@huyuan-ai/cli 1.0.0 → 1.0.2

package/vendor/opencli/dist/clis/xiaohongshu/user-helpers.test.js

@@ -0,0 +1,99 @@
+import { describe, expect, it } from 'vitest';
+import { buildXhsNoteUrl, extractXhsUserNotes, flattenXhsNoteGroups, normalizeXhsUserId, } from './user-helpers.js';
+describe('normalizeXhsUserId', () => {
+    it('extracts the profile id from a full Xiaohongshu URL', () => {
+        expect(normalizeXhsUserId('https://www.xiaohongshu.com/user/profile/615529370000000002026001?xsec_source=pc_search')).toBe('615529370000000002026001');
+    });
+    it('keeps a bare profile id unchanged', () => {
+        expect(normalizeXhsUserId('615529370000000002026001')).toBe('615529370000000002026001');
+    });
+});
+describe('flattenXhsNoteGroups', () => {
+    it('flattens grouped note arrays and ignores empty groups', () => {
+        expect(flattenXhsNoteGroups([[{ id: 'a' }], [], null, [{ id: 'b' }]])).toEqual([
+            { id: 'a' },
+            { id: 'b' },
+        ]);
+    });
+});
+describe('buildXhsNoteUrl', () => {
+    it('includes xsec token when available', () => {
+        expect(buildXhsNoteUrl('user123', 'note456', 'token789')).toBe('https://www.xiaohongshu.com/user/profile/user123/note456?xsec_token=token789&xsec_source=pc_user');
+    });
+});
+describe('extractXhsUserNotes', () => {
+    it('normalizes grouped note cards into CLI rows', () => {
+        const rows = extractXhsUserNotes({
+            noteGroups: [
+                [
+                    {
+                        id: 'note-1',
+                        xsecToken: 'abc',
+                        noteCard: {
+                            noteId: 'note-1',
+                            displayTitle: 'First note',
+                            type: 'video',
+                            interactInfo: { likedCount: '4.6万' },
+                            user: { userId: 'user-1' },
+                        },
+                    },
+                    {
+                        noteCard: {
+                            note_id: 'note-2',
+                            display_title: 'Second note',
+                            type: 'normal',
+                            interact_info: { liked_count: 42 },
+                        },
+                    },
+                ],
+                [],
+            ],
+        }, 'fallback-user');
+        expect(rows).toEqual([
+            {
+                id: 'note-1',
+                title: 'First note',
+                type: 'video',
+                likes: '4.6万',
+                cover: '',
+                url: 'https://www.xiaohongshu.com/user/profile/user-1/note-1?xsec_token=abc&xsec_source=pc_user',
+            },
+            {
+                id: 'note-2',
+                title: 'Second note',
+                type: 'normal',
+                likes: '42',
+                cover: '',
+                url: 'https://www.xiaohongshu.com/user/profile/fallback-user/note-2',
+            },
+        ]);
+    });
+    it('extracts cover urls with fallback priority urlDefault -> urlPre -> url', () => {
+        const rows = extractXhsUserNotes({
+            noteGroups: [
+                [
+                    { noteCard: { noteId: 'cover-1', cover: { urlDefault: 'https://img.example/default.jpg', urlPre: 'https://img.example/pre.jpg', url: 'https://img.example/raw.jpg' } } },
+                    { noteCard: { noteId: 'cover-2', cover: { urlPre: 'https://img.example/pre-only.jpg', url: 'https://img.example/raw-only.jpg' } } },
+                    { noteCard: { noteId: 'cover-3', cover: { url: 'https://img.example/raw-fallback.jpg' } } },
+                ],
+            ],
+        }, 'fallback-user');
+        expect(rows.map(row => row.cover)).toEqual([
+            'https://img.example/default.jpg',
+            'https://img.example/pre-only.jpg',
+            'https://img.example/raw-fallback.jpg',
+        ]);
+    });
+    it('deduplicates repeated notes by note id', () => {
+        const rows = extractXhsUserNotes({
+            noteGroups: [
+                [
+                    { noteCard: { noteId: 'dup-1', displayTitle: 'keep me' } },
+                    { noteCard: { noteId: 'dup-1', displayTitle: 'drop me' } },
+                ],
+            ],
+        }, 'fallback-user');
+        expect(rows).toHaveLength(1);
+        expect(rows[0]?.title).toBe('keep me');
+    });
+});

