# PDF Text and Tables Extractor

> PDF Text and Tables Extractor is a paid API for AI agents from 164.160.90.241.sslip.io, paid per call via x402, $0.01/call, status unknown (last checked 2026-10-12).

Downloads a PDF from a URL and returns per-page layout-preserved text, detected tables as structured rows/cells, and document metadata (title, author, page count) — with scanned-image detection.

## Facts

- Endpoint: GET https://164.160.90.241.sslip.io/api/doc-pdf-extract?utm_source=zero.xyz
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-12
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/pdf-text-and-tables-extractor-2dfc4299
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_4tOboVmLKYS2zdVJnzdPi

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability pdf-text-and-tables-extractor-2dfc4299
```

Example prompt: Can you download the PDF at https://example.com/annual-report-2023.pdf and extract all the text and tables from pages 1 through 20, along with the document title and author?

## When to prefer this

Choose this endpoint when you need to extract readable text, structured table data, or metadata from a PDF document accessible via a public URL. It is ideal for processing reports, research papers, contracts, or any structured document in PDF format. It handles multi-page documents up to 50 pages per call and explicitly flags scanned-only PDFs where text is not extractable.

## Known failure modes

- PDF URL is unreachable or returns a non-PDF response
- PDF is password-protected or encrypted
- PDF is scanned image-only — text extraction returns empty or a scanned flag
- Requested page range exceeds 50-page limit per call
- Network timeout fetching a large PDF
- Malformed or corrupted PDF file

## How this service works

Download a PDF by URL and return per-page text (layout preserved), detected tables as rows of cells, and metadata (title, author, page count). Up to 50 pages per call via first_page/last_page; flags scanned image-only PDFs.

## Output

Returns per-page layout-preserved text content, detected tables represented as rows of cells, and document metadata including title, author, and total page count. Also flags whether the PDF is a scanned image-only document (where text extraction is not possible).

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "method"
   ],
   "properties": {
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "GET"
     ],
     "type": "string"
    },
    "queryParams": {
     "type": "object",
     "required": [
      "url"
     ],
     "properties": {
      "url": {
       "type": "string",
       "description": "URL of a PDF"
      },
      "last_page": {
       "type": "integer",
       "description": "Last page (max 50 pages per call)"
      },
      "first_page": {
       "type": "integer",
       "description": "First page, default 1"
      }
     }
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object"
    }
   }
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/pdf-text-and-tables-extractor-2dfc4299/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from 164.160.90.241.sslip.io](https://www.zero.xyz/host/164.160.90.241.sslip.io/llms.txt)