refactor: replace DOM parsing with vision-based approach

Remove all CSS selectors, regex parsers, and structured extraction.
Instead, capture full-page screenshots (scrolling) and download detail
images. The model reads these directly with vision to extract logistics
data — no fragile DOM dependencies.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

SKILL.md

@@ -1,16 +1,16 @@
 ---
 name: 1688-logistics-scraper
-description: "Extract product weight/size/logistics data from 1688 product pages via Chrome browser, output structured JSON. Use when the user provides a 1688 product URL and needs logistics specs."
+description: "Scrape 1688 product pages via Chrome, capture full-page screenshots and detail images for vision-based extraction of weight/size/logistics data. Use when the user provides a 1688 product URL and needs logistics specs."
 ---
 
 # 1688 Logistics Scraper
 
-Extract product weight, size, and logistics data from 1688 product pages.
+Capture 1688 product pages for vision-based extraction of weight, size, and logistics data.
 
 ## Run
 
 ```bash
-bun scripts/run.ts scrape <url> [--dry-run]
+bun scripts/run.ts scrape <url> [--dry-run] [--port=9222]
 ```
 
 ### Examples
@@ -22,21 +22,12 @@ bun scripts/run.ts scrape 'https://detail.1688.com/offer/852504650877.html' --dr
 
 ## What It Does
 
-1. Opens the 1688 product URL in the browser (port 18800)
+1. Opens the 1688 product URL in the browser (default port 18800)
-2. Extracts weight/size data from wherever it appears on the page — product attributes, variant specs, 包装信息, 商品件重尺 table, logistics section
+2. Scrolls through the entire page, capturing **full-page screenshots** section by section
-3. Downloads detail images (商品详情图片) for analysis — weight/size is often only in images
+3. Downloads all **product detail images** (large images only, skips icons)
-4. Outputs structured JSON
+4. Saves everything to `/tmp/1688-logistics/<offer-id>/`
 
-## Where To Look For Data
+**No DOM parsing or regex.** The model reads the screenshots and images directly to extract logistics data.
-
-Weight/size data on 1688 pages hides in multiple places. Check all before giving up:
-
-1. **Product attributes** (商品属性 / 商品参数) — key-value table, most reliable
-2. **商品件重尺 table** — dedicated weight/dimensions/volume table for logistics
-3. **包装信息 section** — packaging type, box weight, box dimensions, units per box
-4. **Variant/SKU specs** — per-variant weight or size
-5. **Logistics section** — shipping weight, volume, freight info
-6. **Detail images** — downloaded to `/tmp/1688-logistics/<offer-id>/`, read them to find weight/size text baked into images
 
 ## Output
 
@@ -44,47 +35,36 @@ Weight/size data on 1688 pages hides in multiple places. Check all before giving
 {
   "status": "success",
   "url": "https://detail.1688.com/offer/...",
-  "product": {
+  "offerId": "852504650877",
-    "title": "产品标题",
+  "screenshots": [
-    "logistics": {
+    "/tmp/1688-logistics/852504650877/screenshots/page_001.png",
-      "weight": { "value": 0.5, "unit": "kg", "source": "attributes" },
+    "/tmp/1688-logistics/852504650877/screenshots/page_002.png",
-      "dimensions": { "length": 30, "width": 20, "height": 10, "unit": "cm", "source": "attributes" },
+    "/tmp/1688-logistics/852504650877/screenshots/page_003.png"
-      "grossWeight": null,
-      "netWeight": null,
-      "packageWeight": { "value": 2.0, "unit": "kg", "source": "packageInfo" },
-      "volume": null,
-      "shippingMethod": null,
-      "shippingCost": null,
-      "origin": null
-    },
-    "variants": [
-      { "name": "颜色: 红色", "weight": null, "dimensions": null }
   ],
-    "packageInfo": {
+  "detailImages": [
-      "packagingType": "纸箱",
+    "/tmp/1688-logistics/852504650877/images/img_001.jpg",
-      "packagingWeight": { "value": 2.0, "unit": "kg", "source": "packageInfo" },
+    "/tmp/1688-logistics/852504650877/images/img_002.jpg"
-      "packagingDimensions": { "length": 40, "width": 30, "height": 20, "unit": "cm", "source": "packageInfo" },
+  ]
-      "unitsPerPackage": 50,
-      "raw": { "包装方式": "纸箱", "箱规": "40*30*20cm", "装箱数": "50" }
-    },
-    "pieceWeightSize": {
-      "weight": { "value": 0.5, "unit": "kg", "source": "pieceWeightSize" },
-      "dimensions": { "length": 30, "width": 20, "height": 10, "unit": "cm", "source": "pieceWeightSize" },
-      "volume": null,
-      "raw": { "重量": "500g", "尺寸": "30*20*10cm" }
-    }
-  },
-  "detailImages": ["/tmp/1688-logistics/852504650877/img_001.jpg"],
-  "rawAttributes": { "重量": "0.5kg", "尺寸": "30*20*10cm" }
 }
 ```
 
-`null` = not found in text. Check `detailImages` — the data may be in the images.
