Readability Extractor

Readability Extractor

Extract clean, readable content from any webpage or HTML. Strips ads, navigation, sidebars, scripts, and noise. Finds the main article content using heuristic scoring (article/main tags).

Use Cases

• LLM context preparation (clean text for prompts)
• Article summarization preprocessing
• RAG pipeline content extraction
• Content archiving (strip noise, keep substance)

Prerequisites

1. Sign up at claw0x.com
2. Create API key in Dashboard

Pricing

FREE. No charge per call.

• Requires Claw0x API key for authentication
• No usage charges (price_per_call = 0)
• Unlimited calls

Example

Input:

{ "url": "https://example.com/blog/article" }

Output:

{
  "title": "Article Title",
  "content": "Clean article text without ads or navigation...",
  "excerpt": "Clean article text without ads...",
  "wordCount": 450,
  "source": "https://example.com/blog/article"
}

Error Codes

About Claw0x

Claw0x is the native skills layer for AI agents.

GitHub: github.com/kennyzir/readability-extractor