feat: 插件开发 ozon 端主体完成

extension/src/collector/scan.ts

@@ -1,307 +1,21 @@
 /**
- * 统一采集引擎入口 - 扫描当前页
+ * 统一采集引擎入口 - 只做路由：按平台分发到 platforms/ 下的平台文件。
  *
- * 按平台选择采集策略：
- *   - ozon：四路径（SSR data-state ★主路径 → JSON-LD → 页 JSON API → DOM 兜底），多源合并
- *   - taobao/tmall：SSR（window.__ICE_APP_CONTEXT__）★主路径 + DOM 补充（详情图在 DOM 里）
- *   - 1688：纯 DOM（多套选择器变体）
- *
- * 各路径产出的素材最终走同一个合并器：文本按 kind 合并（params 按键并集），
- * 图片按组去重后重排 key。
+ * 平台编排逻辑（各路径与合并策略）见：
+ *   platforms/ozon.ts    Ozon 四路径（SSR data-state / JSON-LD / 站内 API / DOM）
+ *   platforms/taobao.ts  淘宝/天猫（桥读全局 / mtop 签名 API / DOM）
+ *   platforms/1688.ts    1688（桥读 window.context / detailUrl 详情 / DOM）
+ * 共用合并器见 merge.ts。
  */
 import { matchProfile } from '../profiles';
-import { waitForAny } from './dom';
-import { collectImages, type ImageMaterial } from './image';
-import { collectTexts, mergeTexts, type TextMaterial } from './text';
-import { extractJsonLd } from './jsonld';
-import { fetchOzonPageData, type OzonPageData } from './ozon-api';
-import { extractOzonState, type OzonStateData, type BreadcrumbItem } from './ozon-state';
-import { extractSSRData, type SSRData } from './ssr';
-import { buildFromSSR } from './ssr-builder';
-import { dedupeKey, toOriginalUrl, toThumbUrl } from './url';
-import type { SiteProfile } from '../profiles/types';
+import { readWindowKeys } from '../bridge/read-window';
+import { scanOzon } from './platforms/ozon';
+import { scanTaobao } from './platforms/taobao';
+import { scan1688 } from './platforms/1688';
+import type { ScanResult } from './merge';
 