package/vendor/opencli/dist/clis/xiaohongshu/user.d.ts

@@ -0,0 +1 @@
+export {};

package/vendor/opencli/dist/clis/xiaohongshu/user.js

@@ -0,0 +1,56 @@
+import { cli, Strategy } from '../../registry.js';
+import { extractXhsUserNotes, normalizeXhsUserId } from './user-helpers.js';
+async function readUserSnapshot(page) {
+    return await page.evaluate(`
+    (() => {
+      const safeClone = (value) => {
+        try {
+          return JSON.parse(JSON.stringify(value ?? null));
+        } catch {
+          return null;
+        }
+      };
+
+      const userStore = window.__INITIAL_STATE__?.user || {};
+      return {
+        noteGroups: safeClone(userStore.notes?._value || userStore.notes || []),
+        pageData: safeClone(userStore.userPageData?._value || userStore.userPageData || {}),
+      };
+    })()
+  `);
+}
+cli({
+    site: 'xiaohongshu',
+    name: 'user',
+    description: 'Get public notes from a Xiaohongshu user profile',
+    domain: 'www.xiaohongshu.com',
+    strategy: Strategy.COOKIE,
+    browser: true,
+    args: [
+        { name: 'id', type: 'string', required: true, positional: true, help: 'User id or profile URL' },
+        { name: 'limit', type: 'int', default: 15, help: 'Number of notes to return' },
+    ],
+    columns: ['id', 'title', 'type', 'likes', 'url'],
+    func: async (page, kwargs) => {
+        const userId = normalizeXhsUserId(String(kwargs.id));
+        const limit = Math.max(1, Number(kwargs.limit ?? 15));
+        await page.goto(`https://www.xiaohongshu.com/user/profile/${userId}`);
+        let snapshot = await readUserSnapshot(page);
+        let results = extractXhsUserNotes(snapshot ?? {}, userId);
+        let previousCount = results.length;
+        for (let i = 0; results.length < limit && i < 4; i += 1) {
+            await page.autoScroll({ times: 1, delayMs: 1500 });
+            await page.wait(1);
+            snapshot = await readUserSnapshot(page);
+            const nextResults = extractXhsUserNotes(snapshot ?? {}, userId);
+            if (nextResults.length <= previousCount)
+                break;
+            results = nextResults;
+            previousCount = nextResults.length;
+        }
+        if (results.length === 0) {
+            throw new Error('No public notes found for this Xiaohongshu user.');
+        }
+        return results.slice(0, limit);
+    },
+});

package/vendor/opencli/dist/clis/xiaoyuzhou/episode.d.ts

@@ -0,0 +1 @@
+export {};

package/vendor/opencli/dist/clis/xiaoyuzhou/episode.js

@@ -0,0 +1,28 @@
+import { cli, Strategy } from '../../registry.js';
+import { CliError } from '../../errors.js';
+import { fetchPageProps, formatDuration, formatDate } from './utils.js';
+cli({
+    site: 'xiaoyuzhou',
+    name: 'episode',
+    description: 'View details of a Xiaoyuzhou podcast episode',
+    domain: 'www.xiaoyuzhoufm.com',
+    strategy: Strategy.PUBLIC,
+    browser: false,
+    args: [{ name: 'id', positional: true, required: true, help: 'Episode ID (eid from podcast-episodes output)' }],
+    columns: ['title', 'podcast', 'duration', 'plays', 'comments', 'likes', 'date'],
+    func: async (_page, args) => {
+        const pageProps = await fetchPageProps(`/episode/${args.id}`);
+        const ep = pageProps.episode;
+        if (!ep)
+            throw new CliError('NOT_FOUND', 'Episode not found', 'Please check the ID');
+        return [{
+                title: ep.title,
+                podcast: ep.podcast?.title,
+                duration: formatDuration(ep.duration),
+                plays: ep.playCount,
+                comments: ep.commentCount,
+                likes: ep.clapCount,
+                date: formatDate(ep.pubDate),
+            }];
+    },
+});

