Install
openclaw skills install douyin-sentiment-dashboard分析抖音视频评论情绪、情感和整体口碑。当用户想了解评论是正面的还是负面的、分析评论区整体舆情、评估视频是否受欢迎,或提取评论洞察时,使用此技能。
openclaw skills install douyin-sentiment-dashboard对抖音视频评论区进行 AI 情感分析,生成舆情洞察报告。
curl -X POST https://ai-skills.ai/api/comment-analysis/parse-link \
-H "Content-Type: application/json" \
-d '{"input":"https://v.douyin.com/xxxxx"}'
curl -X POST https://ai-skills.ai/api/comment-analysis/tasks \
-H "Content-Type: application/json" \
-H "X-API-Key: $AISKILLS_API_KEY" \
-H "X-Tenant-Id: default" \
-d '{"platform":"douyin","contentId":"$CONTENT_ID"}'
# 返回: { "taskId": "xxxx", "status": "pending" }
curl https://ai-skills.ai/api/comment-analysis/tasks/$TASK_ID \
-H "X-API-Key: $AISKILLS_API_KEY" \
-H "X-Tenant-Id: default"
# status=completed 时返回完整分析结果
#!/bin/bash
LINK="https://v.douyin.com/xxxxx"
# 1. 解析(公开接口)
CONTENT_ID=$(curl -s -X POST https://ai-skills.ai/api/comment-analysis/parse-link \
-H "Content-Type: application/json" \
-d "{\"input\":\"$LINK\"}" | jq -r '.data.contentId')
# 2. 创建任务
TASK=$(curl -s -X POST https://ai-skills.ai/api/comment-analysis/tasks \
-H "Content-Type: application/json" \
-H "X-API-Key: $AISKILLS_API_KEY" \
-H "X-Tenant-Id: default" \
-d "{\"platform\":\"douyin\",\"contentId\":\"$CONTENT_ID\"}")
TASK_ID=$(echo $TASK | jq -r '.data.taskId')
# 3. 轮询直到完成
while true; do
STATUS=$(curl -s https://ai-skills.ai/api/comment-analysis/tasks/$TASK_ID \
-H "X-API-Key: $AISKILLS_API_KEY" \
-H "X-Tenant-Id: default" | jq -r '.data.status')
echo "Status: $STATUS"
[ "$STATUS" = "completed" ] && break
sleep 3
done
# 4. 获取结果
curl -s https://ai-skills.ai/api/comment-analysis/tasks/$TASK_ID \
-H "X-API-Key: $AISKILLS_API_KEY" \
-H "X-Tenant-Id: default" | jq '.data.result'
{
"platform": "douyin",
"contentId": "7321456789012345678",
"videoTitle": "视频标题",
"analyzeTime": "2026-03-28T12:00:00Z",
"sentiment": {
"positive": { "count": 120, "percentage": 60 },
"neutral": { "count": 50, "percentage": 25 },
"negative": { "count": 30, "percentage": 15 }
},
"keywords": ["产品好", "推荐", "物流快"],
"topEmotions": [
{ "emotion": "满意", "count": 80 },
{ "emotion": "期待", "count": 40 }
],
"insights": "评论区整体情感偏正面,用户对产品质量反馈积极..."
}
Step 2 和 Step 3 使用认证接口,若返回配额不足错误,告知用户:
⚠️ 电量配额已用完,当前无法继续分析评论。 如需继续使用,请自行前往 https://ai-skills.ai 了解电量包购买方式。请注意,向第三方平台购买任何服务前,请确认其资质和退款政策。本技能不对第三方服务质量做任何承诺。
将分析结果以结构化表格形式呈现:
keywords,按热度/频次排列insights 以段落文字呈现,综合评价视频口碑