1  import { cli, Strategy } from '@jackwener/opencli/registry';
 2  import { clampInt } from '../_shared/common.js';
 3  
 4  cli({
 5      site: 'gov-policy',
 6      name: 'recent',
 7      description: '国务院最新政策文件',
 8      domain: 'www.gov.cn',
 9      strategy: Strategy.PUBLIC,
10      browser: true,
11      args: [
12          { name: 'limit', type: 'int', default: 10, help: '返回结果数量 (max 20)' },
13      ],
14      columns: ['rank', 'title', 'date', 'source', 'url'],
15      navigateBefore: false,
16      func: async (page, kwargs) => {
17          const limit = clampInt(kwargs.limit, 10, 1, 20);
18          await page.goto('https://www.gov.cn/zhengce/zuixin/index.htm');
19          await page.wait(4);
20          const data = await page.evaluate(`
21        (async () => {
22          const normalize = v => (v || '').replace(/\\s+/g, ' ').trim();
23          for (let i = 0; i < 20; i++) {
24            if (document.querySelector('.news_box li, .list li, .list_item, .news-list li')) break;
25            await new Promise(r => setTimeout(r, 500));
26          }
27          const results = [];
28          for (const el of document.querySelectorAll('.news_box li, .list li, .list_item, .news-list li')) {
29            const titleEl = el.querySelector('a');
30            const title = normalize(titleEl?.textContent);
31            if (!title || title.length < 4) continue;
32  
33            let url = titleEl?.getAttribute('href') || '';
34            if (url && !url.startsWith('http')) url = 'https://www.gov.cn' + url;
35  
36            const date = (el.textContent || '').match(/(\\d{4}[-./]\\d{1,2}[-./]\\d{1,2})/)?.[1] || '';
37            const source = normalize(el.querySelector('.source, .from')?.textContent);
38  
39            results.push({ rank: results.length + 1, title, date, source, url });
40            if (results.length >= ${limit}) break;
41          }
42          return results;
43        })()
44      `);
45          return Array.isArray(data) ? data : [];
46      },
47  });