← 返回 Skills 市场

douyin-keyword-search

Name: douyin-keyword-search
Author: urhd528

作者 urhd528 · GitHub ↗ · v1.0.0

cross-platform ⚠ suspicious

1032

总下载

当前安装

版本数

在 OpenClaw 中安装

/install douyin-keyword-search

功能描述

自动化抓取抖音搜索结果页面的文章数据，支持关键词搜索、格式输出和数量限制，需安装Playwright和Chromium浏览器。

使用说明 (SKILL.md)

抖音关键词搜索抓取技能

通过浏览器自动化抓取抖音搜索结果页面的文章数据。

文件说明

文件	说明
`douyin_keyword_search.py`	Python 主脚本
`douyin_keyword_search.sh`	Shell 包装脚本
`requirements.txt`	Python 依赖列表

安装依赖

pip install -r requirements.txt
python -m playwright install chromium

使用方法

命令行调用

# 基本使用
python douyin_keyword_search.py --keyword "关键词"

# 指定输出格式和数量
python douyin_keyword_search.py -k "科技新闻" -o json -l 30

# 保存到文件
python douyin_keyword_search.py -k "美食" -o csv -f results.csv

# 无头模式（后台运行）
python douyin_keyword_search.py -k "新闻" --headless

参数说明

参数	说明	默认值
`--keyword, -k`	搜索关键词（必填）	-
`--output, -o`	输出格式：json/csv/txt	json
`--limit, -l`	抓取数量限制	20
`--headless`	无头模式，不显示浏览器窗口	false
`--output-file, -f`	输出文件路径	控制台输出

Claude Code 技能调用

在 Claude Code 中配置后可使用：

/skill douyin-keyword-search --keyword "人工智能"

输出示例

[
  {
    "title": "视频标题",
    "author": "作者名称",
    "url": "https://www.douyin.com/video/xxx",
    "stats": ["10万点赞", "5000评论"],
    "keyword": "搜索关键词",
    "crawl_time": "2024-01-01T12:00:00"
  }
]

注意事项

首次使用需要安装 Playwright 和 Chromium 浏览器
抖音需要登录才能查看完整搜索结果，建议首次运行时不使用 --headless 参数
请遵守抖音的使用条款和 robots.txt 规则
建议控制抓取频率，避免对服务器造成压力

许可证

MIT License

安全使用建议

This skill appears to do what it says: automated scraping of Douyin search results using Playwright. Before installing/running, consider: (1) running the code in an isolated environment (virtualenv) because it may install Playwright and download Chromium; (2) the script may prompt you to log in in a non-headless browser and will save a debug screenshot in the script directory if selectors fail; (3) scraping may violate Douyin's terms of service—respect robots.txt and rate limits; (4) inspect the included Python file yourself if you have concerns (it does not exfiltrate data to remote servers). If you do not want the script to auto-install packages, decline the install prompt and run dependency installation manually in a controlled environment.

功能分析

Type: OpenClaw Skill Name: douyin-keyword-search Version: 1.0.0 The skill is classified as suspicious due to a significant arbitrary file write vulnerability in `douyin_keyword_search.py`. The `--output-file` argument allows a user to specify any file path, potentially overwriting critical system files with scraped data, which can lead to denial of service or system instability. Additionally, the script uses `os.system()` for dependency installation, which, while not directly exploitable in this specific context due to hardcoded commands and user prompts, is a less secure practice than using the `subprocess` module.

能力评估

✓ Purpose & Capability

Name/description claim browser-automated Douyin keyword scraping; included files (Python script, shell wrapper, requirements) and SKILL.md all implement and document Playwright + Chromium usage. No unrelated services, credentials, or binaries are requested.

✓ Instruction Scope

SKILL.md instructs installing Playwright and Chromium and how to run the script. The runtime code only visits Douyin pages, extracts page elements, optionally saves a screenshot to the script directory for debugging, and prints/writes results. It does not read unrelated system files or send collected data to external endpoints beyond the target site.

✓ Install Mechanism

There is no automated install spec in the registry metadata; SKILL.md asks the user to run pip and playwright install manually. The repository contains requirements.txt and the script can optionally run pip install via os.system if the user consents. No suspicious external download URLs or archive extraction are used.

✓ Credentials

The skill requires no environment variables, credentials, or config paths. It does check for local Chrome/Edge executable paths on Windows to optionally reuse a local browser, which is reasonable for a browser automation tool.

✓ Persistence & Privilege

Skill does not request persistent 'always' inclusion, does not modify other skills or global agent settings, and does not claim elevated agent privileges.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install douyin-keyword-search
安装完成后，直接呼叫该 Skill 的名称或使用 /douyin-keyword-search 触发
根据 Skill 的参数说明提供必要输入，即可获得结构化输出

版本历史

v1.0.0

- Initial release of the Douyin Keyword Search skill. - Supports automated scraping of article data from Douyin search results via browser automation. - Provides command-line options for keyword, output format (json/csv/txt), result limit, headless mode, and output file path. - Includes sample outputs and detailed usage instructions. - Requires Playwright and Chromium installation.

元数据

Slug douyin-keyword-search

版本 1.0.0

许可证 —

累计安装 9

当前安装数 9

历史版本数 1

常见问题