提取社交分享圖片和 Open Graph 標簽

Bun 的 HTMLRewriter API 可用於高效地從 HTML 內容提取社交分享圖片和 Open Graph 元數據。這對於構建鏈接預覽功能、社交媒體卡片或網絡抓取器特別有用。我們可以使用 HTMLRewriter 將 CSS 選擇器匹配到我們要處理的 HTML 元素、文本和屬性。

interface SocialMetadata {
  title?: string;
  description?: string;
  image?: string;
  url?: string;
  siteName?: string;
  type?: string;
}

async function extractSocialMetadata(url: string): Promise<SocialMetadata> {
  const metadata: SocialMetadata = {};
  const response = await fetch(url);

  const rewriter = new HTMLRewriter()
    // 提取 Open Graph meta 標簽
    .on('meta[property^="og:"]', {
      element(el) {
        const property = el.getAttribute("property");
        const content = el.getAttribute("content");
        if (property && content) {
          // 將 "og:image" 轉換為 "image" 等
          const key = property.replace("og:", "") as keyof SocialMetadata;
          metadata[key] = content;
        }
      },
    })
    // 提取 Twitter Card meta 標簽作為後備
    .on('meta[name^="twitter:"]', {
      element(el) {
        const name = el.getAttribute("name");
        const content = el.getAttribute("content");
        if (name && content) {
          const key = name.replace("twitter:", "") as keyof SocialMetadata;
          // 僅當我們沒有 OG 數據時才使用 Twitter Card 數據
          if (!metadata[key]) {
            metadata[key] = content;
          }
        }
      },
    })
    // 回退到常規 meta 標簽
    .on('meta[name="description"]', {
      element(el) {
        const content = el.getAttribute("content");
        if (content && !metadata.description) {
          metadata.description = content;
        }
      },
    })
    // 回退到 title 標簽
    .on("title", {
      text(text) {
        if (!metadata.title) {
          metadata.title = text.text;
        }
      },
    });

  // 處理響應
  await rewriter.transform(response).blob();

  // 將相對圖片 URL 轉換為絕對 URL
  if (metadata.image && !metadata.image.startsWith("http")) {
    try {
      metadata.image = new URL(metadata.image, url).href;
    } catch {
      // 如果解析失敗，保留原始 URL
    }
  }

  return metadata;
}

// 示例用法
const metadata = await extractSocialMetadata("https://bun.com");
console.log(metadata);
// {
//   title: "Bun — A fast all-in-one JavaScript runtime",
//   description: "Bundle, transpile, install and run JavaScript & TypeScript projects — all in Bun. Bun is a fast all-in-one JavaScript runtime & toolkit designed for speed, complete with a bundler, test runner, and Node.js-compatible package manager.",
//   image: "https://bun.com/share.jpg",
//   type: "website",
//   ...
// }