@jackwener/opencli 0.8.0 → 0.9.0

package/src/clis/xiaoyuzhou/podcast-episodes.ts

@@ -0,0 +1,36 @@
+import { cli, Strategy } from '../../registry.js';
+import { CliError } from '../../errors.js';
+import { fetchPageProps, formatDuration, formatDate } from './utils.js';
+
+cli({
+  site: 'xiaoyuzhou',
+  name: 'podcast-episodes',
+  description: 'List recent episodes of a Xiaoyuzhou podcast (up to 15, SSR limit)',
+  domain: 'www.xiaoyuzhoufm.com',
+  strategy: Strategy.PUBLIC,
+  browser: false,
+  args: [
+    { name: 'id', positional: true, required: true, help: 'Podcast ID (from xiaoyuzhoufm.com URL)' },
+    { name: 'limit', type: 'int', default: 15, help: 'Max episodes to show (up to 15, SSR limit)' },
+  ],
+  columns: ['eid', 'title', 'duration', 'plays', 'date'],
+  func: async (_page, args) => {
+    const pageProps = await fetchPageProps(`/podcast/${args.id}`);
+    const podcast = pageProps.podcast;
+    if (!podcast) throw new CliError('NOT_FOUND', 'Podcast not found', 'Please check the ID');
+    const allEpisodes = podcast.episodes ?? [];
+    const requestedLimit = Number(args.limit);
+    if (!Number.isInteger(requestedLimit) || requestedLimit < 1) {
+      throw new CliError('INVALID_ARGUMENT', 'limit must be a positive integer', 'Example: --limit 5');
+    }
+    const limit = Math.min(requestedLimit, allEpisodes.length);
+    const episodes = allEpisodes.slice(0, limit);
+    return episodes.map((ep: any) => ({
+      eid: ep.eid,
+      title: ep.title,
+      duration: formatDuration(ep.duration),
+      plays: ep.playCount,
+      date: formatDate(ep.pubDate),
+    }));
+  },
+});

package/src/clis/xiaoyuzhou/podcast.ts

@@ -0,0 +1,27 @@
+import { cli, Strategy } from '../../registry.js';
+import { CliError } from '../../errors.js';
+import { fetchPageProps, formatDate } from './utils.js';
+
+cli({
+  site: 'xiaoyuzhou',
+  name: 'podcast',
+  description: 'View a Xiaoyuzhou podcast profile',
+  domain: 'www.xiaoyuzhoufm.com',
+  strategy: Strategy.PUBLIC,
+  browser: false,
+  args: [{ name: 'id', positional: true, required: true, help: 'Podcast ID (from xiaoyuzhoufm.com URL)' }],
+  columns: ['title', 'author', 'description', 'subscribers', 'episodes', 'updated'],
+  func: async (_page, args) => {
+    const pageProps = await fetchPageProps(`/podcast/${args.id}`);
+    const p = pageProps.podcast;
+    if (!p) throw new CliError('NOT_FOUND', 'Podcast not found', 'Please check the ID');
+    return [{
+      title: p.title,
+      author: p.author,
+      description: p.brief,
+      subscribers: p.subscriptionCount,
+      episodes: p.episodeCount,
+      updated: formatDate(p.latestEpisodePubDate),
+    }];
+  },
+});

