@d-zero/beholder 2.1.5 → 3.0.0

package/dist/dom-evaluation.js

@@ -3,28 +3,49 @@
  *
  * These functions are called by {@link ./scraper.ts | Scraper.#fetchData} to extract
  * anchors, images, and meta information after page navigation completes.
+ *
+ * WHY timeouts everywhere: A page whose main thread is blocked (heavy JS, autoplay
+ * video players, infinite loops) makes every CDP round-trip hang. `getMeta` and
+ * `getImageList` therefore collect all data in a single `page.evaluate` and wrap it
+ * in {@link raceWithTimeout} so a blocked thread is abandoned after a bounded budget
+ * instead of accumulating per-property timeouts up to the caller's global timeout.
+ * Note that `page.evaluate` itself runs on the page's main thread and has no built-in
+ * timeout, so the surrounding race is what actually bounds the hang.
  * @see {@link ./types.ts} for the data types returned by these functions
  */
+import { raceWithTimeout } from '@d-zero/shared/race-with-timeout';
 import { domDetailsLog, domLog } from './debug.js';
+import { classify, emptyMeta } from './meta/classify.js';
+import { detectTags } from './meta/tag-detection.js';
 import { parseUrl } from './parse-url.js';
 const pid = `${process.pid}`;
 const log = domLog.extend(pid);
 const dLog = domDetailsLog.extend(pid);
+/**
+ * Default timeout (ms) applied to DOM evaluation operations when the caller does not
+ * specify one. Bounds how long a single `page.evaluate` / property read may hang on a
+ * page whose main thread is unresponsive.
+ *
+ * WHY 180s: Aligned with the upstream `Scraper#fetchData` retryable timeout (3 min) so
+ * a single phase does not exceed the retry budget while still tolerating large pages
+ * (e.g., 1000+ anchors) and slow main threads.
+ */
+export const DEFAULT_DOM_EVALUATION_TIMEOUT = 180_000;
 /**
  * Retrieves a DOM property value from a Puppeteer element handle with a timeout.
  *
- * Races the actual property retrieval against a 10-second timeout.
+ * Races the actual property retrieval against a timeout via {@link raceWithTimeout},
+ * which clears the loser-side timer so it cannot keep the event loop alive.
  * If the property cannot be read or the timeout expires, the fallback value is returned.
  * @template T - The expected type of the property value.
  * @param params - Parameters containing the element, property name, and fallback.
- * @returns The property value, or the fallback if retrieval fails.
+ * @param timeout - Timeout in ms before falling back. Defaults to {@link DEFAULT_DOM_EVALUATION_TIMEOUT}.
+ * @returns The property value, or the fallback if retrieval fails or times out.
  */
-export async function getProp(params) {
+export async function getProp(params, timeout = DEFAULT_DOM_EVALUATION_TIMEOUT) {
     const { $el, propName, fallback } = params;
-    return Promise.race([
-        _getProp($el, propName, fallback),
-        new Promise((res) => setTimeout(() => res(fallback), 10 * 1000)),
-    ]);
+    const { result, timeout: timedOut } = await raceWithTimeout(() => _getProp($el, propName, fallback), timeout);
+    return timedOut ? fallback : result;
 }
 /**
  * Internal implementation of property retrieval without timeout.
@@ -47,227 +68,509 @@ async function _getProp($el, propName, fallback) {
         return fallback;
     }
 }
-/**
- * Retrieves a DOM property value from the first element matching a CSS selector.
- *
- * Combines `page.$()` with {@link getProp} for convenient single-element lookups.
- * @template T - The expected type of the property value.
- * @param params - Parameters containing the page, selector, property name, and fallback.
- * @returns The property value, or the fallback if the element is not found or retrieval fails.
- */
-export async function getPropBySelector(params) {
-    const { page, selector, propName, fallback } = params;
-    const $el = await page.$(selector);
-    if (!$el) {
-        return fallback;
-    }
-    return getProp({ $el, propName, fallback });
-}
 /**
  * Extracts all `<img>` elements from the page and returns their properties.
