@jackwener/opencli 1.0.6 → 1.1.1

package/src/clis/arxiv/utils.ts

@@ -0,0 +1,63 @@
+/**
+ * arXiv adapter utilities.
+ *
+ * arXiv exposes a public Atom/XML API — no key required.
+ * https://info.arxiv.org/help/api/index.html
+ */
+
+import { CliError } from '../../errors.js';
+
+export const ARXIV_BASE = 'https://export.arxiv.org/api/query';
+
+export async function arxivFetch(params: string): Promise<string> {
+  const resp = await fetch(`${ARXIV_BASE}?${params}`);
+  if (!resp.ok) {
+    throw new CliError('FETCH_ERROR', `arXiv API HTTP ${resp.status}`, 'Check your search term or paper ID');
+  }
+  return resp.text();
+}
+
+/** Extract the text content of the first matching XML tag. */
+function extract(xml: string, tag: string): string {
+  const m = xml.match(new RegExp(`<${tag}[^>]*>([\\s\\S]*?)<\\/${tag}>`));
+  return m ? m[1].trim() : '';
+}
+
+/** Extract all text contents of a repeated XML tag. */
+function extractAll(xml: string, tag: string): string[] {
+  const re = new RegExp(`<${tag}[^>]*>([\\s\\S]*?)<\\/${tag}>`, 'g');
+  const results: string[] = [];
+  let m: RegExpExecArray | null;
+  while ((m = re.exec(xml)) !== null) results.push(m[1].trim());
+  return results;
+}
+
+export interface ArxivEntry {
+  id: string;
+  title: string;
+  authors: string;
+  abstract: string;
+  published: string;
+  url: string;
+}
+
+/** Parse Atom XML feed into structured entries. */
+export function parseEntries(xml: string): ArxivEntry[] {
+  const entryRe = /<entry>([\s\S]*?)<\/entry>/g;
+  const entries: ArxivEntry[] = [];
+  let m: RegExpExecArray | null;
+  while ((m = entryRe.exec(xml)) !== null) {
+    const e = m[1];
+    const rawId = extract(e, 'id');
+    const arxivId = rawId.replace(/^https?:\/\/arxiv\.org\/abs\//, '').replace(/v\d+$/, '');
+    entries.push({
+      id: arxivId,
+      title: extract(e, 'title').replace(/\s+/g, ' '),
+      authors: extractAll(e, 'name').slice(0, 3).join(', '),
+      abstract: (() => { const s = extract(e, 'summary').replace(/\s+/g, ' '); return s.length > 200 ? s.slice(0, 200) + '...' : s; })(),
+      published: extract(e, 'published').slice(0, 10),
+      url: `https://arxiv.org/abs/${arxivId}`,
+    });
+  }
+  return entries;
+}

package/src/clis/bilibili/dynamic.ts

@@ -1,5 +1,5 @@
 import { cli, Strategy } from '../../registry.js';
-import { apiGet } from '../../bilibili.js';
+import { apiGet } from './utils.js';
 
 cli({
   site: 'bilibili',

package/src/clis/bilibili/favorite.ts

@@ -1,5 +1,5 @@
 import { cli, Strategy } from '../../registry.js';
-import { apiGet, payloadData } from '../../bilibili.js';
+import { apiGet, payloadData } from './utils.js';
 
 cli({
   site: 'bilibili',

package/src/clis/bilibili/feed.ts

@@ -1,5 +1,5 @@
 import { cli, Strategy } from '../../registry.js';
-import { apiGet, payloadData, getSelfUid, stripHtml } from '../../bilibili.js';
+import { apiGet, payloadData, getSelfUid, stripHtml } from './utils.js';
 
 cli({
   site: 'bilibili',

package/src/clis/bilibili/following.ts

@@ -1,6 +1,6 @@
 import { cli, Strategy } from '../../registry.js';
 import type { IPage } from '../../types.js';
-import { fetchJson, getSelfUid, resolveUid } from '../../bilibili.js';
+import { fetchJson, getSelfUid, resolveUid } from './utils.js';
 
