Rene Fichtmueller 1aba912a15 fix(scrapers): fix ATGBics theme migration, NADDOD URL, disable VCELink
- ATGBics: update HTML parser from old card--product theme to new
  card__info theme (Shopify template changed April 2026); name now
  extracted from href link text instead of aria-label
- NADDOD: correct ensureVendor shop URL from /collections/transceivers
  (404) to /collection/optical-transceivers
- VCELink: disable scraper — site pivoted from optical transceivers to
  audio/video/cable products; all collection URLs return 404
2026-04-20 22:11:24 +02:00

331 lines
13 KiB
TypeScript

/**
* NADDOD Scraper v2 — Chinese compatible transceiver vendor
*
* naddod.com — Migrated from WooCommerce → Astro/Shopify-style in 2025.
* Product URLs: /products/XXXXX.html (numeric IDs, not category slugs)
* Sitemap: /sitemaps/products.xml
*
* Phase 1: Parse sitemap to collect all product URLs (plain HTTP)
* Phase 2: Fetch product detail pages — extract name, price, stock count
* Stock format: "In Stock: 543" (exact) | "In Stock: 2.1k+" (rounded) | "In Stock: Available" (boolean)
* Per-warehouse JSON (warehouse_stock: {us, nl, sg, cn}) is in a JS hydration
* payload that requires JS execution — only the display count is in plain HTML.
* → stock_confidence=2 (aggregated global count) for exact/rounded counts
* → stock_confidence=1 (boolean) for "Available" only
*
* Rate limited: 1 req/2sec.
*/
import { pool, findOrCreateScrapedTransceiver, ensureVendor, upsertPriceObservation, upsertStockObservation } from "../utils/db";
import { contentHash } from "../utils/hash";
const BASE = "https://www.naddod.com";
const SITEMAP_URL = `${BASE}/sitemaps/products.xml`;
const HEADERS = {
"User-Agent": "Mozilla/5.0 (compatible; TIP-Bot/1.0; research)",
Accept: "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8",
"Accept-Language": "en-US,en;q=0.9",
};
// Limit detail-page fetches per run to stay reasonable
const MAX_DETAIL_PAGES = 600;
function sleep(ms: number): Promise<void> {
return new Promise((resolve) => setTimeout(resolve, ms));
}
// ── Classification helpers ──────────────────────────────────────────────────
function detectFormFactor(text: string): string {
const t = text.toLowerCase();
if (/\bosfp\b/.test(t)) return "OSFP";
if (/\bqsfp.?dd800\b|\bqsfp.?dd\s+800\b/.test(t)) return "QSFP-DD800";
if (/\bqsfp.?dd\b/.test(t)) return "QSFP-DD";
if (/\bqsfp56\b/.test(t)) return "QSFP56";
if (/\bqsfp112\b/.test(t)) return "QSFP112";
if (/\bqsfp28\b/.test(t)) return "QSFP28";
if (/\bqsfp\+|\bqsfp\s*plus\b/.test(t)) return "QSFP+";
if (/\bsfp28\b/.test(t)) return "SFP28";
if (/\bsfp.?\+|10g.*sfp|sfp.*10g/.test(t)) return "SFP+";
if (/\bsfp\b/.test(t)) return "SFP";
if (/\bxfp\b/.test(t)) return "XFP";
return "SFP+"; // default
}
function detectSpeedGbps(text: string): { speed: string; speedGbps: number } {
const t = text.toUpperCase();
if (/\b800G\b|\b800GBE\b/.test(t)) return { speed: "800G", speedGbps: 800 };
if (/\b400G\b|\b400GBE\b/.test(t)) return { speed: "400G", speedGbps: 400 };
if (/\b200G\b|\b200GBE\b/.test(t)) return { speed: "200G", speedGbps: 200 };
if (/\b100G\b|\b100GBE\b/.test(t)) return { speed: "100G", speedGbps: 100 };
if (/\b40G\b|\b40GBE\b/.test(t)) return { speed: "40G", speedGbps: 40 };
