feat: 初始化项目，并且接近完成 ozon 部分

2026-08-15 22:19:27 +08:00
commit 1591d5e35a
46 changed files with 9827 additions and 0 deletions
@@ -0,0 +1,146 @@
+/**
+ * 图片提取 - 主图、SKU、详情图、视频
+ * 从 extension-v1 移植，新增：
+ *   - srcset 处理（Ozon 画廊是 <img srcset> / <picture><source>）
+ *   - toOriginalUrl 传平台规则（Ozon /wc\d+/）
+ */
+import {
+  toAbsoluteUrl,
+  toOriginalUrl,
+  urlInBrackets,
+  looksLikeImageUrl,
+  dedupeKey,
+  pickBestFromSrcset,
+} from './url';
+import { queryAllDeep } from './dom';
+import type { ImageGroupKey, SiteProfile, SrcProp } from '../profiles/types';
+
+export interface ImageMaterial {
+  key: string;          // 'main-001'
+  groupKey: ImageGroupKey; // 'main'
+  groupName: string;    // '主图'
+  variantName?: string; // SKU 规格名（仅 sku 组）
+  url: string;          // 已还原为原图
+  thumbUrl: string;     // 页面上的原始小图地址
+  index: number;
+  type: 'img' | 'video';
+  width?: number;
+  height?: number;
+}
+
+/** 从元素上读出图片地址与名称，按 srcProps 顺序降级 */
+function readImageSource(
+  el: Element,
+  srcProps: SrcProp[],
+  nameSelectors?: string[]
+): { url: string; name: string; imgEl: HTMLImageElement | null } {
+  let url = '';
+  let name = '';
+  let imgEl: HTMLImageElement | null = el instanceof HTMLImageElement ? el : null;
+
+  for (const prop of srcProps) {
+    if (url) break;
+
+    if (prop === 'backgroundImage') {
+      if (el.tagName === 'IMG') {
+        const img = el as HTMLImageElement;
+        url = img.currentSrc || img.src || '';
+        name = img.alt || '';
+      } else {
+        const bg = getComputedStyle(el).backgroundImage || '';
+        const cand = (urlInBrackets(bg) || bg).replace(/['"]/g, '');
+        if (looksLikeImageUrl(cand)) url = cand;
+      }
+      continue;
+    }
+
+    if (prop === 'srcset') {
+      // <img srcset> 或 <source srcset>
+      const raw = el.getAttribute('srcset') || (el as any).srcset || '';
+      if (raw) url = pickBestFromSrcset(raw);
+      continue;
+    }
+
+    const raw = (el as any)[prop] || el.getAttribute(prop);
+    if (raw) {
+      // srcset 场景下 currentSrc 才是实际加载的那张
+      url = prop === 'src' ? ((el as HTMLImageElement).currentSrc || (el as HTMLImageElement).src || '') : raw;
+    }
+  }
+
+  // 选择器命中的是容器、图在子节点上
+  if (!url && el.tagName !== 'IMG') {
+    const inner = el.querySelector('img, source');
+    if (inner) {
+      const srcset = inner.getAttribute('srcset');
+      url = srcset
+        ? pickBestFromSrcset(srcset)
+        : inner.getAttribute('data-src') || (inner as HTMLImageElement).currentSrc || (inner as HTMLImageElement).src || '';
+      if (inner instanceof HTMLImageElement) imgEl = inner;
+      if (!name && inner instanceof HTMLImageElement) name = inner.alt || '';
+    }
+  }
+
+  // 名称统一取（SKU 规格名）
+  if (!name && nameSelectors?.length) {
+    for (const sel of nameSelectors) {
+      const t = el.querySelector(sel)?.textContent?.trim();
+      if (t) {
+        name = t;
+        break;
+      }
+    }
+  }
+
+  return { url: url ? toAbsoluteUrl(url) : '', name, imgEl };
+}
+
+export function collectImages(profile: SiteProfile): ImageMaterial[] {
+  const result: ImageMaterial[] = [];
+
+  for (const group of profile.imageGroups) {
+    const srcProps = group.srcProps ?? profile.defaultSrcProps;
+    // 去重按组独立：一张图同时是主图和 SKU 图是正常的
+    const seen = new Set<string>();
+    const activeSet = new Set(group.activeSelectors ? queryAllDeep(group.activeSelectors) : []);
+
+    for (const el of queryAllDeep(group.selectors)) {
+      if (activeSet.has(el)) continue;
+      if (group.excludeWithin?.some((sel) => el.closest(sel))) continue;
+
+      const { url: rawUrl, name, imgEl } = readImageSource(el, srcProps, group.nameSelectors);
+      if (!rawUrl) continue;
+
+      if (group.type === 'video' && !/\.(mp4|avi|mov|wmv|m3u8|webm)(\?|$)/i.test(rawUrl) && !/^blob:/i.test(rawUrl)) {
+        continue;
+      }
+
+      const url = group.type === 'img' ? toOriginalUrl(rawUrl, profile.originalUrlRules) : rawUrl;
+
+      // 尺寸过滤
+      if (group.type === 'img' && (group.minWidth || group.minHeight)) {
+        const measured = imgEl ?? (el as HTMLElement);
+        const w = (measured as HTMLImageElement).naturalWidth || (measured as HTMLElement).offsetWidth || 0;
+        const h = (measured as HTMLImageElement).naturalHeight || (measured as HTMLElement).offsetHeight || 0;
+        if (w > 0 && h > 0 && (w < (group.minWidth ?? 0) || h < (group.minHeight ?? 0))) continue;
+      }
+
+      const k = group.key === 'sku' ? `${dedupeKey(url, profile.originalUrlRules)}::${name}` : dedupeKey(url, profile.originalUrlRules);
+      if (seen.has(k)) continue;
+      seen.add(k);
+
+      result.push({
+        key: `${group.key}-${String(result.filter((r) => r.groupKey === group.key).length + 1).padStart(3, '0')}`,
+        groupKey: group.key,
+        groupName: group.name,
+        variantName: group.key === 'sku' ? name || undefined : undefined,
+        url,
+        thumbUrl: rawUrl,
+        index: result.length,
+        type: group.type,
+      });
+    }
+  }
+
+  return result;
+}