AI
Tool: Document OCR to Structured JSON
Read any document image and return the full OCR text plus clean structured JSON fields using premium AI. Paid Apify plans only.
document-ocr-json-tool.json 200 OK
{ "imageUrl": "https://tesseract.projectnaptha.com/img/eng_bw…", "extractedText": "The quick brown fox jumps over the lazy dog.", "fields": {"language":"English","lineCount":"1"}, "documentType": "text", "observedAt": "2026-07-25T00:17:38.189Z" }
What you get
Every run returns clean, typed records, ready for your CRM, spreadsheet or database.
- One clean record per result, deduped and normalized
- Stable schema in JSON, CSV or Excel, or read it via the Apify API
- Pay per use in the cloud, nothing to install or maintain
Fields it returns
Image UrlExtracted TextFieldsDocument Type
Sample output
A real example record, exactly the shape you receive.
| Image Url | Extracted Text | Fields | Document Type |
|---|---|---|---|
| https://tesseract.projectnaptha.c… | The quick brown fox jumps over th… | {"language":"English","lineCount"… | text |
| https://templates.invoicehome.com… | INVOICE East Repair Inc. 1912 Har… | {"invoiceNumber":"US-001","date":… | invoice |
GET /document-ocr-json-tool
{ "imageUrl": "https://tesseract.projectnaptha.com/img/eng_bw…", "extractedText": "The quick brown fox jumps over the lazy dog.", "fields": {"language":"English","lineCount":"1"}, "documentType": "text", "observedAt": "2026-07-25T00:17:38.189Z" }
Related scrapers
Ready when you are.
Run the scraper live on Apify right now, or have us build one tailored to exactly what you need.