← Back to Skills Marketplace
2537
Downloads
1
Stars
9
Active Installs
1
Versions
Install in OpenClaw
/install scrape-web
Description
使用 Python + Scrapling 获取网页内容，支持简单选择器
README (SKILL.md)
Scrape Web Skill
使用 Scrapling 获取网页内容，返回纯文本或选择器结果。
安装依赖
pip install "scrapling[all]"
scrapling install
pip install httpx
用法
1) 直接抓取纯文本
python scripts/scrape_web.py --url "https://example.com"
2) 使用 CSS 选择器
python scripts/scrape_web.py --url "https://example.com" --selector "title::text"
3) 保存到文件
python scripts/scrape_web.py --url "https://example.com" --out "output.txt"
Usage Guidance
This skill is internally consistent with a web-scraping utility. Before installing, be aware that: (1) you will need a Python environment and will run pip install commands that pull third-party packages (inspect those packages if you need to vet supply-chain risk); (2) 'scrapling install' typically downloads browser binaries (Chromium), which increases disk/network activity; (3) the script will fetch any URL you give it — avoid scraping private/internal resources or sites you don't have permission to access; and (4) no secrets are requested by the skill itself, but be careful not to pass sensitive URLs or credentials to the tool. If you want higher assurance, review the scrapling package's install steps and source before running the install commands.
Capability Analysis
Type: OpenClaw Skill
Name: scrape-web
Version: 1.0.0
The skill is a standard web scraping utility that uses the legitimate 'scrapling' and 'httpx' libraries to fetch and parse web content. The Python script (scripts/scrape_web.py) implements expected functionality such as CSS selector support and optional file output, with no evidence of malicious intent, data exfiltration, or obfuscation.
Capability Assessment
Purpose & Capability
Name/description, SKILL.md, and the included Python script all align: the skill fetches pages (httpx or Scrapling) and supports CSS-like selectors. No unrelated credentials, binaries, or capabilities are requested.
Instruction Scope
Runtime instructions stay within scraping: pip install scrapling[all], scrapling install, pip install httpx, then run the script with --url/--selector/--out. Note: 'scrapling install' may download browser components (Chromium) and the StealthyFetcher will execute headless browser fetches, which is expected for this functionality but increases runtime side effects.
Install Mechanism
There is no formal install spec in the registry; the SKILL.md instructs the operator to pip-install dependencies and run 'scrapling install'. This uses PyPI (normal) and likely downloads browser binaries via scrapling, which is expected but more heavyweight than a pure-HTTP library.
Credentials
The skill declares 'python' in requires.env which is unusual (the code does not read a 'python' env var). This appears to be a check that Python is available rather than a secret. No sensitive credentials or unrelated env vars are requested.
Persistence & Privilege
The skill is not always-enabled and does not request elevated platform privileges. It does not modify other skills or system config. Autonomous invocation is allowed (platform default) but not combined with other concerning flags.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install scrape-web - After installation, invoke the skill by name or use
/scrape-web - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Version 1.1.0 introduces documentation updates for improved usage and installation guidance.
- Added SKILL.md detailing installation steps and command examples.
- Clarified how to scrape web content, use CSS selectors, and save results to files.
- Provided specific dependency installation commands.
Metadata
Frequently Asked Questions
What is Scrape Web?
使用 Python + Scrapling 获取网页内容，支持简单选择器. It is an AI Agent Skill for Claude Code / OpenClaw, with 2537 downloads so far.
How do I install Scrape Web?
Run "/install scrape-web" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Scrape Web free?
Yes, Scrape Web is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Scrape Web support?
Scrape Web is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Scrape Web?
It is built and maintained by 李金木 (@jnmhub); the current version is v1.0.0.
More Skills