A lightweight web scraping skill for extracting structured metadata, headers, and links from any URL.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install web-info-skill
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install web-info-skill using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Web Info Extractor?
Web Info Extractor is a versatile utility designed for developers and researchers who need quick, structured insights from web pages. As part of the ecosystem of Openclaw Skills, this tool streamlines the process of auditing SEO elements like titles and meta descriptions, while also providing technical breakdowns of header structures and link networks. It is particularly useful for building data pipelines or quickly assessing the content architecture of a site without a full browser overhead.
By leveraging this tool within your Openclaw Skills collection, you gain the ability to parse complex web pages into readable statistics and actionable data. Whether you are performing a technical audit or gathering reference material for an AI agent, this skill provides a clean and efficient way to interact with web content.
Web Info Extractor Use Cases
- Performing quick SEO audits to check page titles and meta descriptions.
- Mapping internal and external link structures of a target webpage.
- Analyzing content hierarchy by extracting H1-H6 header tags.
- Gathering page statistics like word count and image alt text for content analysis.
- Automating data collection via structured JSON exports for downstream processing.
How Web Info Extractor Works
- The user provides a URL to the web-info command within the terminal environment.
- The skill utilizes curl to fetch the raw HTML content of the target webpage efficiently.
- It parses the document to identify key metadata, header hierarchies, and anchor tags.
- The skill respects robots.txt directives and privacy standards during the extraction process to ensure ethical usage.
- It formats the extracted data into a readable terminal output or a structured JSON file based on user-defined flags.
Web Info Extractor Setup
To use this skill, ensure you have curl installed on your system. This is one of the more lightweight Openclaw Skills with minimal dependencies.
# Verify curl installation
curl --version
# Basic usage of the skill
web-info https://example.com
Web Info Extractor Data Schema & Taxonomy
The skill organizes data into several logical blocks to provide a comprehensive overview of a webpage. When using the --json flag, it outputs a structured object compatible with other Openclaw Skills.
| Field | Description |
|---|---|
| Title | The content of the HTML title tag |
| Description | The content of the meta description tag for SEO |
| Headers | A hierarchical list of all H1 through H6 elements |
| Links | An array of objects containing anchor text and destination URLs |
| Images | A list of image filenames and their associated alt text |
| Statistics | Numerical data including word count and element tallies |
Web Info Extractor Advanced Features
- Native JSON output support for seamless integration with other CLI tools and automated Openclaw Skills workflows.
- Granular filtering capabilities to extract only links or only headers for high-speed processing.
- Automatic robots.txt compliance to ensure scraping practices remain within site-owner guidelines.
- High-performance execution with no heavy dependencies beyond standard system binaries like curl.
SKILL.md
Loading
Related Openclaw Skills
Where Not Crowded Report
A travel decision-making skill that analyzes crowd trends and costs to suggest peaceful, high-value alternatives to popular holiday destinations.
Duhui Document to PDF Converter
A high-performance async conversion tool that transforms local Office, WPS, and image files into professional PDF documents.
Skill Coach
A specialized AI creation coach that guides developers and experts through the process of packaging professional capabilities into reusable Openclaw Skills.
Handyman Video
A specialized AI agent skill designed to transform handyman reliability and multi-trade expertise into high-converting trust videos.
fcalendar-skill
A specialized tool for recognizing Chinese and English time expressions and querying official Chinese public holiday schedules.
Meeting Transcriber
A high-performance real-time transcription tool using FunASR for accurate speech recognition and automated meeting documentation.
Featured*