+## After Running
+
+Read the screenshots and images to extract:
+
+- **Weight** (重量/毛重/净重/单件重量) — normalize to kg
+- **Dimensions** (尺寸/长宽高) — normalize to cm
+- **Volume** (体积/容积)
+- **Package info** (包装信息) — packaging type, box weight, box dimensions, units per box
+- **Piece weight/size** (商品件重尺) — per-piece logistics specs
+- **Variant-specific** weight/size if shown per SKU
+- **Shipping info** — method, cost, origin
+
+Output the extracted data as structured JSON.
 
 ## Rules
 
 1. If the browser is not running, report the error. Do not try to launch it.
-2. Check all data sources before reporting `null`.
+2. No retries. If it fails, report as-is.
-3. Normalize units: 克→kg, 毫米→cm. Keep raw values in `rawAttributes` and `raw` fields.
+3. Read ALL screenshots — logistics data can appear anywhere on the page.
-4. No retries. If it fails, report as-is.
+4. Read detail images too — weight/size is often baked into product photos.
-5. Trust page content. Do not guess values.

src/index.ts

@@ -3,67 +3,14 @@ import * as path from 'path';
 
 export type Command = 'scrape';
 
-export interface LogisticsValue {
-  value: number | null;
-  unit: string | null;
-  source: string;
-}
-
-export interface Dimensions {
-  length: number | null;
-  width: number | null;
-  height: number | null;
-  unit: string | null;
-  source: string;
-}
-
-export interface LogisticsData {
-  weight: LogisticsValue | null;
-  dimensions: Dimensions | null;
-  grossWeight: LogisticsValue | null;
-  netWeight: LogisticsValue | null;
-  packageWeight: LogisticsValue | null;
-  volume: LogisticsValue | null;
-  shippingMethod: string | null;
-  shippingCost: string | null;
-  origin: string | null;
-}
-
-export interface VariantInfo {
-  name: string;
-  weight: LogisticsValue | null;
-  dimensions: Dimensions | null;
-}
-
-export interface PackageInfo {
-  packagingType: string | null;
-  packagingWeight: LogisticsValue | null;
-  packagingDimensions: Dimensions | null;
-  unitsPerPackage: number | null;
-  raw: Record<string, string>;
-}
-
-export interface PieceWeightSize {
-  weight: LogisticsValue | null;
-  dimensions: Dimensions | null;
-  volume: LogisticsValue | null;
-  raw: Record<string, string>;
-}
-
 export interface ScrapeResult {
   status: 'success' | 'failed';
   url: string;
   command: Command;
   dryRun: boolean;
-  product?: {
+  offerId: string;
-    title: string;
+  screenshots?: string[];
-    logistics: LogisticsData;
-    variants: VariantInfo[];
-    packageInfo: PackageInfo;
-    pieceWeightSize: PieceWeightSize;
-  };
   detailImages?: string[];
-  rawAttributes?: Record<string, string>;
   error?: string;
 }
 
@@ -120,213 +67,87 @@ class CdpSession {
     return res?.result?.value;
   }
 
+  async captureScreenshot(format: string = 'png'): Promise<Buffer> {
+    const res = await this.send('Page.captureScreenshot', {
+      format,
+      captureBeyondViewport: true,
+    });
+    return Buffer.from(res.data, 'base64');
+  }
+
   close() {
     try { this.ws.close(); } catch {}
   }
 }
 
-// --- Parsers ---
+// --- Helpers ---
-
-const WEIGHT_KEYS = ['重量', '毛重', '净重', '单件重量', '包装重量', '产品重量', '单品重量', 'weight'];
-const DIMENSION_KEYS = ['尺寸', '规格', '长宽高', '外箱尺寸', '包装尺寸', '产品尺寸', '大小', 'size', 'dimensions'];
