Yandex 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://yandex.com/search/?text=web+scraping+tools");

// 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://yandex.com/search/?text=web+scraping+tools");
await page.content();

const data = await page.evaluate(`(() => {
  const results = [];
  document.querySelectorAll("[data-cid]").forEach((el, i) => {
    const titleLink = el.querySelector("a[href]:has(h2)") || el.querySelector("h2 a");
    const title = titleLink?.textContent?.trim();
    const url = titleLink?.getAttribute("href");
    const snippet = (el.querySelector("div[data-snf]") ||
      el.querySelector("div > span:not(:has(a))"))?.textContent?.trim();
    if (title) results.push({ position: i + 1, title, url, snippet });
  });
  return JSON.stringify({ total: results.length, results: results.slice(0, 10) });
})()`);

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