Turning a folder of PDFs into a webhook that returns JSON

Описание и применение

Упрощённый рабочий процесс n8n для извлечения структурированных данных из PDF через OCR.space, возвращающий JSON и CSV через веб‑хук.

Задача

Extracting structured data from PDFs at scale without expensive OCR services or custom infrastructure.

Результат

Simplified PDF extraction workflow that eliminates the need for self-hosted OCR infrastructure, reduces cost, and provides structured output via webhook.

Рабочий процесс

• Receive PDF URL or upload via webhook POST
• Send PDF to OCR.space API
• Parse OCR text into structured JSON/CSV using layout heuristics
• Append extraction to Google Sheet (optional)
• Return plain text, JSON, and CSV in webhook response

Доказательства

I ended up solving this with a single n8n workflow instead of a custom service

Источник

OCR.space, which has a genuinely usable free tier (25k requests/month, no card required)

Источник