← 返回 Skills 市场
31100
总下载
57
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install playwright-scraper-skill
功能描述
Playwright-based web scraping OpenClaw Skill with anti-bot protection. Successfully tested on complex sites like Discuss.com.hk.
安全使用建议
Install only for scraping you are authorized to perform. Do not use stealth mode to bypass access controls, Cloudflare challenges, CAPTCHAs, rate limits, or login barriers without explicit permission. Treat screenshots, saved HTML, and JSON output as sensitive data, store them carefully, and delete them when no longer needed. Pin and update Playwright, and keep browser sandboxing enabled where possible.
功能分析
Type: OpenClaw Skill
Name: playwright-scraper-skill
Version: 1.2.0
The skill is designed for web scraping, including bypassing anti-bot measures using Playwright. While the core functionality and documentation are aligned with its stated purpose, the `scripts/playwright-stealth.js` file uses the `--no-sandbox` and `--disable-setuid-sandbox` flags when launching Chromium. Disabling the browser's sandbox is a security risk, as it can make the system more vulnerable if the browser itself is compromised by malicious web content. Although this is a common practice in web scraping for compatibility, it represents a risky capability without clear malicious intent from the skill author, thus classifying it as suspicious.
能力评估
Purpose & Capability
The code and documentation are coherent with the stated scraping purpose, but the core advertised capability is Cloudflare and anti-bot evasion through hidden automation markers, realistic user agents, delays, and human-like behavior.
Instruction Scope
The instructions tell users to use stealth mode for 403 and Cloudflare challenges and mention proxies, cookie management, and CAPTCHA handling without clear authorization, legal, site-policy, privacy, or stop-condition boundaries.
Install Mechanism
Installation uses ordinary npm and Playwright browser install commands with no package lifecycle scripts found. The Playwright dependency is declared as a caret range, while the included lockfile resolves a newer exact Playwright version, so this is a supply-chain hygiene issue rather than evidence of malicious installation behavior.
Credentials
Scraping arbitrary user-provided URLs is expected, but stealth mode saves a screenshot by default and can save full HTML to paths controlled by environment variables, which can leave sensitive page contents on disk with little warning.
Persistence & Privilege
No hidden persistence, credential theft, or privilege escalation was found, but the stealth browser launches Chromium with no-sandbox flags, reducing containment when visiting untrusted pages.
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 playwright-scraper-skill - 安装完成后，直接呼叫该 Skill 的名称或使用
/playwright-scraper-skill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
v1.2.0
Initial ClawHub release: Pure Playwright with anti-bot protection, bilingual docs (EN/ZH), successfully tested on Discuss.com.hk
元数据
常见问题
Playwright Scraper Skill 是什么？
Playwright-based web scraping OpenClaw Skill with anti-bot protection. Successfully tested on complex sites like Discuss.com.hk. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 31100 次。
如何安装 Playwright Scraper Skill？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install playwright-scraper-skill」即可一键安装，无需额外配置。
Playwright Scraper Skill 是免费的吗？
是的，Playwright Scraper Skill 完全免费（开源免费），可自由下载、安装和使用。
Playwright Scraper Skill 支持哪些平台？
Playwright Scraper Skill 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Playwright Scraper Skill？
由 waisimon（@waisimon）开发并维护，当前版本 v1.2.0。
推荐 Skills