packages/scraper/src/scrapers/fs-com.ts

@@ -58,7 +58,6 @@ import {
   upsertPriceObservation,
   upsertStockObservation,
   findOrCreateScrapedTransceiver,
-  markImageVerified,
   pool,
 } from "../utils/db";
 import { contentHash } from "../utils/hash";
@@ -74,7 +73,6 @@ const STOCK_FRESH_HOURS = parseInt(process.env["FS_STOCK_FRESH_HOURS"] ?? "12",
 const FORCE_REVALIDATE = process.env["TIP_FORCE_REVALIDATE"] === "1";
 const ONLY_MISSING_IMAGES = process.env["FS_ONLY_MISSING_IMAGES"] === "1";
 const DB_DETAIL_ONLY = process.env["FS_DB_DETAIL_ONLY"] === "1";
-const URL_DISCOVERY_ONLY = process.env["FS_URL_DISCOVERY_ONLY"] === "1";
 
 const PROXY_URLS = (process.env["PROXY_URLS"] ?? "")
   .split(",")
@@ -264,7 +262,6 @@ interface ProductSummary {
   url: string;
   name: string;
   partNumber: string;
-  targetTransceiverId?: string;
 }
 
 interface ProductDetail extends ProductSummary {
@@ -397,7 +394,7 @@ async function collectProductUrls(
 // ── Phase 2: Scrape product detail pages ──────────────────────────────────────
 
 async function scrapeProductDetails(
-  requests: Array<{ url: string; userData: { name: string; partNumber: string; targetTransceiverId?: string } }>,
+  requests: Array<{ url: string; userData: { name: string; partNumber: string } }>,
   proxyConfiguration: ProxyConfiguration | undefined
 ): Promise<ProductDetail[]> {
   // Purge Phase 2 storage so it starts with a clean request queue
@@ -428,9 +425,7 @@ async function scrapeProductDetails(
       const { name: listingName, partNumber: listingPn } = request.userData as {
         name: string;
         partNumber: string;
-        targetTransceiverId?: string;
       };
-      const { targetTransceiverId } = request.userData as { targetTransceiverId?: string };
       const url = request.url;
 
       try {
@@ -737,7 +732,6 @@ async function scrapeProductDetails(
         specs: raw.specs,
         imageUrl: resolveUrl(raw.imageUrl),
         datasheetUrl: resolveUrl(raw.datasheetUrl),
-        targetTransceiverId,
       });
     },
   }, makeCrawleeConfig("fs-phase2"));
@@ -795,34 +789,11 @@ export async function scrapeFs(): Promise<void> {
 
   // ── Phase 1: Discover product URLs ─────────────────────────────────────────
   let productMap: Map<string, ProductSummary>;
-  if (URL_DISCOVERY_ONLY) {
+  if (DB_DETAIL_ONLY) {
-    console.log("\n[Phase 1] URL discovery mode — probing FS.COM rows without product URLs…");
-    const dbRows = await pool.query(
-      `
-      SELECT t.id, t.part_number
-      FROM transceivers t
-      JOIN vendors v ON v.id = t.vendor_id
-      WHERE v.name = 'FS.COM'
-        AND COALESCE(t.product_page_url, '') = ''
-        AND t.part_number ~ '^FS-[0-9]+$'
-      ORDER BY t.part_number
-      LIMIT $1
-    `,
-      [MAX_DETAIL_PAGES_PER_RUN]
-    );
-    productMap = new Map(
-      dbRows.rows.map((row) => {
-        const partNumber = row.part_number as string;
-        const productId = partNumber.replace(/^FS-/, "");
-        const url = `${BASE_URL}/products/${productId}.html`;
-        return [url, { url, name: partNumber, partNumber, targetTransceiverId: row.id as string }];
-      })
-    );
-  } else if (DB_DETAIL_ONLY) {
     console.log("\n[Phase 1] DB detail-only mode — using existing FS.COM product URLs with missing verification signals…");
     const dbRows = await pool.query(
       `
-      SELECT t.id, t.part_number, t.product_page_url
+      SELECT t.part_number, t.product_page_url
       FROM transceivers t
       JOIN vendors v ON v.id = t.vendor_id
       WHERE v.name = 'FS.COM'
@@ -849,7 +820,7 @@ export async function scrapeFs(): Promise<void> {
       dbRows.rows.map((row) => {
         const url = normalizeFsProductUrl(row.product_page_url as string);
         const partNumber = row.part_number as string;
-        return [url, { url, name: partNumber, partNumber, targetTransceiverId: row.id as string }];
+        return [url, { url, name: partNumber, partNumber }];
       })
     );
   } else {
@@ -918,14 +889,7 @@ export async function scrapeFs(): Promise<void> {
   // ── Phase 2: Scrape detail pages ────────────────────────────────────────────
   const detailRequests = urlsToScrape.map((url) => {
     const s = productMap.get(url);
-    return {
+    return { url, userData: { name: s?.name ?? "FS.com Product", partNumber: s?.partNumber ?? "" } };
-      url,
-      userData: {
-        name: s?.name ?? "FS.com Product",
-        partNumber: s?.partNumber ?? "",
-        targetTransceiverId: s?.targetTransceiverId,
-      },
-    };
   });
 