-const VOLUME_KEYS = ['体积', '容积', 'volume'];
 
 function extractOfferId(url: string): string {
   return url.match(/offer\/(\d+)/)?.[1] || 'unknown';
 }
 
-function parseWeight(raw: string): LogisticsValue | null {
+async function scrollAndCapture(
-  const m = raw.match(/([\d.]+)\s*(kg|g|克|千克|公斤|斤)/i);
+  cdp: CdpSession,
-  if (!m) return null;
+  outputDir: string,
-  let value = parseFloat(m[1]);
+): Promise<string[]> {
-  let unit = m[2].toLowerCase();
+  fs.mkdirSync(outputDir, { recursive: true });
-  if (unit === 'g' || unit === '克') { value /= 1000; unit = 'kg'; }
+  const saved: string[] = [];
-  if (unit === '千克' || unit === '公斤') unit = 'kg';
-  if (unit === '斤') { value *= 0.5; unit = 'kg'; }
-  return { value, unit, source: '' };
-}
 
-function parseDimensions(raw: string): Dimensions | null {
+  // Get page height
-  const m = raw.match(/([\d.]+)\s*[*xX×]\s*([\d.]+)\s*[*xX×]\s*([\d.]+)\s*(cm|mm|毫米|厘米|m|米)?/i);
+  const pageHeight: number = await cdp.evaluate(
-  if (!m) return null;
+    'Math.max(document.body.scrollHeight, document.documentElement.scrollHeight)'
-  let [l, w, h] = [parseFloat(m[1]), parseFloat(m[2]), parseFloat(m[3])];
+  ) || 0;
-  let unit = (m[4] || 'cm').toLowerCase();
+  const viewportHeight: number = await cdp.evaluate('window.innerHeight') || 900;
-  if (unit === 'mm' || unit === '毫米') { l /= 10; w /= 10; h /= 10; unit = 'cm'; }
-  if (unit === '厘米') unit = 'cm';
-  if (unit === 'm' || unit === '米') { l *= 100; w *= 100; h *= 100; unit = 'cm'; }
-  return { length: l, width: w, height: h, unit, source: '' };
-}
 
-function parseVolume(raw: string): LogisticsValue | null {
+  // Scroll through the page and capture screenshots
-  const m = raw.match(/([\d.]+)\s*(m³|cm³|L|ml|升|毫升|立方米|立方厘米)/i);
+  let scrollY = 0;
-  if (!m) return null;
+  let idx = 1;
-  return { value: parseFloat(m[1]), unit: m[2], source: '' };
+  while (scrollY < pageHeight) {
-}
+    await cdp.evaluate(`window.scrollTo(0, ${scrollY})`);
+    await new Promise(r => setTimeout(r, 500)); // wait for render
 
-function matchKey(text: string, keys: string[]): boolean {
+    const buf = await cdp.captureScreenshot('png');
-  const lower = text.toLowerCase();
+    const filePath = path.join(outputDir, `page_${String(idx).padStart(3, '0')}.png`);
-  return keys.some(k => lower.includes(k.toLowerCase()));
+    fs.writeFileSync(filePath, buf);
-}
+    saved.push(filePath);
 
-// --- Page extraction ---
+    scrollY += viewportHeight;
-
+    idx++;
-const JS_EXTRACT_ATTRS = `
-(function() {
-  const attrs = {};
-  const sels = [
-    '.detail-attributes-list .attributes-item',
-    '.obj-leading .obj-content li',
-    '#mod-detail-attributes .attribute-item',
-    '.detail-info table tr',
-    '[class*="attribute"] li',
-    '[class*="param"] li',
-    '.offer-attr-list .offer-attr-item',
-  ];
-  for (const sel of sels) {
-    document.querySelectorAll(sel).forEach(el => {
-      const parts = el.textContent.trim().split(/[:：]/);
-      if (parts.length >= 2) attrs[parts[0].trim()] = parts.slice(1).join(':').trim();
-    });
   }
-  document.querySelectorAll('table tr, .detail-attributes-list tr').forEach(tr => {
-    const cells = tr.querySelectorAll('td, th');
-    if (cells.length >= 2) attrs[cells[0].textContent.trim()] = cells[1].textContent.trim();
