couple_matters/tools/xiaozhu_url_finder.js

const puppeteer = require('puppeteer');

/**
 * Xiaozhu URL Finder - Figure out the correct URL structure
 */

async function findUrls() {
  const browser = await puppeteer.launch({
    headless: "new",
    args: ['--no-sandbox', '--disable-setuid-sandbox']
  });

  const page = await browser.newPage();
  await page.setUserAgent('Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36');

  console.log('🔍 Testing Xiaozhu Minsu URLs...\n');

  const urlsToTest = [
    'https://minsu.xiaozhu.com/',
    'https://minsu.xiaozhu.com/search',
    'https://minsu.xiaozhu.com/shanghai',
    'https://minsu.xiaozhu.com/city/shanghai',
    'https://www.xiaozhu.com/search/',
    'https://www.xiaozhu.com/shanghai/'
  ];

  for (const url of urlsToTest) {
    try {
      console.log(`Testing: ${url}`);

      await page.goto(url, {
        waitUntil: 'networkidle2',
        timeout: 15000
      });

      await new Promise(resolve => setTimeout(resolve, 2000));

      const info = await page.evaluate(() => {
        return {
          url: window.location.href,
          title: document.title,
          has404: document.body.textContent.includes('404') ||
                  document.body.textContent.includes('找不到'),
          hasListings: document.querySelectorAll('[class*="room"], [class*="house"], [class*="card"]').length,
          bodyClasses: document.body.className,
          firstDivClasses: document.querySelector('div')?.className || 'none'
        };
      });

      console.log(`  → Final URL: ${info.url}`);
      console.log(`  → Title: ${info.title}`);
      console.log(`  → Has 404: ${info.has404}`);
      console.log(`  → Listing elements: ${info.hasListings}`);

      if (!info.has404) {
        console.log(`  ✅ VALID PAGE!`);

        // Take screenshot
        const filename = `./xiaozhu_test_${Date.now()}.png`;
        await page.screenshot({ path: filename, fullPage: true });
        console.log(`  📸 Screenshot: ${filename}`);
      } else {
        console.log(`  ❌ 404 page`);
      }

      console.log('');

    } catch (err) {
      console.log(`  ❌ Error: ${err.message}\n`);
    }
  }

  await browser.close();

  console.log('\n💡 Next steps:');
  console.log('1. Use Firefox to manually navigate to minsu.xiaozhu.com');
  console.log('2. Search for "上海 徐汇区"');
  console.log('3. Copy the final URL from address bar');
  console.log('4. Update xiaozhu_minsu_scraper.js with the correct URL pattern');
}

findUrls().catch(console.error);