Public beta docs

API Quickstart

Use POST /v1/scrape to turn a public webpage into clean, model-ready context for AI apps, agents, RAG pipelines, and automation workflows.

1. Endpoint

POST /v1/scrape

Required headers:

Authorization: Bearer DEMO_API_KEY
Content-Type: application/json

2. Request body

{
  "url": "https://example.com",
  "ai": "auto"
}

Field	Required	Description
`url`	Yes	A full public `https://` webpage URL.
`ai`	No	One of `auto`, `off`, `clean`, or `extract`. Defaults to `auto`.

3. AI modes

Mode	Public behavior
`auto`	Default mode. Returns AI-ready cleaned content when possible.
`off`	Returns extracted webpage text without AI cleanup.
`clean`	Applies stronger cleanup for better downstream LLM readability.
`extract`	Compatibility mode. Currently equivalent to `auto` for public beta usage.

4. Copy-paste examples

curl

BASE_URL="https://sou.esim111.net"
API_KEY="YOUR_API_KEY"

curl -sS -X POST "$BASE_URL/v1/scrape" \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"url":"https://example.com","ai":"auto"}'

Python

import json
import urllib.request

BASE_URL = "https://sou.esim111.net"
API_KEY = "YOUR_API_KEY"
payload = {"url": "https://example.com", "ai": "auto"}

request = urllib.request.Request(
    f"{BASE_URL}/v1/scrape",
    data=json.dumps(payload).encode("utf-8"),
    method="POST",
    headers={
        "Authorization": f"Bearer {API_KEY}",
        "Content-Type": "application/json",
    },
)

with urllib.request.urlopen(request, timeout=30) as response:
    body = json.loads(response.read().decode("utf-8"))
    print("success:", body.get("success"))
    print("request_id:", body.get("request_id"))
    print("summary:", body.get("content", {}).get("summary"))

Node.js

const BASE_URL = 'https://sou.esim111.net';
const API_KEY = 'YOUR_API_KEY';

async function main() {
  const response = await fetch(`${BASE_URL}/v1/scrape`, {
    method: 'POST',
    headers: {
      Authorization: `Bearer ${API_KEY}`,
      'Content-Type': 'application/json',
    },
    body: JSON.stringify({
      url: 'https://example.com',
      ai: 'auto',
    }),
  });

  const data = await response.json();
  console.log('status:', response.status);
  console.log('success:', data.success);
  console.log('request_id:', data.request_id);
  console.log('summary:', data.content?.summary);
}

main().catch((error) => {
  console.error(error);
  process.exitCode = 1;
});

5. Response anchors

During beta, integrations should rely first on these stable anchors:

success
request_id
url
content.markdown when extraction succeeds
error.code when extraction fails

6. Error codes

Code	Retry?	Meaning
`INVALID_URL`	No	The URL is malformed or not a supported public `https://` URL.
`TARGET_UNSUPPORTED`	No	The target page type is outside public beta support scope.
`PROCESSING_CAPACITY_LIMITED`	Yes	Processing is busy. Retry shortly with exponential backoff.

For retryable errors, wait 1 second, then 2 seconds, then 4 seconds. Stop after 3 retries and include request_id in support requests.

Good beta targets

Public documentation
Blog posts and news articles
Help center pages
Public company and product pages
Public hiring pages on a best-effort basis

Not supported as a beta promise

Login pages and account dashboards
Payment, checkout, cart, or order pages
CAPTCHA or verification challenge pages
Private, restricted, or session-only content

Keep API keys on your server side. Never paste keys into screenshots, logs, or public support channels.