# PDF and Image to Clean Text for AI Agents (`obkk/pdf-image-to-clean-text`) Actor

Turn PDFs and images into clean text for AI agents and RAG. Scanned pages get OCR, and headers and page numbers are removed. Pay per page.

- **URL**: https://apify.com/obkk/pdf-image-to-clean-text.md
- **Developed by:** [Clean Text Tools](https://apify.com/obkk) (community)
- **Security:** Limited permissions
- **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $2.00 / 1,000 page processeds

This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events.

Learn more: https://docs.apify.com/actors/running/actors-in-store.md#pay-per-event

## What's an Apify Actor?

An Actor is a serverless cloud program that runs on the Apify platform. It has two run modes.
In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours,
and optionally produces a well-defined JSON output, datasets with results, or files in key-value store.
In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server.

Apify vocabulary and the platform model are defined once, in the agent quickstart at https://apify.com/agents.md.

## How to integrate an Actor?

If asked about integration, you help developers integrate Actors into their projects.
You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready.

Do not guess an integration path. Every one of them is in the agent quickstart at https://apify.com/agents.md: the Apify MCP server, Agent Skills with the Apify CLI, the JavaScript and Python clients, the REST API, and the account-free path for an agent with no human to sign in. It also carries the rule on stating cost before the first paid run.

For examples already wired to this Actor's own input schema, see the [API](#api) section below.

Each client library has reference documentation the quickstart does not restate: [JavaScript/TypeScript](https://docs.apify.com/api/client/js/docs.md) (`npm install apify-client`) and [Python](https://docs.apify.com/api/client/python/docs.md) (`pip install apify-client`).

# README

## PDF and Image to Clean Text for AI Agents

Give it links to PDFs or images. Get back clean text ready for an AI agent, a RAG pipeline or a search index.

### What it does

- Reads the text built into a PDF, and uses OCR on scanned pages and images.
- Removes repeated headers, footers and page numbers.
- Joins words split across lines and lines split by the page width, and keeps paragraphs.
- Returns one result per file, with optional text per page.

### Input

| Field | What it does | Default |
|---|---|---|
| `files` | Public links to PDF, PNG, JPG, TIFF, WEBP or BMP files, up to 50 MB each | required |
| `ocrMode` | `auto`, `always` or `never` | `auto` |
| `languages` | OCR languages, such as `eng` or `eng+spa`. Included: eng, spa, fra, deu | `eng` |
| `maxPagesPerFile` | Stops at this page, which also caps the cost of a file | 200 |
| `includePages` | Adds the text and method for each page | false |

### Output

```json
{
  "url": "https://example.com/report.pdf",
  "fileName": "report.pdf",
  "fileType": "pdf",
  "pageCount": 12,
  "totalPages": 12,
  "ocrPages": 3,
  "charCount": 18240,
  "text": "Clean text here..."
}
```

A file that fails returns `url` and `error`, and you aren't charged for it.

### Pricing

You pay per page processed, plus a very small start fee per run. The prices are shown on this page. Set a spending limit on the run and it stops when the limit is reached.

### Use it from an AI agent

Apify's MCP server can call this Actor as a tool. Give your agent `https://mcp.apify.com` and allow this Actor.

### FAQ

**Does it work on scanned documents?** Yes, scanned pages go through OCR with Tesseract. Quality depends on the scan, and handwriting and complex tables often come out poorly.

**Are tables kept?** Table text comes through, but rows and columns aren't guaranteed to stay aligned.

**Are my files stored?** Files are deleted when each one finishes. The extracted text stays in the run's dataset under your account, under your retention settings.

**Password-protected PDFs?** They return an error and no charge.

**Can I use private links?** Signed links work. Internal network addresses are blocked.

**How many pages can it handle?** Up to 2,000 per file, with a 50 MB size limit.

**Was this built with AI?** Yes. It was built and is maintained with AI assistance. The text extraction itself uses standard open-source tools, pypdf and Tesseract, not an AI model.

# Actor input Schema

## `files` (type: `array`):

Public links to PDF, PNG, JPG, TIFF, WEBP or BMP files. Up to 50 MB each.

## `ocrMode` (type: `string`):

auto reads scanned pages with OCR and uses the embedded text elsewhere. always runs OCR on every page. never uses embedded text only.

## `languages` (type: `string`):

Tesseract language codes, such as eng or eng+spa. This build includes eng, spa, fra and deu.

## `maxPagesPerFile` (type: `integer`):

Stops at this page, which also caps the cost of a file.

## `includePages` (type: `boolean`):

Adds a pages array with the text and method for each page.

## Actor input object example

```json
{
  "files": [
    {
      "url": "https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf"
    }
  ],
  "ocrMode": "auto",
  "languages": "eng",
  "maxPagesPerFile": 200,
  "includePages": false
}
```

# Actor output Schema

## `results` (type: `string`):

No description

# API

You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup.

## JavaScript example

```javascript
import { ApifyClient } from 'apify-client';

// Initialize the ApifyClient with your Apify API token
// Replace the '<YOUR_API_TOKEN>' with your token
const client = new ApifyClient({
    token: '<YOUR_API_TOKEN>',
});

// Prepare Actor input
const input = {
    "files": [
        {
            "url": "https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf"
        }
    ]
};

// Run the Actor and wait for it to finish
const run = await client.actor("obkk/pdf-image-to-clean-text").call(input);

// Fetch and print Actor results from the run's dataset (if any)
console.log('Results from dataset');
console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
const { items } = await client.dataset(run.defaultDatasetId).listItems();
items.forEach((item) => {
    console.dir(item);
});

// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs

```

## Python example

```python
from apify_client import ApifyClient

# Initialize the ApifyClient with your Apify API token
# Replace '<YOUR_API_TOKEN>' with your token.
client = ApifyClient("<YOUR_API_TOKEN>")

# Prepare the Actor input
run_input = { "files": [{ "url": "https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf" }] }

# Run the Actor and wait for it to finish
run = client.actor("obkk/pdf-image-to-clean-text").call(run_input=run_input)

# Fetch and print Actor results from the run's dataset (if there are any)
print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}")
for item in client.dataset(run.default_dataset_id).iterate_items():
    print(item)

# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start

```

## CLI example

```bash
echo '{
  "files": [
    {
      "url": "https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf"
    }
  ]
}' |
apify call obkk/pdf-image-to-clean-text --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,obkk/pdf-image-to-clean-text"
        }
    }
}
```

The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an `Authorization: Bearer <APIFY_API_TOKEN>` header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations).

## OpenAPI specification

Download the OpenAPI definition: https://api.apify.com/v2/actors/781mG1bQWfETPhghL/builds/lknrorlIUxw5Dt8LE/openapi.json