feat: edit bloomberg bundles

.gitignore

@@ -17,6 +17,10 @@ node_modules/
 # authored locally — the bundle is the committed unit, not the helper.
 helpers/
 
+# User preferences and research reports (news-hub-feed)
+skills/news-hub-feed/profile.json
+skills/news-hub-feed/reports/
+
 # IDE / agent workspace files
 .zcode/
 AGENTS.md

skills/news-hub-feed/scripts/api-client.js

@@ -20,6 +20,8 @@ const path = require('path');
 const SKILL_DIR = path.dirname(__dirname); // .../skills/news-hub-feed
 const CONFIG_PATH = path.join(SKILL_DIR, 'config.json');
 const TEMPLATE_PATH = path.join(SKILL_DIR, 'references', 'config-template.json');
+const PROFILE_PATH = path.join(SKILL_DIR, 'profile.json');
+const REPORTS_DIR = path.join(SKILL_DIR, 'reports');
 
 // Scopes this skill needs for full functionality.
 const REQUIRED_SCOPES = ['articles:read', 'marks:read', 'marks:write'];
@@ -307,10 +309,50 @@ function truncate(s, maxLen) {
   return s.slice(0, maxLen - 1) + '…';
 }
 
+/**
+ * Ensure a directory exists (recursive mkdir).
+ * @param {string} dir
+ */
+function ensureDir(dir) {
+  if (!fs.existsSync(dir)) {
+    fs.mkdirSync(dir, { recursive: true });
+  }
+}
+
+/**
+ * Return today's date as YYYY-MM-DD (local timezone).
+ * @returns {string}
+ */
+function todayStr() {
+  const d = new Date();
+  const y = d.getFullYear();
+  const m = String(d.getMonth() + 1).padStart(2, '0');
+  const day = String(d.getDate()).padStart(2, '0');
+  return `${y}-${m}-${day}`;
+}
+
+/**
+ * Convert a string into a safe filename component.
+ * Replaces spaces and special chars with underscores, keeps CJK chars.
+ * @param {string} s
+ * @returns {string}
+ */
+function sanitizeFilename(s) {
+  if (!s) return 'untitled';
+  return s
+    .replace(/[\/\\:*?"<>|]/g, '_')
+    .replace(/\s+/g, '_')
+    .replace(/_+/g, '_')
+    .replace(/^_|_$/g, '')
+    .slice(0, 60) || 'untitled';
+}
+
 module.exports = {
   SKILL_DIR,
   CONFIG_PATH,
   TEMPLATE_PATH,
+  PROFILE_PATH,
+  REPORTS_DIR,
   REQUIRED_SCOPES,
   loadConfig,
   requireApi,
@@ -324,4 +366,7 @@ module.exports = {
   parseMarksCsv,
   fmtTime,
   truncate,
+  ensureDir,
+  todayStr,
+  sanitizeFilename,
 };