package/src/clis/xiaoyuzhou/utils.test.ts

@@ -0,0 +1,122 @@
+import { describe, it, expect, vi, beforeEach } from 'vitest';
+import { formatDuration, formatDate, fetchPageProps } from './utils.js';
+
+describe('formatDuration', () => {
+  it('formats typical duration', () => {
+    expect(formatDuration(3890)).toBe('64:50');
+  });
+
+  it('formats zero seconds', () => {
+    expect(formatDuration(0)).toBe('0:00');
+  });
+
+  it('pads single-digit seconds', () => {
+    expect(formatDuration(65)).toBe('1:05');
+  });
+
+  it('formats exact minutes', () => {
+    expect(formatDuration(3600)).toBe('60:00');
+  });
+
+  it('rounds floating-point seconds', () => {
+    expect(formatDuration(3890.7)).toBe('64:51');
+  });
+
+  it('returns dash for NaN', () => {
+    expect(formatDuration(NaN)).toBe('-');
+  });
+
+  it('returns dash for negative', () => {
+    expect(formatDuration(-1)).toBe('-');
+  });
+});
+
+describe('formatDate', () => {
+  it('extracts YYYY-MM-DD from ISO string', () => {
+    expect(formatDate('2026-03-13T11:00:06.686Z')).toBe('2026-03-13');
+  });
+
+  it('handles date-only string', () => {
+    expect(formatDate('2025-01-01')).toBe('2025-01-01');
+  });
+
+  it('returns dash for undefined/empty', () => {
+    expect(formatDate('')).toBe('-');
+    expect(formatDate(undefined as any)).toBe('-');
+  });
+});
+
+describe('fetchPageProps', () => {
+  beforeEach(() => {
+    vi.restoreAllMocks();
+  });
+
+  it('extracts pageProps from valid HTML', async () => {
+    const mockHtml = `<html><script id="__NEXT_DATA__" type="application/json">{"props":{"pageProps":{"podcast":{"title":"Test"}}}}</script></html>`;
+    vi.stubGlobal('fetch', vi.fn().mockResolvedValue({
+      ok: true,
+      text: () => Promise.resolve(mockHtml),
+    }));
+
+    const result = await fetchPageProps('/podcast/abc123');
+    expect(result).toEqual({ podcast: { title: 'Test' } });
+  });
+
+  it('throws on HTTP error', async () => {
+    vi.stubGlobal('fetch', vi.fn().mockResolvedValue({
+      ok: false,
+      status: 404,
+      text: () => Promise.resolve('Not Found'),
+    }));
+
+    await expect(fetchPageProps('/podcast/invalid')).rejects.toThrow('HTTP 404');
+  });
+
+  it('throws when __NEXT_DATA__ is missing', async () => {
+    vi.stubGlobal('fetch', vi.fn().mockResolvedValue({
+      ok: true,
+      text: () => Promise.resolve('<html><body>No data here</body></html>'),
+    }));
+
+    await expect(fetchPageProps('/podcast/abc')).rejects.toThrow('Failed to extract');
+  });
+
+  it('throws when pageProps is empty', async () => {
+    const mockHtml = `<script id="__NEXT_DATA__" type="application/json">{"props":{"pageProps":{}}}</script>`;
+    vi.stubGlobal('fetch', vi.fn().mockResolvedValue({
+      ok: true,
+      text: () => Promise.resolve(mockHtml),
+    }));
+
+    await expect(fetchPageProps('/podcast/abc')).rejects.toThrow('Resource not found');
+  });
+
+  it('throws on malformed JSON in __NEXT_DATA__', async () => {
+    const mockHtml = `<script id="__NEXT_DATA__" type="application/json">{broken json</script>`;
+    vi.stubGlobal('fetch', vi.fn().mockResolvedValue({
+      ok: true,
+      text: () => Promise.resolve(mockHtml),
+    }));
+
+    await expect(fetchPageProps('/podcast/abc')).rejects.toThrow('Malformed __NEXT_DATA__');
+  });
+
+  it('handles multiline JSON in __NEXT_DATA__', async () => {
+    const mockHtml = `<script id="__NEXT_DATA__" type="application/json">
+{
+  "props": {
+    "pageProps": {
+      "episode": {"title": "Multiline Test"}
+    }
+  }
+}
+</script>`;
+    vi.stubGlobal('fetch', vi.fn().mockResolvedValue({
+      ok: true,
+      text: () => Promise.resolve(mockHtml),
+    }));
+
+    const result = await fetchPageProps('/episode/abc');
+    expect(result).toEqual({ episode: { title: 'Multiline Test' } });
+  });
+});

package/src/clis/xiaoyuzhou/utils.ts

@@ -0,0 +1,65 @@
+/**
+ * Shared Xiaoyuzhou utilities — page data extraction and formatting.
+ *
+ * Xiaoyuzhou (小宇宙) is a Next.js app that embeds full page data in
+ * <script id="__NEXT_DATA__">. We fetch the HTML and extract that JSON
+ * instead of using their authenticated API.
+ */
+
+import { CliError } from '../../errors.js';
+
+/**
+ * Fetch a Xiaoyuzhou page and extract __NEXT_DATA__.props.pageProps.
+ * @param path - URL path, e.g. '/podcast/xxx' or '/episode/xxx'
+ */
+export async function fetchPageProps(path: string): Promise<any> {
+  const url = `https://www.xiaoyuzhoufm.com${path}`;
+  // Node.js fetch sends UA "node" which gets blocked; use a browser-like UA
+  const resp = await fetch(url, {
+    headers: { 'User-Agent': 'Mozilla/5.0 (compatible; opencli)' },
+  });
+  if (!resp.ok) {
+    throw new CliError(
+      'FETCH_ERROR',
+      `HTTP ${resp.status} for ${path}`,
+      'Please check the ID — you can find it in xiaoyuzhoufm.com URLs',
+    );
+  }
+  const html = await resp.text();
+  // [\s\S]*? for multiline safety (JSON may span lines)
+  const match = html.match(/<script id="__NEXT_DATA__"[^>]*>([\s\S]*?)<\/script>/);
+  if (!match) {
+    throw new CliError(
+      'PARSE_ERROR',
+      'Failed to extract __NEXT_DATA__',
+      'Page structure may have changed',
+    );
+  }
+  let parsed: any;
+  try { parsed = JSON.parse(match[1]); }
+  catch { throw new CliError('PARSE_ERROR', 'Malformed __NEXT_DATA__ JSON', 'Page structure may have changed'); }
+  const pageProps = parsed.props?.pageProps;
+  if (!pageProps || Object.keys(pageProps).length === 0) {
+    throw new CliError(
+      'NOT_FOUND',
+      'Resource not found',
+      'Please check the ID — you can find it in xiaoyuzhoufm.com URLs',
+    );
+  }
+  return pageProps;
+}
+
+/** Format seconds to mm:ss (e.g. 3890 → "64:50"). Returns '-' for invalid input. */
+export function formatDuration(seconds: number): string {
+  if (!Number.isFinite(seconds) || seconds < 0) return '-';
+  seconds = Math.round(seconds);
+  const m = Math.floor(seconds / 60);
+  const s = seconds % 60;
+  return `${m}:${String(s).padStart(2, '0')}`;
+}
+
+/** Format ISO date string to YYYY-MM-DD. Returns '-' for missing input. */
+export function formatDate(iso: string): string {
+  if (!iso) return '-';
+  return iso.slice(0, 10);
+}

