@cloud411716/fancy-webnovel 1.0.46 → 3.0.0

package/commands/scan/platforms/fanqie.js

@@ -1,146 +0,0 @@
-/**
- * fanqie.js — 番茄小说排行榜采集
- *
- * 策略（优先级递减）：
- *   1. 移动端页面（__INITIAL_STATE__ 内嵌数据）— 无需字体解密
- *   2. Playwright 浏览器  — 仅作为 fallback
- *
- * Playwright 通过 ctx.effect() 注册生命周期，Ctrl+C 时自动清理。
- * 使用 browserContext({ signal }) 确保 page.evaluate 也能响应中止信号。
- */
-
-export const platform = 'fanqie';
-export const label = '番茄';
-
-export const rankList = [
-  { id: '1_2', label: '男频阅读榜', channel: '1', type: '2' },
-  { id: '1_1', label: '男频新书榜', channel: '1', type: '1' },
-  { id: '0_2', label: '女频阅读榜', channel: '0', type: '2' },
-  { id: '0_1', label: '女频新书榜', channel: '0', type: '1' },
-];
-
-// 移动端页面（__INITIAL_STATE__ 内嵌数据）
-const MOBILE_BASE = 'https://m.reader.qq.com';
-
-/**
- * @param {object} ctx
- * @param {string} channel
- * @param {string} type
- * @param {AbortSignal} signal
- */
-async function mobileFetch(ctx, channel, type, signal) {
-  const url = `${MOBILE_BASE}/rank/${channel}_${type}.html`;
-  let timerDispose;
-  const timeout = new Promise((_, reject) => {
-    timerDispose = ctx.timeout(() => reject(new Error('timeout')), 15000);
-  });
-  try {
-    const res = await Promise.race([
-      fetch(url, {
-        headers: {
-          'User-Agent': 'Mozilla/5.0 (iPhone; CPU iPhone OS 17_0 like Mac OS X)',
-          'Accept': 'text/html',
-        },
-        signal,
-      }),
-      timeout,
-    ]);
-    if (!res.ok) throw new Error(`HTTP ${res.status}`);
-    const html = await res.text();
-    const m = html.match(/window\.__INITIAL_STATE__\s*=\s*(\{[\s\S]*?\});/);
-    if (!m) throw new Error('__INITIAL_STATE__ not found');
-    try {
-      return JSON.parse(m[1]);
-    } catch (_) {
-      throw new Error('__INITIAL_STATE__ JSON parse failed');
-    }
-  } finally {
-    try { timerDispose?.(); } catch (_) {}
-  }
-}
-
-/**
- * Scrape one rank list. Tries mobile → Playwright.
- * @param {string} rankId  - e.g. '1_2'
- * @param {object} ctx     - Cordis plugin context
- * @param {AbortSignal} signal
- * @returns {Promise<{ ok: boolean, books: object[], error?: string }>}
- */
-export async function scrapeRank(rankId, ctx, signal) {
-  const [channel, type] = rankId.split('_');
-
-  // 策略1: 移动端页面
-  try {
-    const data = await mobileFetch(ctx, channel, type, signal);
-    const books = parseMobileData(data);
-    if (books.length > 0) return { ok: true, books };
-  } catch (_) { /* try next strategy */ }
-
-  // 策略2: Playwright（通过 ctx.effect 注册生命周期，Ctrl+C 自动清理）
-  let browser;
-  const disposeEffect = ctx.effect(() => {
-    return () => { browser?.close(); };
-  }, 'fanqie: browser cleanup');
-
-  try {
-    const { chromium } = await import('playwright-core');
-    browser = await chromium.launch({ headless: true });
-    const context = await browser.newContext({ signal });
-    const page = await context.newPage();
-    const url = `https://www.fanqie.com/rank/${channel}_${type}/`;
-
-    await page.goto(url, { waitUntil: 'networkidle', signal });
-
-    const books = await page.evaluate(() => {
-      const s = window.__INITIAL_STATE__ || {};
-      let list = null;
-      for (const c of [s.rank, s.rankData, s.page]) {
-        if (c?.book_list) { list = c.book_list; break; }
-        if (c?.bookList)  { list = c.bookList;  break; }
-        if (c?.rankList)  { list = c.rankList;  break; }
-      }
-      if (!list || !Array.isArray(list)) return null;
-      return list.map((b, i) => ({
-        rank:   b.rank ?? (i + 1),
-        title:  b.title ?? b.bookName ?? '',
-        author: b.author ?? '',
-        category: '',
