返回 Skill 列表
extension
分类: 内容与媒体无需 API Key

receipt-scanner

使用OCR和模式匹配从收据图像中提取供应商、日期、项目、金额和总计,并以结构化的JSON格式输出。

person作者: jakexiaohubgithub

Receipt Scanner

Extract structured data from receipt images using OCR.

Features

  • OCR Processing: Extract text from receipt images
  • Data Extraction: Vendor, date, items, amounts, total, tax
  • Pattern Matching: Smart regex patterns for receipts
  • Multi-Format Support: JPG, PNG, PDF receipts
  • JSON/CSV Export: Structured data output
  • Batch Processing: Process multiple receipts

CLI Usage

python receipt_scanner.py --input receipt.jpg --output data.json
python receipt_scanner.py --batch receipts/ --output receipts.csv

Dependencies

  • pytesseract>=0.3.10
  • pillow>=10.0.0
  • opencv-python>=4.8.0
  • pandas>=2.0.0