feat: add safe Playwright scraper skill

This commit is contained in:
Stefano Fiorini
2026-03-10 19:07:30 -05:00
parent 60363f9f0c
commit 4b505e4421
10 changed files with 430 additions and 0 deletions

View File

@@ -0,0 +1,200 @@
#!/usr/bin/env node
const fs = require("fs");
const path = require("path");
const DEFAULT_WAIT_MS = 5000;
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";
function fail(message, details) {
const payload = { error: message };
if (details) payload.details = details;
process.stderr.write(`${JSON.stringify(payload)}\n`);
process.exit(1);
}
function parseWaitTime(raw) {
const value = Number.parseInt(raw || `${DEFAULT_WAIT_MS}`, 10);
if (!Number.isFinite(value) || value < 0) return DEFAULT_WAIT_MS;
return Math.min(value, MAX_WAIT_MS);
}
function parseTarget(rawUrl) {
if (!rawUrl) {
fail("Missing URL. Usage: node scripts/playwright-safe.js <URL>");
}
let parsed;
try {
parsed = new URL(rawUrl);
} catch (error) {
fail("Invalid URL.", error.message);
}
if (!["http:", "https:"].includes(parsed.protocol)) {
fail("Only http and https URLs are allowed.");
}
return parsed.toString();
}
function ensureParentDir(filePath) {
if (!filePath) return;
fs.mkdirSync(path.dirname(filePath), { recursive: true });
}
async function detectChallenge(page) {
try {
return await page.evaluate(() => {
const text = (document.body?.innerText || "").toLowerCase();
return (
text.includes("checking your browser") ||
text.includes("just a moment") ||
text.includes("verify you are human") ||
text.includes("press and hold") ||
document.querySelector('iframe[src*="challenge"]') !== null ||
document.querySelector('iframe[src*="cloudflare"]') !== null
);
});
} catch {
return false;
}
}
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 startedAt = Date.now();
let chromium;
try {
({ chromium } = require("playwright"));
} catch (error) {
fail(
"Playwright is not installed for this skill. Run npm install and npx playwright install chromium first.",
error.message
);
}
let browser;
try {
browser = await chromium.launch({
headless,
ignoreDefaultArgs: ["--enable-automation"],
args: [
"--disable-blink-features=AutomationControlled",
"--disable-features=IsolateOrigins,site-per-process"
]
});
const context = await browser.newContext({
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);
};
}
});
const page = await context.newPage();
const response = await page.goto(requestedUrl, {
waitUntil: "domcontentloaded",
timeout: NAV_TIMEOUT_MS
});
await page.waitForTimeout(waitTime);
let challengeDetected = await detectChallenge(page);
if (challengeDetected) {
await page.waitForTimeout(EXTRA_CHALLENGE_WAIT_MS);
challengeDetected = await detectChallenge(page);
}
const extracted = await page.evaluate((contentLimit) => {
const bodyText = document.body?.innerText || "";
return {
finalUrl: window.location.href,
title: document.title || "",
content: bodyText.slice(0, contentLimit),
metaDescription:
document.querySelector('meta[name="description"]')?.content ||
document.querySelector('meta[property="og:description"]')?.content ||
""
};
}, CONTENT_LIMIT);
const result = {
requestedUrl,
finalUrl: extracted.finalUrl,
title: extracted.title,
content: extracted.content,
metaDescription: extracted.metaDescription,
status: response ? response.status() : null,
challengeDetected,
elapsedSeconds: ((Date.now() - startedAt) / 1000).toFixed(2)
};
if (screenshotPath) {
ensureParentDir(screenshotPath);
await page.screenshot({ path: screenshotPath, fullPage: false, timeout: 10000 });
result.screenshot = screenshotPath;
}
if (saveHtml) {
const htmlTarget =
screenshotPath ? screenshotPath.replace(/\.[^.]+$/, ".html") : path.resolve(`page-${Date.now()}.html`);
ensureParentDir(htmlTarget);
fs.writeFileSync(htmlTarget, await page.content());
result.htmlFile = htmlTarget;
}
process.stdout.write(`${JSON.stringify(result, null, 2)}\n`);
await browser.close();
} catch (error) {
if (browser) {
try {
await browser.close();
} catch {
// Ignore close errors after the primary failure.
}
}
fail("Scrape failed.", error.message);
}
}
main();