-        words:  b.wordCount ?? 0,
-        intro:  (b.description ?? '').slice(0, 150),
-        cover:  b.coverUrl ?? '',
-        bookId: b.bookId ?? '',
-      }));
-    });
-
-    // 嵌套 try-finally：context.close() 失败不影响 disposeEffect 执行
-    try {
-      await context.close();
-    } finally {
-      disposeEffect();
-    }
-
-    if (books && books.length > 0) return { ok: true, books };
-  } catch (_) { /* exhausted */ }
-
-  return { ok: false, books: [], error: 'all strategies exhausted' };
-}
-
-function parseMobileData(data) {
-  if (!data || typeof data !== 'object') return [];
-  let list = null;
-  const cands = [data.rank?.book_list, data.rank?.bookList, data.page?.bookList, data];
-  for (const c of cands) {
-    if (Array.isArray(c) && c.length > 0) { list = c; break; }
-  }
-  if (!list) return [];
-  return list.map((b, i) => ({
-    rank:   b.rank ?? (i + 1),
-    title:  b.title ?? b.name ?? '',
-    author: b.author ?? '',
-    category: '',
-    words:  b.wordCount ?? 0,
-    intro:  (b.description ?? '').slice(0, 150),
-    cover:  b.cover ?? '',
-    bookId: b.bookId ?? '',
-  }));
-}

package/commands/scan/platforms/jinjiang.js

@@ -1,143 +0,0 @@
-/**
- * jinjiang.js — 晋江文学城排行榜采集
- *
- * 策略：纯 HTTP + gb18030 解码。
- * 详情页使用 fetch + arrayBuffer + TextDecoder('gb18030')。
- * 无需 Playwright。
- */
-
-export const platform = 'jinjiang';
-export const label = '晋江';
-
-export const rankList = [
-  { id: '5',  label: '月榜',       channel: 'all', type: '5'  },
-  { id: '7',  label: '总分榜',     channel: 'all', type: '7'  },
-  { id: '4',  label: '季度榜',     channel: 'all', type: '4'  },
-  { id: '12', label: '收入金榜',   channel: 'all', type: '12' },
-  { id: '16', label: '完结金榜',   channel: 'all', type: '16' },
-  { id: '17', label: '新手金榜',   channel: 'all', type: '17' },
-];
-
-const BASE_URL = 'https://www.jjwxc.net/topten.php';
-const DETAIL_BASE = 'https://www.jjwxc.net/onebook.php';
-
-/**
- * Scrape one rank list.
- * @param {string} rankId  - orderstr, e.g. '5'
- * @param {object} ctx      - Cordis plugin context
- * @param {AbortSignal} signal
- * @returns {Promise<{ ok: boolean, books: object[], error?: string }>}
- */
-export async function scrapeRank(rankId, ctx, signal) {
-  const url = `${BASE_URL}?orderstr=${rankId}`;
-
-  // 1. 抓列表页
-  const { ok: listOk, status, body, error: listError } = await httpGet(ctx, url, signal);
-  if (!listOk) return { ok: false, books: [], error: listError ?? `HTTP ${status}` };
-
-  // 2. 解析书籍 ID 列表
-  const bookIds = extractBookIds(body);
-  if (!bookIds.length) return { ok: false, books: [], error: 'no book ids found' };
-
-  // 3. 批量补采详情（每批 6 本）
-  const CHUNK = 6;
-  const books = [];
-  for (let i = 0; i < bookIds.length; i += CHUNK) {
-    if (signal?.aborted) break;
-    const chunk = bookIds.slice(i, i + CHUNK);
-    const details = await Promise.all(chunk.map(id => fetchDetail(ctx, id, signal)));
-    for (const d of details) {
-      if (d) books.push(d);
-    }
-  }
-
-  return books.length > 0
-    ? { ok: true, books }
-    : { ok: false, books: [], error: 'no books collected' };
-}
-
-async function httpGet(ctx, url, signal) {
-  let timerDispose;
-  const timeout = new Promise((_, reject) => {
-    timerDispose = ctx.timeout(() => reject(new Error('timeout')), 15000);
-  });
-  try {
-    const res = await Promise.race([
-      fetch(url, {
-        headers: {
-          'User-Agent': 'Mozilla/5.0 (compatible; fancy-webnovel/1.0)',
-          'Accept': 'text/html',
-          'Accept-Language': 'zh-CN',
-        },
-        signal,
-      }),
-      timeout,
-    ]);