  *
- * For each image, collects the `src`, `currentSrc`, `alt`, bounding box dimensions,
- * natural dimensions, lazy-loading status, and the outer HTML source code.
+ * Collects every image's `src`, `currentSrc`, `alt`, layout dimensions,
+ * natural dimensions, lazy-loading status, and outer HTML in a single
+ * `page.evaluate` call, wrapped in {@link raceWithTimeout}. On timeout (an
+ * unresponsive page) an empty array is returned rather than hanging.
  * @param page - The Puppeteer page to extract images from.
  * @param viewportWidth - The current viewport width in pixels, recorded alongside each image entry.
+ * @param timeout - Timeout in ms for the evaluation. Defaults to {@link DEFAULT_DOM_EVALUATION_TIMEOUT}.
  * @returns An array of {@link ImageElement} objects describing each image on the page.
  */
-export async function getImageList(page, viewportWidth) {
+export async function getImageList(page, viewportWidth, timeout = DEFAULT_DOM_EVALUATION_TIMEOUT) {
     log('Getting images (Viewport: %dpx)', viewportWidth);
-    const $images = await page.$$('img');
-    const imageList = [];
-    for (const $image of $images) {
-        const boundingBox = await $image.boundingBox();
-        const width = boundingBox?.width || 0;
-        const height = boundingBox?.height || 0;
-        const src = await getProp({ $el: $image, propName: 'src', fallback: '' });
-        const currentSrc = await getProp({
-            $el: $image,
-            propName: 'currentSrc',
-            fallback: '',
-        });
-        const alt = await getProp({ $el: $image, propName: 'alt', fallback: '' });
-        const naturalWidth = await getProp({
-            $el: $image,
-            propName: 'naturalWidth',
-            fallback: 0,
-        });
-        const naturalHeight = await getProp({
-            $el: $image,
-            propName: 'naturalHeight',
-            fallback: 0,
-        });
-        const loading = await getProp({ $el: $image, propName: 'loading', fallback: '' });
-        const sourceCode = await getProp({
-            $el: $image,
-            propName: 'outerHTML',
-            fallback: '',
-        });
-        const isLazy = loading.toLowerCase().trim() === 'lazy';
-        imageList.push({
-            src,
-            currentSrc,
-            alt,
-            width,
-            height,
-            naturalWidth,
-            naturalHeight,
-            isLazy,
-            viewportWidth,
-            sourceCode,
+    const { result, timeout: timedOut } = await raceWithTimeout(() => page
+        .evaluate(() => {
+        /* global document */
+        return [...document.images].map((img) => {
+            const rect = img.getBoundingClientRect();
+            return {
+                src: img.src,
+                currentSrc: img.currentSrc,
+                alt: img.alt,
+                width: rect.width,
+                height: rect.height,
+                naturalWidth: img.naturalWidth,
+                naturalHeight: img.naturalHeight,
+                loading: img.loading,
+                sourceCode: img.outerHTML,
+            };
         });
+    })
+        .catch(() => null), timeout);
+    if (timedOut || result == null) {
+        log('Image extraction timed out or failed (Viewport: %dpx); returning []', viewportWidth);
+        return [];
     }
+    const imageList = result.map(({ loading, ...img }) => ({
+        ...img,
+        isLazy: loading.toLowerCase().trim() === 'lazy',
+        viewportWidth,
+    }));
     log('Got %d images (Viewport: %dpx)', imageList.length, viewportWidth);
     dLog('Images are: %O', imageList.map((i) => i.src));
     return imageList;
 }
+/**
+ * One-shot warning latch: only the first time `_client()` is missing in a
+ * process do we log the degradation. Subsequent calls stay silent to avoid
+ * spamming logs while every page in a crawl re-enters the fallback path.
