Document parsing: convert office documents (docx, pptx, xlsx, pdf, odt, ods, odp, rtf, epu

[
  {
    "scheme": "exact",
    "network": "eip155:8453",
    "payTo": "0xc2afB91833f4dE19542A025872C6085cC29185eB",
    "asset": "0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913",
    "amount": "5000",
    "maxTimeoutSeconds": 300
  }
]

{
  "bazaar": {
    "info": {
      "input": {
        "body": {
          "url": "https://example.com/report.docx"
        },
        "bodyType": "json",
        "method": "POST",
        "type": "http"
      },
      "output": {
        "example": {
          "chars": 1834,
          "format": "docx",
          "markdown": "# Quarterly Report\n\n| Region | Revenue |\n|---|---|\n| EMEA | $1.2M |"
        },
        "type": "json"
      }
    },
    "schema": {
      "$schema": "https://json-schema.org/draft/2020-12/schema",
      "properties": {
        "input": {
          "additionalProperties": false,
          "properties": {
            "body": {
              "anyOf": [
                {
                  "required": [
                    "url"
                  ]
                },
                {
                  "required": [
                    "base64"
                  ]
                }
              ],
              "properties": {
                "base64": {
                  "description": "Base64-encoded document bytes (max ~15MB). Provide either url or base64.",
                  "type": "string"
                },
                "filename": {
                  "description": "Optional filename hint (e.g. \"report.docx\") used for format detection when bytes carry no signature (csv).",
                  "type": "string"
                },
                "format": {
                  "description": "Optional explicit format override. One of: doc, docx, odt, pdf, ppt, pptx, rtf, epub, xlsx, ods, odp, csv",
                  "type": "string"
                },
                "url": {
                  "description": "URL of the document to download and parse. Provide either url or base64.",
                  "type": "string"
                }
              },
              "required": []
            },
            "bodyType": {
              "enum": [
                "json",
                "form-data",
                "text"
              ],
              "type": "string"
            },
            "method": {
              "enum": [
                "POST"
              ],
              "type": "string"
            },
            "type": {
              "const": "http",
              "type": "string"
            }
          },
          "required": [
            "type",
            "method",
            "bodyType",
            "body"
          ],
          "type": "object"
        },
        "output": {
          "properties": {
            "example": {
              "type": "object"
            },
            "type": {
              "type": "string"
            }
          },
          "required": [
            "type"
          ],
          "type": "object"
        }
      },
      "required": [
        "input"
      ],
      "type": "object"
    }
  }
}

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

const res = await fetch("https://api.clawfetch.ai/parse");
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://api.clawfetch.ai/parse")
if res.status_code == 402:
    accepts = res.json()["accepts"]
    # pay one of accepts[] via an x402 client, then retry with the payment header