ID to JSON Parser

ID to JSON Parser

Extract structured JSON from any ID document image or PDF. Upload a passport, driver's license, or identity card and get back firstName, dateOfBirth, documentNumber, and every other visible field. No OCR setup, no AI prompt engineering required.

Manual data entry from ID documents is slow and error-prone. This Actor reads uploaded images and PDFs of passports, driver's licenses, and identity cards, then returns the extracted information as clean JSON. It uses AI to identify and parse all relevant fields automatically, so you do not need to configure OCR engines or write extraction rules.

Who uses it	What they scrape ID to JSON Parser for
KYC analysts	Automate identity verification data entry from customer documents.
HR teams	Extract employee details from uploaded ID cards during onboarding.
Travel agencies	Pull passport information into booking systems without manual typing.
Developers	Integrate ID parsing into apps that need structured user identity data.

What it does

This Actor collects structured data from uploaded ID document images or PDFs and returns each document as a flat JSON object.

• 🆔 Multi-document support: Passports, driver's licenses, national ID cards, and other government-issued documents.
• 📄 Image and PDF input: Accepts common image formats and PDF files, processing each page automatically.
• 🤖 AI-powered extraction: Identifies and extracts all visible fields without manual template configuration.
• 🎯 Custom field targeting: Optionally specify exact fields like firstName, dateOfBirth, or documentNumber to extract.
• 🧠 Custom AI guidance: Provide a system prompt to steer the AI toward specific extraction behavior when needed.

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

What you can do with ID to JSON Parser data

🛂 Automate customer onboarding.

KYC teams upload passport scans and receive structured JSON with full name, birth date, and document number for CRM entry.

👥 Speed up employee data collection.

HR departments batch-process driver's license images during hiring to populate payroll systems with verified identity fields.

✈️ Digitize travel document handling.

Travel agencies extract passport details from uploaded images to pre-fill booking forms and reduce manual typing errors.

🔌 Integrate ID parsing into your app.

Developers call this Actor via API to add ID-to-JSON conversion to user verification flows without building their own OCR pipeline.

Why choose this scraper

	What you get
No OCR setup	The AI handles text recognition and field mapping, so you skip OCR configuration entirely.
Structured JSON output	Every document returns a consistent JSON object with field names and values.
Handles multiple IDs	Process batches of documents in a single run, up to the record limit you set.
Custom extraction	Request specific fields or guide the AI with a custom system prompt for niche documents.

How it compares

No other Store actor targets ID to JSON Parser the same way, so the honest comparison is with the alternatives teams actually weigh.

	ID to JSON Parser	Build it in-house	By hand
Setup	Run it now, zero config	Days of engineering	None, but hours per pull
When ID to JSON Parser 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

Upload one or more ID images or PDFs, optionally specify which fields to extract, and set a maximum number of records per run. The Input tab lists every parameter.

A first run with the defaults:

{
  "idImage": [
    "https://api.apify.com/v2/key-value-stores/f5X3J3PwgPxQjikSi/records/7.webp"
  ],
  "maxItems": 10
}

A larger pull:

{
  "idImage": [
    "https://api.apify.com/v2/key-value-stores/f5X3J3PwgPxQjikSi/records/7.webp"
  ],
  "maxItems": 200
}

Pricing

Pay-per-result: $0.03 per result collected. You pay only for the results written to your dataset.

Results collected	Approximate cost
100 results	$3.00
1,000 results	$30.00
10,000 results	$300.00

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 ID 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 ID to JSON Parser 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/id-to-json-parser"

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

Troubleshooting

The extracted JSON is missing some fields I expected.

Try using the fieldsToExtract input to explicitly list the fields you need. You can also provide a systemPrompt to guide the AI toward those specific fields.

The Actor returns no results for my uploaded image.

Check that the image is clear and the ID document is fully visible. Blurry or partially cropped documents may cause extraction failures. Also verify the file format is supported.

Processing is slow for many documents.

Large batch runs take time because each document is processed individually. Reduce the maxItems value or split your uploads into smaller runs for faster turnaround.

The AI misreads some characters on my document.

Character recognition accuracy depends on image quality. Use higher-resolution scans and ensure good lighting. A custom systemPrompt can sometimes help the AI focus on ambiguous fields.

FAQ

Question	Answer
What types of ID documents can it parse?	It handles passports, driver's licenses, national identity cards, and similar government-issued documents. The AI automatically adapts to different layouts and languages.
Can I process PDFs with multiple pages?	Yes, upload PDF files and the Actor will process each page. If a PDF contains multiple ID documents, each will be extracted as a separate record.
Do I need to specify which fields to extract?	No, the fieldsToExtract input is optional. If left empty, the AI will identify and return all important fields it finds on the document.
What output format does it produce?	The Actor returns a dataset of JSON objects, one per document. You can export the dataset as JSON, CSV, Excel, or XML from Apify.
Can I guide the AI with a custom prompt?	Yes, use the systemPrompt input to give the AI specific instructions, such as focusing on certain fields or handling documents in a particular language.
Is there a limit on how many documents I can process?	You set the maxItems limit per run. Each uploaded file or image counts as one record unless a PDF contains multiple IDs.
Does it work with handwritten IDs?	The AI performs best on printed text. Handwritten documents may produce less accurate results depending on legibility.
What languages does it support?	The AI can extract text from documents in many languages, including English, Spanish, French, German, Chinese, Arabic, and others. Accuracy may vary by script and layout.
Can I use this for identity verification?	This Actor extracts data from ID images but does not verify authenticity. Use the structured output as input to your own verification processes.
How do I upload files to the Actor?	Use the file upload input in the Apify console or send file URLs via the API. Both local uploads and remote URLs are supported.

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 Apify. 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.