refactor: consolidate web scraping into web-automation

skills/web-automation/SKILL.md

@@ -1,20 +1,20 @@
 ---
 name: web-automation
-description: Browse and scrape web pages using Playwright with Camoufox anti-detection browser. Use when automating web workflows, extracting page content to markdown, handling authenticated sessions, or scraping websites with bot protection.
+description: Browse and scrape web pages using Playwright with Camoufox anti-detection browser. Use when automating web workflows, extracting rendered page content, handling authenticated sessions, or scraping websites with bot protection.
 ---
 
 # Web Automation with Camoufox (Codex)
 
-Automated web browsing and scraping using Playwright with Camoufox anti-detection browser.
+Automated web browsing and scraping using Playwright with two execution paths under one skill:
 
-## Routing Rule
+- one-shot extraction via `extract.js`
+- broader stateful automation via Camoufox and the existing `auth.ts`, `browse.ts`, `flow.ts`, and `scrape.ts`
 
-Before using this skill, classify the task:
+## When To Use Which Command
 
-- If the task is one-shot page extraction for title/content from a single URL, use `~/.openclaw/workspace/skills/playwright-safe/SKILL.md` instead.
-- If the task needs a multi-step browser flow, authenticated session handling, or interactive navigation/click/type behavior, use this `web-automation` skill.
-
-Do not use `web-automation` for simple single-page extraction when `playwright-safe` is available.
+- Use `node scripts/extract.js "<URL>"` for one-shot extraction from a single URL when you need rendered content, bounded stealth behavior, and JSON output.
+- Use `npx tsx scrape.ts ...` when you need markdown output, Readability extraction, full-page cleanup, or selector-based scraping.
+- Use `npx tsx browse.ts ...`, `auth.ts`, or `flow.ts` when the task needs interactive navigation, persistent sessions, login handling, click/type actions, or multi-step workflows.
 
 ## Requirements
 
@@ -27,6 +27,7 @@ Do not use `web-automation` for simple single-page extraction when `playwright-s
 ```bash
 cd ~/.openclaw/workspace/skills/web-automation/scripts
 pnpm install
+npx playwright install chromium
 npx camoufox-js fetch
 pnpm approve-builds
 pnpm rebuild better-sqlite3 esbuild
@@ -38,13 +39,13 @@ Before running any automation, verify Playwright + Camoufox dependencies are ins
 