-  });
-  return JSON.stringify(attrs);
-})()`;
 
-const JS_EXTRACT_VARIANTS = `
+  return saved;
-(function() {
+}
-  const variants = [];
-  const sels = [
-    '.sku-item-wrapper .sku-item',
-    '[class*="sku"] [class*="item"]',
-    '.obj-sku .obj-content li',
-    '.unit-detail-spec-operator .spec-item',
-  ];
-  for (const sel of sels) {
-    document.querySelectorAll(sel).forEach(el => {
-      const name = el.textContent.trim().replace(/\\s+/g, ' ');
-      if (name && name.length < 200) variants.push({ name, text: el.textContent });
-    });
-  }
-  return JSON.stringify(variants);
-})()`;
 
-const JS_EXTRACT_TITLE = `
+async function downloadDetailImages(
-(function() {
+  cdp: CdpSession,
-  for (const sel of ['.title-text','.detail-title-text','h1[class*="title"]','.mod-detail-title h1','.d-title']) {
+  outputDir: string,
-    const el = document.querySelector(sel);
+): Promise<string[]> {
-    if (el && el.textContent.trim()) return el.textContent.trim();
+  // Get all detail image URLs from the page
-  }
+  const imgUrls: string[] = JSON.parse(await cdp.evaluate(`
-  return document.title || '';
+    (function() {
-})()`;
-
-const JS_EXTRACT_IMAGES = `
-(function() {
       const imgs = [], seen = new Set();
-  const sels = [
+      document.querySelectorAll('img').forEach(img => {
-    '#desc-lazyload-container img',
-    '.detail-desc-decorate-richtext img',
-    '[class*="detail-desc"] img',
-    '.mod-detail-description img',
-    '.offer-attr-item img',
-    '.desc-img-loaded img',
-  ];
-  for (const sel of sels) {
-    document.querySelectorAll(sel).forEach(img => {
         const src = img.src || img.dataset.src || img.dataset.lazySrc || '';
         if (src && !seen.has(src) && (src.startsWith('http') || src.startsWith('//'))) {
+          // Filter for product detail images (skip tiny icons/avatars)
+          if (img.naturalWidth > 200 || img.width > 200 || !img.complete) {
             seen.add(src);
             imgs.push(src.startsWith('//') ? 'https:' + src : src);
           }
-    });
         }
+      });
       return JSON.stringify(imgs);
-})()`;
+    })()
+  `) || '[]');
 
-const JS_EXTRACT_PACKAGE_INFO = `
-(function() {
-  const data = {};
-  // 包装信息 section — various selector patterns on 1688
-  const sels = [
-    '[class*="package-info"] li',
-    '[class*="packaging"] li',
-    '[class*="pack-info"] li',
-    '[class*="baozhuang"] li',
-    '.detail-packing li',
-  ];
-  for (const sel of sels) {
-    document.querySelectorAll(sel).forEach(el => {
-      const parts = el.textContent.trim().split(/[:：]/);
-      if (parts.length >= 2) data[parts[0].trim()] = parts.slice(1).join(':').trim();
-    });
-  }
-  // Also look for table rows inside 包装 sections
-  document.querySelectorAll('table').forEach(table => {
-    const header = table.previousElementSibling;
-    if (header && /包装/.test(header.textContent || '')) {
-      table.querySelectorAll('tr').forEach(tr => {
-        const cells = tr.querySelectorAll('td, th');
-        if (cells.length >= 2) data[cells[0].textContent.trim()] = cells[1].textContent.trim();
-      });
-    }
-  });
-  // Scan all key-value pairs for 包装 related keys
