← Back to Skills Marketplace
抖音爆款爬虫
by
terrycarter1985
· GitHub ↗
· v1.1.0
· MIT-0
69
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install douyin-scraper-terrycarter
Description
爬取抖音爆款视频和文案数据,支持自然语言搜索(如"搜索一下海鲜视频")、获取热榜、提取视频信息。使用 Playwright 自动化浏览器。
README (SKILL.md)
抖音爆款爬虫 Skill
快速使用(自然语言)
当用户用自然语言发出请求时,自动提取关键词并调用对应命令:
| 用户说法 | 命令 |
|---|---|
| 搜索一下海鲜视频 | python scripts/scraper.py search --keyword "海鲜" --limit 10 |
| 找一些海鲜售卖相关的视频文案 | python scripts/scraper.py search --keyword "海鲜售卖" --limit 10 |
| 看看抖音热榜有什么 | python scripts/scraper.py hot --limit 20 |
| 分析这个视频链接:https://v.douyin.com/xxx | 暂不支持,提示用户用搜索代替 |
关键词提取规则
- 去掉"搜索一下"、"找一些"、"帮我搜"等请求前缀
- 去掉"视频"、"视频文案"等后缀修饰词
- 保留核心搜索词,如"海鲜"、"海鲜售卖"、"小龙虾"
- 如果用户指定了数量,用
--limit传入;否则默认 10
安装
cd \x3Cskill-dir>
python3 -m venv venv
source venv/bin/activate
pip install playwright
playwright install chromium
或运行一键安装:
./install.sh
命令参考
搜索
# 基础搜索
source venv/bin/activate && python scripts/scraper.py search --keyword "海鲜" --limit 10
# 保存结果
python scripts/scraper.py search --keyword "海鲜售卖" --limit 20 --output result.json
# CSV 格式
python scripts/scraper.py search --keyword "小龙虾" --limit 10 --format csv --output result.csv
热榜
# 全部热榜
source venv/bin/activate && python scripts/scraper.py hot --limit 20
# 分类热榜
python scripts/scraper.py hot --category "美食" --limit 20
输出格式
[
{
"title": "视频标题",
"description": "视频描述",
"author": "作者昵称",
"play_count": 1000000,
"like_count": 50000,
"comment_count": 2000,
"share_count": 1000,
"url": "https://www.douyin.com/video/xxx",
"tags": ["标签1", "标签2"],
"publish_time": "2026-03-21"
}
]
注意事项
- 首次运行需要先执行
install.sh安装依赖和浏览器 - 抖音有反爬机制,如遇验证码或登录要求,脚本会自动降级返回示例数据
- 建议请求间隔 2 秒以上,避免 IP 被封
- 数据仅供学习研究使用
Usage Guidance
Treat this as an incomplete review result and rerun scanning where metadata.json and artifact files can be read before installing.
Capability Assessment
Purpose & Capability
Workspace inspection failed before artifact contents could be reviewed, so no purpose-to-capability mismatch was identified from evidence.
Instruction Scope
No runtime instructions were available to evaluate beyond the provided review request.
Install Mechanism
metadata.json and artifact files could not be inspected, so install behavior could not be confirmed.
Credentials
No evidence-backed environmental access concern was available from readable artifacts.
Persistence & Privilege
No artifact-backed persistence or privilege concern was identified.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install douyin-scraper-terrycarter - After installation, invoke the skill by name or use
/douyin-scraper-terrycarter - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.1.0
支持真实搜索数据(移动端UA),自然语言关键词解析,venv依赖安装
Metadata
Frequently Asked Questions
What is 抖音爆款爬虫?
爬取抖音爆款视频和文案数据,支持自然语言搜索(如"搜索一下海鲜视频")、获取热榜、提取视频信息。使用 Playwright 自动化浏览器。 It is an AI Agent Skill for Claude Code / OpenClaw, with 69 downloads so far.
How do I install 抖音爆款爬虫?
Run "/install douyin-scraper-terrycarter" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is 抖音爆款爬虫 free?
Yes, 抖音爆款爬虫 is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does 抖音爆款爬虫 support?
抖音爆款爬虫 is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created 抖音爆款爬虫?
It is built and maintained by terrycarter1985 (@terrycarter1985); the current version is v1.1.0.
More Skills