extract-pdf-transactions

Extract transactions from PDF bank statements by using table detection to identify transaction data, then parse dates, descriptions, amounts, and balances into structured records. This Skill automates the extraction process for multi-page PDFs and outputs a CSV with standardized columns ready for analysis.

Yes, this Skill processes multi-page PDFs and supports batch processing of multiple statement files. It auto-detects transaction tables across all pages and consolidates results into a single CSV export with consistent date, description, amount, balance, category, and source_file fields.

Yes, this Skill implements a completely local workflow using pdfplumber and pandas. All processing happens on your machine with no external API calls, making it suitable for sensitive financial data that must remain offline.

This Skill extracts from PDF bank and credit card statements and outputs to CSV format. It handles diverse statement formats from different financial institutions and preserves all parsed transaction fields in the CSV export.

The Skill applies table detection to identify transaction layouts across diverse bank and credit card statement formats. It parses and normalizes dates, amounts, and descriptions regardless of format variation, then validates the data before exporting to CSV.

After parsing, the Skill normalizes and validates extracted transactions, then exports them to CSV with standardized columns: date, description, amount, balance, category, and source_file. The structured output is ready for downstream analysis, import to accounting software, or further processing.