← Back to Skills Marketplace
抖音搜索爬虫
by
terrycarter1985
· GitHub ↗
· v1.2.0
· MIT-0
39
Downloads
0
Stars
0
Active Installs
2
Versions
Install in OpenClaw
/install douyin-scraper-cn
Description
搜索抖音视频和获取热榜数据。当用户用中文说"搜索一下XX视频"、"找一些XX相关视频"、"抖音上搜XX"、"看看XX的视频"、"抖音热榜"等自然语言请求时，自动提取关键词并执行搜索。
README (SKILL.md)
抖音搜索爬虫
自然语言路由（Agent 必读）
当用户发出以下类型的请求时，自动提取关键词并调用本 skill：
| 用户说 | 提取关键词 | 执行命令 |
|---|---|---|
| 搜索一下海鲜视频 | 海鲜 | python3 scripts/scraper.py search --keyword "海鲜" --limit 10 |
| 找一些海鲜售卖相关的视频文案 | 海鲜售卖 | python3 scripts/scraper.py search --keyword "海鲜售卖" --limit 10 |
| 抖音上搜一下小龙虾 | 小龙虾 | python3 scripts/scraper.py search --keyword "小龙虾" --limit 10 |
| 看看抖音热榜 | （无） | python3 scripts/scraper.py hot --limit 20 |
| 美食热榜有什么 | 美食 | python3 scripts/scraper.py hot --category "美食" --limit 20 |
关键词提取规则
- 去掉"搜索一下"、"找一些"、"看看"、"视频"、"相关"、"的"等功能词
- 保留核心搜索意图，如"海鲜售卖"、"小龙虾做法"
- 如果用户指定了数量，用
--limit传入；否则默认 10 - 如果用户要保存结果，加
--output \x3C文件名> --format json
执行方式
所有命令在 skill 目录 下执行：
cd /root/.openclaw/workspace/skills/douyin-scraper
python3 scripts/scraper.py search --keyword "\x3C关键词>" --limit \x3C数量>
搜索结果为占位数据时的回退方案
如果搜索返回 [占位] 标记（抖音搜索需要登录），agent 应：
- 告知用户搜索需要登录态
- 改用
hot命令获取热榜作为替代 - 或使用
browser工具打开抖音搜索页面，让用户手动操作
命令参考
搜索视频（需要登录态，否则返回占位数据）
python3 scripts/scraper.py search --keyword "海鲜" --limit 10
获取热榜（✅ 无需登录，返回真实数据）
python3 scripts/scraper.py hot --limit 20
python3 scripts/scraper.py hot --category "美食" --limit 20
保存结果
python3 scripts/scraper.py search --keyword "海鲜" --limit 10 --output result.json
python3 scripts/scraper.py hot --limit 20 --output hot.csv --format csv
工作原理
- 热榜：直接调用抖音公开 API，无需登录，返回真实热搜词和热度值 ✅
- 搜索：尝试 Playwright 浏览器自动化提取 SSR 数据；抖音搜索需要登录，未登录时返回占位数据并标注
[占位]⚠️
输出格式
每条结果包含：标题、描述、作者、播放/点赞/评论/分享数、链接、标签
注意事项
- 抖音搜索 API 需要登录态，未登录时搜索返回占位数据
- 热榜 API 无需登录，始终返回真实数据
- 建议请求间隔 ≥ 2 秒
- 数据仅供学习研究
Usage Guidance
Install only if you are comfortable with Playwright/Chromium setup and network requests to Douyin. Prefer the Python script, watch for the is_mock or [占位] indicators, and do not rely on the Node.js output or any fallback hot-list data as real analytics unless the publisher fixes the synthetic-result behavior.
Capability Assessment
Purpose & Capability
The Python path matches the stated Douyin search and hot-list purpose and labels mock search fallbacks, but the Node.js path generates synthetic search and hot-list records without marking them as placeholders.
Instruction Scope
The skill tells agents to auto-route broad Chinese video or hot-list requests into networked scraper commands; this is purpose-aligned but should require clear Douyin/search intent.
Install Mechanism
Installation creates a virtual environment, installs Playwright and Chromium, may run npm install, and includes an optional Docker helper that pulls/builds a Playwright image; these setup effects are mostly disclosed.
Credentials
Network access to Douyin and browser automation are proportionate for a scraper, and output file writes occur only when an output path is requested.
Persistence & Privilege
No hidden background service, credential harvesting, privilege escalation, or durable persistence was found beyond normal dependency installation and generated helper files.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install douyin-scraper-cn - After installation, invoke the skill by name or use
/douyin-scraper-cn - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.2.0
支持自然语言搜索路由; 热榜API返回真实数据; 搜索结果标注占位状态; 修复Playwright错误处理
v1.1.0
支持自然语言搜索请求，Playwright 不可用时自动降级为模拟数据
Metadata
Frequently Asked Questions
What is 抖音搜索爬虫?
搜索抖音视频和获取热榜数据。当用户用中文说"搜索一下XX视频"、"找一些XX相关视频"、"抖音上搜XX"、"看看XX的视频"、"抖音热榜"等自然语言请求时，自动提取关键词并执行搜索。 It is an AI Agent Skill for Claude Code / OpenClaw, with 39 downloads so far.
How do I install 抖音搜索爬虫?
Run "/install douyin-scraper-cn" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is 抖音搜索爬虫 free?
Yes, 抖音搜索爬虫 is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does 抖音搜索爬虫 support?
抖音搜索爬虫 is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created 抖音搜索爬虫?
It is built and maintained by terrycarter1985 (@terrycarter1985); the current version is v1.2.0.
More Skills