Skip to main content

​
提取社交分享图片和开放图谱标签

Bun 的 HTMLRewriter API 可以高效地从 HTML 内容中提取社交分享图片和开放图谱（Open Graph）元数据。这对于构建链接预览功能、社交媒体卡片或网页爬虫特别有用。我们可以使用 HTMLRewriter 来匹配 CSS 选择器，从而处理我们想要操作的 HTML 元素、文本和属性。
https://mintcdn.com/ikxin/RzFFGbzo0-4huILA/icons/typescript.svg?fit=max&auto=format&n=RzFFGbzo0-4huILA&q=85&s=a3dffd2241f05776d3bd25171d0c5a79extract-social-meta.ts
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()
    // 提取开放图谱（Open Graph）meta 标签
    .on('meta[property^="og:"]', {
      element(el) {
        const property = el.getAttribute("property");
        const content = el.getAttribute("content");
        if (property && content) {
          // 将 "og:image" 转换为 "image" 等等
          const key = property.replace("og:", "") as keyof SocialMetadata;
          metadata[key] = content;
        }
      },
    })
    // 作为备用，提取 Twitter Card meta 标签
    .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;
          // 仅当没有 OG 数据时使用 Twitter Card 数据
          if (!metadata[key]) {
            metadata[key] = content;
          }
        }
      },
    })
    // 备用，提取普通 meta 标签
    .on('meta[name="description"]', {
      element(el) {
        const content = el.getAttribute("content");
        if (content && !metadata.description) {
          metadata.description = content;
        }
      },
    })
    // 备用，提取标题标签
    .on("title", {
      text(text) {
        if (!metadata.title) {
          metadata.title = text.text;
        }
      },
    });

  // 处理响应内容
  await rewriter.transform(response).blob();

  // 将相对图片 URL 转换为绝对 URL
  if (metadata.image && !metadata.image.startsWith("http")) {
    try {
      metadata.image = new URL(metadata.image, url).href;
    } catch {
      // 如果解析失败，则保留原始 URL
    }
  }

  return metadata;
}
https://mintcdn.com/ikxin/RzFFGbzo0-4huILA/icons/typescript.svg?fit=max&auto=format&n=RzFFGbzo0-4huILA&q=85&s=a3dffd2241f05776d3bd25171d0c5a79Example Usage
// 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",
//   ...
// }