+ */
+let warnedAboutMissingClient = false;
+/**
+ * Returns puppeteer's internal CDP session for the page, or `null` if it is
+ * unreachable (e.g., test mocks, puppeteer wrappers that hide the internal API,
+ * or a future puppeteer release that renames `_client`).
+ *
+ * WHY a warning log: callers transparently fall back to textContent-only mode
+ * when this returns `null`, which masks a silent perf regression if a
+ * puppeteer update removes `_client`. The warning makes the degraded state
+ * observable in production logs so a maintainer can patch the access path.
+ *
+ * Callers fall back to a textContent-only path when this returns `null`.
+ * @param page - The Puppeteer page.
+ */
+function getInternalCDPClient(page) {
+    try {
+        const client = page._client?.();
+        if (!client) {
+            if (!warnedAboutMissingClient) {
+                warnedAboutMissingClient = true;
+                log('WARN: puppeteer Page._client() returned no session — getAnchorList ' +
+                    'falls back to textContent-only mode. Verify the installed puppeteer ' +
+                    'version still exposes the internal _client() accessor.');
+            }
+            return null;
+        }
+        return client;
+    }
+    catch (error) {
+        if (!warnedAboutMissingClient) {
+            warnedAboutMissingClient = true;
+            log('WARN: puppeteer Page._client() threw — getAnchorList falls back to ' +
+                'textContent-only mode. Error: %O', error);
+        }
+        return null;
+    }
+}
+/**
+ * Fetches the full accessibility tree once and builds a `backendDOMNodeId → accessibleName`
+ * map covering every AX node that exposes a backend DOM id.
+ *
+ * WHY include every non-ignored node (not just `role === 'link'`): the original
+ * `page.accessibility.snapshot({ root })` returned whatever AX node represented
+ * the anchor — including anchors whose computed role was overridden via ARIA
+ * (e.g., `<a role="button">`). Mapping every non-ignored node preserves that.
+ *
+ * WHY skip `ignored === true`: puppeteer's high-level snapshot uses
+ * `interestingOnly: true` by default and returns `null` for ignored nodes
+ * (aria-hidden, display:none, visibility:hidden). The old code then fell back
+ * to `textContent.trim()`. Including ignored nodes here would short-circuit
+ * that fallback with the AX tree's empty name and silently drop link text.
+ *
+ * On timeout or CDP failure, an empty map is returned so callers transparently
+ * fall back to `textContent.trim()` for every anchor.
+ * @param client - The CDP session attached to the page.
+ * @param timeout - Maximum time to wait for the AX tree fetch.
+ */
+async function buildAccessibleNameMap(client, timeout) {
+    const { result, timeout: timedOut } = await raceWithTimeout(() => client
+        .send('Accessibility.getFullAXTree')
+        .then((res) => res)
+        .catch((error) => {
+        log('Accessibility.getFullAXTree failed: %O', error);
+        return null;
+    }), timeout);
+    const map = new Map();
+    if (timedOut) {
+        log('Accessibility.getFullAXTree timed out after %dms', timeout);
+        return map;
+    }
+    if (!result?.nodes) {
+        return map;
+    }
+    for (const node of result.nodes) {
+        if (node.backendDOMNodeId == null || node.ignored === true) {
+            continue;
+        }
+        const name = typeof node.name?.value === 'string' ? node.name.value : '';
+        map.set(node.backendDOMNodeId, name);
+    }
+    return map;
+}
+/**
+ * Resolves a CDP backend node id for a given element handle.
+ *
+ * Wrapped in {@link raceWithTimeout} so a single hung `DOM.describeNode` cannot
+ * stall the outer `Promise.all` over every anchor on the page.
+ * @param client - The CDP session attached to the page (must be the same session
+ *                 that owns the handle's `objectId`).
+ * @param objectId - The remote object id of the element handle.
+ * @param timeout - Maximum time to wait for the describeNode call.