-    if (!res.ok) return { ok: false, status: res.status, body: '', error: `HTTP ${res.status}` };
-    const body = await res.text();
-    return { ok: true, status: res.status, body };
-  } catch (err) {
-    return { ok: false, status: 0, body: '', error: err.message };
-  } finally {
-    try { timerDispose?.(); } catch (_) {}
-  }
-}
-
-function extractBookIds(html) {
-  const ids = [];
-  // 两种布局：表格行和交替行
-  const tableRows = html.match(/<tr[^>]*>[\s\S]*?<\/tr>/gi) ?? [];
-  for (const row of tableRows) {
-    const m = row.match(/onebook\.php\?novelid=(\d+)/);
-    if (m) ids.push(m[1]);
-  }
-  // 交替行布局: 书名 / 作者 交替
-  if (!ids.length) {
-    const novelLinks = html.match(/novelid=(\d+)/g) ?? [];
-    for (const link of novelLinks) {
-      const id = link.match(/(\d+)/)?.[1];
-      if (id && !ids.includes(id)) ids.push(id);
-    }
-  }
-  return [...new Set(ids)].slice(0, 60); // 最多 60 本
-}
-
-async function fetchDetail(ctx, novelid, signal) {
-  let timerDispose;
-  const timeout = new Promise((_, reject) => {
-    timerDispose = ctx.timeout(() => reject(new Error('timeout')), 10000);
-  });
-  try {
-    const res = await Promise.race([
-      fetch(`${DETAIL_BASE}?novelid=${novelid}`, { signal }),
-      timeout,
-    ]);
-    if (!res.ok) return null;
-    const buf = await res.arrayBuffer();
-    const h = new TextDecoder('gb18030').decode(new Uint8Array(buf));
-
-    const prop = (/** @type {string} */ name) => {
-      const m = h.match(new RegExp(`itemprop="${name}"[^>]*>([^<]*)<`));
-      return m ? m[1].trim() : '';
-    };
-
-    return {
-      rank:   0,
-      title:  prop('title') || prop('novelname') || '',
-      author: prop('author') || '',
-      category: '',
-      words:  parseInt(prop('wordCount').replace(/[^\d]/g, ''), 10) || 0,
-      collect: prop('collectedCount') || '',
-      nutrition: prop('nutritionCount') || '',
-      score:  prop('scoreCount') || '',
-      status: (h.match(/(连载中|已完结|完结)/) || [, ''])[1],
-      intro:  (h.match(/<meta[^>]+name="description"[^>]+content="([^"]*)"/i)?.[1] ?? '').slice(0, 150),
-      cover:  '',
-      bookId: novelid,
-    };
-  } catch (_) {
-    return null;
-  } finally {
-    try { timerDispose?.(); } catch (_) {}
-  }
-}

package/commands/scan/platforms/qidian.js

@@ -1,102 +0,0 @@
-/**
- * qidian.js — 起点排行榜采集
- *
- * 策略：纯 HTTP mobile SSR。移动端页面在 script 标签里内嵌完整的
- * pageContext JSON，绕过了服务端渲染的加密，直接提取书籍数据。
- * 无需 Playwright。
- *
- * Rank paths (mobile, slug-based):
- *   /rank/hotsales/    畅销榜
- *   /rank/yuepiao/     月票榜
- *   /rank/newbook/     新书榜
- *   /rank/newauthor/   新人作者榜
- */
-
-const MOBILE_BASE = 'https://m.qidian.com';
-
-// rank.id → URL slug, matches RANK_PATHS keys used by scrapeRank()
-const RANK_PATHS = {
-  hotsales:  '/rank/hotsales/',
-  yuepiao:   '/rank/yuepiao/',
-  newbook:   '/rank/newbook/',
-  newauthor: '/rank/newauthor/',
-};
-
-export const platform = 'qidian';
-export const label = '起点';
-
-export const rankList = [
-  { id: 'hotsales',  label: '畅销榜',        channel: '1', type: 'hotsales'  },
-  { id: 'yuepiao',   label: '月票榜',         channel: '1', type: 'yuepiao'   },
-  { id: 'newbook',   label: '新书榜',          channel: '1', type: 'newbook'   },
-  { id: 'newauthor', label: '新人作者榜',       channel: '1', type: 'newauthor' },
-];
-
-const HEADERS = {
-  'User-Agent': 'Mozilla/5.0 (iPhone; CPU iPhone OS 17_0 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/17.0 Mobile/15E148 Safari/604.1',
-  'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
-  'Accept-Language': 'zh-CN,zh;q=0.9,en;q=0.8',
-  'Accept-Encoding': 'identity',
-};
-
-/**
- * Scrape one rank list.
