← 返回 Skills 市场
网页内容提取
作者
freedompixels
· GitHub ↗
· v1.1.1
· MIT-0
156
总下载
0
收藏
0
当前安装
3
版本数
在 OpenClaw 中安装
/install cn-readability-extractor
功能描述
网页内容提取器。输入URL,提取正文内容,去除广告和导航。
使用说明 (SKILL.md)
网页内容提取器
输入URL,提取干净正文。
功能
- 从URL提取正文
- 去除广告、导航、脚本
- 提取标题和描述
- 中英文支持
用法
python3 scripts/readability.py https://example.com
依赖
- Python 3.7+
- requests, certifi
安全使用建议
This skill appears coherent and low-risk: it only fetches the URL you provide and extracts text locally. Before installing, note: (1) SKILL.md mentions the 'requests' package but the script uses urllib — you do not need to provide API keys or credentials; (2) the skill will make network requests to any URL you pass, so avoid running it on untrusted or internal URLs you don't want fetched; (3) the extractor is simple and may not perfectly remove all ads or boilerplate; (4) the package comes from an unknown source — if you plan to run it on sensitive systems, review the script locally (it’s small and readable) or run it in a sandboxed environment.
功能分析
Type: OpenClaw Skill
Name: cn-readability-extractor
Version: 1.1.1
The skill is a legitimate web content extractor designed to fetch and clean text from user-provided URLs. The Python script `scripts/readability.py` uses standard libraries (urllib, html.parser) to remove ads and navigation elements, and the instructions in `SKILL.md` are consistent with this purpose. No evidence of data exfiltration, malicious execution, or prompt injection was found.
能力评估
Purpose & Capability
Name/description (网页内容提取) match the included script: the Python tool fetches a provided URL and extracts readable text while skipping common structural tags. One minor mismatch: SKILL.md lists 'requests' as a dependency but the script uses urllib.request and does not import requests.
Instruction Scope
SKILL.md instructs the agent to run 'python3 scripts/readability.py <URL>'. The script only fetches the given URL, parses HTML locally, and prints results. It does not read local files, environment variables, or transmit data to third-party endpoints beyond the requested URL.
Install Mechanism
No install spec — instruction-only with a bundled Python script. No downloads or external installers invoked by the skill itself.
Credentials
No environment variables, credentials, or config paths are requested. The script uses certifi for SSL verification; this is proportionate to its network fetch behavior.
Persistence & Privilege
Skill is not always-enabled and uses normal autonomous invocation defaults. It does not modify other skills or request persistent system-wide privileges.
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 cn-readability-extractor - 安装完成后,直接呼叫该 Skill 的名称或使用
/cn-readability-extractor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
v1.1.1
- Improved README clarity and formatting.
- Updated skill name and description for conciseness.
- Added emoji metadata.
- Listed package dependencies and minimum Python version.
- Clarified usage instructions.
v1.1.0
v1.1.0: 修复SKILL.md格式,修复缺失脚本
v1.0.0
v1.0.0: initial release - extract clean article text from any URL
元数据
常见问题
网页内容提取 是什么?
网页内容提取器。输入URL,提取正文内容,去除广告和导航。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 156 次。
如何安装 网页内容提取?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install cn-readability-extractor」即可一键安装,无需额外配置。
网页内容提取 是免费的吗?
是的,网页内容提取 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。
网页内容提取 支持哪些平台?
网页内容提取 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 网页内容提取?
由 freedompixels(@freedompixels)开发并维护,当前版本 v1.1.1。
推荐 Skills