package/tests/e2e/public-commands.test.ts

@@ -6,6 +6,11 @@
 import { describe, it, expect } from 'vitest';
 import { runCli, parseJsonOutput } from './helpers.js';
 
+function isExpectedXiaoyuzhouRestriction(code: number, stderr: string): boolean {
+  if (code === 0) return false;
+  return /Error \[FETCH_ERROR\]: HTTP (403|429|451|503)\b/.test(stderr);
+}
+
 describe('public commands E2E', () => {
   // ── hackernews ──
   it('hackernews top returns structured data', async () => {
@@ -53,4 +58,61 @@ describe('public commands E2E', () => {
       expect(data).toBeDefined();
     }
   }, 30_000);
+
+  // ── xiaoyuzhou (Chinese site — may return empty on overseas CI runners) ──
+  it('xiaoyuzhou podcast returns podcast profile', async () => {
+    const { stdout, stderr, code } = await runCli(['xiaoyuzhou', 'podcast', '6013f9f58e2f7ee375cf4216', '-f', 'json']);
+    if (isExpectedXiaoyuzhouRestriction(code, stderr)) {
+      console.warn(`xiaoyuzhou podcast skipped: ${stderr.trim()}`);
+      return;
+    }
+    expect(code).toBe(0);
+    const data = parseJsonOutput(stdout);
+    expect(Array.isArray(data)).toBe(true);
+    expect(data.length).toBe(1);
+    expect(data[0]).toHaveProperty('title');
+    expect(data[0]).toHaveProperty('subscribers');
+    expect(data[0]).toHaveProperty('episodes');
+  }, 30_000);
+
+  it('xiaoyuzhou podcast-episodes returns episode list', async () => {
+    const { stdout, stderr, code } = await runCli(['xiaoyuzhou', 'podcast-episodes', '6013f9f58e2f7ee375cf4216', '-f', 'json']);
+    if (isExpectedXiaoyuzhouRestriction(code, stderr)) {
+      console.warn(`xiaoyuzhou podcast-episodes skipped: ${stderr.trim()}`);
+      return;
+    }
+    expect(code).toBe(0);
+    const data = parseJsonOutput(stdout);
+    expect(Array.isArray(data)).toBe(true);
+    expect(data.length).toBeGreaterThanOrEqual(1);
+    expect(data[0]).toHaveProperty('eid');
+    expect(data[0]).toHaveProperty('title');
+    expect(data[0]).toHaveProperty('duration');
+  }, 30_000);
+
+  it('xiaoyuzhou episode returns episode detail', async () => {
+    const { stdout, stderr, code } = await runCli(['xiaoyuzhou', 'episode', '69b3b675772ac2295bfc01d0', '-f', 'json']);
+    if (isExpectedXiaoyuzhouRestriction(code, stderr)) {
+      console.warn(`xiaoyuzhou episode skipped: ${stderr.trim()}`);
+      return;
+    }
+    expect(code).toBe(0);
+    const data = parseJsonOutput(stdout);
+    expect(Array.isArray(data)).toBe(true);
+    expect(data.length).toBe(1);
+    expect(data[0]).toHaveProperty('title');
+    expect(data[0]).toHaveProperty('podcast');
+    expect(data[0]).toHaveProperty('plays');
+    expect(data[0]).toHaveProperty('comments');
+  }, 30_000);
+
+  it('xiaoyuzhou podcast-episodes rejects invalid limit', async () => {
+    const { stderr, code } = await runCli(['xiaoyuzhou', 'podcast-episodes', '6013f9f58e2f7ee375cf4216', '--limit', 'abc', '-f', 'json']);
+    if (isExpectedXiaoyuzhouRestriction(code, stderr)) {
+      console.warn(`xiaoyuzhou invalid-limit skipped: ${stderr.trim()}`);
+      return;
+    }
+    expect(code).not.toBe(0);
+    expect(stderr).toMatch(/limit must be a positive integer|Argument "limit" must be a valid number/);
+  }, 30_000);
 });