- * @param {string} rankId   - rank id (e.g. 'hotsales')
- * @param {object} ctx      - Cordis plugin context
- * @param {AbortSignal} signal
- * @returns {Promise<{ ok: boolean, books: object[], error?: string }>}
- */
-export async function scrapeRank(rankId, ctx, signal) {
-  const path = RANK_PATHS[rankId];
-  if (!path) return { ok: false, books: [], error: `unknown rank: ${rankId}` };
-
-  const url = MOBILE_BASE + path;
-
-  const { ok, status, body, error } = await httpGet(ctx, url, signal);
-  if (!ok) return { ok: false, books: [], error: error ?? `HTTP ${status}` };
-
-  // Extract pageContext from <script id="vite-plugin-ssr_pageContext">
-  const m = body.match(/<script[^>]+id=["']vite-plugin-ssr_pageContext["'][^>]*>([\s\S]*?)<\/script>/i);
-  if (!m) return { ok: false, books: [], error: 'pageContext not found' };
-
-  let pageContext;
-  try {
-    pageContext = JSON.parse(m[1]);
-  } catch {
-    return { ok: false, books: [], error: 'pageContext JSON parse failed' };
-  }
-
-  const records = pageContext?.pageContext?.pageProps?.pageData?.records ?? [];
-  if (!records.length) return { ok: false, books: [], error: 'no book records found' };
-
-  const books = records.map((r) => ({
-    rank:   r.rankNum ?? 0,
-    title:  r.bName ?? '',
-    author: r.bAuth ?? '',
-    category: r.cat ?? '',
-    words:  r.cnt ?? '0',
-    intro:  (r.desc ?? '').slice(0, 150),
-    bookId: r.bid ?? '',
-  }));
-
-  return { ok: true, books };
-}
-
-async function httpGet(ctx, url, signal) {
-  let timerDispose;
-  const timeout = new Promise((_, reject) => {
-    timerDispose = ctx.timeout(() => reject(new Error('timeout')), 15000);
-  });
-  try {
-    const res = await Promise.race([
-      fetch(url, { headers: HEADERS, signal }),
-      timeout,
-    ]);
-    const body = await res.text();
-    return { ok: res.ok, status: res.status, body };
-  } catch (err) {
-    return { ok: false, status: 0, body: '', error: err.message };
-  } finally {
-    try { timerDispose?.(); } catch (_) {}
-  }
-}

package/commands/scan/platforms/qimao.js

@@ -1,127 +0,0 @@
-/**
- * qimao.js — 七猫小说排行榜采集
- *
- * 策略：纯 HTTP。榜单页通过 XHR 加载 JSON 数据。
- * 无需 Playwright。
- */
-
-export const platform = 'qimao';
-export const label = '七猫';
-
-export const rankList = [
-  { id: 'male_hot',   label: '男生大热榜',  channel: 'male',   type: 'hot'   },
-  { id: 'male_new',   label: '男生新书榜',  channel: 'male',   type: 'new'   },
-  { id: 'female_hot', label: '女生大热榜',  channel: 'female', type: 'hot'   },
-  { id: 'female_new', label: '女生新书榜',  channel: 'female', type: 'new'   },
-];
-
-const RANK_URL = 'https://www.qimao.com/paihang';
-
-/**
- * Scrape one rank list.
