mirror of
https://github.com/jackwener/OpenCLI.git
synced 2026-09-14 18:25:42 +08:00
jakevin
4fe9a73ebc
* refactor: migrate adapter imports to package exports Replace all relative imports (../../src/registry.js, ../../browser/cdp.js, etc.) with package exports (@jackwener/opencli/registry, @jackwener/opencli/errors, etc.) across all 484 adapter files. This decouples adapter import resolution from directory structure: - User CLIs in ~/.opencli/clis/ resolve via node_modules symlink - Internal adapters resolve via Node.js self-referencing - No more shim files needed for import resolution Changes: - package.json: add sub-path exports for all public modules - clis/**: replace relative imports with @jackwener/opencli/... - discovery.ts: simplify ensureUserCliCompatShims to symlink-only - registry-api.ts: export CommandArgs type - Remove root-level shim directories (browser/, download/, pipeline/) - Remove shim entries from tsconfig.json include and package.json files * test: add regression tests for package exports Prevents regressions like #788/#791 by: 1. Scanning all adapter files for forbidden relative imports (../../src/, ../../browser/, etc.) — fails if any remain 2. Verifying every package.json export maps to an existing source file 18 new test cases. * fix: use junction on Windows + broaden test patterns - discovery.ts: use 'junction' symlink type on Windows (no admin required) - package-exports.test.ts: generalize forbidden patterns to catch any depth of ../ traversal (not just ../../ and ../../../) * fix: update stale vi.mock/importActual paths in adapter tests Test files still used old relative paths for vi.mock() and vi.importActual() calls. Updated 5 test files to use package exports. Also broadened regression test patterns to catch mock/importActual paths. * fix: use rm instead of unlink for symlink cleanup, add warn on failure Addresses review feedback from Astro-Han: - rm() handles both symlinks and stale directories (unlink fails on dirs) - Log a warning when symlink creation fails instead of silent catch * docs: update import examples to use package exports Update all documentation, contributing guides, and skills to use @jackwener/opencli/registry instead of ../../src/registry.js. Without this, users following the docs would write adapters with broken imports since the old shim files are no longer created.
70 lines
2.6 KiB
TypeScript
70 lines
2.6 KiB
TypeScript
/**
|
|
* 36kr article detail — INTERCEPT strategy.
|
|
*
|
|
* Fetches the full content of a 36kr article given its ID or URL.
|
|
*/
|
|
import { cli, Strategy } from '@jackwener/opencli/registry';
|
|
import { CliError } from '@jackwener/opencli/errors';
|
|
import type { IPage } from '@jackwener/opencli/types';
|
|
|
|
/** Extract article ID from a full URL or a bare numeric ID string */
|
|
function parseArticleId(input: string): string {
|
|
const m = input.match(/\/p\/(\d+)/);
|
|
return m ? m[1] : input.replace(/\D/g, '');
|
|
}
|
|
|
|
cli({
|
|
site: '36kr',
|
|
name: 'article',
|
|
description: '获取36氪文章正文内容',
|
|
domain: 'www.36kr.com',
|
|
strategy: Strategy.INTERCEPT,
|
|
args: [
|
|
{ name: 'id', positional: true, required: true, help: 'Article ID or full 36kr article URL' },
|
|
],
|
|
columns: ['field', 'value'],
|
|
func: async (page: IPage, args) => {
|
|
const articleId = parseArticleId(String(args.id ?? ''));
|
|
if (!articleId) {
|
|
throw new CliError('INVALID_ARGUMENT', 'Invalid article ID or URL');
|
|
}
|
|
|
|
await page.installInterceptor('36kr.com/api');
|
|
await page.goto(`https://www.36kr.com/p/${articleId}`);
|
|
await page.wait(5);
|
|
|
|
const data: any = await page.evaluate(`
|
|
(() => {
|
|
// Title: 36kr uses class "article-title" on h1
|
|
const title = document.querySelector('.article-title, h1')?.textContent?.trim() || '';
|
|
// Author: second .author-name (first is empty nav link, second has real name)
|
|
const authorEls = document.querySelectorAll('.author-name');
|
|
const author = Array.from(authorEls).map(el => el.textContent?.trim()).filter(Boolean)[0] || '';
|
|
// Date: 36kr uses class "title-icon-item item-time" for the publish date
|
|
const dateRaw = document.querySelector('.item-time')?.textContent?.trim() || '';
|
|
const date = dateRaw.replace(/^[·\s]+/, '').trim();
|
|
// Article body paragraphs
|
|
const bodyEls = document.querySelectorAll('[class*="article-content"] p, [class*="rich-text"] p, .article p');
|
|
const body = Array.from(bodyEls)
|
|
.map(el => el.textContent?.trim())
|
|
.filter(t => t && t.length > 10)
|
|
.join(' ')
|
|
.slice(0, 800);
|
|
return { title, author, date, body };
|
|
})()
|
|
`);
|
|
|
|
if (!data?.title) {
|
|
throw new CliError('NOT_FOUND', 'Article not found or failed to load', 'Check the article ID');
|
|
}
|
|
|
|
return [
|
|
{ field: 'title', value: data.title },
|
|
{ field: 'author', value: data.author || '-' },
|
|
{ field: 'date', value: data.date || '-' },
|
|
{ field: 'url', value: `https://36kr.com/p/${articleId}` },
|
|
{ field: 'body', value: data.body || '-' },
|
|
];
|
|
},
|
|
});
|