190 lines
5.3 KiB
JavaScript
190 lines
5.3 KiB
JavaScript
#!/usr/bin/env node
|
||
// ⚠️ GENERATED FILE – do not edit directly. Edit the canonical source in skills/web-automation/shared/ and run `pnpm run sync:pi`.
|
||
|
||
import fs from "node:fs";
|
||
import path from "node:path";
|
||
import { fileURLToPath } from "node:url";
|
||
|
||
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 __filename = fileURLToPath(import.meta.url);
|
||
const __dirname = path.dirname(__filename);
|
||
|
||
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 extract.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 });
|
||
}
|
||
|
||
function sleep(ms) {
|
||
return new Promise((resolve) => setTimeout(resolve, ms));
|
||
}
|
||
|
||
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 loadCloakBrowser() {
|
||
try {
|
||
return await import("cloakbrowser");
|
||
} catch (error) {
|
||
fail(
|
||
"CloakBrowser is not installed for this skill. Run pnpm install in this skill's scripts directory 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 || undefined;
|
||
const startedAt = Date.now();
|
||
const { ensureBinary, launchContext } = await loadCloakBrowser();
|
||
|
||
let context;
|
||
try {
|
||
await runWithStderrLogs(() => ensureBinary());
|
||
|
||
context = await runWithStderrLogs(() => launchContext({
|
||
headless,
|
||
userAgent,
|
||
locale: "en-US",
|
||
viewport: { width: 1440, height: 900 },
|
||
humanize: true,
|
||
}));
|
||
|
||
const page = await context.newPage();
|
||
const response = await page.goto(requestedUrl, {
|
||
waitUntil: "domcontentloaded",
|
||
timeout: NAV_TIMEOUT_MS
|
||
});
|
||
|
||
await sleep(waitTime);
|
||
|
||
let challengeDetected = await detectChallenge(page);
|
||
if (challengeDetected) {
|
||
await sleep(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(/\.[^.]+$/, ".html")
|
||
: path.resolve(__dirname, `page-${Date.now()}.html`);
|
||
ensureParentDir(htmlTarget);
|
||
fs.writeFileSync(htmlTarget, await page.content());
|
||
result.htmlFile = htmlTarget;
|
||
}
|
||
|
||
process.stdout.write(`${JSON.stringify(result, null, 2)}\n`);
|
||
await context.close();
|
||
} catch (error) {
|
||
if (context) {
|
||
try {
|
||
await context.close();
|
||
} catch {
|
||
// Ignore close errors after the primary failure.
|
||
}
|
||
}
|
||
fail("Scrape failed.", error.message);
|
||
}
|
||
}
|
||
|
||
main();
|