Gemini Homepage 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.gemini.com");

// 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!,
});

await spider.connect();
const page = spider.page!;
await page.goto("https://www.gemini.com");

const data = await page.extractFields({
  images: "img, .image",
  links: "a[href^="/"], a[href^="/author/"]",
  main_content: "main > *",
  text: "p, h2, h3, h4, h5, h6, blockquote, ul, ol, li, div.quote",
});

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