   const details = await scrapeProductDetails(detailRequests, proxyConfiguration);
@@ -947,7 +911,7 @@ export async function scrapeFs(): Promise<void> {
       const textForInference = `${detail.name} ${detail.partNumber} ${Object.values(detail.specs).join(" ")}`;
       const fiberType = parsed.fiberType ?? detectFiberType(textForInference);
 
-      const transceiverId = detail.targetTransceiverId ?? (await findOrCreateScrapedTransceiver({
+      const transceiverId = await findOrCreateScrapedTransceiver({
         partNumber: detail.partNumber,
         vendorId,
         productUrl: detail.url,
@@ -960,37 +924,7 @@ export async function scrapeFs(): Promise<void> {
         wavelengths: parsed.wavelengths,
         imageUrl: detail.imageUrl,
         category: "DataCenter",
-        }));
+      });
-
-      if (detail.targetTransceiverId) {
-        await pool.query(
-          `UPDATE transceivers
-           SET product_page_url = COALESCE(NULLIF(product_page_url, ''), $2),
-               form_factor = COALESCE(NULLIF(form_factor, ''), $3),
-               speed_gbps = CASE WHEN speed_gbps IS NULL OR speed_gbps = 0 THEN COALESCE($4, speed_gbps) ELSE speed_gbps END,
-               speed = COALESCE(NULLIF(speed, ''), $5),
-               reach_label = COALESCE(NULLIF(reach_label, ''), $6),
-               reach_meters = CASE WHEN reach_meters IS NULL OR reach_meters = 0 THEN COALESCE($7, reach_meters) ELSE reach_meters END,
-               fiber_type = COALESCE(NULLIF(fiber_type, ''), $8),
-               wavelengths = COALESCE(NULLIF(wavelengths, ''), $9),
-               updated_at = NOW()
-           WHERE id = $1`,
-          [
-            transceiverId,
-            detail.url,
-            ff,
-            speedInfo?.speedGbps ?? null,
-            speedInfo?.speed ?? null,
-            reach ?? parsed.reachLabel ?? null,
-            parsed.reachMeters ?? null,
-            fiberType ?? null,
-            parsed.wavelengths ?? null,
-          ]
-        );
-        if (detail.imageUrl) {
-          await markImageVerified(transceiverId, detail.imageUrl);
-        }
-      }
 
       const stockLevel = deriveStockLevel(detail.deQty, detail.globalQty, detail.backorderQty);
       const totalQty = (detail.deQty ?? 0) + (detail.globalQty ?? 0);
@@ -1036,18 +970,14 @@ export async function scrapeFs(): Promise<void> {
       });
       if (stockNew) stockWritten++;
 