 cli({
   site: 'bilibili',

package/src/clis/bilibili/history.ts

@@ -1,5 +1,5 @@
 import { cli, Strategy } from '../../registry.js';
-import { apiGet, payloadData } from '../../bilibili.js';
+import { apiGet, payloadData } from './utils.js';
 
 cli({
   site: 'bilibili',

package/src/clis/bilibili/me.ts

@@ -1,5 +1,5 @@
 import { cli, Strategy } from '../../registry.js';
-import { apiGet, getSelfUid } from '../../bilibili.js';
+import { apiGet, getSelfUid } from './utils.js';
 
 cli({
   site: 'bilibili', name: 'me', description: 'My Bilibili profile info', domain: 'www.bilibili.com', strategy: Strategy.COOKIE,

package/src/clis/bilibili/ranking.ts

@@ -1,5 +1,5 @@
 import { cli, Strategy } from '../../registry.js';
-import { apiGet } from '../../bilibili.js';
+import { apiGet } from './utils.js';
 
 cli({
   site: 'bilibili',

package/src/clis/bilibili/search.ts

@@ -1,17 +1,17 @@
 import { cli, Strategy } from '../../registry.js';
-import { apiGet, stripHtml } from '../../bilibili.js';
+import { apiGet, stripHtml } from './utils.js';
 
 cli({
   site: 'bilibili', name: 'search', description: 'Search Bilibili videos or users', domain: 'www.bilibili.com', strategy: Strategy.COOKIE,
   args: [
-    { name: 'keyword', required: true, help: 'Search keyword' },
+    { name: 'query', required: true, positional: true, help: 'Search keyword' },
     { name: 'type', default: 'video', help: 'video or user' },
     { name: 'page', type: 'int', default: 1, help: 'Result page' },
     { name: 'limit', type: 'int', default: 20, help: 'Number of results' },
   ],
   columns: ['rank', 'title', 'author', 'score', 'url'],
   func: async (page, kwargs) => {
-    const { keyword, type = 'video', page: pageNum = 1, limit = 20 } = kwargs;
+    const { query: keyword, type = 'video', page: pageNum = 1, limit = 20 } = kwargs;
     const searchType = type === 'user' ? 'bili_user' : 'video';
     const payload = await apiGet(page, '/x/web-interface/wbi/search/type', { params: { search_type: searchType, keyword, page: pageNum }, signed: true });
     const results: any[] = payload?.data?.result ?? [];

package/src/clis/bilibili/subtitle.ts

@@ -1,6 +1,6 @@
 import { cli, Strategy } from '../../registry.js';
 import type { IPage } from '../../types.js';
-import { apiGet } from '../../bilibili.js';
+import { apiGet } from './utils.js';
 
 cli({
   site: 'bilibili',

package/src/clis/bilibili/user-videos.ts

@@ -1,5 +1,5 @@
 import { cli, Strategy } from '../../registry.js';
-import { apiGet, payloadData, resolveUid } from '../../bilibili.js';
+import { apiGet, payloadData, resolveUid } from './utils.js';
 
 cli({
   site: 'bilibili',

package/src/{bilibili.ts → clis/bilibili/utils.ts}

@@ -2,7 +2,7 @@
  * Bilibili shared helpers: WBI signing, authenticated fetch, nav data, UID resolution.
  */
 
-import type { IPage } from './types.js';
+import type { IPage } from '../../types.js';
 
 const MIXIN_KEY_ENC_TAB = [
   46,47,18,2,53,8,23,32,15,50,10,31,58,3,45,35,27,43,5,49,

package/src/clis/bloomberg/businessweek.ts

@@ -0,0 +1,18 @@
+import { cli, Strategy } from '../../registry.js';
+import { fetchBloombergFeed } from './utils.js';
+
+cli({
+  site: 'bloomberg',
+  name: 'businessweek',
+  description: 'Bloomberg Businessweek top stories (RSS)',
+  domain: 'feeds.bloomberg.com',
+  strategy: Strategy.PUBLIC,
+  browser: false,
+  args: [
+    { name: 'limit', type: 'int', default: 1, help: 'Number of feed items to return (max 20)' },
+  ],
+  columns: ['title', 'summary', 'link', 'mediaLinks'],
+  func: async (_page, kwargs) => {
+    return fetchBloombergFeed('businessweek', kwargs.limit ?? 1);
+  },
+});