-  document.querySelectorAll('[class*="attribute"] li, [class*="param"] li, .offer-attr-list .offer-attr-item').forEach(el => {
-    const text = el.textContent.trim();
-    if (/包装/.test(text)) {
-      const parts = text.split(/[:：]/);
-      if (parts.length >= 2) data[parts[0].trim()] = parts.slice(1).join(':').trim();
-    }
-  });
-  return JSON.stringify(data);
-})()`;
-
-const JS_EXTRACT_PIECE_WEIGHT_SIZE = `
-(function() {
-  const data = {};
-  // 商品件重尺 table — dedicated logistics spec table on 1688
-  const sels = [
-    '[class*="piece-weight"] tr',
-    '[class*="jianzhongchi"] tr',
-    '[class*="weight-size"] tr',
-    '[class*="logistics-info"] tr',
-    '[class*="freight-info"] tr',
-  ];
-  for (const sel of sels) {
-    document.querySelectorAll(sel).forEach(tr => {
-      const cells = tr.querySelectorAll('td, th');
-      if (cells.length >= 2) data[cells[0].textContent.trim()] = cells[1].textContent.trim();
-    });
-  }
-  // Scan tables preceded by headers containing 件重尺
-  document.querySelectorAll('table').forEach(table => {
-    const header = table.previousElementSibling;
-    if (header && /件重尺|物流|运费/.test(header.textContent || '')) {
-      table.querySelectorAll('tr').forEach(tr => {
-        const cells = tr.querySelectorAll('td, th');
-        if (cells.length >= 2) data[cells[0].textContent.trim()] = cells[1].textContent.trim();
-      });
-    }
-  });
-  // Also check spans/divs in logistics area
-  document.querySelectorAll('[class*="logistics"] [class*="item"], [class*="freight"] [class*="item"]').forEach(el => {
-    const parts = el.textContent.trim().split(/[:：]/);
-    if (parts.length >= 2) data[parts[0].trim()] = parts.slice(1).join(':').trim();
-  });
-  return JSON.stringify(data);
-})()`;
-
-async function downloadImages(urls: string[], outputDir: string): Promise<string[]> {
   fs.mkdirSync(outputDir, { recursive: true });
   const saved: string[] = [];
-  for (let i = 0; i < urls.length; i++) {
+  for (let i = 0; i < imgUrls.length; i++) {
     try {
-      const resp = await fetch(urls[i]);
+      const resp = await fetch(imgUrls[i]);
       if (!resp.ok) continue;
       const buf = Buffer.from(await resp.arrayBuffer());
-      const ext = urls[i].match(/\.(jpg|jpeg|png|webp|gif)/i)?.[1] || 'jpg';
+      const ext = imgUrls[i].match(/\.(jpg|jpeg|png|webp|gif)/i)?.[1] || 'jpg';
       const p = path.join(outputDir, `img_${String(i + 1).padStart(3, '0')}.${ext}`);
       fs.writeFileSync(p, buf);
       saved.push(p);
@@ -344,29 +165,21 @@ export async function run(
   cdpPort: number = 18800,
 ): Promise<ScrapeResult> {
   if (command !== 'scrape') {
-    return { status: 'failed', url: '', command, dryRun, error: `unknown command: ${command}` };
+    return { status: 'failed', url: '', command, dryRun, offerId: '', error: `unknown command: ${command}` };
   }
 
   const url = args[0];
   if (!url) {
-    return { status: 'failed', url: '', command, dryRun, error: 'scrape requires <url>' };
+    return { status: 'failed', url: '', command, dryRun, offerId: '', error: 'scrape requires <url>' };
   }
 
+  const offerId = extractOfferId(url);
+
   if (dryRun) {
     return {
-      status: 'success', url, command, dryRun,
+      status: 'success', url, command, dryRun, offerId,
-      product: {
+      screenshots: [],
