transceiver-db/packages/scraper/src/scrapers/tscom.ts

/**
 * T&S Communication Scraper — Chinese compatible transceiver manufacturer
 *
 * www.china-tscom.com — product catalog with USD prices.
 * Paginated: /products/fiber-optic-transceivers/?page=N
 *
 * Rate limited: 1 req/2sec.
 */
import { pool, findOrCreateScrapedTransceiver, ensureVendor, upsertPriceObservation } from "../utils/db";
import { contentHash } from "../utils/hash";
import * as cheerio from "cheerio";

const BASE = "https://www.china-tscom.com";
const CATALOG_PATH = "/products/fiber-optic-transceivers/";
const MAX_PAGES = 15;
const HEADERS = {
  "User-Agent": "Mozilla/5.0 (compatible; TIP-Bot/1.0; research)",
  Accept: "text/html,application/xhtml+xml",
  "Accept-Language": "en-US,en;q=0.9",
};

interface Product {
  partNumber: string;
  name: string;
  url: string;
  price?: number;
  formFactor: string;
  speed: string;
  speedGbps: number;
  reachLabel?: string;
  reachMeters?: number;
  fiberType?: string;
  wavelength?: string;
}

function sleep(ms: number): Promise<void> {
  return new Promise((resolve) => setTimeout(resolve, ms));
}

function detectFormFactor(text: string): { formFactor: string; speed: string; speedGbps: number } {
  const lower = text.toLowerCase();
  if (lower.includes("osfp") && !lower.includes("qsfp")) return { formFactor: "OSFP", speed: "400G", speedGbps: 400 };
  if (lower.includes("qsfp-dd")) return { formFactor: "QSFP-DD", speed: "400G", speedGbps: 400 };
  if (lower.includes("qsfp28")) return { formFactor: "QSFP28", speed: "100G", speedGbps: 100 };
  if (lower.includes("qsfp+") || lower.includes("qsfp plus")) return { formFactor: "QSFP+", speed: "40G", speedGbps: 40 };
  if (lower.includes("sfp56")) return { formFactor: "SFP56", speed: "50G", speedGbps: 50 };
  if (lower.includes("sfp28") || lower.includes("25g")) return { formFactor: "SFP28", speed: "25G", speedGbps: 25 };
  if (lower.includes("sfp+") || lower.includes("10gbase") || lower.includes("10g")) return { formFactor: "SFP+", speed: "10G", speedGbps: 10 };
  if (lower.includes("xfp")) return { formFactor: "XFP", speed: "10G", speedGbps: 10 };
  if (lower.includes("1000base") || lower.includes("1g")) return { formFactor: "SFP", speed: "1G", speedGbps: 1 };
  if (lower.includes("sfp") && !lower.includes("qsfp")) return { formFactor: "SFP", speed: "1G", speedGbps: 1 };
  return { formFactor: "SFP+", speed: "10G", speedGbps: 10 };
}

function detectReach(text: string): { label: string; meters: number } | undefined {
  const patterns: [RegExp, string, number][] = [
    [/\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],
    [/\b300\s*m\b/i, "300m", 300],
    [/\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 [regex, label, meters] of patterns) {
    if (regex.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|rj45|base-t/i.test(text)) return "Copper";
  return "SMF";
}

function detectWavelength(text: string): string {
  const match = text.match(/(\d{3,4})\s*nm/i);
  return match ? match[1] : "";
}

function parseProductList(html: string): Product[] {
  const $ = cheerio.load(html);
  const products: Product[] = [];

  // Try common product grid/list selectors
  const cardSelectors = [
    ".product-item", ".product-card", ".item", "li.product",
    "article", ".product", ".col-product", ".entry",
  ];

  let found = false;
  for (const sel of cardSelectors) {
    if ($(sel).length >= 2) {
      $(sel).each((_i, el) => {
        const nameEl = $(el).find("h2, h3, h4, .product-name, .entry-title, a").first();
        const name = nameEl.text().trim();
        if (!name || name.length < 5 || !/sfp|qsfp|xfp|transceiver|optic/i.test(name)) return;

        const linkEl = $(el).find("a[href]").first();
        const href = linkEl.attr("href") || "";
        const url = href.startsWith("http") ? href : BASE + href;