package/src/clis/bloomberg/economics.ts

@@ -0,0 +1,18 @@
+import { cli, Strategy } from '../../registry.js';
+import { fetchBloombergFeed } from './utils.js';
+
+cli({
+  site: 'bloomberg',
+  name: 'economics',
+  description: 'Bloomberg Economics top stories (RSS)',
+  domain: 'feeds.bloomberg.com',
+  strategy: Strategy.PUBLIC,
+  browser: false,
+  args: [
+    { name: 'limit', type: 'int', default: 1, help: 'Number of feed items to return (max 20)' },
+  ],
+  columns: ['title', 'summary', 'link', 'mediaLinks'],
+  func: async (_page, kwargs) => {
+    return fetchBloombergFeed('economics', kwargs.limit ?? 1);
+  },
+});

package/src/clis/bloomberg/feeds.ts

@@ -0,0 +1,16 @@
+import { cli, Strategy } from '../../registry.js';
+import { BLOOMBERG_FEEDS } from './utils.js';
+
+cli({
+  site: 'bloomberg',
+  name: 'feeds',
+  description: 'List the Bloomberg RSS feed aliases used by the adapter',
+  domain: 'feeds.bloomberg.com',
+  strategy: Strategy.PUBLIC,
+  browser: false,
+  args: [],
+  columns: ['name', 'url'],
+  func: async () => {
+    return Object.entries(BLOOMBERG_FEEDS).map(([name, url]) => ({ name, url }));
+  },
+});

package/src/clis/bloomberg/industries.ts

@@ -0,0 +1,18 @@
+import { cli, Strategy } from '../../registry.js';
+import { fetchBloombergFeed } from './utils.js';
+
+cli({
+  site: 'bloomberg',
+  name: 'industries',
+  description: 'Bloomberg Industries top stories (RSS)',
+  domain: 'feeds.bloomberg.com',
+  strategy: Strategy.PUBLIC,
+  browser: false,
+  args: [
+    { name: 'limit', type: 'int', default: 1, help: 'Number of feed items to return (max 20)' },
+  ],
+  columns: ['title', 'summary', 'link', 'mediaLinks'],
+  func: async (_page, kwargs) => {
+    return fetchBloombergFeed('industries', kwargs.limit ?? 1);
+  },
+});

package/src/clis/bloomberg/main.ts

@@ -0,0 +1,18 @@
+import { cli, Strategy } from '../../registry.js';
+import { fetchBloombergFeed } from './utils.js';
+
+cli({
+  site: 'bloomberg',
+  name: 'main',
+  description: 'Bloomberg homepage top stories (RSS)',
+  domain: 'feeds.bloomberg.com',
+  strategy: Strategy.PUBLIC,
+  browser: false,
+  args: [
+    { name: 'limit', type: 'int', default: 1, help: 'Number of feed items to return (max 20)' },
+  ],
+  columns: ['title', 'summary', 'link', 'mediaLinks'],
+  func: async (_page, kwargs) => {
+    return fetchBloombergFeed('main', kwargs.limit ?? 1);
+  },
+});

package/src/clis/bloomberg/markets.ts

@@ -0,0 +1,18 @@
+import { cli, Strategy } from '../../registry.js';
+import { fetchBloombergFeed } from './utils.js';
+
+cli({
+  site: 'bloomberg',
+  name: 'markets',
+  description: 'Bloomberg Markets top stories (RSS)',
+  domain: 'feeds.bloomberg.com',
+  strategy: Strategy.PUBLIC,
+  browser: false,
+  args: [
+    { name: 'limit', type: 'int', default: 1, help: 'Number of feed items to return (max 20)' },
+  ],
+  columns: ['title', 'summary', 'link', 'mediaLinks'],
+  func: async (_page, kwargs) => {
+    return fetchBloombergFeed('markets', kwargs.limit ?? 1);
+  },
+});

