使用 Bun 提取社交分享图片和 Open Graph 标签

在 GitHub 上编辑

Bun 的 HTMLRewriter API 可用于高效地从 HTML 内容中提取社交分享图片和 Open Graph 元数据。这对于构建链接预览功能、社交媒体卡片或网络爬虫尤其有用。我们可以使用 HTMLRewriter 来匹配 CSS 选择器到我们想要处理的 HTML 元素、文本和属性。

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()
    // Extract Open Graph meta tags
    .on('meta[property^="og:"]', {
      element(el) {
        const property = el.getAttribute("property");
        const content = el.getAttribute("content");
        if (property && content) {
          // Convert "og:image" to "image" etc.
          const key = property.replace("og:", "") as keyof SocialMetadata;
          metadata[key] = content;
        }
      },
    })
    // Extract Twitter Card meta tags as fallback
    .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;
          // Only use Twitter Card data if we don't have OG data
          if (!metadata[key]) {
            metadata[key] = content;
          }
        }
      },
    })
    // Fallback to regular meta tags
    .on('meta[name="description"]', {
      element(el) {
        const content = el.getAttribute("content");
        if (content && !metadata.description) {
          metadata.description = content;
        }
      },
    })
    // Fallback to title tag
    .on("title", {
      text(text) {
        if (!metadata.title) {
          metadata.title = text.text;
        }
      },
    });

  // Process the response
  await rewriter.transform(response).blob();

  // Convert relative image URLs to absolute
  if (metadata.image && !metadata.image.startsWith("http")) {
    try {
      metadata.image = new URL(metadata.image, url).href;
    } catch {
      // Keep the original URL if parsing fails
    }
  }

  return metadata;
}

// Example usage
const metadata = await extractSocialMetadata("https://bun.net.cn");
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.net.cn/share.jpg",
//   type: "website",
//   ...
// }