# Agent Data Bench – Web Page Extractor

> Agent Data Bench – Web Page Extractor is a paid API for AI agents from x402.deepsense.stream, paid per call via x402, $0.005/call, status unknown (last checked 2026-10-20).

Fetches a public web page and returns LLM-ready content: clean markdown, JSON-LD, OpenGraph, heading outline, tables, link graph, word/token counts, and embedding-ready chunks.

## Facts

- Endpoint: GET https://x402.deepsense.stream/api/v1/web/extract?utm_source=zero.xyz
- Price: $0.005/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-20
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agent-data-bench-web-page-extractor-d68ea746
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_R4_3rLT4wu3bhudmK7OlN

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 agent-data-bench-web-page-extractor-d68ea746
```

Example prompt: Can you fetch https://en.wikipedia.org/wiki/Artificial_intelligence and give me the clean markdown content, heading outline, JSON-LD, and embedding-ready chunks so I can load it into my RAG pipeline?

## When to prefer this

Choose this endpoint when you need to convert a single public web page into structured, LLM-ready content — especially when you need multiple data layers at once (clean markdown + JSON-LD + chunks + links) in one paid call. Prefer this over generic scraping tools when your goal is downstream LLM or RAG use, since it handles tokenization, chunking, and boilerplate removal natively. Avoid if you need to crawl multiple pages or require JavaScript rendering of client-side-only SPAs.

## Known failure modes

- URL not publicly accessible or requires authentication — returns error
- Target page blocked by robots.txt — request rejected per robots.txt compliance
- Response body exceeds 2MB cap — truncated or error returned
- SSRF guard triggered for private/internal IP ranges — request blocked
- Malformed or non-HTTP URL provided — validation error
- Target server unreachable or times out — network error returned
- Page contains no parseable content (e.g. pure JS SPA with no SSR) — sparse or empty markdown

## How this service works

Turn a public web page into an LLM-ready document: clean markdown with nav/cookie/script boilerplate removed, parsed JSON-LD, OpenGraph, heading outline, tables, link graph, word and token counts, and embedding-ready chunks. Query: url (required), format=markdown, include=jsonld,headings,tables,links,chunks,openGraph. SSRF-guarded, 2MB cap, honours robots.txt.

## Output

Returns a JSON object containing: cleaned markdown of the page body (boilerplate removed), parsed JSON-LD objects, OpenGraph tags, hierarchical heading outline, extracted tables, a link graph of all page links, word count, token count, and chunked text segments ready for embedding — all derived from the fetched URL.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "method"
   ],
   "properties": {
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "GET"
     ],
     "type": "string"
    },
    "queryParams": {
     "type": "object",
     "required": [
      "url"
     ],
     "properties": {
      "url": {
       "type": "string",
       "description": "Public http(s) URL"
      }
     }
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object"
    }
   }
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agent-data-bench-web-page-extractor-d68ea746/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from x402.deepsense.stream](https://www.zero.xyz/host/x402.deepsense.stream/llms.txt)