This is a fuzzy receipt parser written in Python. It extracts information like the shop, the date, and the total from scanned receipts. It can work as a standalone script or as part of our IOS and Android application.

The receipt-parser-core library depend on imagemagick. Please install imagemagick with your favorite package manager.

To convert all images from the data/img/ folder to text using tesseract and parse the resulting text files, run

A Dockerfile is available with all dependencies needed to run the program.
To build the image, run

To run it on the sample files, try

By default, running the image will execute the make run command. To use with your own images, run the following:

This project started as a hackathon idea. Read more about it on the trivago techblog. Also read the comments on HackerNews There's also a talk about the project. The library is now available at PyPi.