if (/\b25G\b|\b25GBE\b/.test(t)) return { speed: "25G", speedGbps: 25 };
if (/\b10G\b|\b10GBE\b/.test(t)) return { speed: "10G", speedGbps: 10 };
if (/\b1G\b|\b1GBE\b|\bGIGABIT\b/.test(t)) return { speed: "1G", speedGbps: 1 };
return { speed: "Unknown", speedGbps: 0 };
}
function detectReach(text: string): { label: string; meters: number } | undefined {
const patterns: [RegExp, string, number][] = [
[/\b120\s*km\b/i, "120km", 120000],
[/\b80\s*km\b/i, "80km", 80000],
[/\b40\s*km\b/i, "40km", 40000],
[/\b20\s*km\b/i, "20km", 20000],
[/\b10\s*km\b/i, "10km", 10000],
[/\b2\s*km\b/i, "2km", 2000],
[/\b550\s*m\b/i, "550m", 550],
[/\b500\s*m\b/i, "500m", 500],
[/\b400\s*m\b/i, "400m", 400],
[/\b300\s*m\b/i, "300m", 300],
[/\b150\s*m\b/i, "150m", 150],
[/\b100\s*m\b/i, "100m", 100],
[/\bLR4\b/, "10km", 10000], [/\bLR\b/, "10km", 10000],
[/\bER4?\b/, "40km", 40000], [/\bZR4?\b/, "80km", 80000],
[/\bSR4?\b/, "300m", 300], [/\bDR4?\b/, "500m", 500],
[/\bFR4?\b/, "2km", 2000],
];
for (const [re, label, meters] of patterns) {
if (re.test(text)) return { label, meters };
}
return undefined;
}
function detectFiber(text: string): string {
if (/single.?mode|smf|[^a-z]lx[^a-z]|[^a-z]lr[^a-z]|[^a-z]er[^a-z]|[^a-z]zr[^a-z]|bidi|cwdm|dwdm/i.test(text)) return "SMF";
if (/multi.?mode|mmf|[^a-z]sx[^a-z]|[^a-z]sr[^a-z]/i.test(text)) return "MMF";
if (/copper|dac|twinax|rj.?45|base-t/i.test(text)) return "Copper";
return "";
}
function detectWavelength(text: string): string {
const m = text.match(/(\d{3,4})\s*nm/i);
return m ? m[1] : "";
}
function isTransceiver(name: string): boolean {
const lower = name.toLowerCase();
// Include: SFP, QSFP, OSFP, XFP, DAC/AOC cables count as transceivers for stock tracking
return /sfp|qsfp|osfp|xfp|transceiver|dac|aoc|cwdm|dwdm/i.test(lower);
}
// ── Stock parsing ───────────────────────────────────────────────────────────
/**
* Parse NADDOD stock display text.
* "In Stock: 543" → { qty: 543, confidence: 2 }
* "In Stock: 2.1k+" → { qty: 2100, confidence: 2 } (approximate, rounded)
* "In Stock: Available" → { qty: undefined, confidence: 1 }
* Returns null if no stock text found.
*/
function parseStockText(html: string): { qty?: number; confidence: 1 | 2 } | null {
// Look for "In Stock: X" pattern in page text
const m = html.match(/In\s+Stock[:\s]+([^\s<"]+)/i);
if (!m) return null;
const raw = m[1].trim().toLowerCase();
// "Available" = boolean only
if (/^avail/i.test(raw)) return { confidence: 1 };
// Numeric: "543" or "2.1k+" or "1.5k+"
const kMatch = raw.match(/^([\d.]+)k\+?$/);
if (kMatch) {
const qty = Math.round(parseFloat(kMatch[1]) * 1000);
return { qty: isNaN(qty) ? undefined : qty, confidence: 2 };
}
const exact = parseInt(raw.replace(/[^0-9]/g, ""), 10);
if (!isNaN(exact) && exact >= 0) return { qty: exact, confidence: 2 };
return { confidence: 1 }; // fallback: boolean
}
// ── HTTP helpers ────────────────────────────────────────────────────────────
async function fetchText(url: string): Promise<string> {
const resp = await fetch(url, { headers: HEADERS, signal: AbortSignal.timeout(30000) });
if (!resp.ok) throw new Error(`HTTP ${resp.status}`);
return resp.text();
}
/**
* Parse product detail page HTML → extract name, price, stock.
