PDF to JSON Parser

PDF to JSON Parser

Extract structured JSON data from any PDF file, no manual data entry. Upload one or more PDFs and get clean, organized JSON with all important fields automatically identified. No coding required. Export to CSV, JSON, Excel, or XML.

PDFs are everywhere, but getting data out of them is a pain. Manual copying is slow and error-prone, and many PDFs are scanned or have complex layouts. This tool reads your PDF files and uses AI to extract the key information into a structured JSON format. You get clean, usable data without writing a single line of code.

Who uses it	What they scrape PDF for
Data analysts	Pull data from PDF reports for analysis in Excel or BI tools
Developers	Convert PDF documents into JSON for integration into applications
Business professionals	Extract key information from contracts, invoices, or research papers

What it does

This Actor extracts structured JSON data from PDF files, automatically identifying and returning important fields such as title, author, date, and more.

• 📄 Multiple file upload: Upload one or more PDFs in a single run, each processed automatically.
• 🔍 Custom field extraction: Specify exactly which fields you need (e.g., title, author, price) for targeted results.
• 🧠 AI-powered extraction: Uses a smart default prompt to identify and extract meaningful information from any PDF.
• ⚙️ Custom system prompt: Provide your own instructions to guide the AI for specialized extraction needs.

Results export to CSV, JSON, Excel, or XML, or straight from the API.

What you can do with PDF data

📊 Analyze PDF reports.

Data analysts upload monthly sales reports in PDF and extract key metrics like revenue and growth into JSON for quick analysis in spreadsheets.

📄 Automate invoice processing.

Accounting teams upload invoices and extract fields like invoice number, date, and total amount, feeding them directly into their accounting software.

📚 Digitize research papers.

Researchers convert academic papers into structured JSON to build searchable databases of citations and abstracts.

🛠️ Integrate PDF data into apps.

Developers use the extracted JSON to populate web forms or mobile apps with data from uploaded PDFs, saving users from manual entry.

Why choose this scraper

	What you get
Time-saving	Automatically extracts data from PDFs in seconds, eliminating manual data entry.
Accurate	AI-powered extraction reduces errors compared to manual copying.
Flexible	Works with any PDF, from simple text documents to complex forms and reports.
Structured output	Returns data in a consistent JSON format, ready for further processing.

How it compares

No other Store actor targets PDF the same way, so the honest comparison is with the alternatives teams actually weigh.

	PDF to JSON Parser	Build it in-house	By hand
Setup	Run it now, zero config	Days of engineering	None, but hours per pull
When PDF changes	Maintained for you	You fix it	You re-learn the page
Proxies, retries, anti-bot	Built in	Your problem	Browser only
Output	Fixed JSON schema, CSV/Excel export	Whatever you build	Copy-paste
Cost	Pay per result	Engineering time	Analyst hours

Configure the run

Configure the run by uploading your PDF files and optionally specifying the fields you want extracted. The AI processes each file and returns only the data you need, in a clean JSON format. The Input tab lists every parameter.

A first run with the defaults:

{
  "pdfFile": [
    "https://api.apify.com/v2/key-value-stores/Fy9UrApb6rz0dRBqm/records/sample.pdf?signature=1c819r8xjMsE0Fi3AhqnT"
  ],
  "maxItems": 10
}

A larger pull:

{
  "pdfFile": [
    "https://api.apify.com/v2/key-value-stores/Fy9UrApb6rz0dRBqm/records/sample.pdf?signature=1c819r8xjMsE0Fi3AhqnT"
  ],
  "maxItems": 200
}

Pricing

Pay-per-result: $1 per result collected. You pay only for the results written to your dataset.

Results collected	Approximate cost
100 results	$100.00
1,000 results	$1000.00
10,000 results	$10000.00

New Apify accounts start with $5 in free credit.

Free users

Free-plan runs return up to 10 results as a preview. Upgrade your Apify plan to collect more results per run.

Run it

1. Create a free Apify account with $5 in credit.
2. Open the PDF to JSON Parser.
3. Set your inputs and any filters, then click Start.
4. Export the results as CSV, Excel, JSON, or XML from the Dataset tab.

Run it programmatically through the Apify API (run-sync-get-dataset-items) or the ApifyClient for JavaScript and Python.

Use with AI agents (MCP)

Give an AI agent live access to PDF through the Model Context Protocol. Add the Actor to Claude, Cursor, or any MCP client:

$claude mcp add --transport http apify "https://mcp.apify.com?tools=parseforge/pdf-to-json-parser"

Then prompt it in plain language to run the scraper and read back the results.

Troubleshooting

Why am I getting no results?

Make sure you have uploaded at least one PDF file. If you specified custom fields, ensure they are comma-separated and match the content of the PDF. Also check that the PDF is not password-protected or corrupted.

The extracted fields are not what I expected.

Try specifying the exact fields you need in the 'Fields to Extract' input. You can also provide a custom system prompt to guide the AI more precisely.

The run fails with an error.

Check that your PDF files are valid and not too large. If the issue persists, contact Apify support with the run ID for assistance.

How do I increase the number of documents processed?

Adjust the 'Maximum documents' input to a higher value. Note that processing more documents may increase the cost and time of the run.

FAQ

Question	Answer
What types of PDFs can I upload?	You can upload any PDF file, including scanned documents, forms, reports, and text-based PDFs. The AI handles various layouts and formats.
How does the AI decide which fields to extract?	By default, the AI uses a smart prompt that identifies important fields like title, author, date, and other key information. You can also specify custom fields to extract.
Can I extract data from multiple PDFs at once?	Yes, you can upload multiple PDF files in a single run. Each file is processed individually, and you get a separate JSON output for each.
What is the maximum number of documents I can process?	You can set the maximum number of documents per run, but the practical limit depends on your Apify plan and the size of your PDFs.
Do I need to provide a system prompt?	No, it's optional. If you don't provide one, a smart default prompt is used that extracts meaningful information from the PDF.
What output formats are supported?	The Actor returns data in JSON format, which you can then export to CSV, Excel, XML, or other formats using Apify's export features.
Is my data secure?	Yes, your PDFs are processed securely on Apify's infrastructure. Files are not stored permanently and are deleted after processing.
Can I use this for free?	Apify offers a free tier with limited usage. You can try the Actor with the sample PDF to see how it works before committing to a paid plan.

Related actors

Browse the full ParseForge collection for more scrapers.

🆘 Need help? Email parseforge@protonmail.com with your run ID, your input, and what you expected.

⚠️ Disclaimer. This Actor is unofficial and is not affiliated with, endorsed by, or sponsored by PDF. It collects only publicly available data. You are responsible for using the collected data in compliance with the source's terms of service and applicable data-protection laws, including GDPR, CCPA, and PIPL. Do not use it to collect personal data unlawfully.