# Sparks RE API — Web Page to Markdown Extractor

> Sparks RE API — Web Page to Markdown Extractor is a paid API for AI agents from sparks-re-api.sparksdigital-re.workers.dev, paid per call via x402, $0.01/call, status unknown (last checked 2026-10-29).

Fetches a public webpage URL or raw HTML and converts it to clean, structured Markdown with extracted title, headings, links, and word count

## Facts

- Endpoint: POST https://sparks-re-api.sparksdigital-re.workers.dev/utilities/extract?utm_source=zero.xyz
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-29
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/sparks-re-api-web-page-to-markdown-extractor-823e45f9
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_wWDiR5kGslPdZGm75SdfF

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability sparks-re-api-web-page-to-markdown-extractor-823e45f9 -d '<json body>'
```

Example prompt: Fetch the listing at https://www.zillow.com/homedetails/123-main-st/ and convert it to clean Markdown so I can analyze the property details — limit the output to 8000 characters.

## When to prefer this

Choose this endpoint when you need to convert a live public webpage or raw HTML into clean, structured Markdown for downstream text analysis, AI processing, or content extraction — particularly within the Sparks RE workflow where subsequent steps (FHA compliance scan, property normalization) expect Markdown or plain text input. Prefer this over a generic scraper when you want pre-extracted metadata like headings, word count, and link count alongside the content.

## Known failure modes

- URL is not publicly accessible or behind a login wall — returns empty or partial markdown
- Malformed URL input — returns a validation error
- Page content exceeds max_chars limit — content is truncated at the specified character count
- Network timeout fetching the remote URL — returns a fetch error
- HTML is heavily JavaScript-rendered and static scrape yields minimal content

## How this service works

AI-powered real estate tools for property normalization, FHA compliance scanning, and investor metrics calculation. Powered by x402 micropayments.

## Output

Returns a JSON object containing the page title, an array of headings, the full Markdown-formatted content, the source URL, total word count, meta description, and count of links found on the page.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "url": {
   "type": "string",
   "description": "Public webpage URL to fetch and convert to clean Markdown"
  },
  "html": {
   "type": "string",
   "description": "Optional raw HTML string to parse directly"
  },
  "max_chars": {
   "type": "number",
   "description": "Maximum Markdown length (default 16000)"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "title": "Example Domain",
  "headings": [
   "H1: Example Domain"
  ],
  "markdown": "# Example Domain\n\nThis domain is for use in illustrative examples in documents.",
  "source_url": "https://example.com",
  "word_count": 28,
  "description": "",
  "links_count": 1
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/sparks-re-api-web-page-to-markdown-extractor-823e45f9/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from sparks-re-api.sparksdigital-re.workers.dev](https://www.zero.xyz/host/sparks-re-api.sparksdigital-re.workers.dev/llms.txt)