skills/news-hub-feed/scripts/report.js

+'use strict';
+
+/**
+ * report.js — Research report helper for news-hub-feed.
+ *
+ * Two sub-commands:
+ *
+ *   fetch — batch-fetch article details for the agent to synthesize into a report.
+ *     node scripts/report.js fetch <csv-of-ids> [--fields summary,original,translation] [--json]
+ *
+ *   save  — save a finished Markdown report to reports/ with frontmatter.
+ *     node scripts/report.js save --title <title> [--articles <csv-ids>] --stdin
+ *     node scripts/report.js save --title <title> [--articles <csv-ids>] --content <path>
+ *
+ * The agent writes the report body; this script handles the API fetching and
+ * the file I/O (ensuring frontmatter, directory, filename).
+ */
+
+const fs = require('fs');
+const path = require('path');
+const {
+  loadConfig,
+  requireApi,
+  apiRequest,
+  parseArgs,
+  csvSplit,
+  fmtTime,
+  ensureDir,
+  todayStr,
+  sanitizeFilename,
+  REPORTS_DIR,
+} = require('./api-client');
+
+const HELP = `\
+用法:
+  node scripts/report.js fetch <id1,id2,...> [--fields summary,original,translation] [--json]
+  node scripts/report.js save --title <title> [--articles <csv-ids>] --stdin
+  node scripts/report.js save --title <title> [--articles <csv-ids>] --content <file-path>
+`;
+
+// ---------------------------------------------------------------------------
+// fetch sub-command
+// ---------------------------------------------------------------------------
+
+/**
+ * Batch-fetch article details.
+ * @param {object} cfg
+ * @param {string[]} ids — array of numeric string IDs
+ * @param {string} fields — comma-separated fields param
+ * @returns {Promise<Array>}
+ */
+async function fetchArticles(cfg, ids, fields) {
+  const results = [];
+  for (const id of ids) {
+    const query = {};
+    if (fields) query.fields = fields;
+    try {
+      const article = await apiRequest(cfg, 'GET', `/articles/${id}`, { query });
+      results.push(article);
+    } catch (err) {
+      results.push({
+        articleId: id,
+        error: err.message,
+        code: err.code || 'ERROR',
+      });
+    }
+  }
+  return results;
+}
+
+async function cmdFetch(cfg, positional, flags) {
+  if (positional.length < 1) {
+    console.error('用法: node scripts/report.js fetch <id1,id2,...> [--fields ...] [--json]');
+    process.exit(1);
+  }
+
+  // Accept both CSV and space-separated IDs
+  let ids;
+  if (positional[0].includes(',')) {
+    ids = csvSplit(positional[0]);
+  } else {
+    ids = positional.slice();
+  }
+
+  // Validate all IDs are numeric
+  for (const id of ids) {
+    if (!/^\d+$/.test(id)) {
+      console.error(`✗ 文章 ID 必须是正整数，得到: ${id}`);
+      process.exit(1);
+    }
+  }
+
+  const fields = flags.fields || 'summary,translation';
+  console.error(`正在拉取 ${ids.length} 篇文章 (fields=${fields})…`);
+
+  const articles = await fetchArticles(cfg, ids, fields);
+
+  // Check for errors
+  const errors = articles.filter((a) => a.error);
+  if (errors.length > 0) {
+    console.error(`⚠️  ${errors.length} 篇拉取失败:`);
+    for (const e of errors) {
+      console.error(`  #${e.articleId}: ${e.error}`);
+    }
+  }
+
+  if (flags.json) {
+    process.stdout.write(JSON.stringify(articles, null, 2) + '\n');
+  } else {
+    // Print a compact summary for agent reference
+    console.log(`\n已拉取 ${articles.length - errors.length}/${ids.length} 篇文章:\n`);
+    for (const a of articles) {
+      if (a.error) {
+        console.log(`  #${a.articleId} ❌ ${a.error}`);
+        continue;
+      }
+      console.log(`  #${a.articleId}  ${a.titleZh || a.titleEn || '(无标题)'}`);
+      console.log(`        ${a.source || ''} | ${a.category || ''} | ${fmtTime(a.publishedAt)}`);
+      if (a.tags && a.tags.length > 0) {
+        console.log(`        tags: ${a.tags.join(', ')}`);
+      }
+      if (a.summaryOverview) {
+        console.log(`        概述: ${a.summaryOverview}`);
