Google Hotels Scraper

import { SpiderBrowser } from "spider-browser";

const spider = new SpiderBrowser({
  apiKey: process.env.SPIDER_API_KEY!,
});

await spider.connect();
const page = spider.page!;
await page.goto("https://www.google.com/travel/hotels/London?q=hotels+in+london&g2lb=2502548&hl=en&gl=us&cs=1&ssta=1&ts=CAESCgoCCAMKAggDEAAaRwopEicyJTB4NDg3NjA0ZGVhZjIyMWU5YjoweDEzZDRhMTM4MTc2NmQxMTQSGhIUCgcI6A8QBhgTEgcI6A8QBhgUGAEyAhAAKgsKBygBOgNHQlAaAA");

// No selectors, no schema. Spider reads the page and names the fields.
const data = await page.scrape();

console.log(data);
await spider.close();

import { SpiderBrowser } from "spider-browser";

const spider = new SpiderBrowser({
  apiKey: process.env.SPIDER_API_KEY!,
  stealth: 2,
});

await spider.connect();
const page = spider.page!;
await page.goto("https://www.google.com/travel/hotels/London?q=hotels+in+london&g2lb=2502548&hl=en&gl=us&cs=1&ssta=1&ts=CAESCgoCCAMKAggDEAAaRwopEicyJTB4NDg3NjA0ZGVhZjIyMWU5YjoweDEzZDRhMTM4MTc2NmQxMTQSGhIUCgcI6A8QBhgTEgcI6A8QBhgUGAEyAhAAKgsKBygBOgNHQlAaAA");
await page.content(15000);

const data = await page.evaluate(`(() => {
  const hotels = [];
  document.querySelectorAll("[data-ved]").forEach(el => {
    const name = el.querySelector("h2, h3, [role='heading']")?.textContent?.trim();
    const price = [...(el.querySelectorAll("span") || [])].find(s => /$[d,]+/.test(s.textContent || ""))?.textContent?.trim();
    const rating = el.querySelector("[aria-label*='star'], [aria-label*='rating']")?.getAttribute("aria-label") || el.querySelector("[aria-label*='star']")?.textContent?.trim();
    const reviews = [...(el.querySelectorAll("span") || [])].find(s => /[d,]+s*review/i.test(s.textContent || ""))?.textContent?.trim();
    if (name) hotels.push({ name, price, rating, reviews });
  });
  return JSON.stringify({ total: hotels.length, hotels: hotels.slice(0, 10) });
})()`);

console.log(JSON.parse(data));
await spider.close();