← 返回 Skills 市场
8510
总下载
9
收藏
95
当前安装
1
版本数
在 OpenClaw 中安装
/install scrape
功能描述
Legal web scraping with robots.txt compliance, rate limiting, and GDPR/CCPA-aware data handling.
安全使用建议
Install only if you intend to perform authorized public scraping. Before using the examples, confirm the target site's robots.txt and terms, prefer official APIs, avoid login-protected or personal data, consider failing closed when robots.txt cannot be checked, and avoid logging sensitive URL parameters.
功能分析
Type: OpenClaw Skill
Name: scrape
Version: 1.0.0
The skill bundle is designed for ethical and legal web scraping, providing comprehensive guidelines in `SKILL.md` for compliance (robots.txt, ToS, GDPR/CCPA, rate limiting) and implementing these safeguards in `code.md`. The code uses standard Python libraries to perform web requests, handle rate limits, and log activity, all aligned with the stated purpose. There is no evidence of malicious intent, data exfiltration to unauthorized parties, persistence mechanisms, or prompt injection attempts designed to subvert the agent's purpose; instead, the instructions actively promote responsible behavior.
能力评估
Purpose & Capability
The stated purpose is legal web scraping, and the artifact provides checklist guidance plus example Python patterns for robots.txt checks, session setup, rate-limited requests, retries, and audit logging.
Instruction Scope
The instructions are mostly restrictive and user-protective, but the example robots.txt helper returns allowed if robots.txt cannot be read, so cautious users should fail closed or ask before scraping.
Install Mechanism
The bundle contains only SKILL.md and code.md markdown files, with no executable scripts, install hooks, package installation, or declared runtime secrets.
Credentials
Outbound requests to user-selected websites are inherent to the skill and disclosed; it does not request local credentials, browser profiles, session stores, or unrelated sensitive files.
Persistence & Privilege
The examples include audit logging of scraped URLs and response statuses, which is purpose-aligned but could retain sensitive query strings if users choose poorly scoped targets; no background persistence or privilege escalation is present.
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 scrape - 安装完成后，直接呼叫该 Skill 的名称或使用
/scrape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
元数据
常见问题
Scrape 是什么？
Legal web scraping with robots.txt compliance, rate limiting, and GDPR/CCPA-aware data handling. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 8510 次。
如何安装 Scrape？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install scrape」即可一键安装，无需额外配置。
Scrape 是免费的吗？
是的，Scrape 完全免费（开源免费），可自由下载、安装和使用。
Scrape 支持哪些平台？
Scrape 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 Scrape？
由 Iván（@ivangdavila）开发并维护，当前版本 v1.0.0。
推荐 Skills