compass_teams_nhs/scripts/compass-fetch-patchright.mjs

#!/usr/bin/env node
/**
 * Phase 2 proof-of-fetch for the Compass / NHS project — patchright path.
 *
 * The pi-browser-harness (headless Chrome) can load the Compass login page but
 * Cloudflare answers the login POST with a managed challenge that headless
 * Chrome does not clear. patchright launches Chrome with the automation leaks
 * patched, and the login POST goes through. This script:
 *
 *   1. logs in once with the parent account (COMPASS_USERNAME / COMPASS_PASSWORD),
 *   2. fetches the pages we need for ONE child,
 *   3. stores the raw HTML + a manifest with a SHA-256 and byte count per page.
 *
 * Read-only against the school: it only navigates and reads.
 *
 * Usage:
 *   node scripts/compass-fetch-patchright.mjs --child Harry [--pages "name=url,..."]
 *
 * Environment (never commit these):
 *   COMPASS_USERNAME / COMPASS_PASSWORD  parent/guardian account
 *   COMPASS_CHROME                        Chrome binary (default: Nix profile google-chrome)
 *   COMPASS_LOGIN_URL                     default https://nhs-vic.compass.education/login.aspx
 *   COMPASS_UA                            browser user-agent override
 *
 * Exit codes: 0 ok, 2 Cloudflare challenge not cleared, 3 second factor, 4 login rejected.
 */
import { chromium } from "patchright";
import crypto from "node:crypto";
import fs from "node:fs";
import path from "node:path";

const DEFAULT_URL = "https://nhs-vic.compass.education/login.aspx";
const DEFAULT_UA =
  "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/150.0.0.0 Safari/537.36";
const DEFAULT_CHROME = "/etc/profiles/per-user/sam/bin/google-chrome";
const CHALLENGE = /just a moment|verifying|checking your browser|attention required/i;

// Default pages: one child's record and the calendar. The parent landing page
// (/ ) is always stored as "home" right after login. userId is per child and is
// read from the landing page links or passed with --user-id.
const DEFAULT_PAGES = [
  { name: "child-profile", url: "/Records/User.aspx?userId={userId}" },
  { name: "calendar", url: "/Organise/Calendar/" },
];

const sleep = (ms) => new Promise((r) => setTimeout(r, ms));
const sha256 = (s) => crypto.createHash("sha256").update(s, "utf8").digest("hex");

function parseArgs(argv) {
  const args = { child: "Harry", userId: null, out: path.resolve("var/raw"), pages: null };
  for (let i = 2; i < argv.length; i++) {
    const a = argv[i];
    if (a === "--child") args.child = argv[++i];
    else if (a === "--user-id") args.userId = argv[++i];
    else if (a === "--out") args.out = argv[++i];
    else if (a === "--pages") {
      args.pages = String(argv[++i]).split(",").map((p) => {
        const [name, url] = p.split("=");
        return { name, url };
      });
    } else throw new Error(`unknown argument: ${a}`);
  }
  return args;
}

async function waitPastChallenge(page, seconds) {
  for (let i = 0; i < seconds; i++) {
    await page.waitForTimeout(1000);
    const t = await page.title().catch(() => "");
    if (t && !CHALLENGE.test(t)) return t;
  }
  return await page.title().catch(() => "");
}

async function storePage(page, outDir, slug, baseUrl) {
  const html = await page.content();
  const state = { url: page.url(), title: await page.title() };
  const bytes = Buffer.byteLength(html, "utf8");
  const hash = sha256(html);
  fs.writeFileSync(path.join(outDir, `${slug}.html`), html);
  const meta = {
    slug,
    url: state.url,
    title: state.title,
    fetchedAt: new Date().toISOString(),
    bytes,
    sha256: hash,
  };
  fs.writeFileSync(path.join(outDir, `${slug}.meta.json`), JSON.stringify(meta, null, 2) + "\n");
  return meta;
}