+      }
+      console.log();
+    }
+  }
+}
+
+// ---------------------------------------------------------------------------
+// save sub-command
+// ---------------------------------------------------------------------------
+
+async function cmdSave(positional, flags) {
+  if (!flags.title) {
+    console.error('✗ --title 是必需的');
+    console.error(HELP);
+    process.exit(1);
+  }
+
+  let content;
+  if (flags.stdin) {
+    // Read from stdin
+    content = fs.readFileSync(0, 'utf8');
+  } else if (flags.content) {
+    if (!fs.existsSync(flags.content)) {
+      console.error(`✗ 文件不存在: ${flags.content}`);
+      process.exit(1);
+    }
+    content = fs.readFileSync(flags.content, 'utf8');
+  } else {
+    console.error('✗ 需要 --stdin 或 --content <path> 之一');
+    console.error(HELP);
+    process.exit(1);
+  }
+
+  // Parse article IDs
+  const articleIds = flags.articles ? csvSplit(flags.articles) : [];
+
+  // Extract categories from content? No — let the agent provide them.
+  // Build frontmatter
+  const date = todayStr();
+  const now = new Date().toISOString().replace(/\.\d{3}Z$/, 'Z');
+
+  const frontmatter = {
+    date,
+    title: flags.title,
+    articles: articleIds,
+    generatedAt: now,
+  };
+
+  const frontmatterYaml = formatFrontmatter(frontmatter);
+
+  // Combine: frontmatter + content (strip existing frontmatter from content if present)
+  const bodyContent = stripFrontmatter(content);
+  const fullReport = `---\n${frontmatterYaml}---\n\n${bodyContent.trim()}\n`;
+
+  // Ensure reports directory exists
+  ensureDir(REPORTS_DIR);
+
+  // Generate filename
+  const filename = `${date}_${sanitizeFilename(flags.title)}.md`;
+  const filepath = path.join(REPORTS_DIR, filename);
+
+  fs.writeFileSync(filepath, fullReport);
+
+  console.log(`✓ 报告已保存: ${filepath}`);
+
+  // Update briefing history if there's a matching entry for today
+  try {
+    const { loadProfile, saveProfile } = require('./profile');
+    const profile = loadProfile();
+    const todayEntry = profile.briefingHistory.find((h) => h.date === date);
+    if (todayEntry) {
+      todayEntry.reportGenerated = `reports/${filename}`;
+      saveProfile(profile);
+    }
+  } catch {
+    // Profile may not exist yet — non-fatal
+  }
+}
+
+function formatFrontmatter(fm) {
+  const lines = [];
+  lines.push(`date: ${fm.date}`);
+  lines.push(`title: "${fm.title.replace(/"/g, '\\"')}"`);
+  if (fm.articles.length > 0) {
+    lines.push(`articles: [${fm.articles.join(', ')}]`);
+  } else {
+    lines.push(`articles: []`);
+  }
+  lines.push(`generatedAt: ${fm.generatedAt}`);
+  return lines.join('\n') + '\n';
+}
+
+function stripFrontmatter(text) {
+  if (text.startsWith('---\n')) {
+    const end = text.indexOf('\n---\n', 4);
+    if (end !== -1) {
+      return text.slice(end + 5);
+    }
+  }
+  return text;
+}
+
+// ---------------------------------------------------------------------------
+// Main dispatch
+// ---------------------------------------------------------------------------
+
+async function main() {
+  const { flags, positional } = parseArgs(process.argv.slice(2));
+  const subcommand = positional[0];
+  const rest = positional.slice(1);
+
+  if (!subcommand || subcommand === 'help' || subcommand === '--help' || subcommand === '-h') {
+    console.log(HELP);
+    return;
+  }
+
+  switch (subcommand) {
+    case 'fetch': {
+      const cfg = loadConfig();
+      requireApi(cfg);
+      await cmdFetch(cfg, rest, flags);
+      break;
+    }
+    case 'save':
+      await cmdSave(rest, flags);
+      break;
+    default:
+      console.error(`✗ 未知子命令: ${subcommand}\n`);
+      console.log(HELP);
+      process.exit(1);
+  }
+}
+
+module.exports = { fetchArticles, formatFrontmatter, stripFrontmatter };
+
+main().catch((err) => {
+  console.error(`\n✗ ${err.message}`);
+  process.exit(1);
+});

