This project collects news articles from NewsAPI, detects their language, and prepares them for sentiment analysis using PySpark. Results are stored in Firebase Firestore, simulating a cloud-connected data pipeline.
- Fetch news articles using the NewsAPI
- Detect language of each article using
langdetect - Store article titles and sentiment scores in Firebase Firestore
- Load and prepare the dataset using PySpark
langdetect– for language detectionfirebase-admin– to connect with Firebasepyspark– to process and display big datarequests– to access NewsAPIdatetime,getpass– for automation