READY-TO-RUN WORKFLOW

Convert a website page to Markdown for RAG

Turn a public web page into clean Markdown with headings, links, metadata, JSON-LD, and a traceable source URL.

BUILT FORAI builders, RAG developers, researchers, documentation teams, and data engineers

LIVE PRICINGFrom $1.00 per 1,000 pages

Run the verified example Review Actor details

THE OUTCOME

A clean Markdown record you can inspect, export, or pass into a RAG and LLM ingestion pipeline.

1
Open the verified one-page example and run it unchanged.
2
Inspect the Markdown, headings, metadata, links, and source URL.
3
Replace example.com with a public page you are authorized to collect.
4
Raise the page and depth caps only after the first bounded result is correct.

SAMPLE INPUT

{
  "startUrls": [
    {
      "url": "https://example.com"
    }
  ],
  "maxPages": 1,
  "maxDepth": 0,
  "sameDomainOnly": true,
  "useSitemaps": false,
  "respectRobotsTxt": true
}

Open this prefilled example →

STRUCTURED OUTPUT

Fields ready for export and automation

Source URLFinal URLTitleDescriptionHeadingsMarkdownLinksJSON-LDCrawl depthScraped at

COMMON QUESTIONS

Before you run the workflow

Does it execute JavaScript?

No. It is a fast HTTP crawler for public HTML pages. JavaScript-only applications may return incomplete content.

Can I crawl a whole documentation site?

Yes, after verifying one page. Increase the page and depth caps gradually and keep same-domain and robots.txt controls enabled.

Can I use the output in a RAG pipeline?

Yes. Each row keeps clean Markdown together with source and metadata fields for traceable ingestion.

START WITH A BOUNDED SAMPLE

Open the Actor, keep the sample small, and inspect the first dataset.

Run this exact example