skills.rest
DreamMacer
DreamMacerCOMMUNITY
Explore all skills by this author →
GitHub

financial-document-parser

Extract structured data from invoices, receipts, and bank statements in PDF, image, and CSV formats.

Updated Aug 31, 2026
Search Tags:#ocr#pdf extraction#receipt#expense categorization#bank statement#financial report#invoice parsing
One-click install
npx skills add https://github.com/DreamMacer/jiuwenswarm --skill financial-document-parser-dreammacer
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: financial-document-parser
Source: https://github.com/DreamMacer/jiuwenswarm/tree/main/resources/agent/workspace/skills/financial-document-parser
Command: npx skills add https://github.com/DreamMacer/jiuwenswarm --skill financial-document-parser-dreammacer

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pdfplumber, pdf2image, pytesseract.

What problem does it solve? Manually reading invoices, receipts, and bank statements to record amounts, vendors, and line items is slow and error-prone. This Skill automates the extraction of structured financial data from PDFs, scanned images, and CSV statements, then categorizes expenses and generates reports. ## Core Features & Use Cases - Multi-Format Parsing: Extracts fields like invoice number, date, vendor, subtotal, tax, and total from PDF invoices, image receipts (via OCR), and CSV bank statements. - Automatic Expense Categorization: Classifies line items into categories such as Software, Travel, Meals, and Utilities using keyword matching. - Report Generation: Outputs results as Markdown reports, JSON data, or CSV exports, with insights like top spending categories and flags for large transactions. - Use Case: You receive a folder of monthly vendor invoices as PDFs. Run the parser on each file to extract totals and line items, categorize expenses, and export a consolidated CSV for your accounting records. ## Quick Start Ask the AI to parse your financial document by providing its file path, for example: parse the invoice at /path/to/invoice.pdf and show me the expense breakdown.

Frequently Asked Questions about financial-document-parser

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I extract data from PDF invoices in Python?▼

Use pdfplumber to extract text and tables from PDF pages, then apply regex patterns to capture fields like invoice number, date, vendor, and totals. The FinancialParser class in this Skill wraps this workflow and outputs Markdown, JSON, or CSV.

How to parse scanned PDF receipts with OCR?▼

Install pdf2image and pytesseract, plus the tesseract-ocr system package with chi_sim language support. The parser converts PDF pages to images and runs OCR with Chinese and English recognition when direct text extraction fails.

What file formats does this financial parser support?▼

It supports PDF files for invoices and statements, PNG and JPG images for receipts via OCR, and CSV files for bank statements. Other formats raise an unsupported format error.

Does the parser handle Chinese invoices and mixed-language documents?▼

Yes, it recognizes Chinese field labels like 发票号, 合计, and 税额 alongside English patterns, and OCR uses the chi_sim language model. Expense categorization keywords also cover both Chinese and English terms.

Why does text extraction fail on some PDF documents?▼

Scanned PDFs contain images instead of a text layer, so pdfplumber returns empty text. The parser automatically falls back to OCR if pdf2image and pytesseract are installed; otherwise you must install those dependencies first.

What are the limitations of keyword-based expense categorization?▼

Line items are categorized by matching description keywords against a fixed list covering categories like Software, Travel, and Meals. Items with unrecognized descriptions default to Other and require manual reclassification.

Related Skills

Explore More Finance & Accounting Skills→
tiandiyiqitiandiyiqi

invoice-organizer

Extracts invoice data, renames files, and classifies them into folders.

Community
Intermediate
claude-office-skillsclaude-office-skills
368

expense-report

Organize and categorize business expenses into structured reimbursement reports.

Official
Intermediate
tstojeckitstojecki

usd-currency-convert

Convert USD amounts to EUR, PLN, or AUD using historical exchange rates.

Community
Intermediate
wanrengangwanrengang
6

pdf

Automate PDF data extraction, form filling, merging, splitting, rotating, watermarking, password protection, optimization, and OCR using Python libraries pypdf, pdf2image, and Pillow.

Community
Intermediate