- * @param {string} rankId  - e.g. 'male_hot'
- * @param {object} ctx      - Cordis plugin context
- * @param {AbortSignal} signal
- * @returns {Promise<{ ok: boolean, books: object[], error?: string }>}
- */
-export async function scrapeRank(rankId, ctx, signal) {
-  const [channelId, rankTypeId] = rankId.split('_');
-
-  const channelMap = { male: 'boy', female: 'girl' };
-  const rankTypeMap = { hot: 'hot', new: 'new' };
-  const channel = channelMap[channelId] ?? channelId;
-  const rankType = rankTypeMap[rankTypeId] ?? rankTypeId;
-
-  const url = `${RANK_URL}/${channel}/${rankType}/date/`;
-
-  const { ok, status, body, error } = await httpGet(ctx, url, signal);
-  if (!ok) return { ok: false, books: [], error: error ?? `HTTP ${status}` };
-
-  const books = parseBooks(body, channelId, rankTypeId);
-  return books.length > 0
-    ? { ok: true, books }
-    : { ok: false, books: [], error: 'no books found in page' };
-}
-
-async function httpGet(ctx, url, signal) {
-  let timerDispose;
-  const timeout = new Promise((_, reject) => {
-    timerDispose = ctx.timeout(() => reject(new Error('timeout')), 15000);
-  });
-  try {
-    const res = await Promise.race([
-      fetch(url, {
-        headers: {
-          'User-Agent': 'Mozilla/5.0 (compatible; fancy-webnovel/1.0)',
-          'Accept': 'text/html,application/xhtml+xml',
-          'Accept-Language': 'zh-CN,zh;q=0.9',
-        },
-        signal,
-      }),
-      timeout,
-    ]);
-    const body = await res.text();
-    return { ok: res.ok, status: res.status, body };
-  } catch (err) {
-    return { ok: false, status: 0, body: '', error: err.message };
-  } finally {
-    try { timerDispose?.(); } catch (_) {}
-  }
-}
-
-function parseBooks(html, channelId, rankTypeId) {
-  const books = [];
-
-  // 尝试从 JSON 数据块提取
-  const jsonMatch = html.match(/var\s+RANK_DATA\s*=\s*(\{.*?\});/s)
-    ?? html.match(/window\.__INITIAL_STATE__\s*=\s*(\{.*?\});/s);
-
-  if (jsonMatch) {
-    try {
-      const data = JSON.parse(jsonMatch[1]);
-      const list = data?.rankList ?? data?.bookList ?? data?.books ?? [];
-      return normalizeBooks(list, channelId, rankTypeId);
-    } catch (_) { /* fall through */ }
-  }
-
-  // DOM 解析: 从页面 HTML 提取书籍信息
-  // 匹配模式: <a class="book-title">书名</a> ... <span class="author">作者</span>
-  const titleMatches = [...html.matchAll(/class="(?:book-)?title[^"]*"[^>]*>([^<]+)<\/a>/g)];
-  const authorMatches = [...html.matchAll(/class="author[^"]*"[^>]*>([^<]+)<\/a>/g)];
-  const rankMatches = [...html.matchAll(/class="(?:rank|num)[^"]*"[^>]*>(\d+)<\/span>/g)];
-
-  const count = Math.min(titleMatches.length, authorMatches.length);
-  for (let i = 0; i < count; i++) {
-    const title = (titleMatches[i][1] ?? '').trim();
-    const author = (authorMatches[i][1] ?? '').trim();
-    if (!title || /^(上一页|下一页|跳转)$/.test(title)) continue;
-    if (!author || /^(上一页|下一页|跳转|友情链接)$/.test(author)) continue;
-
-    books.push({
-      rank:    rankMatches[i] ? parseInt(rankMatches[i][1], 10) : (i + 1),
-      title,
-      author,
-      category: '',
-      words:   0,
-      intro:   '',
-      cover:   '',
-      bookId:  '',
-    });
-  }
-
-  return books;
-}
-
-function normalizeBooks(list, channelId, rankTypeId) {
-  if (!Array.isArray(list)) return [];
-  return list.map((b, i) => ({
-    rank:   b.rank ?? (i + 1),
-    title:  b.title ?? b.bookTitle ?? '',
-    author: b.author ?? '',
-    category: b.categoryName ?? b.typeName ?? '',
-    words:  b.wordCount ?? b.words ?? 0,
-    intro:  (b.description ?? '').slice(0, 150),
-    cover:  b.cover ?? b.thumbnail ?? '',
-    bookId: b.bookId ?? b.id ?? '',
-  }));
-}