mirror of
https://github.com/jackwener/OpenCLI.git
synced 2026-09-14 18:25:42 +08:00
jakevin
d2974a9ff6
* refactor(adapters): convert adapter layer from TypeScript to JavaScript Core framework stays TypeScript; adapter layer moves to JS-first. Adapters are essentially "executable config + browser scripts" that barely use TS features — this simplifies the build/distribution pipeline by removing the dist/clis/ intermediate compilation step. Changes: - Convert all 753 adapter files in clis/ from .ts to .js - Update tsconfig to exclude clis/ from compilation - Simplify build-manifest to scan clis/*.js directly (no dist/clis/) - Update discovery, main, fetch-adapters to load JS adapters from clis/ - Update generate-verified to output .js artifacts - Update package.json files field: dist/clis/ → clis/ - Fix all test files for the .ts → .js transition * fix(main): use findPackageRoot for BUILTIN_CLIS path The previous relative path (../../clis from __dirname) only worked for dist/src/main.js but broke dev mode (tsx src/main.ts) where __dirname is <repo>/src — resolving to /clis instead of <repo>/clis. Use findPackageRoot() which works for both dev and prod paths.
63 lines
2.6 KiB
JavaScript
63 lines
2.6 KiB
JavaScript
/**
|
|
* 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';
|
|
/** Extract article ID from a full URL or a bare numeric ID string */
|
|
function parseArticleId(input) {
|
|
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, 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/${articleId}`);
|
|
await page.wait(5);
|
|
const data = await page.evaluate(`
|
|
(() => {
|
|
// Title: 36kr uses class "article-title" on h1
|
|
const title = document.querySelector('.article-title, h1')?.textContent?.trim() || '';
|
|
// Author: second .author-name (first is empty nav link, second has real name)
|
|
const authorEls = document.querySelectorAll('.author-name');
|
|
const author = Array.from(authorEls).map(el => el.textContent?.trim()).filter(Boolean)[0] || '';
|
|
// Date: 36kr uses class "title-icon-item item-time" for the publish date
|
|
const dateRaw = document.querySelector('.item-time')?.textContent?.trim() || '';
|
|
const date = dateRaw.replace(/^[·\s]+/, '').trim();
|
|
// Article body paragraphs
|
|
const bodyEls = document.querySelectorAll('[class*="article-content"] p, [class*="rich-text"] p, .article p');
|
|
const body = Array.from(bodyEls)
|
|
.map(el => el.textContent?.trim())
|
|
.filter(t => t && t.length > 10)
|
|
.join(' ')
|
|
.slice(0, 800);
|
|
return { title, author, date, body };
|
|
})()
|
|
`);
|
|
if (!data?.title) {
|
|
throw new CliError('NOT_FOUND', 'Article not found or failed to load', 'Check the article ID');
|
|
}
|
|
return [
|
|
{ field: 'title', value: data.title },
|
|
{ field: 'author', value: data.author || '-' },
|
|
{ field: 'date', value: data.date || '-' },
|
|
{ field: 'url', value: `https://36kr.com/p/${articleId}` },
|
|
{ field: 'body', value: data.body || '-' },
|
|
];
|
|
},
|
|
});
|