# ForgeMesh Web Content Extractor

> ForgeMesh Web Content Extractor is a paid API for AI agents from x402.forgemesh.io, paid per call via x402, $0.005/call, status unknown (last checked 2026-09-13).

Fetches any public web page and returns its readable article content as clean markdown, stripping boilerplate, navigation, and ads.

## Facts

- Endpoint: POST https://x402.forgemesh.io/web-extract
- Price: $0.005/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-13
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/forgemesh-web-content-extractor-f19e668a
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_9Or0iW5tjWKLYhZaKFma0

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 forgemesh-web-content-extractor-f19e668a -d '<json body>'
```

Example prompt: Can you fetch the article at https://www.bbc.com/news/technology-12345678 and give me just the readable content as clean markdown, without any ads or navigation?

## When to prefer this

Use this endpoint when you need to extract clean, readable text from a specific public web page URL and want markdown output without boilerplate. It is ideal for article reading, summarization pipelines, or research tasks where you have a URL and need its content. Prefer this over raw HTTP fetchers when you need clean prose rather than raw HTML, and over general search APIs when you already know the exact URL.

## Known failure modes

- 403 Forbidden — page explicitly disallows AI/bot access via robots.txt or Content-Signal/aipref declaration
- Invalid or non-public URL — SSRF guard blocks private/internal IP ranges
- Content exceeds 2MB cap — response truncated or rejected
- Unreachable URL — network timeout or DNS failure
- Non-article page with no extractable readable content — sparse or empty markdown returned

## How this service works

Web content extraction: fetch any public web page and get its readable article content as clean markdown — boilerplate, nav, and ads stripped automatically. For "get me the readable text of this page" requests. Honors robots.txt and Content-Signal/aipref declarations (explicit disallow returns an unpaid 403). SSRF-guarded, 2MB cap.

## Output

Returns the main readable article content of the requested web page as clean markdown, with navigation menus, ads, headers, footers, and other boilerplate stripped out. If the page disallows AI access (robots.txt or aipref/Content-Signal), returns a 403 error instead of content.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "url": {
   "type": "string",
   "description": "Public web page URL"
  },
  "html": {
   "type": "string",
   "description": "Raw HTML alternative to url"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "title": "Micropayment",
  "markdown": "A **micropayment** is a financial transaction..."
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/forgemesh-web-content-extractor-f19e668a/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from x402.forgemesh.io](https://www.zero.xyz/host/x402.forgemesh.io/llms.txt)