package/vendor/opencli/dist/clis/xiaoyuzhou/podcast-episodes.d.ts

@@ -0,0 +1 @@
+export {};

package/vendor/opencli/dist/clis/xiaoyuzhou/podcast-episodes.js

@@ -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) => ({
+            eid: ep.eid,
+            title: ep.title,
+            duration: formatDuration(ep.duration),
+            plays: ep.playCount,
+            date: formatDate(ep.pubDate),
+        }));
+    },
+});

package/vendor/opencli/dist/clis/xiaoyuzhou/podcast.d.ts

@@ -0,0 +1 @@
+export {};

package/vendor/opencli/dist/clis/xiaoyuzhou/podcast.js

@@ -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/vendor/opencli/dist/clis/xiaoyuzhou/utils.d.ts

@@ -0,0 +1,16 @@
+/**
+ * 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.
+ */
+/**
+ * Fetch a Xiaoyuzhou page and extract __NEXT_DATA__.props.pageProps.
+ * @param path - URL path, e.g. '/podcast/xxx' or '/episode/xxx'
+ */
+export declare function fetchPageProps(path: string): Promise<any>;
+/** Format seconds to mm:ss (e.g. 3890 → "64:50"). Returns '-' for invalid input. */
+export declare function formatDuration(seconds: number): string;
+/** Format ISO date string to YYYY-MM-DD. Returns '-' for missing input. */
+export declare function formatDate(iso: string): string;

package/vendor/opencli/dist/clis/xiaoyuzhou/utils.js

@@ -0,0 +1,55 @@
+/**
+ * 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) {
+    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 ${path}`, 'Please check the ID — you can find it in xiaoyuzhoufm.com URLs');
+    }
+    const html = await resp.text();
+    // [\s\S]*? for multiline safety (JSON may span lines)
+    const match = html.match(/<script id="__NEXT_DATA__"[^>]*>([\s\S]*?)<\/script>/);
+    if (!match) {
+        throw new CliError('PARSE_ERROR', 'Failed to extract __NEXT_DATA__', 'Page structure may have changed');
+    }
+    let parsed;
+    try {
+        parsed = JSON.parse(match[1]);
+    }
+    catch {
+        throw new CliError('PARSE_ERROR', 'Malformed __NEXT_DATA__ JSON', 'Page structure may have changed');
+    }
+    const pageProps = parsed.props?.pageProps;
+    if (!pageProps || Object.keys(pageProps).length === 0) {
+        throw new CliError('NOT_FOUND', 'Resource not found', 'Please check the ID — you can find it in xiaoyuzhoufm.com URLs');
+    }
+    return pageProps;
+}
+/** Format seconds to mm:ss (e.g. 3890 → "64:50"). Returns '-' for invalid input. */
+export function formatDuration(seconds) {
+    if (!Number.isFinite(seconds) || seconds < 0)
+        return '-';
+    seconds = Math.round(seconds);
+    const m = Math.floor(seconds / 60);
+    const s = seconds % 60;
+    return `${m}:${String(s).padStart(2, '0')}`;
+}
+/** Format ISO date string to YYYY-MM-DD. Returns '-' for missing input. */
+export function formatDate(iso) {
+    if (!iso)
+        return '-';
+    return iso.slice(0, 10);
+}

package/vendor/opencli/dist/clis/xiaoyuzhou/utils.test.d.ts

@@ -0,0 +1 @@
+export {};

package/vendor/opencli/dist/clis/xiaoyuzhou/utils.test.js

@@ -0,0 +1,99 @@
+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)).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/vendor/opencli/dist/clis/xueqiu/comments.d.ts

