Skip to content

feat(beholder)!: expand meta extraction with frontmatter-keys schema and Wappalyzer tag detection #878

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
YusukeHirao merged 1 commit into from
Jun 16, 2026
Merged

feat(beholder)!: expand meta extraction with frontmatter-keys schema and Wappalyzer tag detection #878

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
55 changes: 54 additions & 1 deletion cspell.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -40,6 +40,59 @@
"elif",

// code-review effort level
"xhigh"
"xhigh",

// HTML meta tag terms (frontmatter-keys.md)
"Fediverse",
"DCTERMS",
"dcterms",
"rdfa",
"Rdfa",
"noimageindex",
"noodp",
"noydir",
"indexifembedded",
"ahrefs",
"detectify",
"seznam",
"nositelinkssearchbox",
"nopagereadaloud",
"adsense",
"nopin",
"rels",
"gbfs",
"lrdd",

// Wappalyzer (technology fingerprint library)
"wappalyzer",
"Wappalyzer",

// Analytics / tag provider names + identifiers
"pintrk",
"optimizely",
"Optimizely",
"Tawk",
"tawk",
"grecaptcha",
"hjid",
"hjsv",
"fbevents",
"Matomo",
"matomo",
"sdkid",
"zdassets",
"cbid",
"XYZW",

// Microsoft verification / DCTERMS keys
"msvalidate",
"conformsto",
"isformatof",
"ispartof",
"isreferencedby",
"isreplacedby",
"isrequiredby",
"isversionof",
"tableofcontents"
]
}
3 changes: 2 additions & 1 deletion packages/@d-zero/beholder/package.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,7 +23,8 @@
"@d-zero/puppeteer-page-scan": "4.5.1",
"@d-zero/shared": "0.22.0",
"debug": "4.4.3",
"puppeteer": "24.37.5"
"puppeteer": "24.37.5",
"simple-wappalyzer": "1.1.99"
},
"devDependencies": {
"@types/debug": "4.1.12"
Expand Down
55 changes: 9 additions & 46 deletions packages/@d-zero/beholder/src/dom-evaluation.spec.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,6 +12,7 @@ import {
getMeta,
getProp,
} from './dom-evaluation.js';
import { emptyMeta } from './meta/classify.js';

afterEach(() => {
vi.useRealTimers();
Expand Down Expand Up @@ -41,68 +42,30 @@ function mockElementHandle(value: unknown): ElementHandle<Element> {
}

describe('getMeta', () => {
it('maps raw evaluation result into a Meta object and parses robots directives', async () => {
const page = mockPageEvaluate({
title: 'Example',
lang: 'ja',
description: 'desc',
keywords: 'a,b',
robots: 'noindex, NOFOLLOW',
canonical: 'https://example.com/',
alternate: 'https://example.com/en',
'og:type': 'website',
'og:title': 'OG Title',
'og:site_name': 'Site',
'og:description': 'OG desc',
'og:url': 'https://example.com/',
'og:image': 'https://example.com/img.png',
'twitter:card': 'summary',
});

const meta = await getMeta(page);

expect(meta).toStrictEqual({
title: 'Example',
lang: 'ja',
description: 'desc',
keywords: 'a,b',
noindex: true,
nofollow: true,
noarchive: false,
canonical: 'https://example.com/',
alternate: 'https://example.com/en',
'og:type': 'website',
'og:title': 'OG Title',
'og:site_name': 'Site',
'og:description': 'OG desc',
'og:url': 'https://example.com/',
'og:image': 'https://example.com/img.png',
'twitter:card': 'summary',
});
});

it('returns a minimal fallback when evaluation rejects', async () => {
it('returns emptyMeta() when page.evaluate rejects', async () => {
const page = {
evaluate: () => Promise.reject(new Error('execution context destroyed')),
content: () => Promise.resolve('<html></html>'),
} as unknown as Page;

const meta = await getMeta(page);
const meta = await getMeta(page, { url: 'https://example.com/' });

expect(meta).toStrictEqual({ title: '' });
expect(meta).toEqual(emptyMeta());
});

it('returns a minimal fallback when the main thread is unresponsive (timeout)', async () => {
it('returns emptyMeta() when the main thread is unresponsive (timeout)', async () => {
vi.useFakeTimers();
const page = {
// Never resolves — simulates a blocked main thread.
evaluate: () => new Promise(() => {}),
content: () => new Promise(() => {}),
} as unknown as Page;

const promise = getMeta(page, 5000);
const promise = getMeta(page, { url: 'https://example.com/' }, 5000);
await vi.advanceTimersByTimeAsync(5000);
const meta = await promise;

expect(meta).toStrictEqual({ title: '' });
expect(meta).toEqual(emptyMeta());
expect(vi.getTimerCount()).toBe(0);
});
});
Expand Down
Loading
Loading