+ * @returns The backend node id, or `null` if unavailable / timed out / failed.
+ */
+async function resolveBackendNodeId(client, objectId, timeout) {
+    const { result, timeout: timedOut } = await raceWithTimeout(() => client
+        .send('DOM.describeNode', { objectId })
+        .then((res) => res)
+        .catch(() => null), timeout);
+    if (timedOut || !result) {
+        return null;
+    }
+    return result.node?.backendNodeId ?? null;
+}
 /**
  * Extracts all anchor (`<a>` and `<area>`) elements with `href` attributes from the page.
  *
  * For each anchor, resolves the `href` to an `ExURL` via `parseUrl`, retrieves
  * the accessible name (from the accessibility tree, falling back to `textContent`),
  * and filters out non-HTTP links.
+ *
+ * WHY Strategy F (single AX-tree fetch + parallel `DOM.describeNode`): the old
+ * implementation called `page.accessibility.snapshot({ root })` per anchor, which
+ * triggers a CDP round-trip *and* a Chrome-side AX subtree computation (~42ms
+ * each). On a page with 1181 anchors that compounded to ~53s. By fetching the
+ * full AX tree once and using `DOM.describeNode` in parallel to map element
+ * handles back to AX nodes by `backendDOMNodeId`, the same data is collected in
+ * ~150ms on the same page — a ~350× speed-up while preserving the original
+ * accessible-name semantics. See issue #876 for measurements.
+ *
+ * WHY the whole operation is wrapped in `raceWithTimeout`: even with bounded
+ * per-CDP-call timeouts, a degenerate page (blocked main thread, thousands of
+ * anchors, runaway describeNode latency) could chain enough sub-timeouts to
+ * exceed the caller's `timeout` budget. The outer race guarantees the function
+ * returns within `timeout`, surfacing whatever anchors were collected so far so
+ * the upstream scrape phase can continue rather than tripping a retryable retry.
  * @param page - The Puppeteer page to extract anchors from.
  * @param options - Optional URL parsing options (e.g., `disableQueries`).
+ * @param timeout - Total time budget in ms for the whole extraction. Defaults to {@link DEFAULT_DOM_EVALUATION_TIMEOUT}.
  * @returns An array of {@link AnchorData} objects for all HTTP(S) links found on the page.
  */
-export async function getAnchorList(page, options) {
+export async function getAnchorList(page, options, timeout = DEFAULT_DOM_EVALUATION_TIMEOUT) {
     log('Getting anchors');
     const $anchors = await page.$$('a[href], area[href]');
-    const anchorList = [];
-    for (const $anchor of $anchors) {
-        const $href = await getProp({ $el: $anchor, propName: 'href', fallback: '' });
-        const hrefVal = $href.toString();
-        const href = parseUrl(hrefVal, options);
+    if ($anchors.length === 0) {
+        log('Got 0 anchors');
+        return [];
+    }
+    const collected = [];
+    let axHits = 0;
+    let textFallbacks = 0;
+    // Set after the overall race trips so in-flight `resolveAnchor` calls can
+    // short-circuit instead of continuing to consume CDP capacity and pushing
+    // late entries into the already-returned `collected` array.
+    let cancelled = false;
+    const work = async () => {
+        const client = getInternalCDPClient(page);
+        if (cancelled)
+            return;
+        const nameByBackendId = client
+            ? await buildAccessibleNameMap(client, timeout)
+            : new Map();
+        if (cancelled)
+            return;
+        await Promise.all($anchors.map(async ($anchor) => {
+            if (cancelled)
+                return;
+            const resolved = await resolveAnchor($anchor, client, nameByBackendId, options, timeout);
+            if (cancelled || !resolved) {
+                return;
+            }
+            if (resolved.source === 'ax') {
+                axHits++;
+            }
+            else {
+                textFallbacks++;
+            }
+            collected.push(resolved.anchor);
+        }));
+    };
+    const { timeout: timedOut } = await raceWithTimeout(work, timeout);
+    cancelled = true;
+    if (timedOut) {
+        log('getAnchorList timed out after %dms; returning %d anchors collected so far', timeout, collected.length);
+    }
+    // Snapshot so post-return mutations from any in-flight Promise.all callback
+    // (already gated by `cancelled`, but not synchronously cancellable) cannot
+    // alter the array the caller now holds.
