使用 HTMLRewriter 提取网页中的链接

async function extractLinks(url: string) {
  const links = new Set<string>();
  const response = await fetch(url);

  const rewriter = new HTMLRewriter().on("a[href]", {
    element(el) {
      const href = el.getAttribute("href");
      if (href) {
        links.add(href);
      }
    },
  });

  // 等待响应被处理完成
  await rewriter.transform(response).blob();
  console.log([...links]); // ["https://bun.com", "/docs", ...]
}

// 从 Bun 网站提取所有链接
await extractLinks("https://bun.com");

async function extractLinksFromURL(url: string) {
  const response = await fetch(url);
  const links = new Set<string>();

  const rewriter = new HTMLRewriter().on("a[href]", {
    element(el) {
      const href = el.getAttribute("href");
      if (href) {
        // 将相对 URL 转换为绝对 URL
        try { 
          const absoluteURL = new URL(href, url).href; 
          links.add(absoluteURL);
        } catch { 
          links.add(href); 
        } 
      }
    },
  });

  // 等待响应被处理完成
  await rewriter.transform(response).blob();
  return [...links];
}

const websiteLinks = await extractLinksFromURL("https://example.com");