-      const hasSourceDetails =
+      if (Object.keys(detail.specs).length > 0) {
-        Object.keys(detail.specs).length > 0 ||
-        Boolean(fiberType || parsed.connector || parsed.wavelengths || parsed.reachLabel || reach);
-
-      if (hasSourceDetails) {
         const updated = await updateVerifiedSpecs({
           transceiverId,
           fiberType,
           connector: parsed.connector,
           wavelengths: parsed.wavelengths,
           reachMeters: parsed.reachMeters,
-          reachLabel: reach ?? parsed.reachLabel,
+          reachLabel: parsed.reachLabel,
           powerConsumptionW: parsed.powerConsumptionW,
           tempRange: parsed.tempRange,
           modulation: parsed.modulation,

sync/CURRENT.md

@@ -1,86 +1,9 @@
 # Current TIP Sync State
 
-Updated: 2026-05-09 11:59 UTC
+Updated: 2026-05-09 09:18 UTC
 
 ## Newest Work
 
-- Priority Crawlee evaluation + FS.com URL discovery on 2026-05-09:
-  - operator asked whether these repos help:
-    - `https://github.com/apify/crawlee`
-    - `https://github.com/apify/crawlee-python`
-    - `https://github.com/hiteshchoudhary/crawlee-project`
-  - evaluation:
-    - `apify/crawlee` is directly relevant and already in use in TIP via TypeScript `PlaywrightCrawler`
-    - current TIP benefit is not adding Crawlee, but using Crawlee more deliberately:
-      - bounded RequestQueues
-      - stable `uniqueKey`
-      - explicit retry/no-text classes
-      - isolated storage directories
-      - AutoscaledPool telemetry as safety signal
-      - hard concurrency caps on Erik
-    - `apify/crawlee-python` is useful for future isolated Pi/Proxmox workers, especially for Python-native extraction experiments, but should not replace the current TypeScript scraper core today
-    - `hiteshchoudhary/crawlee-project` is a small community/demo project, useful as inspiration only; not a production dependency for TIP
-  - code improved:
-    - `packages/scraper/src/scrapers/fs-com.ts`
-      - added `FS_URL_DISCOVERY_ONLY=1`
-      - maps existing `FS-<numeric-id>` rows without `product_page_url` to `https://www.fs.com/de/products/<id>.html`
-      - carries `targetTransceiverId` through the crawler so verified source evidence updates the original row instead of creating duplicates
-      - marks current FS.com product images verified for target rows
-      - accepts deterministic H1/part/spec evidence for detail verification when FS.com does not expose a traditional spec table
-  - live runs on Erik:
-    - URL discovery pilot:
-      - target `20`
-      - scraped `19`
-      - failed `0`
-      - no-url rows dropped from `76` to `57`
-    - full URL discovery:
-      - target `56`
-      - scraped `55`
-      - failed `1` (`https://www.fs.com/de/products/229461.html`, transient `ERR_NETWORK_CHANGED`)
-      - no-url rows dropped to `2`
-    - DB reconciliation with improved detail evidence:
-      - target `57`
-      - scraped `55`
-      - failed `0`
-      - new prices `41`
-      - stock observations `40`
-      - specs verified `55`
-    - `pnpm -C packages/scraper build` passed on Erik after the code change
-  - FS.com final state after URL discovery:
-    - total rows: `383`
-    - price verified: `379`
-    - image verified: `374`
-    - details verified: `373`
-    - price+image+details: `373`
-    - fully verified: `205`
-    - missing URL: `2`
-    - missing image URL: `9`
-    - missing reach label: `4`
-    - missing fiber type: `9`
-    - HTML product-like rows:
-      - total `373`
-      - image `372`
-      - details `371`
-      - complete `371`
-    - no-url rows:
-      - `Change`
-      - `FS-229461`
-    - category rows: `4`
-  - TIP health after run:
-    - status `healthy`
-    - load status `ok`
-    - memory used `13%`
-    - global verified counters:
-      - price `11557`
-      - image `10711`
-      - details `9929`
-      - fully `8526`
-  - training pool:
-    - pushed `4d9a11c crawl: add fscom url discovery learning record`
-  - truth:
-    - FS.com is still not 100% complete
-    - honest current claim: `371/373` HTML product-like rows complete; remaining work is small and classifiable
-
 - TIP FS.com / Fiberstore targeted verification push on 2026-05-09:
   - operator requested FS.com/Fiberstore next, with all crawler/scraper/robot learnings written to the TIPLLM training pool and no external AI
   - code improved:

sync/history/2026-05-09-crawlee-evaluation-and-fscom-url-discovery.md

@@ -1,118 +0,0 @@
-# Crawlee Evaluation and FS.com URL Discovery
-
-Date: 2026-05-09
-
-## Question
-
-Operator asked with highest priority whether these repositories help TIP:
-
-- `https://github.com/apify/crawlee`
-- `https://github.com/apify/crawlee-python`
-- `https://github.com/hiteshchoudhary/crawlee-project`
-
-## Evaluation
-
-`apify/crawlee` helps directly, but TIP already uses it in the TypeScript scraper stack. The priority is to harden our current usage rather than introduce a new crawler framework.
-
-Best immediate Crawlee practices for TIP:
-
-- keep per-vendor bounded runs
-- use stable `uniqueKey`/target IDs so retries do not create duplicate rows
-- keep Crawlee storage directories isolated per vendor/run class
-- record no-text and max-retry URLs as a separate retry class
-- use AutoscaledPool telemetry as a safety signal
-- keep Erik at low concurrency and move heavier work to Pi/Proxmox workers
-
-`apify/crawlee-python` is useful for future isolated worker experiments on Pi/Proxmox, especially where Python extraction libraries help. It should not replace the current TypeScript crawler core today.
-
-`hiteshchoudhary/crawlee-project` is a small community/demo app, not a production building block for TIP.
-
-## Code
-
-Changed:
-
-- `packages/scraper/src/scrapers/fs-com.ts`
-
-Added:
-
-- `FS_URL_DISCOVERY_ONLY=1`
-- target row propagation with `targetTransceiverId`
-- image verification for target rows
-- H1/part/spec deterministic detail verification when FS.com lacks a spec table
-
-## Live Runs
-
-URL discovery pilot:
-
-- target `20`
-- scraped `19`
-- failed `0`
-- no-url rows: `76` -> `57`
-
-Full URL discovery:
-
-- target `56`
-- scraped `55`
-- failed `1`
-- failed URL: `https://www.fs.com/de/products/229461.html`
-- no-url rows: `57` -> `2`
-
-DB reconciliation:
-
-- target `57`
-- scraped `55`
-- failed `0`
-- new prices `41`
-- stock observations `40`
-- specs verified `55`
-
-Build:
-
-- `pnpm -C packages/scraper build` passed on Erik
-
-## FS.com Final State
-
-- total rows: `383`
-- price verified: `379`
-- image verified: `374`
-- details verified: `373`
-- price+image+details: `373`
-- fully verified: `205`
-- missing URL: `2`
-- missing image URL: `9`
-- missing reach label: `4`
-- missing fiber type: `9`
-- HTML product-like rows: `373`
-- HTML product-like complete: `371`
-- no-url rows: `2`
-- category rows: `4`
-
-Remaining no-url rows:
-
-- `Change`
-- `FS-229461`
-
-TIP health after run:
-
-- status: `healthy`
-- load status: `ok`
-- memory used: `13%`
-- global image verified: `10711`
-- global details verified: `9929`
-- global fully verified: `8526`
-
-## Training Pool
-
-Pushed:
-
-- `4d9a11c crawl: add fscom url discovery learning record`
-
-## Next
-
-Do not claim FS.com is 100% complete yet. Remaining work:
-
-- classify `Change`
-- retry or classify `FS-229461`
-- classify 4 category rows
-- close 9 image/fiber gaps
-- then move to next high-value competitor with the same bounded Crawlee pattern