-        title: '<dry-run>',
-        logistics: {
-          weight: null, dimensions: null, grossWeight: null, netWeight: null,
-          packageWeight: null, volume: null, shippingMethod: null, shippingCost: null, origin: null,
-        },
-        variants: [],
-        packageInfo: { packagingType: null, packagingWeight: null, packagingDimensions: null, unitsPerPackage: null, raw: {} },
-        pieceWeightSize: { weight: null, dimensions: null, volume: null, raw: {} },
-      },
       detailImages: [],
-      rawAttributes: {},
     };
   }
 
@@ -378,121 +191,27 @@ export async function run(
     await cdp.send('Runtime.enable');
     await cdp.send('Page.navigate', { url });
 
-    // Wait for load
+    // Wait for page load + dynamic content
     await new Promise(r => setTimeout(r, 5000));
 
-    const title: string = await cdp.evaluate(JS_EXTRACT_TITLE) || '';
+    const outputDir = path.join('/tmp', '1688-logistics', offerId);
-    const rawAttributes: Record<string, string> = JSON.parse(await cdp.evaluate(JS_EXTRACT_ATTRS) || '{}');
-    const rawVariants: Array<{ name: string; text: string }> = JSON.parse(await cdp.evaluate(JS_EXTRACT_VARIANTS) || '[]');
-    const imgUrls: string[] = JSON.parse(await cdp.evaluate(JS_EXTRACT_IMAGES) || '[]');
 
-    const variants: VariantInfo[] = rawVariants.map(v => {
+    // Capture full-page screenshots (scrolling)
-      const weight = parseWeight(v.text);
+    const screenshotDir = path.join(outputDir, 'screenshots');
-      const dimensions = parseDimensions(v.text);
+    const screenshots = await scrollAndCapture(cdp, screenshotDir);
-      if (weight) weight.source = 'variant';
-      if (dimensions) dimensions.source = 'variant';
-      return { name: v.name, weight, dimensions };
-    });
 
-    const logistics: LogisticsData = {
+    // Download detail images
-      weight: null, dimensions: null, grossWeight: null, netWeight: null,
+    const imgDir = path.join(outputDir, 'images');
-      packageWeight: null, volume: null, shippingMethod: null, shippingCost: null, origin: null,
+    const detailImages = await downloadDetailImages(cdp, imgDir);
-    };
-
-    for (const [key, val] of Object.entries(rawAttributes)) {
-      if (matchKey(key, ['毛重'])) {
-        logistics.grossWeight = parseWeight(val);
-        if (logistics.grossWeight) logistics.grossWeight.source = 'attributes';
-      } else if (matchKey(key, ['净重'])) {
-        logistics.netWeight = parseWeight(val);
-        if (logistics.netWeight) logistics.netWeight.source = 'attributes';
-      } else if (matchKey(key, ['包装重量'])) {
-        logistics.packageWeight = parseWeight(val);
-        if (logistics.packageWeight) logistics.packageWeight.source = 'attributes';
-      } else if (matchKey(key, WEIGHT_KEYS)) {
-        logistics.weight = parseWeight(val);
-        if (logistics.weight) logistics.weight.source = 'attributes';
-      }
-      if (matchKey(key, DIMENSION_KEYS)) {
-        const parsed = parseDimensions(val);
-        if (parsed) { parsed.source = 'attributes'; logistics.dimensions = parsed; }
-      }
-      if (matchKey(key, VOLUME_KEYS)) {
-        const parsed = parseVolume(val);
-        if (parsed) { parsed.source = 'attributes'; logistics.volume = parsed; }
-      }
