# Web Page Content Extractor (x402atlas)

> Web Page Content Extractor (x402atlas) is a paid API for AI agents from websearch.use.x402atlas.com, paid per call via x402, $0.01/call, status unknown (last checked 2026-09-16).

Fetches up to 5 URLs in one call and returns the main content of each page as clean markdown or plain text, optionally reranked by a query.

## Facts

- Endpoint: GET https://websearch.use.x402atlas.com/extract
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-16
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/web-page-content-extractor-x402atlas-d92d6cd7
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_Hd0EN4ct1pdMdL-kM37ft

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 web-page-content-extractor-x402atlas-d92d6cd7
```

Example prompt: Fetch the main content from these three articles — https://example.com/article1, https://example.com/article2, and https://example.com/article3 — and return each one as clean markdown so I can use them in my research pipeline.

## When to prefer this

Use this endpoint when you need to extract clean, LLM-ready content from specific known URLs (up to 5 at once), especially for RAG ingestion, article reading, or AI agent context building. Prefer it over a search endpoint when you already have the URLs and just need their textual content. It is particularly useful when you want markdown output that strips HTML boilerplate.

## Known failure modes

- URL is paywalled or bot-blocked — URL appears in failed_urls with no content
- URL is malformed or unreachable — included in failed_urls array
- More than 5 URLs provided — request rejected due to maxItems constraint
- chunks_per_source requested without a query param — may be ignored or return error
- Network timeout fetching a URL — that URL listed in failed_urls

## How this service works

Read any web page or article: fetch up to 5 URLs in one batch call and extract the main content as clean, LLM-ready markdown or plain text. Convert webpages to markdown, scrape page text, pull article content for RAG ingestion and AI agent context.

## Output

A JSON object containing a results array where each entry has the URL and its extracted content as markdown or plain text, plus a failed_urls list for any URLs that could not be fetched, and a queried_at timestamp in UTC.

## 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": [
      "urls"
     ],
     "properties": {
      "urls": {
       "oneOf": [
        {
         "type": "string"
        },
        {
         "type": "array",
         "items": {
          "type": "string"
         },
         "maxItems": 5,
         "minItems": 1
        }
       ],
       "description": "One URL or an array of up to 5 absolute http(s) URLs to extract content from"
      },
      "query": {
       "type": "string",
       "maxLength": 1000,
       "description": "Optional intent — extracted chunks are reranked by relevance to it"
      },
      "format": {
       "enum": [
        "markdown",
        "text"
       ],
       "type": "string",
       "default": "markdown",
       "description": "Output content format"
      },
      "chunks_per_source": {
       "type": "integer",
       "maximum": 5,
       "minimum": 1,
       "description": "Relevant snippets per URL, 1..5 (requires query)"
      }
     }
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object",
     "required": [
      "queried_at",
      "results"
     ],
     "properties": {
      "results": {
       "type": "array",
       "items": {
        "type": "object",
        "required": [
         "url",
         "content"
        ],
        "properties": {
         "url": {
          "type": "string"
         },
         "content": {
          "type": "string",
          "description": "Extracted page content as markdown or text"
         }
        }
       }
      },
      "queried_at": {
       "type": "string",
       "format": "date-time",
       "description": "Time the extraction was executed (UTC)"
      },
      "failed_urls": {
       "type": "array",
       "items": {
        "type": "string"
       },
       "description": "URLs that could not be extracted"
      }
     }
    }
   }
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "results": [
   {
    "url": "https://en.wikipedia.org/wiki/Artificial_intelligence",
    "content": "# Artificial intelligence\n\nArtificial intelligence (AI) is intelligence exhibited by machines..."
   }
  ],
  "queried_at": "2026-07-01T12:00:00Z"
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/web-page-content-extractor-x402atlas-d92d6cd7/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from websearch.use.x402atlas.com](https://www.zero.xyz/host/websearch.use.x402atlas.com/llms.txt)