feat: AI生图功能丰富

extensions/collector/src/api/report.ts

@@ -5,6 +5,8 @@
 import type { TextMaterial } from '../collector/merge';
 
 export interface ReportProductPayload {
+  /** 后续批次写入首次上报创建的商品；调用方首次上报无需提供。 */
+  product_id?: string;
   source: {
     platform: string;
     itemId: string | null;
@@ -22,16 +24,24 @@ export interface ReportProductPayload {
   }>;
   /** 下载源图时需带的 Referer origin（如 https://detail.1688.com） */
   refererOrigin?: string;
+  /** 多批上报时，仅最后一批启动素材下载，避免同一商品出现并发重复下载。 */
+  process_assets?: boolean;
 }
 
 export interface ReportProductResult {
   product_id: string;
   stage?: string;
   assets_queued?: number;
+  assets_skipped?: number;
 }
 
-/** 上报采集结果到 ozon-seller-kit 后台（由 background 转发，绕 CORS） */
-export async function reportProduct(
+/**
+ * 后端单次最多接收 100 个素材；插件在此自动拆批，用户无需手动删减或分批上报。
+ * 所有批次共用首次返回的 product_id，且只在最后一批启动下载队列。
+ */
+const MATERIALS_BATCH_SIZE = 100;
+
+async function postMaterials(
   reportBaseUrl: string,
   payload: ReportProductPayload,
 ): Promise<ReportProductResult> {
@@ -44,3 +54,43 @@ export async function reportProduct(
   if (!res.ok) throw new Error(data?.detail || `上报失败 HTTP ${res.status}`);
   return data as ReportProductResult;
 }
+
+/** 上报采集结果到 ozon-seller-kit 后台（由 background 转发，绕 CORS）。 */
+export async function reportProduct(
+  reportBaseUrl: string,
+  payload: ReportProductPayload,
+): Promise<ReportProductResult> {
+  const batches = payload.images.length > 0
+    ? Array.from({ length: Math.ceil(payload.images.length / MATERIALS_BATCH_SIZE) }, (_, index) =>
+      payload.images.slice(index * MATERIALS_BATCH_SIZE, (index + 1) * MATERIALS_BATCH_SIZE),
+    )
+    : [[]];
+
+  let productId = payload.product_id;
+  let lastResult: ReportProductResult | null = null;
+  let assetsQueued = 0;
+  let assetsSkipped = 0;
+
+  for (let index = 0; index < batches.length; index += 1) {
+    try {
+      const result = await postMaterials(reportBaseUrl, {
+        ...payload,
+        product_id: productId,
+        // 文本仅需在首批写入；后续批次只追加素材，避免覆盖人工编辑的信息。
+        texts: index === 0 ? payload.texts : [],
+        images: batches[index],
+        process_assets: index === batches.length - 1,
+      });
+      productId = result.product_id;
+      lastResult = result;
+      assetsQueued += result.assets_queued ?? 0;
+      assetsSkipped += result.assets_skipped ?? 0;
+    } catch (error) {
+      const prefix = batches.length > 1 ? `第 ${index + 1}/${batches.length} 批上报失败：` : '';
+      throw new Error(prefix + (error instanceof Error ? error.message : String(error)));
+    }
+  }
+
+  if (!lastResult) throw new Error('上报未返回商品信息');
+  return { ...lastResult, assets_queued: assetsQueued, assets_skipped: assetsSkipped };
+}

extensions/collector/src/collector/detail-images.ts

@@ -7,20 +7,64 @@ import type { ImageMaterial } from './image';
 import type { SiteProfile } from '../profiles/types';
 
 const IMAGE_ATTRS = ['src', 'data-src', 'data-lazyload-src', 'data-original', 'data-lazy', 'data-ks-lazyload'];
+const IMAGE_EXTENSION_RE = /\.(?:avif|bmp|gif|jpe?g|png|webp)$/i;
+const IMAGE_EXTENSION_IN_PATH_RE = /\.(?:avif|bmp|gif|jpe?g|png|webp)\//i;
 
