FreightWaves 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.freightwaves.com/news");
await page.content();

const data = await page.evaluate(`(() => {
  const articles = [];
  document.querySelectorAll(".post-card, article.entry").forEach(el => {
    const title = el.querySelector("h2 a, .entry-title a")?.textContent?.trim();
    const author = el.querySelector(".author-name, .entry-author")?.textContent?.trim();
    const date = el.querySelector(".post-date, .entry-date")?.textContent?.trim();
    const summary = el.querySelector("p, .excerpt")?.textContent?.trim();
    const link = el.querySelector("h2 a, .entry-title a")?.href;
    if (title) articles.push({ title, author, date, summary, link });
  });
  return JSON.stringify({ total: articles.length, articles: articles.slice(0, 15) });
})()`);

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

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

import requests

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

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