GNewsScraper is a TypeScript package that scrapes article data from Google News based on a keyword or phrase. It returns the results as an array of JSON objects, making it convenient to access and use the scraped information

This repository is part of an NLP course for humanities and cultural studies. This course uses historical newspapers as a source and applies NLP methods to them. NLP tasks: Tokenization, Lemmatization, TF-IDF, Part-of-speech tagging, semantic search with transformers, article extraction and OCR post-correction with LLMs, NER and text classification