_WebdriverHardening(t *testing.T) {
+	scripts := buildFirefoxStealthScripts(firefoxHWProfiles[0])
 	found := false
-	for _, s := range stealthFirefoxScripts {
+	for _, s := range scripts {
 		if strings.Contains(s, "getOwnPropertyDescriptor") && strings.Contains(s, "webdriver") {
 			found = true
 			break
@@ -260,8 +271,9 @@ func TestStealthFirefoxScripts_WebdriverHardening(t *testing.T) {
 }
 
 func TestStealthFirefoxScripts_WebGLSpoof(t *testing.T) {
+	scripts := buildFirefoxStealthScripts(firefoxHWProfiles[0])
 	found := false
-	for _, s := range stealthFirefoxScripts {
+	for _, s := range scripts {
 		if strings.Contains(s, "37446") && strings.Contains(s, "Mesa DRI") {
 			found = true
 			break
@@ -273,8 +285,9 @@ func TestStealthFirefoxScripts_WebGLSpoof(t *testing.T) {
 }
 
 func TestStealthFirefoxScripts_MozInnerScreen(t *testing.T) {
+	scripts := buildFirefoxStealthScripts(firefoxHWProfiles[0])
 	found := false
-	for _, s := range stealthFirefoxScripts {
+	for _, s := range scripts {
 		if strings.Contains(s, "mozInnerScreenX") && strings.Contains(s, "mozInnerScreenY") {
 			found = true
 			break
@@ -286,8 +299,9 @@ func TestStealthFirefoxScripts_MozInnerScreen(t *testing.T) {
 }
 
 func TestStealthFirefoxScripts_HardwareConcurrency(t *testing.T) {
+	scripts := buildFirefoxStealthScripts(firefoxHWProfiles[0])
 	found := false
-	for _, s := range stealthFirefoxScripts {
+	for _, s := range scripts {
 		if strings.Contains(s, "hardwareConcurrency") {
 			found = true
 			break
@@ -299,8 +313,9 @@ func TestStealthFirefoxScripts_HardwareConcurrency(t *testing.T) {
 }
 
 func TestStealthFirefoxScripts_PDFjsPlugins(t *testing.T) {
+	scripts := buildFirefoxStealthScripts(firefoxHWProfiles[0])
 	found := false
-	for _, s := range stealthFirefoxScripts {
+	for _, s := range scripts {
 		if strings.Contains(s, "PDF.js") && strings.Contains(s, "plugins") {
 			found = true
 			break
@@ -314,17 +329,19 @@ func TestStealthFirefoxScripts_PDFjsPlugins(t *testing.T) {
 // --- Cross-category validation ---
 
 func TestStealthScripts_NoOverlap(t *testing.T) {
+	chromiumScripts := buildChromiumStealthScripts(chromiumHWProfiles[0])
+	firefoxScripts := buildFirefoxStealthScripts(firefoxHWProfiles[0])
 	all := make(map[string]string) // script -> category
 	for _, s := range stealthCommonScripts {
 		all[s] = "common"
 	}
-	for _, s := range stealthChromiumScripts {
+	for _, s := range chromiumScripts {
 		if cat, ok := all[s]; ok {
 			t.Fatalf("chromium script also appears in %s category", cat)
 		}
 		all[s] = "chromium"
 	}
-	for _, s := range stealthFirefoxScripts {
+	for _, s := range firefoxScripts {
 		if cat, ok := all[s]; ok {
 			t.Fatalf("firefox script also appears in %s category", cat)
 		}
@@ -354,8 +371,9 @@ func TestStealthCommonScripts_NoFirefoxMarkers(t *testing.T) {
 }
 
 func TestStealthChromiumScripts_NoFirefoxMarkers(t *testing.T) {
+	scripts := buildChromiumStealthScripts(chromiumHWProfiles[0])
 	firefoxMarkers := []string{"mozInnerScreen", "Mesa DRI", "PDF.js"}
-	for _, s := range stealthChromiumScripts {
+	for _, s := range scripts {
 		for _, marker := range firefoxMarkers {
 			if strings.Contains(s, marker) {
 				t.Fatalf("chromium script contains Firefox-specific marker %q", marker)
@@ -365,8 +383,9 @@ func TestStealthChromiumScripts_NoFirefoxMarkers(t *testing.T) {
 }
 
