Crawl a URL using Firecrawl

import Firecrawl from "@mendable/firecrawl-js";
import { task } from "@trigger.dev/sdk";

// Initialize the Firecrawl client with your API key
const firecrawlClient = new Firecrawl({
  apiKey: process.env.FIRECRAWL_API_KEY, // Get this from your Firecrawl dashboard
});

export const firecrawlCrawl = task({
  id: "firecrawl-crawl",
  run: async (payload: { url: string }) => {
    const { url } = payload;

    // Crawl: scrapes all the URLs of a web page and return content in LLM-ready format
    const crawlResult = await firecrawlClient.crawl(url, {
      limit: 100, // Limit the number of URLs to crawl
      scrapeOptions: {
        formats: ["markdown", "html"],
      },
    });

    if (crawlResult.status === "failed") {
      throw new Error(`Failed to crawl: ${url}`);
    }

    return {
      data: crawlResult,
    };
  },
});

import Firecrawl from "@mendable/firecrawl-js";
import { task } from "@trigger.dev/sdk";

// Initialize the Firecrawl client with your API key
const firecrawlClient = new Firecrawl({
  apiKey: process.env.FIRECRAWL_API_KEY, // Get this from your Firecrawl dashboard
});

export const firecrawlScrape = task({
  id: "firecrawl-scrape",
  run: async (payload: { url: string }) => {
    const { url } = payload;

    // Scrape: scrapes a URL and get its content in LLM-ready format (markdown, structured data via LLM Extract, screenshot, html)
    const scrapeResult = await firecrawlClient.scrape(url, {
      formats: ["markdown", "html"],
    });

    return {
      data: scrapeResult,
    };
  },
});