Extract text and ruled tables from a PDF (10 MiB, 20 pages, no OCR)
Extract text and ruled tables from a PDF (10 MiB, 20 pages, no OCR).
100000 (raw units)
price
1
calls / 30d
1
unique payers
2026-09-09
updated
Provider
api.dekist42.com · discovered, not yet claimed by its owner
Payment (x402 accepts[])
[
{
"scheme": "exact",
"network": "eip155:8453",
"payTo": "0x80036Fc0D82a46240F5610f4Bf27844157675107",
"asset": "0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913",
"amount": "100000",
"maxTimeoutSeconds": 300
}
]Output schema
{
"bazaar": {
"info": {
"input": {
"body": {
"pdf_base64": "JVBERi0..."
},
"bodyType": "json",
"method": "POST",
"type": "http"
},
"output": {
"example": {
"document_sha256": "0000000000000000000000000000000000000000000000000000000000000000",
"engine": "pdfplumber",
"page_count": 1,
"pages": [
{
"height": 400,
"page": 1,
"tables": [],
"text": "Example",
"width": 400
}
],
"schema_version": "1.0",
"warnings": [
"No OCR"
]
},
"type": "json"
}
},
"schema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"input": {
"additionalProperties": false,
"properties": {
"body": {
"additionalProperties": false,
"properties": {
"pdf_base64": {
"description": "Base64 PDF bytes; maximum 10 MiB and 20 pages. No URLs.",
"maxLength": 13981016,
"minLength": 1,
"title": "Pdf Base64",
"type": "string"
}
},
"required": [
"pdf_base64"
],
"title": "ExtractionInput",
"type": "object"
},
"bodyType": {
"enum": [
"json",
"form-data",
"text"
],
"type": "string"
},
"method": {
"enum": [
"POST",
"PUT",
"PATCH"
],
"type": "string"
},
"type": {
"const": "http",
"type": "string"
}
},
"required": [
"type",
"method",
"bodyType",
"body"
],
"type": "object"
},
"output": {
"properties": {
"example": {
"properties": {
"document_sha256": {
"title": "Document Sha256",
"type": "string"
},
"engine": {
"title": "Engine",
"type": "string"
},
"page_count": {
"title": "Page Count",
"type": "integer"
},
"pages": {
"items": {
"properties": {
"height": {
"title": "Height",
"type": "number"
},
"page": {
"description": "One-based source page number",
"minimum": 1,
"title": "Page",
"type": "integer"
},
"tables": {
"items": {
"properties": {
"bbox": {
"description": "x0, top, x1, bottom; PDF points",
"maxItems": 4,
"minItems": 4,
"prefixItems": [
{
"type": "number"
},
{
"type": "number"
},
{
"type": "number"
},
{
"type": "number"
}
],
"title": "Bbox",
"type": "array"
},
"rows": {
"items": {
"items": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
]
},
"type": "array"
},
"title": "Rows",
"type": "array"
}
},
"required": [
"bbox",
"rows"
],
"title": "Table",
"type": "object"
},
"title": "Tables",
"type": "array"
},
"text": {
"title": "Text",
"type": "string"
},
"width": {
"title": "Width",
"type": "number"
}
},
"required": [
"page",
"width",
"height",
"text",
"tables"
],
"title": "PageResult",
"type": "object"
},
"title": "Pages",
"type": "array"
},
"schema_version": {
"title": "Schema Version",
"type": "string"
},
"warnings": {
"items": {
"type": "string"
},
"title": "Warnings",
"type": "array"
}
},
"required": [
"schema_version",
"document_sha256",
"page_count",
"pages",
"warnings",
"engine"
],
"title": "ExtractionResult",
"type": "object"
},
"type": {
"type": "string"
}
},
"required": [
"type"
],
"type": "object"
}
},
"required": [
"input"
],
"type": "object"
}
}
}Use it
curl
curl "https://api.dekist42.com/v1/extract" # -> 402 Payment Required, accepts[] lists how to pay # retry with a PAYMENT-SIGNATURE (or PAYMENT header) once paid
JavaScript
const res = await fetch("https://api.dekist42.com/v1/extract");
if (res.status === 402) {
const { accepts } = await res.json();
// pay one of accepts[] via an x402 client, then retry with the payment header
}Python
import httpx
res = httpx.get("https://api.dekist42.com/v1/extract")
if res.status_code == 402:
accepts = res.json()["accepts"]
# pay one of accepts[] via an x402 client, then retry with the payment headerMachine-readable
Everything on this page is also available as clean JSON at /resources/8230.json, and this resource appears in /discovery/resources and /discovery/search.