skills/news-source-analyzer/bloomberg-technology.nhsource.json

+{
+  "format": "news-harvester-source",
+  "version": 1,
+  "exportedAt": "2026-08-14T02:47:27.378Z",
+  "source": {
+    "id": "bloomberg-technology",
+    "name": "彭博社科技",
+    "homepageUrl": "https://www.bloomberg.com/technology",
+    "method": "browser",
+    "vaultFolder": "Bloomberg/Technology"
+  },
+  "files": {
+    "helpers/bloomberg-technology.md": "---\nsource: bloomberg-technology\n\n# ── 发现阶段 ──\n# Bloomberg Technology 首页文章分散在多个 LineupContent* 卡片容器 +\n# styles_itemTextContainer 列表中，用复合 listSelector 一次性圈中。\nlistSelector: '[class*=\"LineupContent\"], [class*=\"itemTextContainer\"]'\nlinkSelector: 'a[href]'\n\n# 文章 URL 形如 /news/articles/YYYY-MM-DD/<slug> 或 /news/features/YYYY-MM-DD/<slug>\n# 视频 /news/videos/ 用 excludeUrlPattern 排除。\nurlPattern: 'bloomberg\\.com/news/(articles|features)/.+'\nexcludeUrlPattern: 'bloomberg\\.com/news/videos/'\n\nscrollSteps: 3\nscrollWaitMs: 2000\nwaitMs: 20000\nmaxLinks: 30\n\n# ── 提取阶段 ──\n# Bloomberg 正文段落 class 为 ArticleBodyText_articleBodyContent__xxxxx，\n# 直接命中正文 <p>，避免误抓 newsletter / MostRead 等侧边栏内容。\n# body-content p 作为 fallback（整个正文容器内的所有 <p>）。\nbodySelectors:\n  - '[class*=\"ArticleBodyText\"]'\n  - '[data-testid=\"paragraph\"]'\n  - '[class*=\"body-content\"] p'\n  - '[class*=\"articleBodyContent\"] p'\n  - '[class*=\"ArticleBody\"] p'\n  - '[class*=\"article-body\"] p'\n  - 'article p'\nbodyMinParagraphs: 3\n\ndateSelector: 'time[datetime]'\n# Bloomberg 作者署名在 byline 容器中，JSON-LD 作为最终 fallback。\nauthorSelector: '[rel=\"author\"], [class*=\"author\"] a, [class*=\"byline\"] a, [class*=\"Byline\"] a'\n\nimageSelector: 'img'\nimageMinWidth: 200\nexcludeImage:\n  - logo\n  - icon\n  - avatar\n  - profile\n\n# Bloomberg 文末常见署名/订阅推广噪声 + 推荐文章标题噪声。\nnoisePrefixes:\n  - 'Sign up for'\n  - 'Subscribe to'\n  - 'Read more:'\n  - 'Read More:'\n  - 'Most Read from Bloomberg'\n  - 'This article was produced'\n  - '©2026 Bloomberg'\n  - 'Bloomberg may send me'\n  - 'By submitting my information'\n  - 'By continuing, I agree'\n\ntitleStripSuffix: ' - Bloomberg$'\nmaxBodyChars: 15000\n---\n# bloomberg-technology 抓取备忘\n\n- 首页 `https://www.bloomberg.com/technology` 文章卡片分布在多个 `LineupContent*`\n  容器（4Up/3Up/2Up/Basic）以及 `styles_itemTextContainer` 列表中，inspect 实测\n  首屏约 22 篇文章链接 + 4 个视频。用复合 `listSelector` 圈中所有卡片。\n- `urlPattern` 限定 `/news/(articles|features)/.+`，天然排除 `/technology/ai` 等\n  section 页与 `/markets` 等导航；`excludeUrlPattern` 排除 `/news/videos/`。\n- 反爬/付费墙：Bloomberg 对 headless 有反爬，正文可能因未登录被截断。\n  如 preview 出现 charCount<500 或 CAPTCHA（exit 70），需\n  `node scripts/ensure-chromium.js --login --url https://www.bloomberg.com/technology`\n  在窗口浏览器登录后退出，持久化 cookie 到 userDataDir。\n- 正文段落 class 为 `ArticleBodyText_articleBodyContent__xxxxx`（哈希后缀会变），\n  用 `[class*=\"ArticleBodyText\"]` 精确命中，避免误抓 newsletter / MostRead 推荐区块。\n  waitMs=20000 给足页面渲染时间，防止正文容器加载不全时 fallback 兜底抓到推荐标题。\n- 作者署名在 byline 容器中，authorSelector 已覆盖 `[class*=\"byline\"] a`；\n  若 CSS 选择器全部未命中，fetcher-helper 会自动 fallback 到 JSON-LD `author` 字段。\n- 验证: node scripts/preview.js --url https://www.bloomberg.com/technology \\\n  --recipe helpers/bloomberg-technology.md --count 3\n",
+    "helpers/bloomberg-technology.fixtures.json": "{\n  \"articles\": [\n    \"https://www.bloomberg.com/news/articles/2026-08-13/trump-enlists-private-sector-to-boost-cyber-offensive-arsenal\",\n    \"https://www.bloomberg.com/news/articles/2026-08-13/anthropic-said-in-talks-to-buy-ai-startup-decart-for-6-billion\",\n    \"https://www.bloomberg.com/news/features/2026-08-12/thousands-of-india-workers-are-helping-ai-firms-train-robots-to-replace-them\"\n  ],\n  \"sections\": [\n    \"https://www.bloomberg.com/technology/ai\",\n    \"https://www.bloomberg.com/technology/big-tech\"\n  ],\n  \"minLinks\": 10\n}\n"
+  }
+}
\ No newline at end of file