async function main() {
  const args = parseArgs(process.argv);
  const baseUrl = process.env.COMPASS_LOGIN_URL || DEFAULT_URL;
  const chrome = process.env.COMPASS_CHROME || DEFAULT_CHROME;
  const user = process.env.COMPASS_USERNAME;
  const pass = process.env.COMPASS_PASSWORD;
  if (!user || !pass) throw new Error("COMPASS_USERNAME and COMPASS_PASSWORD are required");

  const runId = new Date().toISOString().replace(/[:.]/g, "-");
  const outDir = path.join(args.out, args.child.toLowerCase(), runId);
  fs.mkdirSync(outDir, { recursive: true });

  const manifest = {
    child: args.child,
    runId,
    startedAt: new Date().toISOString(),
    fetcher: "patchright",
    loginUrl: baseUrl,
    loggedIn: false,
    secondFactor: false,
    pages: [],
    errors: [],
  };

  const browser = await chromium.launch({
    headless: true,
    executablePath: chrome,
    args: ["--no-sandbox", "--disable-dev-shm-usage", "--disable-blink-features=AutomationControlled"],
  });
  const ctx = await browser.newContext({
    locale: "en-AU",
    userAgent: process.env.COMPASS_UA || DEFAULT_UA,
    viewport: { width: 1280, height: 900 },
    timezoneId: "Australia/Melbourne",
  });
  const page = await ctx.newPage();

  try {
    await page.goto(baseUrl, { waitUntil: "domcontentloaded", timeout: 60000 });
    if (CHALLENGE.test(await waitPastChallenge(page, 40))) {
      manifest.errors.push("cloudflare_challenge_not_cleared");
      return 2;
    }

    await page.fill("#username", user);
    await page.fill("#password", pass);
    await page.click("#button1");
    if (CHALLENGE.test(await waitPastChallenge(page, 45))) {
      manifest.errors.push("cloudflare_login_post_challenge");
      return 2;
    }

    const stillLogin = await page.$("#username");
    const otp = await page.evaluate(() =>
      [...document.querySelectorAll("input")].some((i) => /otp|one-?time|passcode|verification|code/i.test((i.name || "") + " " + (i.id || ""))),
    );
    if (otp && stillLogin) {
      manifest.secondFactor = true;
      manifest.pages.push(await storePage(page, outDir, "second-factor-required", baseUrl));
      return 3;
    }
    if (stillLogin) {
      manifest.errors.push("login_rejected");
      manifest.pages.push(await storePage(page, outDir, "login-rejected", baseUrl));
      return 4;
    }
    manifest.loggedIn = true;
    manifest.pages.push(await storePage(page, outDir, "home", baseUrl));

    let userId = args.userId;
    if (!userId) {
      const match = (await page.content()).match(/Records\/User\.aspx\?userId=(\d+)/i);
      if (match) userId = match[1];
    }
    manifest.userId = userId || null;

    const pages = args.pages || DEFAULT_PAGES;
    for (const p of pages) {
      if (p.url.includes("{userId}") && !userId) {
        manifest.errors.push(`no_user_id:${p.name}`);
        continue;
      }
      const url = new URL(p.url.replace("{userId}", userId || ""), baseUrl).toString();
      await page.goto(url, { waitUntil: "domcontentloaded", timeout: 60000 });
      if (CHALLENGE.test(await waitPastChallenge(page, 40))) {
        manifest.errors.push(`challenge:${p.name}`);
        continue;
      }
      manifest.pages.push(await storePage(page, outDir, p.name, baseUrl));
    }
  } catch (err) {
    manifest.errors.push(String(err && err.message ? err.message : err));
  } finally {
    manifest.finishedAt = new Date().toISOString();
    fs.writeFileSync(path.join(outDir, "manifest.json"), JSON.stringify(manifest, null, 2) + "\n");
    await browser.close().catch(() => {});
  }

  console.log(`stored ${manifest.pages.length} page(s) to ${outDir}`);
  for (const p of manifest.pages) console.log(`  ${p.slug}: ${p.bytes} bytes sha256=${p.sha256} (${p.title})`);
  if (manifest.errors.length) console.error("errors: " + manifest.errors.join("; "));
  return manifest.errors.length ? 1 : 0;
}

main()
  .then((code) => process.exit(code))
  .catch((err) => {
    console.error(err);
    process.exit(1);
  });