john
2049bc8c6e
Trying to push a WeChat draft locally surfaced two problems. isNewsMorningContentDegraded matched cards with `class="card(?:\s|")`, which never matches news002's `class="lead-card"`. Headline cards were therefore invisible to the check, so a healthy news002 page could be flagged as degraded and regenerated. Count cards through the shared extractor instead, which handles card, lead-card and highlight-box alike. Add scripts/dryrun-news-morning-draft.mjs to run a page through the dedup gate, degradation check, inline conversion and footer layout without calling the WeChat API, since local IPs are not in the official account whitelist (errcode 40164) and a real push would write into the production draft box. Co-authored-by: Cursor <cursoragent@cursor.com>
86 lines
3.5 KiB
JavaScript
86 lines
3.5 KiB
JavaScript
#!/usr/bin/env node
|
||
/**
|
||
* 本地 dry-run：把一张早报 HTML 走完「去重闸门 → 微信 inline 转换 → 统一页脚」全链路，
|
||
* 输出最终草稿正文，但不调用任何微信接口、不落 DB。
|
||
*
|
||
* 用于在本机 IP 不在公众号白名单时验证 news001 / news002 的草稿产出。
|
||
*
|
||
* 用法：
|
||
* node scripts/dryrun-news-morning-draft.mjs <页面.html> [输出目录]
|
||
*/
|
||
import fs from 'node:fs';
|
||
import path from 'node:path';
|
||
import {
|
||
dedupeNewsMorningHtml,
|
||
formatNewsMorningDedupeSummary,
|
||
} from '../wechat-news-morning-dedup.mjs';
|
||
import {
|
||
convertNewsPageHtmlToWechatArticle,
|
||
isDailyNewsFormat,
|
||
isNewsMorningContentDegraded,
|
||
} from '../wechat-news-morning-draft.mjs';
|
||
|
||
const MAX_WECHAT_CONTENT_CHARS = 20000;
|
||
|
||
const input = process.argv[2];
|
||
const outDir = process.argv[3] || path.dirname(input ?? '.');
|
||
if (!input || !fs.existsSync(input)) {
|
||
console.error('用法：node scripts/dryrun-news-morning-draft.mjs <页面.html> [输出目录]');
|
||
process.exit(1);
|
||
}
|
||
|
||
const publicUrl = 'https://m.tkmind.cn/MindSpace/dry-run/public/daily-news-dryrun.html';
|
||
const raw = fs.readFileSync(input, 'utf8');
|
||
|
||
console.log(`输入：${input}（${raw.length} 字符）`);
|
||
|
||
// 1. 去重闸门
|
||
const deduped = dedupeNewsMorningHtml(raw);
|
||
console.log(`\n[1] 去重闸门：${formatNewsMorningDedupeSummary(deduped)}`);
|
||
if (deduped.removedSectionIds.length) {
|
||
console.log(` 移除空栏目：${deduped.removedSectionIds.join(', ')}`);
|
||
}
|
||
|
||
// 2. 降级检测
|
||
const degraded = isNewsMorningContentDegraded(deduped.html);
|
||
console.log(`\n[2] 降级检测：${degraded ? '❌ 判定为降级页（卡片不足/检索失败）' : '✅ 正常'}`);
|
||
|
||
// 3. 识别版式 + 转换为微信草稿
|
||
console.log(`\n[3] 版式识别：${isDailyNewsFormat(deduped.html) ? '✅ daily-news' : '❌ 非早报版式'}`);
|
||
|
||
const article = convertNewsPageHtmlToWechatArticle(
|
||
deduped.html,
|
||
{ publicUrl, qrcodeImageUrl: 'https://mmbiz.qpic.cn/dryrun-qrcode.png' },
|
||
);
|
||
|
||
console.log('\n[4] 草稿产出：');
|
||
console.log(` 标题：${article.title}`);
|
||
console.log(` 摘要：${String(article.digest ?? '').slice(0, 60)}`);
|
||
console.log(` 正文长度：${article.content.length} / ${MAX_WECHAT_CONTENT_CHARS}`
|
||
+ (article.content.length > MAX_WECHAT_CONTENT_CHARS ? ' ❌ 超限' : ' ✅ 未超限'));
|
||
|
||
const checks = [
|
||
// 微信不支持 <style>，早报路径必须全部内联。
|
||
['无 <style> 块（已内联）', !/<style/i.test(article.content)],
|
||
['正文使用内联 style', (article.content.match(/style="/g) ?? []).length > 20],
|
||
['含「阅读原文」引导', /阅读原文/u.test(article.content)],
|
||
['含关注二维码区', /<img[^>]+dryrun-qrcode/i.test(article.content)],
|
||
['无 <script> 残留', !/<script/i.test(article.content)],
|
||
['无 MindSpace 平台水印', !/data-mindspace-page-tag/i.test(article.content)],
|
||
];
|
||
console.log('\n[5] 合规检查：');
|
||
for (const [label, ok] of checks) console.log(` ${ok ? '✅' : '❌'} ${label}`);
|
||
|
||
const base = path.basename(input, '.html');
|
||
const outHtml = path.join(outDir, `${base}.wechat-draft.html`);
|
||
fs.writeFileSync(outHtml, `<!DOCTYPE html><html><head><meta charset="utf-8">
|
||
<meta name="viewport" content="width=device-width,initial-scale=1">
|
||
<title>${article.title}（微信草稿 dry-run）</title></head>${article.content}</html>`);
|
||
console.log(`\n草稿正文已写入：${outHtml}`);
|
||
|
||
const outDeduped = path.join(outDir, `${base}.deduped.html`);
|
||
if (deduped.changed) {
|
||
fs.writeFileSync(outDeduped, deduped.html);
|
||
console.log(`去重后页面已写入：${outDeduped}`);
|
||
}
|