+    const result = [...collected];
+    log('Got %d anchors (%d via AX, %d via textContent)', result.length, axHits, textFallbacks);
+    dLog('Anchors are: %O', result.map((a) => a.href.href));
+    return result;
+}
+/**
+ * Resolves a single anchor handle into an {@link AnchorData} entry, or `null`
+ * if the anchor's href is not an HTTP(S) URL.
+ *
+ * Fires `getProp(href)` and `DOM.describeNode` in parallel, then looks up the
+ * accessible name from the pre-built AX map. If the anchor is not represented
+ * in the AX map (or CDP is unavailable), falls back to a lazy `textContent`
+ * fetch — only paying the extra CDP round-trip when actually needed.
+ * @param $anchor - The Puppeteer element handle for an anchor element.
+ * @param client - The shared CDP session, or `null` if unavailable.
+ * @param nameByBackendId - Map from `backendDOMNodeId` to accessible name.
+ * @param options - URL parsing options.
+ * @param timeout - Per-CDP-call timeout in ms.
+ * @returns The resolved anchor along with the name source, or `null` when the
+ *          anchor's href is not crawlable.
+ */
+async function resolveAnchor($anchor, client, nameByBackendId, options, timeout) {
+    try {
+        const objectId = $anchor.remoteObject().objectId;
+        const [hrefVal, backendNodeId] = await Promise.all([
+            getProp({ $el: $anchor, propName: 'href', fallback: '' }, timeout),
+            client && objectId != null
+                ? resolveBackendNodeId(client, objectId, timeout)
+                : Promise.resolve(null),
+        ]);
+        const href = parseUrl(hrefVal.toString(), options);
         if (!href || !href.isHTTP) {
-            continue;
+            return null;
         }
-        const axNode = await page.accessibility.snapshot({ root: $anchor });
-        const textContent = await getProp({
-            $el: $anchor,
-            propName: 'textContent',
-            fallback: '',
-        });
-        const accessibleName = axNode ? axNode.name || '' : textContent.trim();
-        const link = {
-            href,
-            textContent: accessibleName,
-        };
-        anchorList.push(link);
+        const axName = backendNodeId == null ? undefined : nameByBackendId.get(backendNodeId);
+        if (axName !== undefined) {
+            return { anchor: { href, textContent: axName }, source: 'ax' };
+        }
+        const textContent = await getProp({ $el: $anchor, propName: 'textContent', fallback: '' }, timeout);
+        return { anchor: { href, textContent: textContent.trim() }, source: 'text' };
+    }
+    catch (error) {
+        // `remoteObject()` (and other synchronous handle accesses) can throw when
+        // the handle is disposed (page navigated mid-extraction). Drop just this
+        // anchor rather than poisoning the Promise.all over every other anchor.
+        dLog('resolveAnchor failed for an anchor: %O', error);
+        return null;
     }
-    log('Got %d anchors', anchorList.length);
-    dLog('Anchors are: %O', anchorList.map((a) => a.href.href));
-    return anchorList;
 }
+const WINDOW_GLOBALS_TO_CHECK = [
+    'dataLayer',
+    'gtag',
+    'ga',
+    '_gaq',
+    'fbq',
+    '_fbq',
+    'clarity',
+    '_hjSettings',
+    '_hjid',
+    'twq',
+    'ttq',
+    '_linkedin_partner_id',
+    'pintrk',
+    'amplitude',
+    'mixpanel',
+    'analytics',
+    'heap',
+    'posthog',
+    'plausible',
+    'fathom',
+    '_paq',
+    's_account',
+    's',
+    'ym',
+    'UET',
+    'optimizely',
+    '_hsq',
+    'Sentry',
+    'Intercom',
+    'intercomSettings',
+    'drift',
+    'Tawk_API',
+    'zE',
+    'OneTrust',
+    'Cookiebot',
+    'Stripe',
+    'grecaptcha',
+];
 /**
- * Extracts comprehensive meta information from the page's `<head>`.
