运行时包管理器打包器测试运行器代码检查格式化指南参考博客反馈

提取社交分享图片和开放图谱标签

提取社交分享图片和开放图谱标签

Bun 的 HTMLRewriter API 通过将 CSS 选择器与要处理的元素、文本和属性进行匹配,从 HTML 中提取社交分享图片和 Open Graph 元数据。你可以使用它来构建链接预览、社交媒体卡片或网页抓取工具。

extract-social-meta.ts
interface SocialMetadata {
  title?: string;
  description?: string;
  image?: string;
  url?: string;
  site_name?: 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;
          // Only use Twitter Card data if nothing has set this key yet (OG tags always overwrite it)
          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;
}
示例用法
// 示例用法
const metadata = await extractSocialMetadata("https://bun.sh");
console.log(metadata);
// {
//   title: "Bun — A fast all-in-one JavaScript runtime",
//   description: "Bundle, install, and run JavaScript &amp; TypeScript — all in Bun. Bun is a fast JavaScript runtime &amp; toolkit with a bundler, test runner, and npm-compatible package manager built in.",
//   image: "https://bun.sh/share_v4.png",
//   type: "website",
//   ...
// }