feat(kb): 新增一件代发 FAQ 知识库

bridge/src/faq-fetcher.js

@@ -2,6 +2,7 @@
 
 const fs = require('fs');
 const path = require('path');
+const vm = require('node:vm');
 
 function stripHtml(value) {
   return String(value || '')
@@ -40,6 +41,47 @@ function extractFaqFromLdJson(html, max = 50) {
   return [];
 }
 
+// Nuxt SSR 页面（如 dropshipping.yehwang.com）没有 FAQPage JSON-LD，
+// FAQ 数据内嵌在 window.__NUXT__ 的 payload 里（data[].info.content = [{title, content(HTML)}]）。
+// 在隔离 sandbox 里求值这段自执行脚本，只取回返回对象，不接触宿主全局。
+function extractNuxtPayload(html) {
+  const m = String(html || '').match(/__NUXT__=([\s\S]*?)<\/script>/);
+  if (!m) return null;
+  try {
+    return vm.runInNewContext(m[1].replace(/;\s*$/, ''), Object.create(null), { timeout: 2000 });
+  } catch {
+    return null;
+  }
+}
+
+function extractFaqFromNuxt(html, max = 50) {
+  const payload = extractNuxtPayload(html);
+  if (!payload || !payload.data) return [];
+  const out = [];
+  const seen = new Set();
+  const walk = (node) => {
+    if (out.length >= max) return;
+    if (Array.isArray(node)) {
+      for (const item of node) walk(item);
+      return;
+    }
+    if (!node || typeof node !== 'object') return;
+    if (typeof node.title === 'string' && typeof node.content === 'string') {
+      const q = stripHtml(node.title);
+      const a = stripHtml(node.content);
+      if (q && a && !seen.has(q)) {
+        seen.add(q);
+        out.push({ q, a });
+      }
+    }
+    for (const value of Object.values(node)) {
+      if (value && typeof value === 'object') walk(value);
+    }
+  };
+  walk(payload.data);
+  return out;
+}
+
 function loadFaqConfig(file) {
   try {
     return JSON.parse(fs.readFileSync(file, 'utf8'));
@@ -53,20 +95,21 @@ function createFaqFetcher(config = {}) {
   const timeoutMs = config.timeoutMs || 15000;
   const max = config.maxFaqsPerPage || 50;
 
-  async function fetchPage(url) {
-    const res = await fetch(url, {
+  async function fetchPage(page) {
+    const res = await fetch(page.url, {
       headers: { 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0 Safari/537.36', Accept: 'text/html,application/xhtml+xml' },
       signal: AbortSignal.timeout(timeoutMs),
     });
-    if (!res.ok) throw new Error(`fetch ${url} failed: HTTP ${res.status}`);
-    return extractFaqFromLdJson(await res.text(), max);
+    if (!res.ok) throw new Error(`fetch ${page.url} failed: HTTP ${res.status}`);
+    const html = await res.text();
+    return page.extractor === 'nuxt' ? extractFaqFromNuxt(html, max) : extractFaqFromLdJson(html, max);
   }
 
   async function fetchAll() {
     const out = [];
     for (const page of pages) {
       try {
-        const questions = await fetchPage(page.url);
+        const questions = await fetchPage(page);
         out.push({ ...page, questions });
       } catch (err) {
         out.push({ ...page, questions: [], error: err.message });
@@ -78,4 +121,4 @@ function createFaqFetcher(config = {}) {
   return { fetchPage, fetchAll, pages };
 }
 
-module.exports = { createFaqFetcher, loadFaqConfig, extractFaqFromLdJson, stripHtml };
+module.exports = { createFaqFetcher, loadFaqConfig, extractFaqFromLdJson, extractFaqFromNuxt, extractNuxtPayload, stripHtml };