Extract PDF extracts structured data from PDFs and images, including tables, OCR text, images, and stamps, built on ComPDF data extraction and AI document extraction capabilities with exports to JSON, XML, CSV, Excel, TXT, or HTML for automation, analytics, and LLM workflows. It suits triggers such as “extract pdf text,” “extract tables from pdf,” “pdf ocr,” “pdf to json,” “parse invoice pdf,” and “extract data from pdf.” Example queries include “Extract all tables from this PDF and export them to CSV,” “Parse this invoice PDF and return the amount, vendor, and tax ID,” and “OCR this scanned PDF and return structured JSON.”

Install

openclaw skills install @compdf-youna/extract-pdf-compdf