+ * Extracts comprehensive metadata from the page.
+ *
+ * Two passes happen in parallel:
+ * 1. Browser-side `collectHead()` serializes every `<meta>`, `<link>`,
+ *    relevant `<script>`, `<base>`, `<noscript>`/`<iframe>` and a curated
+ *    set of `window` globals into a `RawHeadEntry[]`. Node-side `classify()`
+ *    then maps those entries to typed `Meta` fields using the lookup tables
+ *    in `./meta/keys.ts`, with unknown entries preserved in `Meta.others`.
+ * 2. `detectTags()` runs `simple-wappalyzer` over the page HTML to produce
+ *    `Meta.tags` (technology detection + real-ID extraction).
  *
- * Collects the following metadata:
- * - `title` - The document title.
- * - `lang` - The `lang` attribute of the `<html>` element.
- * - `description` - The `<meta name="description">` content.
- * - `keywords` - The `<meta name="keywords">` content.
- * - `noindex` / `nofollow` / `noarchive` - Parsed from the `<meta name="robots">` directives.
- * - `canonical` - The `<link rel="canonical">` content.
- * - `alternate` - The `<link rel="alternate">` content.
- * - Open Graph tags: `og:type`, `og:title`, `og:site_name`, `og:description`, `og:url`, `og:image`.
- * - `twitter:card` - The Twitter Card type.
- * @param page - The Puppeteer page to extract meta information from.
- * @returns An object containing all extracted meta properties.
+ * The whole call is wrapped in `raceWithTimeout`. On timeout an empty `Meta`
+ * (with `title: ''` and empty required arrays/objects) is returned.
+ * @param page
+ * @param context
+ * @param timeout
+ * @example
+ * ```ts
+ * const meta = await getMeta(page, {
+ *   url: 'https://example.com/',
+ *   html: await page.content(),
+ *   statusCode: response.status,
+ *   headers: response.headers,
+ * });
+ * console.log(meta.title);                         // <title> text
+ * console.log(meta.og?.image);                     // og:image[] array
+ * console.log(meta.robots?.noindex);               // parsed robots
+ * console.log(meta.tags.detected.Analytics);       // Wappalyzer hits
+ * console.log(meta.tags.entries.find(e => e.provider === 'Google Analytics')?.id);
+ * ```
  */
-export async function getMeta(page) {
+export async function getMeta(page, context, timeout = DEFAULT_DOM_EVALUATION_TIMEOUT) {
     log('Getting Meta');
-    const robotsVal = await getPropBySelector({
-        page,
-        selector: 'meta[name="robots"]',
-        propName: 'content',
-        fallback: '',
-    });
-    const robots = new Set(robotsVal.split(',').map((robot) => robot.trim().toLowerCase()));
-    const meta = {
-        title: await getPropBySelector({
-            page,
-            selector: 'title',
-            propName: 'textContent',
-            fallback: '',
-        }),
-        lang: await getPropBySelector({
-            page,
-            selector: 'html',
-            propName: 'lang',
-            fallback: '',
-        }),
-        description: await getPropBySelector({
-            page,
-            selector: 'meta[name="description"]',
-            propName: 'content',
-            fallback: '',
-        }),
-        keywords: await getPropBySelector({
-            page,
-            selector: 'meta[name="keywords"]',
-            propName: 'content',
-            fallback: '',
-        }),
-        noindex: robots.has('noindex'),
-        nofollow: robots.has('nofollow'),
-        noarchive: robots.has('noarchive'),
-        canonical: await getPropBySelector({
-            page,
-            selector: 'link[rel="canonical"]',
-            propName: 'href',
-            fallback: '',
-        }),
-        alternate: await getPropBySelector({
-            page,
-            selector: 'link[rel="alternate"]',
-            propName: 'href',
-            fallback: '',
-        }),
-        'og:type': await getPropBySelector({
-            page,
-            selector: 'meta[property="og:type"]',
-            propName: 'content',
