A powerful utility that converts complex HTML and web pages into clean, readable text or structured JSON using the MinerU engine.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install html-to-text
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 html-to-text 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 HTML to Text?
This Openclaw Skills utility leverages MinerU, an open-source document intelligence engine from OpenDataLab, to transform HTML content into plain text formats. It effectively strips away boilerplate markup while preserving the essential readability and structure of the document. By outputting content as Markdown or structured JSON, it provides a developer-friendly bridge between raw web content and data-hungry AI pipelines. Utilizing Openclaw Skills for text extraction ensures high-quality data processing for LLM applications.
HTML to Text Use Cases
- Scraping readable content from web URLs for RAG (Retrieval-Augmented Generation) pipelines via Openclaw Skills.
- Cleaning up local HTML files for text analysis or NLP tasks.
- Converting web articles into a simplified format for mobile or low-bandwidth display.
- Automating data extraction from complex web page structures into clean JSON fields for search indexing.
How HTML to Text Works
- The user provides a local HTML file or a web URL to the Openclaw Skills utility.
- The skill invokes the MinerU engine via the mineru-open-api CLI tool.
- The tool communicates with the MinerU API using a secure token to begin processing the document.
- The HTML is parsed by the document intelligence engine, stripping tags and identifying the main content blocks.
- The resulting clean text is output as Markdown or returned within a JSON structure for easy programmatic access.
HTML to Text Setup
To get started with this skill from the Openclaw Skills collection, install the MinerU API client:
npm install -g mineru-open-api
# or via Go (macOS/Linux):
go install github.com/opendatalab/MinerU-Ecosystem/cli/mineru-open-api@latest
Then, authenticate with your token:
export MINERU_TOKEN="your-token"
mineru-open-api auth
HTML to Text Data Schema & Taxonomy
| Feature | Description |
|---|---|
| Input Formats | Local .html files or Web Page URLs |
| Output Formats | Markdown (default), JSON (-f json) |
| Metadata | Supports language hints (e.g., --language en) |
| Stream | Progress logs to stderr; extracted content to stdout |
| Storage | Optional file or directory output via the -o flag |
HTML to Text Advanced Features
- Seamless integration with the OpenDataLab MinerU open-source document intelligence ecosystem.
- Multi-language support with specialized processing hints for optimized Chinese and English extraction.
- JSON output mode designed specifically for automated text extraction fields in data pipelines.
- Built-in crawling capabilities to fetch and process live web content directly from any public URL using Openclaw Skills.
SKILL.md
Loading
Related Openclaw Skills
Douyin Content Analyzer
An AI-driven content analysis module that transforms raw Whisper transcriptions into structured, professional reports with key point extraction.
Douyin Orchestrator
An automated workflow engine that downloads, transcribes, and analyzes Douyin videos and notes into structured knowledge.
Ocr Pro
A high-performance OCR and document extraction tool utilizing Vision Language Models for complex layouts.
PDF Analysis
A powerful document intelligence skill for extracting structured content, tables, and formulas from PDFs using MinerU.
Douyin Fetcher
An AI agent skill for automated Douyin video and audio extraction using browser automation and DASH stream merging.
Corpus Search
A high-performance semantic search and metadata filtering tool designed for querying structured text databases and literary corpora.
METADATA
Featured*