package/src/clis/bloomberg/news.ts

@@ -0,0 +1,136 @@
+import { cli, Strategy } from '../../registry.js';
+import { CliError } from '../../errors.js';
+import {
+  extractStoryMediaLinks,
+  renderStoryBody,
+  validateBloombergLink,
+  type BloombergStory,
+} from './utils.js';
+
+cli({
+  site: 'bloomberg',
+  name: 'news',
+  description: 'Read a Bloomberg story/article page and return title, full content, and media links',
+  domain: 'www.bloomberg.com',
+  strategy: Strategy.COOKIE,
+  browser: true,
+  args: [
+    { name: 'link', positional: true, required: true, help: 'Bloomberg story/article URL or relative Bloomberg path' },
+  ],
+  columns: ['title', 'summary', 'link', 'mediaLinks', 'content'],
+  func: async (page, kwargs) => {
+    const url = validateBloombergLink(kwargs.link);
+
+    // Navigate and wait for the page to hydrate before extracting story data.
+    await page.goto(url);
+    await page.wait(5);
+
+    const loadStory = async () => page.evaluate(`(() => {
+      const isRobot = /Are you a robot/i.test(document.title)
+        || /unusual activity/i.test(document.body.innerText)
+        || /click the box below to let us know you're not a robot/i.test(document.body.innerText);
+
+      if (isRobot) {
+        return {
+          errorCode: 'ROBOT_PAGE',
+          title: document.title,
+          preview: document.body.innerText.slice(0, 400),
+        };
+      }
+
+      const raw = document.querySelector('#__NEXT_DATA__')?.textContent;
+      if (!raw) {
+        return {
+          errorCode: 'NO_NEXT_DATA',
+          title: document.title,
+          preview: document.body.innerText.slice(0, 400),
+        };
+      }
+
+      let parsed;
+      try {
+        parsed = JSON.parse(raw);
+      } catch (err) {
+        return {
+          errorCode: 'BAD_NEXT_DATA',
+          title: document.title,
+          preview: document.body.innerText.slice(0, 400),
+          message: String(err),
+        };
+      }
+
+      const story = parsed?.props?.pageProps?.story;
+      if (!story) {
+        return {
+          errorCode: 'NO_STORY',
+          title: document.title,
+          preview: document.body.innerText.slice(0, 400),
+        };
+      }
+
+      return {
+        story: {
+          headline: story.headline || story.seoHeadline || story.seoTitle || document.querySelector('h1')?.textContent?.trim() || document.title,
+          summary: story.summary || story.socialDescription || story.seoDescription || document.querySelector('meta[name="description"]')?.getAttribute('content') || '',
+          url: story.url || story.readingUrl || location.href,
+          body: story.body || null,
+          lede: story.lede || null,
+          ledeImageUrl: story.ledeImageUrl || null,
+          socialImageUrl: story.socialImageUrl || null,
+          imageAttachments: story.imageAttachments || {},
+          videoAttachments: story.videoAttachments || {},
+        }
+      };
+    })()`);
+
+    let result: any = await loadStory();
+
+    // Retry once — Bloomberg pages sometimes hydrate slowly.
+    if (result?.errorCode === 'NO_NEXT_DATA' || result?.errorCode === 'NO_STORY') {
+      await page.wait(4);
+      result = await loadStory();
+    }
+
+    if (result?.errorCode === 'ROBOT_PAGE') {
+      throw new CliError(
+        'FETCH_ERROR',
+        'Bloomberg served the bot-protection page instead of article content',
+        'Try again later or open the article in a regular Chrome session first, then rerun the command. This command uses your current Bloomberg access and does not bypass paywall or entitlement checks.',
+      );
+    }
+
+    if (result?.errorCode) {
+      throw new CliError(
+        'PARSE_ERROR',
+        `Bloomberg page did not expose article story data (${result.errorCode})`,
+        'This command currently works on standard Bloomberg story/article pages that expose __NEXT_DATA__. Audio, video, newsletter, or other non-standard/blocked pages may not work. Access still depends on your current Bloomberg session.',
+      );
+    }
+
+    const story = result?.story as BloombergStory | undefined;
+    if (!story) {
+      throw new CliError(
+        'PARSE_ERROR',
+        'Failed to extract Bloomberg story data',
+        'Bloomberg may have changed the page structure.',
+      );
+    }
+
+    const content = renderStoryBody(story.body);
+    if (!content) {
+      throw new CliError(
+        'PARSE_ERROR',
+        'Bloomberg article body was empty after parsing',
+        'Bloomberg may have changed the story-body format, the URL may not point to a standard article page, or the page may not be accessible in your current Bloomberg session.',
+      );
+    }
+
+    return [{
+      title: story.headline || '',
+      summary: story.summary || '',
+      link: story.url || url,
+      mediaLinks: extractStoryMediaLinks(story),
+      content,
+    }];
+  },
+});