-            fallback: '',
-        }),
-        'og:title': await getPropBySelector({
-            page,
-            selector: 'meta[property="og:title"]',
-            propName: 'content',
-            fallback: '',
-        }),
-        'og:site_name': await getPropBySelector({
-            page,
-            selector: 'meta[property="og:site_name"]',
-            propName: 'content',
-            fallback: '',
-        }),
-        'og:description': await getPropBySelector({
-            page,
-            selector: 'meta[property="og:description"]',
-            propName: 'content',
-            fallback: '',
-        }),
-        'og:url': await getPropBySelector({
-            page,
-            selector: 'meta[property="og:url"]',
-            propName: 'content',
-            fallback: '',
-        }),
-        'og:image': await getPropBySelector({
-            page,
-            selector: 'meta[property="og:image"]',
-            propName: 'content',
-            fallback: '',
-        }),
-        'twitter:card': await getPropBySelector({
-            page,
-            selector: 'meta[name="twitter:card"]',
-            propName: 'content',
-            fallback: '',
-        }),
-    };
+    const { result, timeout: timedOut } = await raceWithTimeout(() => runGetMeta(page, context), timeout);
+    if (timedOut || result == null) {
+        log('Meta extraction timed out or failed; returning fallback');
+        return emptyMeta();
+    }
     log('Got meta');
-    dLog('Meta data are: %O', meta);
-    return meta;
+    dLog('Meta data are: %O', result);
+    return result;
+}
+/**
+ *
+ * @param page
+ * @param context
+ */
+async function runGetMeta(page, context) {
+    try {
+        const rawPromise = collectHeadOnPage(page);
+        const htmlPromise = context.html === undefined
+            ? page.content().catch(() => '')
+            : Promise.resolve(context.html);
+        const [raw, html] = await Promise.all([rawPromise, htmlPromise]);
+        const tags = await detectTags({
+            url: context.url,
+            html,
+            ...(context.statusCode === undefined ? {} : { statusCode: context.statusCode }),
+            ...(context.headers === undefined ? {} : { headers: context.headers }),
+        });
+        return classify(raw, {
+            tags,
+            ...(context.includeRaw ? { includeRaw: true } : {}),
+        });
+    }
+    catch (error) {
+        log('runGetMeta failed: %O', error);
+        return null;
+    }
+}
+/**
+ *
+ * @param page
+ */
+async function collectHeadOnPage(page) {
+    const raw = await page
+        .evaluate((knownGlobals) => {
+        const entries = [];
+        const html = document.documentElement;
+        entries.push({
+            kind: 'html',
+            lang: html.lang || undefined,
+            dir: html.dir || undefined,
+            xmlns: html.getAttribute('xmlns') ?? undefined,
+            prefix: html.getAttribute('prefix') ?? undefined,
+            vocab: html.getAttribute('vocab') ?? undefined,
+            typeOf: html.getAttribute('typeof') ?? undefined,
+            itemscope: html.hasAttribute('itemscope') || undefined,
+            itemtype: html.getAttribute('itemtype') ?? undefined,
+            amp: html.hasAttribute('amp') || undefined,
+            lightning: html.hasAttribute('⚡') || undefined,
+        }, { kind: 'title', content: document.title });
+        for (const base of document.querySelectorAll('base')) {
+            if (!(base instanceof HTMLBaseElement))
+                continue;
+            entries.push({
+                kind: 'base',
+                href: base.getAttribute('href') ?? undefined,
+                target: base.getAttribute('target') ?? undefined,
+            });
+        }
+        for (const meta of document.querySelectorAll('meta')) {
+            if (!(meta instanceof HTMLMetaElement))
+                continue;
