Node.js处理Twitter API返回JSON：如何将media_keys替换为预览URL

需求背景 #

我正在使用Node.js开发对接Twitter API的应用，Twitter API返回的JSON结构示例如下：

result = {
"data": [
    {
        "id": "1410481286947483648",
        "created_at": "2021-07-01T06:11:58.000Z",
        "text": "RT @weatherdak: Absolutely mind-blowing wildfire behavior in British Columbia.\n\nIncredible & massive storm-producing pyrocumulonimbus plume…"
    },
    {
        "attachments": {
            "media_keys": [
                "7_1408149248726667266"
            ]
        },
        "id": "1408168068237434883",
        "created_at": "2021-06-24T21:00:04.000Z",
        "text": "RT @Brophyst: Tornado in Brno, Czech Republic :O "
    },

    {
        "attachments": {
            "media_keys": [
                "16_1406870837026770949"
            ]
        },
        "id": "1406870843972632579",
        "created_at": "2021-06-21T07:05:22.000Z",
        "text": "Working on a new storm chasing application with incoming thunder rumbling. "
    },
    {
        "id": "1405081317985947648",
        "created_at": "2021-06-16T08:34:26.000Z",
        "text": "@thefunkygirl @TornadoGreg @cgphotography Slender tornadoes are (almost) the best!"
    }
],
"includes": {
    "media": [
        {
            "media_key": "7_1408149248726667266",
            "preview_image_url": "https://pbs.twimg.com/ext_tw_video_thumb/1408149248726667266/pu/img/qNKbx0MtaSGG0Sv0.jpg",
            "type": "video"
        },
        {
            "media_key": "16_1406870837026770949",
            "preview_image_url": "https://pbs.twimg.com/tweet_video_thumb/E4Y1koXWUAU1Ls5.jpg",
            "type": "animated_gif"
        }
    ]
},
"meta": {
    "oldest_id": "1405081317985947648",
    "newest_id": "1410481286947483648",
    "result_count": 10,
    "next_token": "7140dibdnow9c7btw3z0ry2hiovfdas2sur0h2hu1m6ns"
}
}

转换要求 #

移除原JSON中的attachments/media_keys子段以及独立的includes子段，将attachments/media_keys替换为匹配到的preview_image_url和type字段。
转换前单条推文示例：

{
    "attachments": {
        "media_keys": [
            "16_1406870837026770949"
        ]
    },
    "id": "1406870843972632579",
    "created_at": "2021-06-21T07:05:22.000Z",
    "text": "Working on a new storm chasing application with incoming thunder rumbling."
}

转换后单条推文示例：

{
    "preview_image_url": "https://pbs.twimg.com/tweet_video_thumb/E4Y1koXWUAU1Ls5.jpg",
    "type": "animated_gif",
    "id": "1406870843972632579",
    "created_at": "2021-06-21T07:05:22.000Z",
    "text": "Working on a new storm chasing application with incoming thunder rumbling."
}

实现方案 #

处理思路 #

1. 先将includes.media数组转换为以media_key为键的映射表，避免每次查找媒体信息都遍历数组，提升处理效率
2. 遍历data数组中的每一条推文数据，对每条数据做如下处理：
   • 保留原有的id、created_at、text等核心字段
   • 如果当前推文存在attachments.media_keys，就取第一个key到映射表中匹配对应的preview_image_url和type，直接合并到当前推文对象中
   • 丢弃原有的attachments字段，最终返回处理后的推文数组即可

完整代码实现 #

function transformTwitterResult(rawResult) {
  // 构建media_key到媒体信息的映射
  const mediaMap = {}
  if (rawResult.includes?.media) {
    rawResult.includes.media.forEach(mediaItem => {
      mediaMap[mediaItem.media_key] = {
        preview_image_url: mediaItem.preview_image_url,
        type: mediaItem.type
      }
    })
  }

  // 处理每条推文数据
  const transformedData = rawResult.data.map(tweet => {
    // 复制所有原有字段
    const processedTweet = { ...tweet }
    // 删除冗余的attachments字段
    delete processedTweet.attachments

    // 匹配并合并媒体信息
    if (tweet.attachments?.media_keys?.length) {
      const firstMediaKey = tweet.attachments.media_keys[0]
      const matchedMedia = mediaMap[firstMediaKey]
      if (matchedMedia) {
        Object.assign(processedTweet, matchedMedia)
      }
    }
    return processedTweet
  })

  // 可按需保留meta字段，不需要的话直接返回transformedData即可
  return {
    data: transformedData,
    meta: rawResult.meta
  }
}

// 调用方法
const rawResult = /* 替换为Twitter API返回的原始结果 */
const processedResult = transformTwitterResult(rawResult)
// 打印格式化后的结果
console.log(JSON.stringify(processedResult, null, 2))

效果说明 #

上述代码处理后，带媒体附件的推文会直接新增preview_image_url和type字段，无附件的推文保留原有核心字段，完全匹配要求的转换效果。

内容的提问来源于stack exchange，提问作者Christoffer