*/
function parseDetailPage(html: string, url: string): {
name: string;
price?: number;
stock: { qty?: number; confidence: 1 | 2 } | null;
} | null {
// Product name: og:title or <title> or <h1>
const ogTitle = html.match(/<meta\s+property="og:title"\s+content="([^"]+)"/i)?.[1];
const h1 = html.match(/<h1[^>]*>([^<]{15,})<\/h1>/i)?.[1]?.trim();
const titleTag = html.match(/<title[^>]*>([^<]+)<\/title>/i)?.[1]?.trim();
const name = (ogTitle || h1 || titleTag || "").replace(/\s+/g, " ").slice(0, 200);
if (!name || name.length < 10) return null;
if (!isTransceiver(name)) return null;
// Price: "US$ 10.90" or "$10.90"
const priceMatch = html.match(/US\$\s*([\d,]+\.?\d{0,2})/i) ||
html.match(/\$\s*([\d,]+\.\d{2})\b/);
const price = priceMatch ? parseFloat(priceMatch[1].replace(/,/g, "")) : undefined;
// Stock count
const stock = parseStockText(html);
return { name, price: price && price > 0 && price < 500000 ? price : undefined, stock };
}
// ── Sitemap parsing ─────────────────────────────────────────────────────────
async function fetchProductUrlsFromSitemap(): Promise<string[]> {
console.log(` Fetching sitemap: ${SITEMAP_URL}`);
const xml = await fetchText(SITEMAP_URL);
// Extract all <loc> URLs that match /products/XXXXX.html
const urls: string[] = [];
const locRegex = /<loc>([^<]+\/products\/\d+\.html)<\/loc>/gi;
let m: RegExpExecArray | null;
while ((m = locRegex.exec(xml)) !== null) {
const url = m[1].trim();
// Keep only canonical English URLs (no language prefix)
if (!url.includes("/en/") && !url.includes("/de/") && !url.includes("/fr/")) {
urls.push(url);
}
}
return [...new Set(urls)]; // deduplicate
}
// ── Main scraper ────────────────────────────────────────────────────────────
export async function scrapeNaddod(): Promise<void> {
console.log("=== NADDOD Scraper v2 Starting (sitemap + detail mode) ===\n");
const vendorId = await ensureVendor(
"NADDOD",
"compatible",
"https://www.naddod.com",
"https://www.naddod.com/collection/optical-transceivers",
);
// ── Phase 1: Discover product URLs via sitemap ────────────────────────────
console.log("[Phase 1] Discovering products from sitemap...");
let productUrls: string[] = [];
try {
productUrls = await fetchProductUrlsFromSitemap();
console.log(` Found ${productUrls.length} product URLs in sitemap`);
} catch (err) {
console.error(` Sitemap fetch failed: ${(err as Error).message}`);
return;
}
if (productUrls.length === 0) {
console.warn(" No product URLs found — aborting");
return;
}
// Limit to avoid excessive runtime
const urls = productUrls.slice(0, MAX_DETAIL_PAGES);
console.log(` Processing ${urls.length} products (limit: ${MAX_DETAIL_PAGES})`);
// ── Phase 2: Fetch detail pages + write to DB ─────────────────────────────
console.log("\n[Phase 2] Fetching product detail pages...");
let processed = 0;
let priceUpdates = 0;
let stockWritten = 0;
let stockSkipped = 0;
let skippedNonTx = 0;
let errors = 0;
for (const url of urls) {
await sleep(2000);
try {
const html = await fetchText(url);
const detail = parseDetailPage(html, url);
if (!detail) {
skippedNonTx++;
continue;
}
const { name, price, stock } = detail;
const { speed, speedGbps } = detectSpeedGbps(name);
const formFactor = detectFormFactor(name);
const reach = detectReach(name);
const fiberType = detectFiber(name);
const wavelength = detectWavelength(name);
// Extract part number from name (first word-group before "Compatible" or vendor name)
const partNumber = name.split(/\s+(?:compatible|for\s+[A-Z]|sfp|qsfp)/i)[0]?.trim().slice(0, 80) || name.slice(0, 60);
const txId = await findOrCreateScrapedTransceiver({
partNumber,
vendorId,
formFactor,
speedGbps,
speed,
reachMeters: reach?.meters,
reachLabel: reach?.label,
fiberType,
wavelengths: wavelength,
category: "DataCenter",
});
// Price observation
if (price && price > 0) {
const hash = contentHash({ price, part: partNumber });
const isNew = await upsertPriceObservation({
transceiverId: txId,
sourceVendorId: vendorId,
price,
currency: "USD",
stockLevel: stock?.qty !== undefined && stock.qty > 0 ? "in_stock" :
stock?.confidence === 1 ? "in_stock" : "on_request",
url,
contentHash: hash,
});
if (isNew) priceUpdates++;
}
// Stock observation
if (stock !== null) {
const stockLevel = stock.qty !== undefined ? (stock.qty > 0 ? "in_stock" : "out_of_stock") : "in_stock";
const isNew = await upsertStockObservation({
transceiverId: txId,
sourceVendorId: vendorId,
stockLevel,
quantityAvailable: stock.qty !== undefined && stock.qty > 0 ? stock.qty : undefined,
productUrl: url,
stockConfidence: stock.confidence,
priceCurrency: "USD",
priceIncludesTax: false,
});
if (isNew) stockWritten++;
else stockSkipped++;
}
processed++;
if (processed % 50 === 0) {
console.log(` Progress: ${processed}/${urls.length} | prices: ${priceUpdates} | stock: ${stockWritten} new / ${stockSkipped} unchanged`);
}
} catch (err) {
errors++;
if (errors <= 10) console.warn(` Error for ${url}: ${(err as Error).message.slice(0, 120)}`);
}
}
console.log("\n=== NADDOD Scraper v2 Complete ===");
console.log(` Products processed: ${processed}`);
console.log(` Non-transceivers skip: ${skippedNonTx}`);
console.log(` Price observations: ${priceUpdates} new`);
console.log(` Stock observations: ${stockWritten} new, ${stockSkipped} unchanged`);
if (errors > 0) console.warn(` Errors: ${errors}`);
}
if (require.main === module) {
scrapeNaddod()
.then(() => pool.end())
.catch((err) => { console.error("Fatal:", err); pool.end(); process.exit(1); });
}