@@ -0,0 +1,118 @@
+import type { IPage } from '../../types.js';
+/**
+ * Minimal browser-response shape used by the classifier.
+ */
+export interface XueqiuCommentsResponse {
+    status: number;
+    contentType: string;
+    json: unknown;
+    textSnippet: string;
+}
+/**
+ * Minimal normalized row shape used during pagination and deduplication.
+ */
+export interface XueqiuCommentRow {
+    id: string;
+    author: string;
+    text?: string;
+    likes?: number;
+    replies?: number;
+    retweets?: number;
+    created_at?: string | null;
+    url?: string | null;
+}
+/**
+ * Public CLI row shape. This intentionally omits the internal stable ID used
+ * only for deduplication, so machine-readable output matches the command
+ * contract and table columns.
+ */
+export type XueqiuCommentOutputRow = Omit<XueqiuCommentRow, 'id'>;
+/**
+ * Pagination options for collecting enough rows to satisfy `--limit`.
+ */
+export interface CollectCommentRowsOptions {
+    symbol: string;
+    limit: number;
+    pageSize: number;
+    maxRequests: number;
+    fetchPage: (pageNumber: number, pageSize: number) => Promise<XueqiuCommentsResponse>;
+    warn?: (message: string) => void;
+}
+type XueqiuCommentsKind = 'auth' | 'anti-bot' | 'argument' | 'empty' | 'incompatible' | 'unknown';
+/**
+ * Extract the raw item list from one classified JSON payload.
+ *
+ * @param json Raw parsed JSON payload from browser fetch.
+ * @returns Discussion items when the response shape is usable.
+ */
+export declare function getCommentItems(json: unknown): Record<string, any>[];
+/**
+ * Classify one raw browser response before command-level error handling.
+ *
+ * @param response Structured browser response payload.
+ * @returns Tagged result describing the response class.
+ */
+export declare function classifyXueqiuCommentsResponse(response: XueqiuCommentsResponse): {
+    kind: XueqiuCommentsKind;
+};
+/**
+ * Merge one new page of rows while preserving the first occurrence of each ID.
+ *
+ * @param current Rows already collected.
+ * @param incoming Rows from the next page.
+ * @returns Deduplicated merged rows.
+ */
+export declare function mergeUniqueCommentRows(current: XueqiuCommentRow[], incoming: XueqiuCommentRow[]): XueqiuCommentRow[];
+/**
+ * Normalize one raw xueqiu discussion item into the CLI row shape.
+ *
+ * Returned rows represent stock-scoped discussion posts, not replies under
+ * one parent post.
+ *
+ * @param item Raw API item.
+ * @returns Cleaned CLI row.
+ */
+export declare function normalizeCommentItem(item: Record<string, any>): XueqiuCommentRow;
+/**
+ * Remove internal-only fields before returning rows to the CLI renderer.
+ *
+ * @param row Internal row shape used during pagination.
+ * @returns Public output row that matches the documented command contract.
+ */
+export declare function toCommentOutputRow(row: XueqiuCommentRow): XueqiuCommentOutputRow;
+/**
+ * Convert response classification into a compact warning phrase.
+ *
+ * @param kind Classifier result kind.
+ * @returns Human-readable reason fragment for stderr warnings.
+ */
+export declare function describeFailureKind(kind: XueqiuCommentsKind): string;
+/**
+ * Fetch one discussion page from inside the browser context so cookies and
+ * any site-side request state stay attached to the request.
+ *
+ * @param page Active browser page.
+ * @param symbol Normalized stock symbol.
+ * @param pageNumber Internal page counter, starting from 1.
+ * @param pageSize Item count per internal request.
+ * @returns Structured response for command-side classification.
+ */
+export declare function fetchCommentsPage(page: IPage, symbol: string, pageNumber: number, pageSize: number): Promise<XueqiuCommentsResponse>;
+/**
+ * Collect enough stock discussion rows to satisfy the requested limit.
+ *
+ * This helper owns the internal pagination policy so the public command
+ * contract can stay small and expose only `--limit`.
+ *
+ * @param options Pagination inputs and a page-fetch callback.
+ * @returns Deduplicated normalized rows, possibly partial with a warning.
+ */
+export declare function collectCommentRows(options: CollectCommentRowsOptions): Promise<XueqiuCommentRow[]>;
+/**
+ * Convert raw CLI input into a normalized stock symbol.
+ *
+ * @param raw User-provided CLI argument.
+ * @returns Upper-cased symbol string.
+ */
+export declare function normalizeSymbolInput(raw: unknown): string;
+export {};