fix: add error-graphic, icon-library, illustration filters to GENERIC_IMAGE_PATTERNS

- /404[-_]error/i, /error[-_]graphic/i — Broadcom 404-ERROR-GRAPHIC.png
- /\/icon[-_]library\//i — D-Link navigation/icon-library path images
- /[-_]illustration[._]/i — Arista Cloud-Legacy_Illustration and similar diagrams
- Nokia banner, Huawei marketing, banners/ path patterns (Playwright scraper)
- Cookie consent patterns synced to switch-image-fetcher.ts (was only in Playwright)
This commit is contained in:
Rene Fichtmueller 2026-04-21 07:38:01 +02:00
parent 88403eb7eb
commit 403a718119
2 changed files with 19 additions and 0 deletions

View File

@ -280,6 +280,18 @@ const GENERIC_IMAGE_PATTERNS: RegExp[] = [
// ── Generic about/press/brand pages ──────────────────────────────────────
/\/press[-_]kit/i,
/\/media[-_]kit/i,
// ── Vendor error / 404 graphics ──────────────────────────────────────────
/404[-_]error/i,
/error[-_]graphic/i,
// ── Navigation icon libraries ────────────────────────────────────────────
/\/icon[-_]library\//i,
// ── Diagrams and illustrations ───────────────────────────────────────────
/[-_]illustration[._]/i,
// ── Cookie consent / GDPR overlay images ────────────────────────────────
/cdn\.cookielaw\.org/i,
/cookiebot\.com/i,
/trustarc\.com/i,
/consent-manager/i,
];
function isGenericImage(url: string): boolean {

View File

@ -75,6 +75,13 @@ const GENERIC_IMAGE_PATTERNS: RegExp[] = [
/bg_products/i,
// Generic "banners" path segment used by CMSes
/\/banners?\//i,
// Vendor error / 404 graphics
/404[-_]error/i,
/error[-_]graphic/i,
// Navigation icon libraries (D-Link, other CMSes)
/\/icon[-_]library\//i,
// Diagrams and illustrations (not product photos)
/[-_]illustration[._]/i,
];
function isGenericImage(url: string): boolean {