Fetch a PDF and extract its text per page, with the document info
Fetch a PDF and extract its text per page, with the document info
10000 (raw units)
price
1
calls / 30d
1
unique payers
2026-09-16
updated
Provider
api.agentsouk.dev · discovered, not yet claimed by its owner
Payment (x402 accepts[])
[
{
"scheme": "exact",
"network": "eip155:8453",
"payTo": "0xA0a2494006B72109137630bC026434a809731c07",
"asset": "0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913",
"amount": "10000",
"maxTimeoutSeconds": 900
}
]Output schema
{
"bazaar": {
"info": {
"input": {
"body": {
"url": "https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf"
},
"bodyType": "json",
"method": "POST",
"type": "http"
},
"output": {
"example": {
"bytes": 13264,
"clipped": false,
"content_type": "application/pdf",
"error": null,
"fetched_at": "2026-09-16T00:00:00.000Z",
"final_url": "https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf",
"http_status": 200,
"info": {
"author": "Evangelos Vlachogiannis",
"created_at": "2007-02-23T15:56:37.000Z",
"creator": "Writer",
"modified_at": null,
"producer": "OpenOffice.org 2.1",
"subject": null,
"title": null
},
"pages": [
{
"chars": 14,
"page": 1,
"start": 0
}
],
"pages_read": 1,
"pages_total": 1,
"text": "Dummy PDF file",
"text_chars": 14,
"text_layer": true,
"total_chars": 14,
"url": "https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf",
"word_count": 3
},
"type": "json"
}
},
"schema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"input": {
"additionalProperties": false,
"properties": {
"body": {
"properties": {
"max_chars": {
"default": 50000,
"maximum": 200000,
"minimum": 100,
"type": "integer"
},
"pages": {
"description": "Pages to extract, e.g. \"1-5\" or \"1,3,8-10\" (at most 100); the first 100 by default",
"pattern": "^\\d{1,6}(-\\d{1,6})?(,\\d{1,6}(-\\d{1,6})?)*$",
"type": "string"
},
"url": {
"description": "Public http(s) URL of a PDF",
"format": "uri",
"type": "string"
}
},
"required": [
"url"
],
"type": "object"
},
"bodyType": {
"enum": [
"json"
],
"type": "string"
},
"method": {
"enum": [
"POST"
],
"type": "string"
},
"type": {
"const": "http",
"type": "string"
}
},
"required": [
"type",
"method",
"bodyType",
"body"
],
"type": "object"
},
"output": {
"properties": {
"example": {
"properties": {
"bytes": {
"type": "integer"
},
"clipped": {
"description": "true when max_chars, the 100-page cap or the output size cut something",
"type": "boolean"
},
"content_type": {
"description": "media type as served, parameters dropped",
"type": [
"string",
"null"
]
},
"error": {
"description": "set when the file beat the parse limits after it had been accepted",
"type": [
"string",
"null"
]
},
"fetched_at": {
"format": "date-time",
"type": "string"
},
"final_url": {
"type": "string"
},
"http_status": {
"type": "integer"
},
"info": {
"properties": {
"author": {
"type": [
"string",
"null"
]
},
"created_at": {
"format": "date-time",
"type": [
"string",
"null"
]
},
"creator": {
"type": [
"string",
"null"
]
},
"modified_at": {
"format": "date-time",
"type": [
"string",
"null"
]
},
"producer": {
"type": [
"string",
"null"
]
},
"subject": {
"type": [
"string",
"null"
]
},
"title": {
"type": [
"string",
"null"
]
}
},
"type": "object"
},
"pages": {
"description": "where each read page sits in text",
"items": {
"properties": {
"chars": {
"type": "integer"
},
"page": {
"type": "integer"
},
"start": {
"type": "integer"
}
},
"type": "object"
},
"type": "array"
},
"pages_read": {
"type": "integer"
},
"pages_total": {
"type": "integer"
},
"text": {
"description": "the read pages, separated by blank lines",
"type": "string"
},
"text_chars": {
"type": "integer"
},
"text_layer": {
"description": "false when no read page carried any text (a scan); null when the parse failed",
"type": [
"boolean",
"null"
]
},
"total_chars": {
"description": "characters of the pages the parser read (it stops one page after the text budget is spent), before clipping and without separators; null when nothing was parsed",
"type": [
"integer",
"null"
]
},
"url": {
"type": "string"
},
"word_count": {
"type": "integer"
}
},
"type": "object"
},
"type": {
"type": "string"
}
},
"required": [
"type"
],
"type": "object"
}
},
"required": [
"input"
],
"type": "object"
}
}
}Use it
curl
curl "https://api.agentsouk.dev/v1/x402/lst_01M2N6GWB06867BFMSKJATK2QC" # -> 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.agentsouk.dev/v1/x402/lst_01M2N6GWB06867BFMSKJATK2QC");
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.agentsouk.dev/v1/x402/lst_01M2N6GWB06867BFMSKJATK2QC")
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/7881.json, and this resource appears in /discovery/resources and /discovery/search.