 ```bash
 cd ~/.openclaw/workspace/skills/web-automation/scripts
-node -e "require.resolve('playwright-core/package.json');require.resolve('camoufox-js/package.json');console.log('OK: playwright-core + camoufox-js installed')"
+node -e "require.resolve('playwright/package.json');require.resolve('playwright-core/package.json');require.resolve('camoufox-js/package.json');console.log('OK: playwright + playwright-core + camoufox-js installed')"
 node -e "const fs=require('fs');const t=fs.readFileSync('browse.ts','utf8');if(!/camoufox-js/.test(t)){throw new Error('browse.ts is not configured for Camoufox')}console.log('OK: Camoufox integration detected in browse.ts')"
 ```
 
 If any check fails, stop and return:
 
-"Missing dependency/config: web-automation requires `playwright-core` + `camoufox-js` and Camoufox-based scripts. Run setup in this skill, then retry."
+"Missing dependency/config: web-automation requires `playwright`, `playwright-core`, and `camoufox-js` with Camoufox-based scripts. Run setup in this skill, then retry."
 
 If runtime fails with missing native bindings for `better-sqlite3` or `esbuild`, run:
 
@@ -56,11 +57,35 @@ pnpm rebuild better-sqlite3 esbuild
 
 ## Quick Reference
 
+- One-shot JSON extract: `node scripts/extract.js "https://example.com"`
 - Browse page: `npx tsx browse.ts --url "https://example.com"`
 - Scrape markdown: `npx tsx scrape.ts --url "https://example.com" --mode main --output page.md`
 - Authenticate: `npx tsx auth.ts --url "https://example.com/login"`
 - Natural-language flow: `npx tsx flow.ts --instruction 'go to https://example.com then click on "Login" then type "user@example.com" in #email then press enter'`
 
+## One-shot extraction
+
+Use `extract.js` when you need a single page fetch with JavaScript rendering and lightweight anti-bot shaping, but not a full automation session.
+
+```bash
+node scripts/extract.js "https://example.com"
+WAIT_TIME=5000 node scripts/extract.js "https://example.com"
+SCREENSHOT_PATH=/tmp/page.png SAVE_HTML=true node scripts/extract.js "https://example.com"
+```
+
+Output is JSON only and includes fields such as:
+
+- `requestedUrl`
+- `finalUrl`
+- `title`
+- `content`
+- `metaDescription`
+- `status`
+- `elapsedSeconds`
+- `challengeDetected`
+- optional `screenshot`
+- optional `htmlFile`
+
 ## General flow runner
 
 Use `flow.ts` for multi-step commands in plain language (go/click/type/press/wait/screenshot).
@@ -76,3 +101,4 @@ npx tsx flow.ts --instruction 'go to https://search.fiorinis.com then type "pipp
 - Sessions persist in Camoufox profile storage.
 - Use `--wait` for dynamic pages.
 - Use `--mode selector --selector "..."` for targeted extraction.
+- `extract.js` keeps stealth and bounded anti-bot shaping while keeping the Chromium sandbox enabled.

skills/web-automation/scripts/extract.js

@@ -0,0 +1,208 @@
+#!/usr/bin/env node
+
+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 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);
+
+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 skills/web-automation/scripts/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 });
+}
+
+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 loadPlaywright() {
+  try {
+    return await import("playwright");
+  } catch (error) {
+    fail(
+      "Playwright is not installed for this skill. Run pnpm install and npx playwright install chromium in skills/web-automation/scripts first.",
+      error.message
+    );
+  }
+}
+
+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();
+  const { chromium } = await loadPlaywright();
+
+  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(/\.[^.]+$/, ".html")
+        : path.resolve(__dirname, `page-${Date.now()}.html`);
+      ensureParentDir(htmlTarget);
+      fs.writeFileSync(htmlTarget, await page.content());
+      result.htmlFile = htmlTarget;
+    }
+
+    process.stdout.write(`${JSON.stringify(result, null, 2)}\n`);
+    await browser.close();
+  } catch (error) {
+    if (browser) {
+      try {
+        await browser.close();
+      } catch {
+        // Ignore close errors after the primary failure.
+      }
+    }
+    fail("Scrape failed.", error.message);
+  }
+}
+
+main();

skills/web-automation/scripts/package.json

@@ -4,6 +4,7 @@
   "description": "Web browsing and scraping scripts using Camoufox",
   "type": "module",
   "scripts": {
+    "extract": "node extract.js",
     "browse": "tsx browse.ts",
     "scrape": "tsx scrape.ts",
     "fetch-browser": "npx camoufox-js fetch"
@@ -14,6 +15,7 @@
     "camoufox-js": "^0.8.5",
     "jsdom": "^24.0.0",
     "minimist": "^1.2.8",
+    "playwright": "^1.58.2",
     "playwright-core": "^1.40.0",
     "turndown": "^7.1.2",
     "turndown-plugin-gfm": "^1.0.2"

skills/web-automation/scripts/pnpm-lock.yaml

@@ -23,6 +23,9 @@ importers:
       minimist:
         specifier: ^1.2.8
         version: 1.2.8
+      playwright:
+        specifier: ^1.58.2
+        version: 1.58.2
       playwright-core:
         specifier: ^1.40.0
         version: 1.57.0
@@ -440,6 +443,11 @@ packages:
   fs-constants@1.0.0:
     resolution: {integrity: sha512-y6OAwoSIf7FyjMIv94u+b5rdheZEjzR63GTyZJm5qh4Bi+2YgwLCcI/fPFZkL5PSixOt6ZNKm+w+Hfp/Bciwow==}
 
+  fsevents@2.3.2:
+    resolution: {integrity: sha512-xiqMQR4xAeHTuB9uWm+fFRcIOgKBMiOBP+eXiyT7jsgVCq1bkVygt00oASowB7EdtpOHaaPgKt812P9ab+DDKA==}
+    engines: {node: ^8.16.0 || ^10.6.0 || >=11.0.0}
+    os: [darwin]
+
   fsevents@2.3.3:
     resolution: {integrity: sha512-5xoDfX+fL7faATnagmWPpbFtwh/R77WmMMqqHGS65C3vvB0YHrgF+B1YmZ3441tMj5n63k0212XNoJwzlhffQw==}
     engines: {node: ^8.16.0 || ^10.6.0 || >=11.0.0}
@@ -679,6 +687,16 @@ packages:
     engines: {node: '>=18'}
     hasBin: true
 
+  playwright-core@1.58.2:
+    resolution: {integrity: sha512-yZkEtftgwS8CsfYo7nm0KE8jsvm6i/PTgVtB8DL726wNf6H2IMsDuxCpJj59KDaxCtSnrWan2AeDqM7JBaultg==}
+    engines: {node: '>=18'}
+    hasBin: true
+
+  playwright@1.58.2:
+    resolution: {integrity: sha512-vA30H8Nvkq/cPBnNw4Q8TWz1EJyqgpuinBcHET0YVJVFldr8JDNiU9LaWAE1KqSkRYazuaBhTpB5ZzShOezQ6A==}
+    engines: {node: '>=18'}
+    hasBin: true
+
   prebuild-install@7.1.3:
     resolution: {integrity: sha512-8Mf2cbV7x1cXPUILADGI3wuhfqWvtiLA1iclTDbFRZkgRQS0NqsPZphna9V+HyTEadheuPmjaJMsbzKQFOzLug==}
     engines: {node: '>=10'}
@@ -1196,6 +1214,9 @@ snapshots:
 
   fs-constants@1.0.0: {}
 
+  fsevents@2.3.2:
+    optional: true
+
   fsevents@2.3.3:
     optional: true
 
@@ -1428,6 +1449,14 @@ snapshots:
 
   playwright-core@1.57.0: {}
 
+  playwright-core@1.58.2: {}
+
+  playwright@1.58.2:
+    dependencies:
+      playwright-core: 1.58.2
+    optionalDependencies:
+      fsevents: 2.3.2
+
   prebuild-install@7.1.3:
     dependencies:
       detect-libc: 2.1.2