AI
Tool: Content Moderation & Toxicity Scorer
Score any text for toxicity, hate speech, harassment, sexual, violent, self-harm and spam content with premium AI. Get a safe flag and per-category scores. Paid Apify plans only.
content-moderation-tool.json 200 OK
{ "text": "Thanks so much for your help today, this reall…", "truncated": false, "safe": true, "overallToxicity": 0.01, "categories": {"toxicity":0.01,"hateSpeech":0,"harassment"…, "flagged": [], "reason": "A friendly, appreciative message with no unsaf…", "observedAt": "2026-07-25T00:15:43.180Z" }
你会得到什么
每次运行都返回干净、带类型的记录，可直接用于你的 CRM、表格或数据库。
- 每个结果对应一条干净记录，已去重并规范化
- JSON、CSV 或 Excel 的稳定结构，也可通过 Apify API 读取
- 在云端按用量付费，无需安装或维护
返回的字段
TextTruncatedSafeOverall ToxicityCategoriesFlaggedReason
示例输出
一条真实的示例记录，正是你收到的结构。
| Text | Truncated | Safe | Overall Toxicity |
|---|---|---|---|
| Thanks so much for your help toda… | false | true | 0.01 |
| You people are complete idiots an… | false | false | 0.82 |
| Meeting moved to 3pm, see you in … | false | true | 0 |
GET /content-moderation-tool
{ "text": "Thanks so much for your help today, this reall…", "truncated": false, "safe": true, "overallToxicity": 0.01, "categories": {"toxicity":0.01,"hateSpeech":0,"harassment"…, "flagged": [], "reason": "A friendly, appreciative message with no unsaf…", "observedAt": "2026-07-25T00:15:43.180Z" }
相关爬虫