package/src/clis/bloomberg/opinions.ts

@@ -0,0 +1,18 @@
+import { cli, Strategy } from '../../registry.js';
+import { fetchBloombergFeed } from './utils.js';
+
+cli({
+  site: 'bloomberg',
+  name: 'opinions',
+  description: 'Bloomberg Opinion top stories (RSS)',
+  domain: 'feeds.bloomberg.com',
+  strategy: Strategy.PUBLIC,
+  browser: false,
+  args: [
+    { name: 'limit', type: 'int', default: 1, help: 'Number of feed items to return (max 20)' },
+  ],
+  columns: ['title', 'summary', 'link', 'mediaLinks'],
+  func: async (_page, kwargs) => {
+    return fetchBloombergFeed('opinions', kwargs.limit ?? 1);
+  },
+});

package/src/clis/bloomberg/politics.ts

@@ -0,0 +1,18 @@
+import { cli, Strategy } from '../../registry.js';
+import { fetchBloombergFeed } from './utils.js';
+
+cli({
+  site: 'bloomberg',
+  name: 'politics',
+  description: 'Bloomberg Politics top stories (RSS)',
+  domain: 'feeds.bloomberg.com',
+  strategy: Strategy.PUBLIC,
+  browser: false,
+  args: [
+    { name: 'limit', type: 'int', default: 1, help: 'Number of feed items to return (max 20)' },
+  ],
+  columns: ['title', 'summary', 'link', 'mediaLinks'],
+  func: async (_page, kwargs) => {
+    return fetchBloombergFeed('politics', kwargs.limit ?? 1);
+  },
+});

package/src/clis/bloomberg/tech.ts

@@ -0,0 +1,18 @@
+import { cli, Strategy } from '../../registry.js';
+import { fetchBloombergFeed } from './utils.js';
+
+cli({
+  site: 'bloomberg',
+  name: 'tech',
+  description: 'Bloomberg Tech top stories (RSS)',
+  domain: 'feeds.bloomberg.com',
+  strategy: Strategy.PUBLIC,
+  browser: false,
+  args: [
+    { name: 'limit', type: 'int', default: 1, help: 'Number of feed items to return (max 20)' },
+  ],
+  columns: ['title', 'summary', 'link', 'mediaLinks'],
+  func: async (_page, kwargs) => {
+    return fetchBloombergFeed('tech', kwargs.limit ?? 1);
+  },
+});