-export type { ImageMaterial, TextMaterial };
-
-export interface ScanResult {
-  platform: string;
-  itemId: string | null;
-  url: string;
-  texts: TextMaterial[];
-  images: ImageMaterial[];
-  breadcrumbs: BreadcrumbItem[];
-  scannedAt: number;
-  stats: Record<string, number>; // 分组统计
-  warnings: string[];            // 警告（如详情图为 0）
-  source: 'state' | 'ssr' | 'jsonld' | 'api' | 'dom' | 'mixed'; // 主路径
-}
-
-const GROUP_ORDER: Array<{ key: ImageMaterial['groupKey']; name: string }> = [
-  { key: 'main', name: '主图' },
-  { key: 'sku', name: 'SKU图片' },
-  { key: 'detail', name: '详情图' },
-  { key: 'video', name: '视频' },
-];
-
-// ── Ozon：结构化合并（state + jsonld + api）───────────────────────────────
-
-interface StructuredBundle {
-  title?: string;
-  price?: string;
-  brand?: string;
-  description?: string;
-  characteristics: Array<{ key: string; value: string }>;
-  galleryImages: string[];
-  videos: string[];
-  videoCovers: string[];
-  skuVariants: Array<{ name: string; image?: string }>;
-}
-
-function mergeStructured(
-  state: OzonStateData,
-  jsonld: ReturnType<typeof extractJsonLd>,
-  api: OzonPageData | null
-): StructuredBundle {
-  const bundle: StructuredBundle = {
-    title: state.title || jsonld?.title || api?.title,
-    price: state.price || jsonld?.price || api?.price,
-    brand: jsonld?.brand,
-    description: api?.description || jsonld?.description,
-    characteristics: [...state.characteristics],
-    galleryImages: [...state.galleryImages],
-    videos: [...state.videos],
-    videoCovers: [...state.videoCovers],
-    skuVariants: [...state.skuVariants],
-  };
-
-  for (const u of api?.images ?? []) {
-    if (!bundle.galleryImages.includes(u)) bundle.galleryImages.push(u);
-  }
-  for (const u of api?.videos ?? []) {
-    if (!bundle.videos.includes(u)) bundle.videos.push(u);
-  }
-  const seenChars = new Set(bundle.characteristics.map((c) => `${c.key}::${c.value}`));
-  for (const c of api?.characteristics ?? []) {
-    const k = `${c.key}::${c.value}`;
-    if (!seenChars.has(k)) {
-      seenChars.add(k);
-      bundle.characteristics.push(c);
-    }
-  }
-
-  return bundle;
-}
-
-function buildFromBundle(profile: SiteProfile, bundle: StructuredBundle): {
-  texts: TextMaterial[];
-  images: ImageMaterial[];
-} {
-  const texts: TextMaterial[] = [];
-  const images: ImageMaterial[] = [];
-
-  if (bundle.title) texts.push({ kind: 'title', content: bundle.title });
-  if (bundle.price) texts.push({ kind: 'price', content: bundle.price });
-  if (bundle.brand) texts.push({ kind: 'brand', content: bundle.brand });
-  if (bundle.characteristics.length) {
-    texts.push({
-      kind: 'params',
-      content: bundle.characteristics.map((p) => `${p.key}: ${p.value}`).join('\n'),
-      pairs: bundle.characteristics,
-    });
-  }
-  if (bundle.description) texts.push({ kind: 'desc', content: bundle.description });
-
-  let idx = 0;
-  bundle.galleryImages.forEach((u, i) => {
-    const orig = toOriginalUrl(u, profile.originalUrlRules);
-    images.push({
-      key: `main-${String(i + 1).padStart(3, '0')}`,
-      groupKey: 'main',
-      groupName: '主图',
-      url: orig,
-      thumbUrl: toThumbUrl(orig),
-      index: idx++,
-      type: 'img',
-    });
-  });
-
-  bundle.skuVariants.forEach((s, i) => {
-    if (!s.image) return;
-    const orig = toOriginalUrl(s.image, profile.originalUrlRules);
-    images.push({
-      key: `sku-${String(i + 1).padStart(3, '0')}`,
-      groupKey: 'sku',
-      groupName: 'SKU图片',
-      variantName: s.name || undefined,
-      url: orig,
-      thumbUrl: toThumbUrl(orig),
-      index: idx++,
-      type: 'img',
-    });
-  });
-
-  bundle.videos.forEach((u, i) => {
-    images.push({
-      key: `video-${String(i + 1).padStart(3, '0')}`,
-      groupKey: 'video',
-      groupName: '视频',
-      url: u,
-      thumbUrl: bundle.videoCovers[i] ?? '',
-      index: idx++,
-      type: 'video',
-    });
-  });
-
-  return { texts, images };
-}
-
-// ── 统一合并器 ────────────────────────────────────────────────────────────
-
-/** 按组分组合并：靠前来源优先，靠后来源填缺，按 dedupeKey 去重后重排 index */
-function mergeImages(
-  primary: ImageMaterial[],
-  fallback: ImageMaterial[],
-  profile: SiteProfile
-): ImageMaterial[] {
-  const byGroup = new Map<string, ImageMaterial[]>();
-  const seen = new Set<string>();
-  let counter = 0;
-
-  const push = (m: ImageMaterial) => {
-    const k = m.groupKey === 'sku'
-      ? `${dedupeKey(m.url, profile.originalUrlRules)}::${m.variantName ?? ''}`
-      : dedupeKey(m.url, profile.originalUrlRules);
-    if (seen.has(k)) return;
-    seen.add(k);
-    const arr = byGroup.get(m.groupKey) ?? [];
-    arr.push({ ...m, index: counter++ });
-    byGroup.set(m.groupKey, arr);
-  };
-
-  for (const m of primary) push(m);
-  for (const m of fallback) push(m);
-
-  const out: ImageMaterial[] = [];
-  for (const g of GROUP_ORDER) {
-    const arr = byGroup.get(g.key);
-    if (!arr) continue;
-    arr.forEach((m, i) => {