 func TestStealthFirefoxScripts_NoChromiumMarkers(t *testing.T) {
+	scripts := buildFirefoxStealthScripts(firefoxHWProfiles[0])
 	chromiumMarkers := []string{"window.chrome", "chrome.app", "chrome.csi", "chrome.loadTimes", "HeadlessChrome", "cdc_", "Chrome PDF Plugin", "ANGLE"}
-	for _, s := range stealthFirefoxScripts {
+	for _, s := range scripts {
 		for _, marker := range chromiumMarkers {
 			if strings.Contains(s, marker) {
 				t.Fatalf("firefox script contains Chromium-specific marker %q", marker)
@@ -439,3 +458,76 @@ func TestMergeOptions_ExplicitUAPreserved(t *testing.T) {
 		t.Fatalf("expected explicit UA %q preserved, got %q", customUA, got.UserAgent)
 	}
 }
+
+// --- Hardware profile pools ---
+
+func TestChromiumHWProfiles_NotEmpty(t *testing.T) {
+	if len(chromiumHWProfiles) < 2 {
+		t.Fatalf("expected at least 2 chromium hardware profiles, got %d", len(chromiumHWProfiles))
+	}
+}
+
+func TestFirefoxHWProfiles_NotEmpty(t *testing.T) {
+	if len(firefoxHWProfiles) < 2 {
+		t.Fatalf("expected at least 2 firefox hardware profiles, got %d", len(firefoxHWProfiles))
+	}
+}
+
+func TestBuildChromiumStealthScripts_ProfileValues(t *testing.T) {
+	p := chromiumHWProfiles[1] // NVIDIA profile
+	scripts := buildChromiumStealthScripts(p)
+	joined := strings.Join(scripts, "\n")
+	if !strings.Contains(joined, p.WebGLVendor) {
+		t.Fatalf("expected chromium scripts to contain vendor %q", p.WebGLVendor)
+	}
+	if !strings.Contains(joined, p.WebGLRenderer) {
+		t.Fatalf("expected chromium scripts to contain renderer %q", p.WebGLRenderer)
+	}
+}
+
+func TestBuildFirefoxStealthScripts_ProfileValues(t *testing.T) {
+	p := firefoxHWProfiles[2] // AMD profile
+	scripts := buildFirefoxStealthScripts(p)
+	joined := strings.Join(scripts, "\n")
+	if !strings.Contains(joined, p.WebGLVendor) {
+		t.Fatalf("expected firefox scripts to contain vendor %q", p.WebGLVendor)
+	}
+	if !strings.Contains(joined, p.WebGLRenderer) {
+		t.Fatalf("expected firefox scripts to contain renderer %q", p.WebGLRenderer)
+	}
+}
+
+func TestBuildChromiumStealthScripts_ConnectionJitter(t *testing.T) {
+	p := chromiumHWProfiles[0]
+	seen := make(map[string]bool)
+	for range 50 {
+		scripts := buildChromiumStealthScripts(p)
+		// The connection script is at index 5.
+		seen[scripts[5]] = true
+	}
+	if len(seen) < 2 {
+		t.Fatal("expected connection script to vary across calls due to jitter, but all 50 were identical")
+	}
+}
+
+func TestChromiumHWProfiles_NoSingleQuotes(t *testing.T) {
+	for i, p := range chromiumHWProfiles {
+		if strings.Contains(p.WebGLVendor, "'") {
+			t.Fatalf("chromium profile %d vendor contains single quote (breaks JS)", i)
+		}
+		if strings.Contains(p.WebGLRenderer, "'") {
+			t.Fatalf("chromium profile %d renderer contains single quote (breaks JS)", i)
+		}
+	}
+}
+
+func TestFirefoxHWProfiles_NoSingleQuotes(t *testing.T) {
+	for i, p := range firefoxHWProfiles {
+		if strings.Contains(p.WebGLVendor, "'") {
+			t.Fatalf("firefox profile %d vendor contains single quote (breaks JS)", i)
+		}
+		if strings.Contains(p.WebGLRenderer, "'") {
+			t.Fatalf("firefox profile %d renderer contains single quote (breaks JS)", i)
+		}
+	}
+}