CarFax Scraper

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.carfax.com/Used-Toyota-Camry_w302");

// 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.carfax.com/Used-Toyota-Camry_w302");
await page.content();

const data = await page.evaluate(`(() => {
  const vehicles = [];
  document.querySelectorAll("article, a[href*='/vehicle/']").forEach(el => {
    const title = el.querySelector("h2, h3, [class*='title']")?.textContent?.trim();
    const price = [...el.querySelectorAll("span")].find(s => /$[d,]+/.test(s.textContent))?.textContent?.trim();
    const mileage = [...el.querySelectorAll("span")].find(s => /[d,]+ mi/i.test(s.textContent))?.textContent?.trim();
    const owners = [...el.querySelectorAll("span")].find(s => /d+.*owner/i.test(s.textContent))?.textContent?.trim();
    const accidents = [...el.querySelectorAll("span")].find(s => /d+.*accident|no accident/i.test(s.textContent))?.textContent?.trim();
    if (title) vehicles.push({ title, price, mileage, owners, accidents });
  });
  return JSON.stringify({ total: vehicles.length, vehicles: vehicles.slice(0, 10) });
})()`);

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

curl -X POST https://api.spider.cloud/fetch/carfax.com/ \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{}'

import requests

resp = requests.post(
    "https://api.spider.cloud/fetch/carfax.com/",
    headers={
        "Authorization": "Bearer YOUR_API_KEY",
        "Content-Type": "application/json",
    },
    json={},
)
print(resp.json())

const resp = await fetch("https://api.spider.cloud/fetch/carfax.com/", {
  method: "POST",
  headers: {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({}),
});
const data = await resp.json();
console.log(data);