-      m.key = `${g.key}-${String(i + 1).padStart(3, '0')}`;
-      m.groupName = g.name;
-    });
-    out.push(...arr);
-  }
-  return out;
-}
-
-function finalize(
-  profile: SiteProfile,
-  itemId: string | null,
-  texts: TextMaterial[],
-  images: ImageMaterial[],
-  breadcrumbs: BreadcrumbItem[],
-  source: ScanResult['source']
-): ScanResult {
-  const stats: Record<string, number> = {};
-  for (const img of images) stats[img.groupKey] = (stats[img.groupKey] ?? 0) + 1;
-
-  const warnings: string[] = [];
-  if (!texts.some((t) => t.kind === 'title')) warnings.push('未采集到标题');
-  if (images.length === 0) warnings.push('未扫描到任何图片/视频');
-  if ((stats.detail ?? 0) === 0) warnings.push('详情图为 0 张，请滚动到页面底部后重新采集');
-
-  return {
-    platform: profile.id,
-    itemId,
-    url: location.href,
-    texts,
-    images,
-    breadcrumbs,
-    scannedAt: Date.now(),
-    stats,
-    warnings,
-    source,
-  };
-}
-
-// ── 各平台策略 ────────────────────────────────────────────────────────────
-
-/** Ozon：四路径合并（来自 extension-v2 生产逻辑） */
-async function scanOzon(profile: SiteProfile, itemId: string | null): Promise<ScanResult> {
-  const state = extractOzonState();
-  let source: ScanResult['source'] = state.title || state.galleryImages.length ? 'state' : 'dom';
-
-  const jsonld = extractJsonLd();
-
-  let api: OzonPageData | null = null;
-  if (itemId) {
-    try {
-      api = await fetchOzonPageData(itemId);
-    } catch (err) {
-      console.warn('[SuiteCollector] API 提取异常:', err);
-    }
-  }
-
-  const bundle = mergeStructured(state, jsonld, api);
-  const structured = buildFromBundle(profile, bundle);
-  if ((structured.texts.some((t) => t.kind === 'title') || structured.images.length > 0) && source === 'dom') {
-    source = 'mixed';
-  }
-
-  const anchor = await waitForAny(profile.readySelectors, profile.readyTimeoutMs ?? 8_000);
-  if (!anchor) console.warn('[SuiteCollector] 等待页面就绪超时（继续尝试 DOM 采集）');
-  const domTexts = collectTexts(profile).materials;
-  const domImages = collectImages(profile);
-
-  const texts = mergeTexts(structured.texts, domTexts);
-  const images = mergeImages(structured.images, domImages, profile);
-  return finalize(profile, itemId, texts, images, state.breadcrumbs, source);
-}
-
-/** 淘宝/天猫：SSR 主路径 + DOM 补充（详情图、SKU 兜底都在 DOM 里） */
-async function scanTaobao(profile: SiteProfile, itemId: string | null): Promise<ScanResult> {
-  const ssrData: SSRData | null = extractSSRData();
-
-  let primaryTexts: TextMaterial[] = [];
-  let primaryImages: ImageMaterial[] = [];
-  let source: ScanResult['source'] = 'dom';
-  let breadcrumbs: BreadcrumbItem[] = [];
-
-  if (ssrData) {
-    const built = buildFromSSR(ssrData, profile);
-    // ssr-builder 的本地类型 groupKey 是 string，这里对齐到 ImageGroupKey
-    primaryTexts = built.texts;
-    primaryImages = built.images as ImageMaterial[];
-    source = 'ssr';
-  }
-
-  const anchor = await waitForAny(profile.readySelectors, profile.readyTimeoutMs ?? 10_000);
-  if (!anchor) console.warn('[SuiteCollector] 等待页面就绪超时（继续尝试 DOM 采集）');
-  const { materials: domTexts, missingRequired } = collectTexts(profile);
-  const domImages = collectImages(profile);
-
-  if (primaryImages.length > 0 && domImages.length > 0) source = 'mixed';
-
-  const texts = mergeTexts(primaryTexts, domTexts);
-  const images = mergeImages(primaryImages, domImages, profile);
-  const result = finalize(profile, itemId ?? ssrData?.item.itemId ?? null, texts, images, breadcrumbs, source);
-  if (missingRequired.length > 0) result.warnings.push(`缺少必需字段: ${missingRequired.join(', ')}`);
-  return result;
-}
-
-/** 1688：纯 DOM（多套画廊选择器变体覆盖线上版本） */
-async function scan1688(profile: SiteProfile, itemId: string | null): Promise<ScanResult> {
-  const anchor = await waitForAny(profile.readySelectors, profile.readyTimeoutMs ?? 10_000);
-  if (!anchor) console.warn('[SuiteCollector] 等待页面就绪超时（继续尝试 DOM 采集）');
-
-  const { materials: texts, missingRequired } = collectTexts(profile);
-  const images = collectImages(profile);
-  const result = finalize(profile, itemId, texts, images, [], 'dom');
-  if (missingRequired.length > 0) result.warnings.push(`缺少必需字段: ${missingRequired.join(', ')}`);
-  return result;
-}
-
-// ── 入口 ──────────────────────────────────────────────────────────────────
+export type { ScanResult };
+export type { ImageMaterial, TextMaterial } from './merge';
 
 export async function scanCurrentPage(): Promise<ScanResult | null> {
   const profile = matchProfile(location.href);
@@ -334,9 +48,16 @@ export async function scanCurrentPage(): Promise<ScanResult | null> {
   return result;
 }
 
+// 诊断工具：列出页面全局数据键（在商品页 console 跑 __SuiteCollector.probe()）
+export async function probeWindowKeys(): Promise<string[]> {
+  const res = await readWindowKeys(['*'], 1500);
+  return (res['__sc_window_keys__'] as string[]) ?? [];
+}
+
 // 暴露到全局供 side panel / console 调用
 if (typeof window !== 'undefined') {
   (window as any).__SuiteCollector = {
     scan: scanCurrentPage,
+    probe: probeWindowKeys,
   };
 }