refactor: migrate web-automation to cloakbrowser

This commit is contained in:
Stefano Fiorini
2026-03-11 20:26:59 -05:00
parent c9254ed7eb
commit 4078073f0b
14 changed files with 200 additions and 553 deletions

View File

@@ -9,8 +9,6 @@ const MAX_WAIT_MS = 20000;
const NAV_TIMEOUT_MS = 30000;
const EXTRA_CHALLENGE_WAIT_MS = 8000;
const CONTENT_LIMIT = 12000;
const DEFAULT_USER_AGENT =
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/136.0.0.0 Safari/537.36";
const __filename = fileURLToPath(import.meta.url);
const __dirname = path.dirname(__filename);
@@ -52,6 +50,10 @@ function ensureParentDir(filePath) {
fs.mkdirSync(path.dirname(filePath), { recursive: true });
}
function sleep(ms) {
return new Promise((resolve) => setTimeout(resolve, ms));
}
async function detectChallenge(page) {
try {
return await page.evaluate(() => {
@@ -70,73 +72,51 @@ async function detectChallenge(page) {
}
}
async function loadPlaywright() {
async function loadCloakBrowser() {
try {
return await import("playwright");
return await import("cloakbrowser");
} catch (error) {
fail(
"Playwright is not installed for this skill. Run pnpm install and npx playwright install chromium in skills/web-automation/scripts first.",
"CloakBrowser is not installed for this skill. Run pnpm install in skills/web-automation/scripts first.",
error.message
);
}
}
async function runWithStderrLogs(fn) {
const originalLog = console.log;
const originalError = console.error;
console.log = (...args) => process.stderr.write(`${args.join(" ")}\n`);
console.error = (...args) => process.stderr.write(`${args.join(" ")}\n`);
try {
return await fn();
} finally {
console.log = originalLog;
console.error = originalError;
}
}
async function main() {
const requestedUrl = parseTarget(process.argv[2]);
const waitTime = parseWaitTime(process.env.WAIT_TIME);
const screenshotPath = process.env.SCREENSHOT_PATH || "";
const saveHtml = process.env.SAVE_HTML === "true";
const headless = process.env.HEADLESS !== "false";
const userAgent = process.env.USER_AGENT || DEFAULT_USER_AGENT;
const userAgent = process.env.USER_AGENT || undefined;
const startedAt = Date.now();
const { chromium } = await loadPlaywright();
const { ensureBinary, launchContext } = await loadCloakBrowser();
let browser;
let context;
try {
browser = await chromium.launch({
headless,
ignoreDefaultArgs: ["--enable-automation"],
args: [
"--disable-blink-features=AutomationControlled",
"--disable-features=IsolateOrigins,site-per-process"
]
});
await runWithStderrLogs(() => ensureBinary());
const context = await browser.newContext({
context = await runWithStderrLogs(() => launchContext({
headless,
userAgent,
locale: "en-US",
viewport: { width: 1440, height: 900 },
extraHTTPHeaders: {
"Accept-Language": "en-US,en;q=0.9",
Accept: "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8"
}
});
await context.addInitScript(() => {
Object.defineProperty(navigator, "webdriver", {
get: () => false
});
Object.defineProperty(navigator, "languages", {
get: () => ["en-US", "en"]
});
Object.defineProperty(navigator, "plugins", {
get: () => [1, 2, 3, 4, 5]
});
window.chrome = window.chrome || { runtime: {} };
const originalQuery = window.navigator.permissions?.query?.bind(window.navigator.permissions);
if (originalQuery) {
window.navigator.permissions.query = (parameters) => {
if (parameters?.name === "notifications") {
return Promise.resolve({ state: Notification.permission });
}
return originalQuery(parameters);
};
}
});
humanize: true,
}));
const page = await context.newPage();
const response = await page.goto(requestedUrl, {
@@ -144,11 +124,11 @@ async function main() {
timeout: NAV_TIMEOUT_MS
});
await page.waitForTimeout(waitTime);
await sleep(waitTime);
let challengeDetected = await detectChallenge(page);
if (challengeDetected) {
await page.waitForTimeout(EXTRA_CHALLENGE_WAIT_MS);
await sleep(EXTRA_CHALLENGE_WAIT_MS);
challengeDetected = await detectChallenge(page);
}
@@ -192,11 +172,11 @@ async function main() {
}
process.stdout.write(`${JSON.stringify(result, null, 2)}\n`);
await browser.close();
await context.close();
} catch (error) {
if (browser) {
if (context) {
try {
await browser.close();
await context.close();
} catch {
// Ignore close errors after the primary failure.
}