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

@@ -0,0 +1,135 @@
+import { describe, expect, it } from 'vitest';
+import { extractStoryMediaLinks, parseBloombergRss, renderStoryBody } from './utils.js';
+
+describe('Bloomberg utils', () => {
+  it('parses Bloomberg RSS items with summary, link, and deduped media links', () => {
+    const xml = `<?xml version="1.0" encoding="UTF-8"?>
+      <rss xmlns:media="http://search.yahoo.com/mrss/">
+        <channel>
+          <item>
+            <title><![CDATA[Headline One]]></title>
+            <description><![CDATA[Summary <b>One</b> &amp; more]]></description>
+            <link>https://www.bloomberg.com/news/articles/2026-03-19/example-one</link>
+            <media:content url="https://assets.bwbx.io/example-one.jpg" type="image/jpeg">
+              <media:thumbnail url="https://assets.bwbx.io/example-one.jpg" />
+            </media:content>
+          </item>
+          <item>
+            <title>Headline Two</title>
+            <description>Summary Two</description>
+            <guid isPermaLink="true">https://www.bloomberg.com/news/articles/2026-03-19/example-two</guid>
+            <enclosure url="https://assets.bwbx.io/example-two.png" type="image/png" />
+          </item>
+        </channel>
+      </rss>`;
+
+    const items = parseBloombergRss(xml);
+    expect(items).toHaveLength(2);
+    expect(items[0]).toEqual({
+      title: 'Headline One',
+      summary: 'Summary One & more',
+      link: 'https://www.bloomberg.com/news/articles/2026-03-19/example-one',
+      mediaLinks: ['https://assets.bwbx.io/example-one.jpg'],
+    });
+    expect(items[1]).toEqual({
+      title: 'Headline Two',
+      summary: 'Summary Two',
+      link: 'https://www.bloomberg.com/news/articles/2026-03-19/example-two',
+      mediaLinks: ['https://assets.bwbx.io/example-two.png'],
+    });
+  });
+
+  it('renders Bloomberg story rich-text body into readable text', () => {
+    const body = {
+      type: 'document',
+      content: [
+        { type: 'inline-newsletter', data: { position: 'top' }, content: [] },
+        {
+          type: 'paragraph',
+          data: {},
+          content: [
+            { type: 'text', value: 'Lead paragraph with ' },
+            { type: 'entity', content: [{ type: 'text', value: 'linked text' }] },
+            { type: 'text', value: '.' },
+          ],
+        },
+        {
+          type: 'heading',
+          data: { level: 2 },
+          content: [{ type: 'text', value: 'Key Points' }],
+        },
+        {
+          type: 'list',
+          data: { style: 'unordered' },
+          content: [
+            {
+              type: 'list-item',
+              content: [
+                { type: 'paragraph', content: [{ type: 'text', value: 'Point one' }] },
+              ],
+            },
+            {
+              type: 'list-item',
+              content: [
+                { type: 'paragraph', content: [{ type: 'text', value: 'Point two' }] },
+              ],
+            },
+          ],
+        },
+        {
+          type: 'blockquote',
+          content: [{ type: 'text', value: 'Quoted line' }],
+        },
+        {
+          type: 'media',
+          data: {
+            attachment: {
+              caption: '<p>Chart caption</p>',
+            },
+          },
+        },
+        { type: 'ad', data: { num: 1 }, content: [] },
+      ],
+    };
+
+    expect(renderStoryBody(body)).toBe([
+      'Lead paragraph with linked text.',
+      '## Key Points',
+      '- Point one\n- Point two',
+      '> Quoted line',
+      'Chart caption',
+    ].join('\n\n'));
+  });
+
+  it('collects deduped story media links from lede, attachments, and body media', () => {
+    const story = {
+      ledeImageUrl: 'https://assets.bwbx.io/lede.webp',
+      lede: { url: 'https://assets.bwbx.io/lede.webp' },
+      socialImageUrl: 'https://assets.bwbx.io/social.png',
+      imageAttachments: {
+        one: { url: 'https://assets.bwbx.io/figure.jpg' },
+      },
+      body: {
+        content: [
+          {
+            type: 'media',
+            data: {
+              chart: {
+                src: 'https://resource.bloomberg.com/images/chart.png',
+                fallback: 'https://assets.bwbx.io/chart-fallback.png',
+              },
+            },
+          },
+        ],
+      },
+    };
+
+    expect(extractStoryMediaLinks(story)).toEqual([
+      'https://assets.bwbx.io/lede.webp',
+      'https://assets.bwbx.io/social.png',
+      'https://assets.bwbx.io/figure.jpg',
+      'https://resource.bloomberg.com/images/chart.png',
+      'https://assets.bwbx.io/chart-fallback.png',
+    ]);
+  });
+});