← 返回 Skills 市场
Web Scraping
作者
zhangqixin9527
· GitHub ↗
· v1.0.0
· MIT-0
11921
总下载
6
收藏
66
当前安装
1
版本数
在 OpenClaw 中安装
/install web-scraping
功能描述
Extract structured information from websites using web_fetch for simple pages and browser automation for dynamic sites, login-gated flows, pagination, infini...
安全使用建议
Install only if you intentionally want an agent to scrape sites, including potentially logged-in pages. Before use, confirm the target site, fields to collect, whether account/private data may be accessed, and where results will be stored; avoid using it for sensitive accounts unless you explicitly need that data and can manage retention and site-policy risk.
能力评估
Purpose & Capability
The scraping, browser automation, extraction, and workspace output behavior fit a scraping-focused skill, but login-gated collection raises privacy and account-data stakes.
Instruction Scope
The invocation description appears broad enough to activate for generic website, monitoring, summary, or lookup requests, which can lead to scraping behavior when the user did not clearly ask for it.
Install Mechanism
No install-time execution, package-install risk, or hidden setup behavior was identified from the supplied evidence.
Credentials
Supporting login-gated scraping means the skill may access account-scoped or private data, and the instructions do not show clear consent, site-policy, or data-minimization boundaries.
Persistence & Privilege
Saving scraped results to the workspace is purpose-aligned, but the artifacts do not show clear user confirmation, retention limits, or safeguards for sensitive scraped content.
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 web-scraping - 安装完成后，直接呼叫该 Skill 的名称或使用
/web-scraping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 web-scraping skill.
- Supports data extraction from both static and dynamic websites.
- Automatically chooses between direct HTML fetching and browser automation based on site complexity and interaction needs.
- Handles dynamic content, authentication, infinite scroll, pagination, and search/filter flows.
- Outputs structured data in concise bullet lists, JSON, or CSV formats.
- Includes reliability rules for deduplication, error handling, and workspace file management.
元数据
常见问题
Web Scraping 是什么？
Extract structured information from websites using web_fetch for simple pages and browser automation for dynamic sites, login-gated flows, pagination, infini... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 11921 次。
如何安装 Web Scraping？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install web-scraping」即可一键安装，无需额外配置。
Web Scraping 是免费的吗？
是的，Web Scraping 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Web Scraping 支持哪些平台？
Web Scraping 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 Web Scraping？
由 zhangqixin9527（@zhangqixin9527）开发并维护，当前版本 v1.0.0。
推荐 Skills