Web scraping API for AI agents — extract clean text and metadata from one safe public HTTP

[
  {
    "scheme": "exact",
    "network": "eip155:8453",
    "payTo": "0xc29185fa176357612f3194735753e520e91adc46",
    "asset": "0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913",
    "amount": "5000",
    "maxTimeoutSeconds": 120
  }
]

{
  "bazaar": {
    "info": {
      "input": {
        "method": "GET",
        "queryParams": {
          "max_chars": "12000",
          "url": "https://example.com/"
        },
        "type": "http"
      },
      "output": {
        "example": {
          "extraction": {
            "final_url": "https://example.com/",
            "text": "Example Domain ...",
            "title": "Example Domain"
          },
          "product": "SML Web Extract One-Shot",
          "status": "ready"
        },
        "type": "json"
      }
    },
    "schema": {
      "$schema": "https://json-schema.org/draft/2020-12/schema",
      "additionalProperties": false,
      "properties": {
        "input": {
          "additionalProperties": false,
          "properties": {
            "body": {
              "additionalProperties": true,
              "description": "GET resource; no JSON request body is required.",
              "type": "object"
            },
            "method": {
              "const": "GET",
              "type": "string"
            },
            "queryParams": {
              "additionalProperties": true,
              "properties": {
                "max_chars": {
                  "description": "Maximum clean-text characters, 1000-50000 Search intents: web scraping api for ai agents, web scraping api, web scraping, web extraction, html to text, clean web text.",
                  "type": "string"
                },
                "url": {
                  "description": "Public HTTPS URL to extract Search intents: web scraping api for ai agents, web scraping api, web scraping, web extraction, html to text, clean web text.",
                  "type": "string"
                }
              },
              "required": [
                "url"
              ],
              "type": "object"
            },
            "type": {
              "const": "http",
              "type": "string"
            }
          },
          "required": [
            "type",
            "method",
            "queryParams"
          ],
          "type": "object"
        },
        "output": {
          "additionalProperties": false,
          "properties": {
            "example": {
              "type": "object"
            },
            "type": {
              "const": "json",
              "type": "string"
            }
          },
          "required": [
            "type",
            "example"
          ],
          "type": "object"
        }
      },
      "required": [
        "input",
        "output"
      ],
      "type": "object"
    }
  }
}

curl "https://squeezeos-api.onrender.com/api/web/extract-once"
# -> 402 Payment Required, accepts[] lists how to pay
# retry with a PAYMENT-SIGNATURE (or PAYMENT header) once paid

const res = await fetch("https://squeezeos-api.onrender.com/api/web/extract-once");
if (res.status === 402) {
  const { accepts } = await res.json();
  // pay one of accepts[] via an x402 client, then retry with the payment header
}

import httpx
res = httpx.get("https://squeezeos-api.onrender.com/api/web/extract-once")
if res.status_code == 402:
    accepts = res.json()["accepts"]
    # pay one of accepts[] via an x402 client, then retry with the payment header