|
| 1 | +--- |
| 2 | +title: "Crawl a URL using Firecrawl" |
| 3 | +sidebarTitle: "Firecrawl URL crawl" |
| 4 | +description: "This example demonstrates how to crawl a URL using Firecrawl with Trigger.dev." |
| 5 | +--- |
| 6 | + |
| 7 | +## Overview |
| 8 | + |
| 9 | +Firecrawl is a tool for crawling websites and extracting clean markdown that's structured in an LLM-ready format. |
| 10 | + |
| 11 | +Here are two examples of how to use Firecrawl with Trigger.dev: |
| 12 | + |
| 13 | +## Prerequisites |
| 14 | + |
| 15 | +- A project with [Trigger.dev initialized](/quick-start) |
| 16 | +- A [Firecrawl](https://firecrawl.dev/) account |
| 17 | + |
| 18 | +## Example 1: crawl an entire website with Firecrawl |
| 19 | + |
| 20 | +This task crawls a website and returns the `crawlResult` object. You can set the `limit` parameter to control the number of URLs that are crawled. |
| 21 | + |
| 22 | +```ts trigger/firecrawl-url-crawl.ts |
| 23 | +import FirecrawlApp from "@mendable/firecrawl-js"; |
| 24 | +import { task } from "@trigger.dev/sdk/v3"; |
| 25 | + |
| 26 | +// Initialize the Firecrawl client with your API key |
| 27 | +const firecrawlClient = new FirecrawlApp({ |
| 28 | + apiKey: process.env.FIRECRAWL_API_KEY, // Get this from your Firecrawl dashboard |
| 29 | +}); |
| 30 | + |
| 31 | +export const firecrawlCrawl = task({ |
| 32 | + id: "firecrawl-crawl", |
| 33 | + run: async (payload: { url: string }) => { |
| 34 | + const { url } = payload; |
| 35 | + |
| 36 | + // Crawl: scrapes all the URLs of a web page and return content in LLM-ready format |
| 37 | + const crawlResult = await firecrawlClient.crawlUrl(url, { |
| 38 | + limit: 100, // Limit the number of URLs to crawl |
| 39 | + scrapeOptions: { |
| 40 | + formats: ["markdown", "html"], |
| 41 | + }, |
| 42 | + }); |
| 43 | + |
| 44 | + if (!crawlResult.success) { |
| 45 | + throw new Error(`Failed to crawl: ${crawlResult.error}`); |
| 46 | + } |
| 47 | + |
| 48 | + return { |
| 49 | + data: crawlResult, |
| 50 | + }; |
| 51 | + }, |
| 52 | +}); |
| 53 | +``` |
| 54 | + |
| 55 | +### Testing your task |
| 56 | + |
| 57 | +You can test your task by triggering it from the Trigger.dev dashboard. |
| 58 | + |
| 59 | +```json |
| 60 | +"url": "<url-to-crawl>" // Replace with the URL you want to crawl |
| 61 | +``` |
| 62 | + |
| 63 | +## Example 2: scrape a single URL with Firecrawl |
| 64 | + |
| 65 | +This task scrapes a single URL and returns the `scrapeResult` object. |
| 66 | + |
| 67 | +```ts trigger/firecrawl-url-scrape.ts |
| 68 | +import FirecrawlApp, { ScrapeResponse } from "@mendable/firecrawl-js"; |
| 69 | +import { task } from "@trigger.dev/sdk/v3"; |
| 70 | + |
| 71 | +// Initialize the Firecrawl client with your API key |
| 72 | +const firecrawlClient = new FirecrawlApp({ |
| 73 | + apiKey: process.env.FIRECRAWL_API_KEY, // Get this from your Firecrawl dashboard |
| 74 | +}); |
| 75 | + |
| 76 | +export const firecrawlScrape = task({ |
| 77 | + id: "firecrawl-scrape", |
| 78 | + run: async (payload: { url: string }) => { |
| 79 | + const { url } = payload; |
| 80 | + |
| 81 | + // Scrape: scrapes a URL and get its content in LLM-ready format (markdown, structured data via LLM Extract, screenshot, html) |
| 82 | + const scrapeResult = (await firecrawlClient.scrapeUrl(url, { |
| 83 | + formats: ["markdown", "html"], |
| 84 | + })) as ScrapeResponse; |
| 85 | + |
| 86 | + if (!scrapeResult.success) { |
| 87 | + throw new Error(`Failed to scrape: ${scrapeResult.error}`); |
| 88 | + } |
| 89 | + |
| 90 | + return { |
| 91 | + data: scrapeResult, |
| 92 | + }; |
| 93 | + }, |
| 94 | +}); |
| 95 | +``` |
| 96 | + |
| 97 | +### Testing your task |
| 98 | + |
| 99 | +You can test your task by triggering it from the Trigger.dev dashboard. |
| 100 | + |
| 101 | +```json |
| 102 | +"url": "<url-to-scrape>" // Replace with the URL you want to scrape |
| 103 | +``` |
0 commit comments