+            const name = meta.getAttribute('name');
+            const property = meta.getAttribute('property');
+            const httpEquiv = meta.getAttribute('http-equiv');
+            const itemprop = meta.getAttribute('itemprop');
+            const charset = meta.getAttribute('charset');
+            const content = meta.getAttribute('content');
+            const media = meta.getAttribute('media');
+            entries.push({
+                kind: 'meta',
+                name: name ? name.toLowerCase() : undefined,
+                property: property ? property.toLowerCase() : undefined,
+                httpEquiv: httpEquiv ? httpEquiv.toLowerCase() : undefined,
+                itemprop: itemprop ?? undefined,
+                charset: charset ?? undefined,
+                content: content ?? undefined,
+                media: media ?? undefined,
+            });
+        }
+        for (const link of document.querySelectorAll('link[href]')) {
+            if (!(link instanceof HTMLLinkElement))
+                continue;
+            const relRaw = link.getAttribute('rel') ?? '';
+            const rel = relRaw.toLowerCase().split(/\s+/u).filter(Boolean);
+            entries.push({
+                kind: 'link',
+                rel,
+                href: link.getAttribute('href') ?? '',
+                type: link.getAttribute('type') ?? undefined,
+                media: link.getAttribute('media') ?? undefined,
+                sizes: link.getAttribute('sizes') ?? undefined,
+                title: link.getAttribute('title') ?? undefined,
+                hreflang: link.getAttribute('hreflang') ?? undefined,
+                as: link.getAttribute('as') ?? undefined,
+                crossorigin: link.getAttribute('crossorigin') ?? undefined,
+                color: link.getAttribute('color') ?? undefined,
+                blocking: link.getAttribute('blocking') ?? undefined,
+                imagesrcset: link.getAttribute('imagesrcset') ?? undefined,
+            });
+        }
+        const STRUCTURED_TYPES = new Set([
+            'application/ld+json',
+            'speculationrules',
+            'application/json+oembed',
+            'application/xml+oembed',
+        ]);
+        for (const script of document.querySelectorAll('script[type]')) {
+            if (!(script instanceof HTMLScriptElement))
+                continue;
+            const scriptType = (script.getAttribute('type') ?? '').toLowerCase();
+            if (!STRUCTURED_TYPES.has(scriptType))
+                continue;
+            const src = script.getAttribute('src') ?? undefined;
+            const text = script.textContent ?? '';
+            const inHead = !!script.closest('head');
+            const inNoscript = !!script.closest('noscript');
+            const location = inHead ? 'head' : inNoscript ? 'noscript' : 'body';
+            entries.push({
+                kind: 'script',
+                scriptType,
+                content: text || undefined,
+                src,
+                location,
+            });
+        }
+        for (const iframe of document.querySelectorAll('iframe[src]')) {
+            if (!(iframe instanceof HTMLIFrameElement))
+                continue;
+            const src = iframe.getAttribute('src') ?? '';
+            if (!src)
+                continue;
+            const inHead = !!iframe.closest('head');
+            const inNoscript = !!iframe.closest('noscript');
+            const location = inHead ? 'head' : inNoscript ? 'noscript' : 'body';
+            entries.push({ kind: 'iframe', src, location });
+        }
+        const win = window;
+        const presentGlobals = knownGlobals.filter((name) => win[name] !== undefined);
+        if (presentGlobals.length > 0) {
+            entries.push({ kind: 'window-global', names: presentGlobals });
+        }
+        return entries;
+    }, WINDOW_GLOBALS_TO_CHECK)
+        .catch(() => []);
+    return raw;
 }