Overview
- Skill Key
- adastraabyssoque/camoufox-tools
- Author
- adastraabyssoque
- Source Repo
- openclaw/skills
- Version
- -
- Source Path
- skills/adastraabyssoque/camoufox-tools
- Latest Commit SHA
- 699de4adab627d09b2c9172f6ebc49f6a42987ff
Official OpenClaw
rules
36%
camoufox-tools
Simplified CLI tools for camoufox anti-detection browser automation. Provides fox-open, fox-scrape, fox-eval, fox-close, and fox-bilibili-stats commands for easy web scraping and data extraction.
Stars
0
Installs
0
Status
ACTIVE
Visibility
PUBLIC
安装方式
直接复制以下提示词，发送给你的 AI 助手即可完成安装。
请先检查是否已安装 SkillHub 商店，若未安装，请根据 https://skillhub-1388575217.cos.ap-guangzhou.myqcloud.com/install/skillhub.md 安装 SkillHub 商店，然后安装 camoufox-tools 技能。 若已安装，则直接安装 camoufox-tools 技能。
Extracted Content
SKILL.md excerpt
# camoufox-tools
🦊 封装 camoufox + agent-browser 的最佳实践，提供简化的命令行工具用于反检测浏览器自动化和数据抓取。
## 为什么需要这个 Skill？
- **反检测**: camoufox 是基于 Firefox 的防指纹浏览器，能绕过 Bilibili 等网站的风控
- **简化命令**: 隐藏复杂的 `--executable-path` 和 `--headed` 参数
- **最佳实践**: 自动处理 `close` 规范，避免资源泄漏
- **即装即用**: 一键安装，无需记忆长路径
## 安装
```bash
# 运行安装脚本，将工具添加到 PATH
cd ~/.openclaw/workspace/skills/camoufox-tools
./install.sh
# 或者手动添加到 PATH
export PATH="$HOME/.openclaw/workspace/skills/camoufox-tools/bin:$PATH"
```
## 环境变量
```bash
# 可选：自定义 camoufox 路径（默认: ~/.local/share/camoufox/camoufox）
export CAMOUFOX_PATH=/path/to/camoufox
```
## 工具列表
### 1. fox-open - 有头模式打开网页
使用 camoufox 有头模式打开指定网页。
```bash
fox-open "https://example.com"
fox-open "https://bilibili.com"
```
**特性:**
- 自动关闭之前的 browser 实例
- 自动使用 `--headed` 模式
- 自动填充 camoufox 路径
---
### 2. fox-scrape - 抓取页面内容
抓取网页内容，支持等待时间和 CSS 选择器。
```bash
# 基本用法
fox-scrape "https://example.com"
# 等待 5 秒后抓取
fox-scrape "https://example.com" --wait 5000
# 抓取特定元素
fox-scrape "https://example.com" --selector ".article-content"
# 短选项
fox-scrape "https://example.com" -w 5000 -s ".content"
```
**选项:**
- `-w, --wait <ms>` - 等待时间（毫秒，默认 3000）
- `-s, --selector <sel>` - CSS 选择器，提取特定元素
**特性:**
- 自动启动 browser（如未运行）
- 任务完成后自动关闭 browser
---
### 3. fox-eval - 执行 JavaScript
在当前页面执行 JavaScript 代码。
```bash
# 获取页面标题
fox-eval "document.title"
# 获取元素文本
fox-eval "document.querySelector('.like-btn').textContent"
# 获取多个元素
fox-eval "[...document.querySelectorAll('.stat')].map(e => e.textContent)"
```
**注意:** 需要先使用 `fox-open` 打开网页。
---
### 4. fox-close - 规范关闭
关闭所有 browser 实例，释放资源。
```bash
fox-close
```
**建议:** 在每个任务完成后执行，避免资源占用。...
Related Claw Skills
capt-marbles
firecrawl
Web scraping and crawling with Firecrawl API. Fetch webpage content as markdown, take screenshots, extract structured data, search the web, and crawl documentation sites. Use when the user needs to scrape a URL, get current web info, capture a screenshot, extract specific data from pages, or crawl docs for a framework/library.
capt-marbles
phantombuster
Control PhantomBuster automation agents via API. List agents, launch automations, get output/results, check status, and abort running agents. Use when the user needs to run LinkedIn scraping, Twitter automation, lead generation phantoms, or any PhantomBuster workflow.
camopel
arxivkb
Local arXiv paper manager with semantic search. Crawls arXiv categories, downloads PDFs, chunks content, and indexes with FAISS + Ollama embeddings. No cloud API keys required — everything runs locally.
camopel
finviz-crawler
Continuous financial news crawler for finviz.com with SQLite storage, article extraction, and query tool. Use when monitoring financial markets, building news digests, or needing a local financial news database. Runs as a background daemon or systemd service.
cccccqqqqq
scrapling
Advanced web scraping with Scrapling — MCP-native guidance for extraction, crawling, and anti-bot handling. Use via mcporter (MCP) for execution; this skill provides strategy, recipes, and best practices.
dorukardahan
traktor
Extract all assets and content from websites including images, SVGs, fonts, videos, and page structure. Parallel agents with thorough scraping coverage. Triggers: "extract assets", "scrape website", "download site assets", "get all images from", or "/traktor url". Supports multiple URLs.