Newspaper 📰 Website Scraper and translation with llama2 🦙

img

Introduction

This project is a web scraper that scrapes the website of the newspaper, currently supporting German and French newspapers due to the limitation of Ollama API. The project is written in Python and uses the beautifulsoup4 library to scrape the website. The project also uses the Ollama API to translate the scraped articles into English.

Installation

  1. Clone the repository
  2. Install the requirements by:
pip install -r requirements.txt
  1. makw sure you have a valid Ollama API key and put it in the config.py file
  2. Run the main.py file by
python main.py
  1. Enjoy reading the 🗼🥐 news!

Limitation

According to llama2 limited translation support, this model for now only supports the Dutch and French news websites. More to come soon....