This project aims to extract RDF shapes by mining Wikipedia abstracts. The Wikipedia abstracts are supposed to be provided with a local XML Wikipedia dump. Depending the type of extractor you use, you may need to provide some other files too.
The main classes of this repository are LarewaExtractor and FredExtractor. You can find both in the wikipedia_shexer package. Read the documentation within the code of these classes to run the extractors.
You can find some examples of other classes of this project within the package playground.
NOTE: This is a work-in-progress project. Some of the code plublished here is still unstable and incomplete. If you are interested in this software and you run into any issue, contact me and I'll be happy to help: fernandezalvdaniel@uniovi.es