image-suite-studio/extension/src/collector/platforms/ozon.ts

/**
 * Ozon 采集编排（平台文件）：四路径合并（来自 extension-v2 生产逻辑）。
 *   ① SSR widget state（DOM data-state 属性，白名单）★主路径
 *   ② JSON-LD（schema.org/Product）
 *   ③ 站内页 JSON API（entrypoint-api.bx）
 *   ④ DOM data-widget 选择器兜底 + 详情图补充
 */
import { autoScrollToBottom, waitForAny } from '../dom';
import { collectImages, type ImageMaterial } from '../image';
import { collectTexts, mergeTexts, type TextMaterial } from '../text';
import { toOriginalUrl, toThumbUrl } from '../url';
import { extractJsonLd } from '../jsonld';
import { fetchOzonPageData, type OzonPageData } from '../ozon-api';
import { extractOzonState, type OzonStateData } from '../ozon-state';
import { finalize, mergeImages, type ScanResult } from '../merge';
import type { SiteProfile } from '../../profiles/types';

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 };
}

export 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';
  }

  // ── 路径④：DOM 采集（兜底 + 详情图补充）──
  // 先滚到底触发懒加载（详情图不滚不加载），有界滚动防无限推荐流
  await autoScrollToBottom();
  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);
}