peoplelib/src/sources/standardebooks.js

const { fetchText, fetchJson, clampPage, decodeEntities, stripTags } = require('./http');

const BASE = 'https://standardebooks.org';
const PAGE_SIZE = 24;
const DETAIL_TTL = 5 * 60 * 1000;
const detailCache = new Map();

function absolute(url) {
  return url ? new URL(url, BASE).toString() : '';
}

function slugFromUrl(url) {
  return String(url || '').replace(/^https?:\/\/standardebooks\.org\/ebooks\//, '').replace(/^\/?ebooks\//, '').replace(/^\/+|\/+$/g, '');
}

function postId(slug) { return encodeURIComponent(slug); }

function parseCatalog(html) {
  const items = [];
  const re = /<li\s+typeof="schema:Book"\s+about="([^"]+)"([\s\S]*?)(?=<li\s+typeof="schema:Book"|<\/ol>)/g;
  let m;
  while ((m = re.exec(html))) {
    const slug = slugFromUrl(m[1]);
    const block = m[2];
    const title = stripTags((block.match(/property="schema:name">([\s\S]*?)<\/span>/) || [])[1] || '');
    const author = stripTags((block.match(/class="author"[^>]*>([\s\S]*?)<\/p>/) || [])[1] || '');
    const cover = (block.match(/<img[^>]*property="schema:image"[^>]*src="([^"]+)"/) || [])[1]
      || (block.match(/<img[^>]*src="([^"]+)"[^>]*property="schema:image"/) || [])[1] || '';
    if (!slug || !title) continue;
    items.push({
      postId: postId(slug),
      title,
      cover: absolute(decodeEntities(cover)),
      date: '',
      url: `${BASE}/ebooks/${slug}`,
      subtitle: author
    });
  }
  return items;
}

function catalogMaxPage(html, page) {
  const pages = Array.from(html.matchAll(/[?&]page=(\d+)/g)).map((m) => parseInt(m[1], 10));
  return Math.max(page, ...pages.filter(Number.isFinite));
}

function publicationToItem(p) {
  const metadata = p.metadata || {};
  const slug = slugFromUrl(metadata.identifier);
  // OPDS 的 author 可能是字符串、对象或两者混排的数组
  const raw = Array.isArray(metadata.author) ? metadata.author : (metadata.author ? [metadata.author] : []);
  const authors = raw.map((a) => (typeof a === 'string' ? a : (a && a.name) || '')).filter(Boolean);
  const image = (p.images || []).find((x) => x && x.href);
  return {
    postId: postId(slug),
    title: metadata.title || '(无标题)',
    cover: image ? absolute(image.href) : '',
    date: String(metadata.published || '').slice(0, 10),
    url: `${BASE}/ebooks/${slug}`,
    subtitle: authors.join(', ')
  };
}

function parseDetail(html, slug) {
  const title = stripTags((html.match(/<h1[^>]*property="schema:name"[^>]*>([\s\S]*?)<\/h1>/) || [])[1] || '');
  const authorBlock = (html.match(/<a[^>]*property="schema:author"[^>]*>([\s\S]*?)<\/a>/) || [])[1] || '';
  const author = stripTags((authorBlock.match(/property="schema:name"[^>]*>([\s\S]*?)<\/span>/) || [])[1] || authorBlock);
  const brief = decodeEntities((html.match(/<meta[^>]*property="schema:description"[^>]*content="([^"]*)"/) || [])[1] || '');
  const cover = (html.match(/<meta[^>]*property="schema:image"[^>]*content="([^"]+)"/) || [])[1] || '';
  const date = (html.match(/<meta[^>]*property="schema:datePublished"[^>]*content="([^"]+)"/) || [])[1] || '';
  const epub = (html.match(/<a[^>]*property="schema:contentUrl"[^>]*href="([^"]+)"[^>]*class="epub"/) || [])[1] || '';
  return { slug, title, author, brief, cover: absolute(cover), date, epub: absolute(epub) };
}

function validateSlug(post) {
  const slug = decodeURIComponent(post);
  if (!/^[a-z0-9-]+(?:\/[a-z0-9-]+)+$/i.test(slug)) throw new Error('无效的 Standard Ebooks ID');
  return slug;
}

async function loadDetail(post) {
  const slug = validateSlug(post);
  const cached = detailCache.get(slug);
  if (cached && cached.expiresAt > Date.now()) return cached.promise;
  const promise = fetchText(`${BASE}/ebooks/${slug}`).then((html) => {
    const detail = parseDetail(html, slug);
    if (!detail.title) throw new Error('未找到该图书');
    return detail;
  });
  detailCache.set(slug, { promise, expiresAt: Date.now() + DETAIL_TTL });
  while (detailCache.size > 50) detailCache.delete(detailCache.keys().next().value);
  try {
    return await promise;
  } catch (e) {
    detailCache.delete(slug);
    throw e;
  }
}

module.exports = {
  id: 'standardebooks',
  name: 'Standard Ebooks',
  supportsSearch: true,

  async list(page) {
    page = clampPage(page);
    const html = await fetchText(`${BASE}/ebooks?page=${page}&per-page=${PAGE_SIZE}&view=list`);
    return { items: parseCatalog(html), maxPage: catalogMaxPage(html, page), page };
  },

  async search(keyword, page) {
    page = clampPage(page);
    const j = await fetchJson(`${BASE}/feeds/opds/all?query=${encodeURIComponent(keyword)}&per-page=${PAGE_SIZE}&page=${page}`, {
      headers: { 'Accept': 'application/opds+json' }
    });
    const publications = j.publications || [];
    return {
      items: publications.map(publicationToItem).filter((x) => decodeURIComponent(x.postId)),
      maxPage: publications.length === PAGE_SIZE ? page + 1 : page,
      page
    };
  },

  async detail(postId) {
    const e = await loadDetail(postId);
    return {
      postId,
      title: e.title,
      cover: e.cover,
      authors: e.author ? [e.author] : [],
      date: e.date,
      tags: [],
      brief: e.brief,
      url: `${BASE}/ebooks/${e.slug}`,
      links: [{ name: 'Standard Ebooks 页', url: `${BASE}/ebooks/${e.slug}` }]
    };
  },

  async download(postId) {
    const e = await loadDetail(postId);
    if (!e || !e.epub) throw new Error('未找到 EPUB 下载');
    const url = new URL(e.epub);
    url.searchParams.set('source', 'download');
    return {
      files: [{
        name: `${e.title.replace(/[\\/:*?"<>|]/g, '_').slice(0, 60)}.epub`,
        link: url.toString(),
        format: 'EPUB'
      }],
      links: []
    };
  }
};