参数
| 参数 | 必填 | 取值 |
|---|---|---|
| platform | 是 | tiktok / instagram / youtube / twitter / douyin / xiaohongshu |
| post_id | 是 | 内容 id,也支持视频链接里的数字 id |
| limit | 否 | 返回条数,按需分批;单次同步返回,不建议一次拉太大 |
原始条目 vs 结论,怎么选
要做情感分类、关键词抽取、话术库沉淀——用原始条目自己算,规则完全可控;只要判断「这个词下的观众在问什么」——用评论洞察,省一轮后处理和一次额外调用。
楼中楼
抖音的楼中楼评论是本站独家端点能力之一,返回里带层级信息;需要按 A-B 两层展开时直接在结果里取,不用二次拼接。
批量场景
一条内容一次调用。做几十条的批量分析时建议加 1–2 秒间隔,避免触发上游频控;失败会自动退款,不算一次成功计费。
复制即可运行
cURL
curl -s https://lucydomi.com/mcp/v1/get_comments \
-H "Authorization: Bearer $BUSYBEE_API_KEY" \
-H "Content-Type: application/json" \
-X POST \
-d '{"platform": "tiktok", "post_id": "7690199760430566669", "limit": 20}'Python(标准库)
import os, json, urllib.request
KEY = os.environ["BUSYBEE_API_KEY"]
req = urllib.request.Request(
"https://lucydomi.com/mcp/v1/get_comments",
data=json.dumps({"platform": "tiktok", "post_id": "7690199760430566669", "limit": 20}).encode(),
headers={"Authorization": f"Bearer {KEY}", "Content-Type": "application/json"},
method="POST",
)
data = json.load(urllib.request.urlopen(req, timeout=60))
for it in data["items"]:
print(it.get("url"), it.get("text", "")[:60])真实返回样例
下面这段是线上真实返回(已截断到 1 条,去掉了计费字段)。
{
"ok": true,
"platform": "tiktok",
"tool": "get_comments",
"count": 3,
"items": [
{
"platform": "tiktok",
"id": "7693873719371072278",
"post_id": "7690199760430566669",
"author": {
"id": "7662430993471472662",
"handle": "arturo_h19",
"name": "Arturo Hlebov"
},
"text": "What makes it Spanish?",
"likes": 31,
"replies": 11,
"created_at": "2026-10-07T10:40:33+00:00"
},
{
"platform": "tiktok",
"id": "7691731924267926280",
"post_id": "7690199760430566669",
"author": {
"id": "6729605861440177158",
"handle": "bubibat",
"name": "bubibat"
},
"text": "The honey? the salt? the cinnamon??? Disastrous.",
"likes": 136,
"replies": 6,
"created_at": "2026-10-01T16:08:21+00:00"
},
{
"platform": "tiktok",
"id": "7700520488221983495",
"post_id": "7690199760430566669",
"author": {
"id": "6963131498518758401",
"handle": "tempisunreachable",
"name": "ِ"
},
"text": "In Saudi, this drink is pretty famous although it has nothing to do with the Spanish lol",
"likes": 0,
"replies": 0,
"created_at": "2026-10-25T08:32:35+00:00"
}
]
}常见问题
评论拉不全怎么办?
公开接口能拿到的是平台对外展示的那部分;隐藏、折叠、被删的评论拿不到,任何渠道都一样。
能按点赞排序吗?
返回条目自带点赞数,排序请在你这一侧做,口径由你定(比如只看 top 10 高赞)。
和评论洞察的区别?
这个给原始条目,洞察给聚合结论(情绪分布、提问占比、高频词、高赞评论)。