# agents.thirdmade.net Web Scraper

> agents.thirdmade.net Web Scraper is a paid API for AI agents from agents.thirdmade.net, paid per call via x402, $0.01/call, status unknown (last checked 2026-09-14).

Scrapes any public web page and returns clean structured JSON containing the page title, text content, and meta information, billed per call in USDC on Base.

## Facts

- Endpoint: GET https://agents.thirdmade.net/scrape
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agents-thirdmade-net-web-scraper-ac27991a
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_B3x7Yb_Z0N6FwhBQBXR9C

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 agents-thirdmade-net-web-scraper-ac27991a
```

Example prompt: Can you scrape the page at https://example.com/article and give me the title and full text content as clean structured JSON?

## When to prefer this

Choose this endpoint when you need quick, clean plain-text extraction from a single public URL and want structured JSON output (title, text, meta) without managing your own scraping infrastructure. It's ideal for agent workflows that need to read web content on-demand and pay per call without subscriptions. If you need to crawl entire sites, render JavaScript-heavy SPAs deeply, or extract custom CSS-selected fields, a more configurable scraping service may be more appropriate.

## Known failure modes

- URL is behind a login or paywall — returns empty or partial content
- Page uses heavy JavaScript rendering that can't be statically fetched — may return incomplete text
- Invalid or malformed URL — likely returns an error response
- Page returns a non-200 HTTP status (404, 403, 500) — scrape fails or returns error
- USDC payment fails or wallet has insufficient balance — call is rejected with 402

## How this service works

Scrape any public web page and get clean structured JSON (title, text, meta). Pay per call with USDC on Base.

## Output

Returns a JSON object containing the scraped page's URL, title, cleaned body text, text length (character count), and source field. Content is cleaned and structured, not raw HTML.

## 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": "The public webpage URL to scrape"
      }
     }
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object",
     "properties": {
      "url": {
       "type": "string"
      },
      "text": {
       "type": "string"
      },
      "title": {
       "type": "string"
      },
      "length": {
       "type": "number"
      },
      "source": {
       "type": "string"
      }
     }
    }
   }
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agents-thirdmade-net-web-scraper-ac27991a/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agents.thirdmade.net](https://www.zero.xyz/host/agents.thirdmade.net/llms.txt)