-      if (matchKey(key, ['产地', '发货地', '所在地'])) {
-        logistics.origin = val;
-      }
-    }
-
-    // Extract 包装信息
-    const rawPkgInfo: Record<string, string> = JSON.parse(await cdp.evaluate(JS_EXTRACT_PACKAGE_INFO) || '{}');
-    const packageInfo: PackageInfo = {
-      packagingType: null,
-      packagingWeight: null,
-      packagingDimensions: null,
-      unitsPerPackage: null,
-      raw: rawPkgInfo,
-    };
-    for (const [key, val] of Object.entries(rawPkgInfo)) {
-      if (matchKey(key, ['包装方式', '包装类型', '包装形式'])) packageInfo.packagingType = val;
-      if (matchKey(key, ['包装重量', '箱重'])) {
-        packageInfo.packagingWeight = parseWeight(val);
-        if (packageInfo.packagingWeight) packageInfo.packagingWeight.source = 'packageInfo';
-      }
-      if (matchKey(key, ['包装尺寸', '外箱尺寸', '箱规'])) {
-        packageInfo.packagingDimensions = parseDimensions(val);
-        if (packageInfo.packagingDimensions) packageInfo.packagingDimensions.source = 'packageInfo';
-      }
-      if (matchKey(key, ['装箱数', '每箱数量', '入数'])) {
-        const n = parseInt(val, 10);
-        if (!isNaN(n)) packageInfo.unitsPerPackage = n;
-      }
-    }
-
-    // Extract 商品件重尺
-    const rawPws: Record<string, string> = JSON.parse(await cdp.evaluate(JS_EXTRACT_PIECE_WEIGHT_SIZE) || '{}');
-    const pieceWeightSize: PieceWeightSize = {
-      weight: null,
-      dimensions: null,
-      volume: null,
-      raw: rawPws,
-    };
-    for (const [key, val] of Object.entries(rawPws)) {
-      if (matchKey(key, WEIGHT_KEYS)) {
-        pieceWeightSize.weight = parseWeight(val);
-        if (pieceWeightSize.weight) pieceWeightSize.weight.source = 'pieceWeightSize';
-      }
-      if (matchKey(key, DIMENSION_KEYS)) {
-        pieceWeightSize.dimensions = parseDimensions(val);
-        if (pieceWeightSize.dimensions) pieceWeightSize.dimensions.source = 'pieceWeightSize';
-      }
-      if (matchKey(key, VOLUME_KEYS)) {
-        pieceWeightSize.volume = parseVolume(val);
-        if (pieceWeightSize.volume) pieceWeightSize.volume.source = 'pieceWeightSize';
-      }
-    }
-
-    // Backfill logistics from pieceWeightSize if not found in attributes
-    if (!logistics.weight && pieceWeightSize.weight) logistics.weight = pieceWeightSize.weight;
-    if (!logistics.dimensions && pieceWeightSize.dimensions) logistics.dimensions = pieceWeightSize.dimensions;
-    if (!logistics.volume && pieceWeightSize.volume) logistics.volume = pieceWeightSize.volume;
-    if (!logistics.packageWeight && packageInfo.packagingWeight) logistics.packageWeight = packageInfo.packagingWeight;
-
-    const offerId = extractOfferId(url);
-    const imgDir = path.join('/tmp', '1688-logistics', offerId);
-    const detailImages = await downloadImages(imgUrls, imgDir);
 
     return {
-      status: 'success', url, command, dryRun,
+      status: 'success', url, command, dryRun, offerId,
-      product: { title, logistics, variants, packageInfo, pieceWeightSize },
+      screenshots,
       detailImages,
-      rawAttributes,
     };
   } catch (error) {
     return {
-      status: 'failed', url, command, dryRun,
+      status: 'failed', url, command, dryRun, offerId,
       error: error instanceof Error ? error.message : String(error),
     };
   } finally {