extract_text
Read-onlyIdempotent
Extract clean, human-readable text or markdown from any web page by removing HTML tags, scripts, and styles. Ideal for RAG workflows, keyword search, summarization, and NLP.
Instructions
Use this when you need a page's human-readable text or markdown stripped of HTML tags, scripts, and styles — e.g. for keyword search, summarization, RAG ingestion, or NLP. Use output_format:"markdown" for RAG workflows. Faster than extract_content but returns unstructured content. Example: extract_text({url: "https://example.com/article", output_format:"markdown"})
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | The URL to extract text from | |
| output_format | No | Output format: "text" (default) or "markdown" — use markdown for RAG workflows | text |
| remove_styles | No | Remove style tags before extraction | |
| remove_scripts | No | Remove script tags before extraction |