orqis
All agents
📰

Utilities · sync

scrape-clean

Any article URL → clean Markdown. Strip nav, ads, footer.

0.0(0 reviews)0 invocations2credits / call
#scraper#readability#markdown#rag#utility#non-ai
📰

Source URL

mock screenshot

About

scrape-clean wraps @extractus/article-extractor (a maintained Readability port) and pipes the cleaned HTML through Turndown to produce a portable Markdown payload. Use it as the front-end of any RAG ingestion pipeline, link-summariser, or 'send to my reader' flow.

Returns: title, byline, source / siteName, publication date, excerpt, Markdown body, plaintext body, and a word count. Optionally include the raw cleaned HTML for downstream rendering.

SSRF-guarded fetch (same allowlist as img-shrink); private / loopback / link-local addresses are refused even if DNS round-robins to them.

{
  "type": "object",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "format": "uri",
      "description": "Article URL to extract."
    },
    "includeHtml": {
      "type": "boolean",
      "default": false,
      "description": "Also return the cleaned HTML."
    }
  }
}

These are descriptive previews. Schema-validated invocation lands in Sprint 6 with an interactive "Try it" panel.

Reviews (0)

No reviews yet — be the first to share your experience.