 function normalizeEscapedText(raw: string): string {
   return raw
     .replace(/\\u([0-9a-f]{4})/gi, (_, hex) => String.fromCharCode(Number.parseInt(hex, 16)))
     .replace(/\\x([0-9a-f]{2})/gi, (_, hex) => String.fromCharCode(Number.parseInt(hex, 16)))
+    // 1688/淘宝详情接口常把 HTML 放在 JSON/JS 字符串中。若不还原 \"，DOMParser
+    // 会把它编码为 %22，并可能把后面的真实 https URL 误解析成当前 CDN 的路径。
+    .replace(/\\(["'])/g, '$1')
     .replace(/\\\//g, '/');
 }
 
+function trimImageCandidate(value: string): string {
+  return value
+    .trim()
+    .replace(/[),;]+$/, '')
+    // “...jpg/” 是详情字符串错误拼接的常见形态，不是有效图片路径。
+    .replace(/(\.(?:avif|bmp|gif|jpe?g|png|webp))\/+$/i, '$1');
+}
+
+/**
+ * 修复被外层 CDN 路径/转义引号包裹的图片地址，例如：
+ * https://itemcdn.tmall.com/%22https://cbu01.alicdn.com/img/...jpg/
+ * 仅在检测到两个 URL 且内层是标准图片路径时取内层，正常带签名参数的 URL 保持原样。
+ */
+function recoverEmbeddedImageUrl(value: string): string | null {
+  let decoded = value;
+  try {
+    decoded = decodeURIComponent(value);
+  } catch {
+    // 非法百分号编码时仍按原文解析。
+  }
+  const matches = decoded.match(/https?:\/\/[^\s'"<>\\]+/gi) ?? [];
+  if (matches.length < 2) return null;
+
+  for (const match of matches.reverse()) {
+    const candidate = trimImageCandidate(match);
+    try {
+      const url = new URL(candidate);
+      if (/^https?:$/i.test(url.protocol) && IMAGE_EXTENSION_RE.test(url.pathname)) return url.href;
+    } catch {
+      // 继续检查更外层的候选。
+    }
+  }
+  return null;
+}
+
 function normalizeUrl(raw: string, baseUrl: string): string | null {
-  const value = raw.trim().replace(/^['"]|['"]$/g, '');
+  const cleaned = raw.trim().replace(/^['"]|['"]$/g, '');
+  const value = recoverEmbeddedImageUrl(cleaned) ?? cleaned;
   if (!value || /^data:|^javascript:|^blob:/i.test(value)) return null;
   try {
     const url = new URL(value, baseUrl);
-    return /^https?:$/i.test(url.protocol) ? url.href : null;
+    if (!/^https?:$/i.test(url.protocol)) return null;
+    // 不允许图片扩展名后仍跟路径段（如 .jpg/），该 URL 不会指向图片资源。
+    if (IMAGE_EXTENSION_IN_PATH_RE.test(url.pathname)) return null;
+    return url.href;
   } catch {
     return null;
   }
@@ -53,7 +97,7 @@ export function extractDetailImageUrls(raw: string, baseUrl: string): string[] {
   // 某些 1688 响应会把 HTML 包在 JS 字符串里；补扫图片 CDN 的 URL 字面量。
   const candidates = decoded.match(/(?:https?:)?\/\/[^\s'"<>\\]+/g) ?? [];
   for (const candidate of candidates) {
-    const url = normalizeUrl(candidate.replace(/[),;]+$/, ''), baseUrl);
+    const url = normalizeUrl(trimImageCandidate(candidate), baseUrl);
     if (!url) continue;
     const hostIsImageCdn = /(?:alicdn|taobaocdn|tmallcdn)\.com$/i.test(new URL(url).hostname);
     const hasImageExt = /\.(?:avif|bmp|gif|jpe?g|png|webp)(?:[?#]|$)/i.test(url);