Douyin prohibited-word checker
Check Douyin captions, scripts and product copy against a built-in list of common prohibited and sensitive wording: hits by category with positions, context and suggested rewrites, plus width/traditional normalisation, whitelist, custom words and masking — all in your browser.
Runs in your browserEvery computation happens in your browser — your data never leaves this device.
The list is a curated set of common prohibited/sensitive wording, not Douyin's official full list; platform rules change often, so results are for self-checking only and are not legal advice.
Uncheck a category to skip it — the list is organised by category.
Detection report
Matched locally against the built-in list with leftmost-longest overlap handling; for pre-publish self-checks only.
What this tool does
- Pre-publish self-check: paste a Douyin caption, spoken script, product title or description and get every hit at once — absolute wording, medical and efficacy claims, off-platform funnels and engagement bait, investment promises — each with a suggested rewrite.
- Filter by category: keep only the Advertising Law absolute wording, or only the off-platform contact and funnel phrases, by unchecking the others; the risk score and the per-category counts follow the filter.
- Maintain your own whitelist: brand names and hospital names that legitimately contain a listed word can be whitelisted, and those hits are reported separately as ignored instead of counting towards the risk level.
- Extend the list with your own words: add internal banned words line by line under Extra words (filed as Custom words), then use the masked preview to get a version you can publish.
Example
Input
这款全网最好的祛痘面霜，保证有效，需要的话加微信私聊。
Output
Risk level: high (5 hits, 0 ignored) By category: Absolute wording 2; Medical claims 1; Platform violations 2 Hits: 1. 最好 [Absolute wording] chars 5-6 -> suggest: 较好 / 理想 context: 这款全网最好的祛痘面霜，… 2. 祛痘 [Medical claims] chars 8-9 -> suggest: 清爽控油 context: …款全网最好的祛痘面霜，保证有… 3. 保证有效 [Absolute wording] chars 13-16 -> suggest: 有助于改善 context: …的祛痘面霜，保证有效，需要的话加… 4. 加微信 [Platform violations] chars 22-24 -> suggest: 在平台内沟通 context: …效，需要的话加微信私聊。 5. 私聊 [Platform violations] chars 25-26 -> suggest: 平台内互动 context: …要的话加微信私聊。 Masked preview: 这款全网**的**面霜，****，需要的话*****。
Positions are 1-based, inclusive character ranges; the masked preview replaces each hit with * by default.
Frequently asked questions
Is this Douyin's official word list?
No. The built-in list is a curated set of common prohibited and sensitive wording drawn from Article 9/17/25 of China's Advertising Law, the special-cosmetics and health-food rules, and Douyin's community and e-commerce creator guidelines — 185 entries (65 absolute wording, 37 medical claims, 45 platform violations, 26 finance, 12 superstition). It covers common phrasing only and is not an official full list. Platform rules change often, so treat the result as a pre-publish self-check, not legal advice.
Why is a harmless phrase like 第一时间 flagged?
The entry 第一 comes from the ranking wording banned by Article 9 of the Advertising Law, so it also matches ordinary compounds such as 第一时间. Add 第一时间 to the whitelist and it is reported as ignored instead of counted. Whitelisting works on whole phrases: a hit inside a whitelisted phrase is ignored too, so whitelisting 第一人民医院 clears 第一 inside that hospital name.
How does the matching work — will one word be reported many times?
It uses Aho–Corasick (a trie with failure links) so the text is scanned once regardless of dictionary size, then resolves overlaps leftmost-longest: 全网最低价 is reported once as 全网最低 instead of also reporting 最低价. Normalisation handles full-width to half-width (％ to %), traditional to simplified (333 built-in single-character pairs, 網 to 网) and case folding; all three are 1:1 substitutions, so positions map back to the original text exactly.
How is the risk level calculated?
Each hit carries a category weight: 2 points for absolute wording and platform violations, 3 points for medical claims and finance. A total of 0 is "none", 1–3 "low", 4–9 "medium" and 10 or more "high". Whitelisted hits score nothing, so the level moves with your whitelist and category filter.
Is my text uploaded, and how long can it be?
Nothing is uploaded — matching runs entirely in your browser, the page makes no network requests and the text is not logged. The limit is 20000 characters per run; longer copy should be checked in sections such as title and body.
Keywords：抖音违禁词抖音敏感词检测违禁词检测广告法绝对化用语医疗功效宣称douyin prohibited wordsbanned words checkeradvertising compliance