product-spec-pdf-parser

To extract structured FF&E data from PDF product specs, this tool uses PyMuPDF to read text and maps it directly to a 33-column master sheet schema. It processes single or batch PDFs from catalogs and fact sheets into structured rows.

Parsing large PDF catalogs into a Google Sheets master schedule is handled by chunking large files and mapping the extracted text to a structured 33-column schema. Outputs can be routed directly to Google Sheets, CSV, or markdown.

Data extraction from password-protected or image-based PDF spec sheets is supported through specific edge-case handling. The parser uses PyMuPDF for text extraction and applies fallback chunking logic for these complex PDF formats.

Product variants in fact sheets and price books are processed using expand or summarize handling modes. This supports procurement workflows by either detailing every variant or summarizing them within the master product sheet schema.

Populating a master product schedule from multiple PDF configurator files is done by batching the inputs and mapping the PyMuPDF-extracted text to the 33-column data schema. The structured output is then exported to your chosen destination like CSV or Google Sheets.