import FirecrawlApp from "@mendable/firecrawl-js";

const firecrawl = new FirecrawlApp({
  apiKey: process.env.FIRECRAWL_API_KEY!,
});

// Scrape a single page to clean markdown
const result = await firecrawl.scrapeUrl("https://docs.example.com/api", {
  formats: ["markdown"],
  onlyMainContent: true,  // strips nav, footer, sidebars
  waitFor: 2000,           // wait 2s for JS to render
});

if (result.success) {
  console.log("Title:", result.metadata?.title);
  console.log("Source:", result.metadata?.sourceURL);
  console.log("Markdown:", result.markdown?.substring(0, 200));
}

// Crawl a site — Firecrawl follows links, renders JS, returns all pages
const crawlResult = await firecrawl.crawlUrl("https://docs.example.com", {
  limit: 50,                   // max pages to crawl
  maxDepth: 3,                 // link depth from start URL
  includePaths: ["/docs/*", "/api/*"],   // only these paths
  excludePaths: ["/blog/*", "/changelog/*"],
  allowBackwardLinks: false,   // only crawl child paths
  scrapeOptions: {
    formats: ["markdown"],
    onlyMainContent: true,
  },
});

console.log(`Crawled ${crawlResult.data?.length} pages`);
for (const page of crawlResult.data || []) {
  console.log(`  ${page.metadata?.sourceURL}: ${page.markdown?.length} chars`);
}

// Start an async crawl job — returns immediately with job ID
const job = await firecrawl.asyncCrawlUrl("https://docs.example.com", {
  limit: 500,
  scrapeOptions: { formats: ["markdown"] },
});

console.log(`Crawl started: ${job.id}`);

// Poll for completion with backoff
let pollInterval = 2000;
let status = await firecrawl.checkCrawlStatus(job.id);

while (status.status === "scraping") {
  console.log(`Progress: ${status.completed}/${status.total} pages`);
  await new Promise(r => setTimeout(r, pollInterval));
  pollInterval = Math.min(pollInterval * 1.5, 30000);
  status = await firecrawl.checkCrawlStatus(job.id);
}

if (status.status === "completed") {
  console.log(`Done: ${status.data?.length} pages scraped`);
} else {
  console.error("Crawl failed:", status.error);
}

import { writeFileSync, mkdirSync } from "fs";

function processResults(pages: any[], outputDir: string) {
  mkdirSync(outputDir, { recursive: true });

  const manifest = pages.map((page, i) => {
    const url = page.metadata?.sourceURL || `page-${i}`;
    const slug = new URL(url).pathname
      .replace(/\//g, "_")
      .replace(/^_|_$/g, "") || "index";
    const filename = `${slug}.md`;

    // Clean markdown: collapse whitespace, remove JS links
    const content = (page.markdown || "")
      .replace(/\n{3,}/g, "\n\n")
      .replace(/\[.*?\]\(javascript:.*?\)/g, "")
      .trim();

    writeFileSync(`${outputDir}/${filename}`, content);

    return { url, filename, chars: content.length };
  });

  writeFileSync(`${outputDir}/manifest.json`, JSON.stringify(manifest, null, 2));
  return manifest;
}

const result = await firecrawl.scrapeUrl("https://example.com", {
  formats: ["markdown", "html", "links"],
  onlyMainContent: true,
});

console.log("Markdown:", result.markdown?.length);
console.log("HTML:", result.html?.length);
console.log("Links:", result.links?.length);

const job = await firecrawl.asyncCrawlUrl("https://docs.example.com", {
  limit: 100,
  scrapeOptions: { formats: ["markdown"] },
  webhook: {
    url: "https://api.yourapp.com/webhooks/firecrawl",
    events: ["completed", "page"],
  },
});
console.log(`Crawl ${job.id} started — webhook will fire on completion`);