        // USD price patterns
        const priceText = $(el).find(".price, .product-price, .amount, [data-price]").text();
        const priceMatch = priceText.match(/\$\s*([\d,]+\.?\d{0,2})/) ||
          priceText.match(/([\d,]+\.?\d{0,2})\s*USD/i);
        let price: number | undefined;
        if (priceMatch) {
          const parsed = parseFloat(priceMatch[1].replace(",", ""));
          if (parsed > 0 && parsed < 50000) price = parsed;
        }

        const skuText = $(el).find(".sku, [data-sku], .model, .part-number").text().trim();
        const partNumber = skuText ||
          name.match(/[A-Z0-9][-A-Z0-9]{5,}/)?.[0] ||
          name.replace(/\s+/g, "-").slice(0, 60);

        const ff = detectFormFactor(name);
        const reach = detectReach(name);

        products.push({
          partNumber,
          name,
          url,
          price,
          ...ff,
          reachLabel: reach?.label,
          reachMeters: reach?.meters,
          fiberType: detectFiber(name),
          wavelength: detectWavelength(name),
        });
      });
      if (products.length > 0) { found = true; break; }
    }
  }

  // Fallback: anchor-based extraction
  if (!found) {
    $("a[href]").each((_i, el) => {
      const name = $(el).text().trim();
      const href = $(el).attr("href") || "";
      if (name.length < 8 || name.length > 200 || !/sfp|qsfp|transceiver/i.test(name)) return;
      const url = href.startsWith("http") ? href : BASE + href;
      const ff = detectFormFactor(name);
      const reach = detectReach(name);
      products.push({
        partNumber: name.match(/[A-Z0-9][-A-Z0-9]{5,}/)?.[0] || name.replace(/\s+/g, "-").slice(0, 60),
        name, url, ...ff,
        reachLabel: reach?.label, reachMeters: reach?.meters,
        fiberType: detectFiber(name), wavelength: detectWavelength(name),
      });
    });
  }

  const seen = new Set<string>();
  return products.filter((p) => {
    if (!p.url || seen.has(p.url)) return false;
    seen.add(p.url);
    return true;
  });
}

async function fetchPage(url: string): Promise<string> {
  const resp = await fetch(url, { headers: HEADERS, signal: AbortSignal.timeout(30000) });
  if (!resp.ok) throw new Error(`HTTP ${resp.status} for ${url}`);
  return resp.text();
}

export async function scrapeTsCom(): Promise<void> {
  console.log("=== T&S Communication Scraper Starting ===\n");

  const vendorId = await ensureVendor(
    "T&S Communication",
    "compatible",
    "https://www.china-tscom.com",
    BASE + CATALOG_PATH,
  );

  let allProducts: Product[] = [];

  for (let page = 1; page <= MAX_PAGES; page++) {
    try {
      const url = page === 1
        ? BASE + CATALOG_PATH
        : `${BASE}${CATALOG_PATH}?page=${page}`;
      const html = await fetchPage(url);
      const pageProducts = parseProductList(html);
      allProducts.push(...pageProducts);
      console.log(`  Page ${page}: ${pageProducts.length} products`);
      if (pageProducts.length === 0) {
        console.log(`  Empty page ${page}, stopping pagination.`);
        break;
      }
      if (page < MAX_PAGES) await sleep(2000);
    } catch (err) {
      console.warn(`  Page ${page} failed: ${(err as Error).message}`);
      break;
    }
  }

  const seen = new Set<string>();
  allProducts = allProducts.filter((p) => {
    if (seen.has(p.url)) return false;
    seen.add(p.url);
    return true;
  });

  console.log(`\nTotal unique products: ${allProducts.length}`);

  let totalProducts = 0;
  let priceUpdates = 0;

  for (const product of allProducts) {
    try {
      const txId = await findOrCreateScrapedTransceiver({
        partNumber: product.partNumber,
        vendorId,
        formFactor: product.formFactor,
        speedGbps: product.speedGbps,
        speed: product.speed,
        reachMeters: product.reachMeters,
        reachLabel: product.reachLabel,
        fiberType: product.fiberType,
        wavelengths: product.wavelength,
        category: "DataCenter",
      });

      if (product.price && product.price > 0) {
        const hash = contentHash(JSON.stringify({ price: product.price, part: product.partNumber }));
        const updated = await upsertPriceObservation({
          transceiverId: txId,
          sourceVendorId: vendorId,
          price: product.price,
          currency: "USD",
          stockLevel: "in_stock",
          url: product.url,
          contentHash: hash,
        });
        if (updated) priceUpdates++;
      }
      totalProducts++;
    } catch (err) {
      console.warn(`  Error saving ${product.partNumber}: ${(err as Error).message.slice(0, 80)}`);
    }
  }

  console.log(`\n=== T&S Communication Complete: ${totalProducts} products, ${priceUpdates} prices ===`);
}

if (require.main === module) {
  scrapeTsCom()
    .then(() => pool.end())
    .catch((err) => { console.error("Fatal:", err); pool.end(); process.exit(1); });
}