修复搜索和用户主页的笔记 ID 提取及风控绕过问题

- 搜索页笔记 href 格式为 /search_result/<id>，修正正则以兼容 /explore/ 和 /search_result/ - 用户主页笔记 href 格式为 /user/profile/<userId>/<noteId>，扩展正则并取正确捕获组 - 用户主页访问前先 warm-up 到 /explore，绕过 XHS headless IP 风控（code 300012） - xsec_source 改为 pc_feed 以匹配用户从 feed 页获取的 token 类型 - 新增 debug-search.ts / debug-qrcode.ts / debug-profile.ts 诊断脚本
2026-03-01 22:44:45 +08:00
parent 8b39520ec7
commit 56d5a6de96
5 changed files with 265 additions and 4 deletions
@@ -0,0 +1,106 @@
+/**
+ * Standalone diagnostic script — run with:
+ *   npx tsx scripts/debug-qrcode.ts
+ *
+ * Opens XHS explore page in headless mode and dumps:
+ *   - page title & URL after navigation
+ *   - all element counts for candidate selectors
+ *   - screenshot saved to /tmp/xhs-debug.png
+ */
+
+import { chromium } from 'rebrowser-playwright';
+import { writeFileSync } from 'node:fs';
+
+const EXPLORE_URL = 'https://www.xiaohongshu.com/explore';
+const WAIT_MS = 15_000; // wait 15s for SPA to settle
+
+const SELECTORS_TO_PROBE = [
+  // Current (fixed)
+  'img.qrcode-img',
+  '.qrcode-img',
+  // Original (broken)
+  '.login-container .qrcode-img',
+  // Login button candidates
+  '.login-btn',
+  'button.login-btn',
+  // Logged-in indicator candidates
+  '.user .link-wrapper .channel',
+  // Modal/container
+  '.container',
+  'div.container',
+  // QR area
+  '.code-area',
+  '.qrcode',
+  // Phone input (also in modal)
+  'input[name="xhs-pc-web-phone"]',
+];
+
+async function main() {
+  console.log('Launching browser (headless: false)...');
+  const browser = await chromium.launch({
+    headless: false,
+    args: ['--no-sandbox', '--disable-setuid-sandbox', '--disable-dev-shm-usage', '--disable-gpu'],
+  });
+
+  const ctx = await browser.newContext();
+  const page = await ctx.newPage();
+
+  console.log(`Navigating to ${EXPLORE_URL} ...`);
+  const t0 = Date.now();
+  await page.goto(EXPLORE_URL, { waitUntil: 'domcontentloaded' });
+  console.log(`  domcontentloaded in ${Date.now() - t0}ms`);
+  console.log(`  title: "${await page.title()}"`);
+  console.log(`  url:   ${page.url()}`);
+
+  console.log(`\nWaiting ${WAIT_MS / 1000}s for SPA to render...`);
+  await page.waitForTimeout(WAIT_MS);
+  console.log(`  title after wait: "${await page.title()}"`);
+  console.log(`  url   after wait: ${page.url()}`);
+
+  console.log('\n--- Selector probe results ---');
+  for (const sel of SELECTORS_TO_PROBE) {
+    const count = await page.locator(sel).count();
+    const marker = count > 0 ? '✓' : '✗';
+    console.log(`  ${marker}  [${count}]  ${sel}`);
+    if (count > 0 && sel.includes('qrcode')) {
+      // Print src attribute if it's an img
+      try {
+        const src = await page.locator(sel).first().getAttribute('src');
+        const preview = src ? src.slice(0, 60) + '...' : '(null)';
+        console.log(`        src: ${preview}`);
+      } catch {/* not an img */}
+    }
+  }
+
+  // Dump all img srcs that look like QR codes (data URIs)
+  console.log('\n--- All <img> with data: src on page ---');
+  const imgs = await page.locator('img[src^="data:"]').all();
+  for (const img of imgs) {
+    const cls = await img.getAttribute('class').catch(() => '');
+    const src = await img.getAttribute('src').catch(() => '');
+    console.log(`  class="${cls}" src="${src?.slice(0, 80)}..."`);
+  }
+
+  // Save screenshot
+  const screenshotPath = '/tmp/xhs-debug.png';
+  await page.screenshot({ path: screenshotPath, fullPage: false });
+  console.log(`\nScreenshot saved → ${screenshotPath}`);
+
+  // Also dump page HTML around any element matching qrcode
+  console.log('\n--- Outer HTML of .qrcode (if found) ---');
+  const qrDiv = page.locator('.qrcode').first();
+  if (await qrDiv.count() > 0) {
+    const html = await qrDiv.evaluate((el: Element) => el.outerHTML.slice(0, 500));
+    console.log(html);
+  } else {
+    console.log('  .qrcode not found');
+  }
+
+  await browser.close();
+  console.log('\nDone.');
+}
+
+main().catch((err) => {
+  console.error('Fatal:', err);
+  process.exit(1);
+});