Automated News Scraping and Summarization Platform

Rami Borni

Backend Engineer
Software Engineer
Web Developer
Django
LangChain
Next.js

Overview

Client: News Company

Link: No link - This is internal service in the company and shouldn't be shared

Project Description

Develop a platform that uses AI to automatically scrape specific news, summarize, and rephrase them. The platform allows admin control over the news selection process and displays results in a dedicated RSS feed for each news module.

Objectives

Automate News Scraping: Utilize AI to autonomously choose and scrape relevant news articles.
Summarization and Rephrasing: Implement AI algorithms to summarize and rephrase the scraped news articles.
Admin Control: Provide an admin dashboard to manage news modules, sources, and keywords.
Manual Selection: Allow admins to manually select news articles if desired.
RSS Feed Generation: Output summarized news in specific RSS feeds for each module.

Technology Stack

Frontend: React, Next.js
Backend: Python, Django
Database: MongoDB
AI Integration: Langchain

Features

News Module Creation:
Admin creates a news module.
Admin specifies news sources and keywords for semantic search.
2. AI-Powered News Scraping:
The AI identifies and scrapes relevant news articles based on the specified keywords and sources.
Semantic search ensures that the AI understands the context and meaning of the keywords.
3. Summarization and Rephrasing:
AI algorithms summarize the content of the scraped articles.
AI rephrases the summarized content to ensure originality and coherence.
4. Admin Dashboard:
User-friendly interface for creating and managing news modules.
Options to activate or deactivate auto mode for each module.
Table view of all fetched news with options for manual selection.
5. Manual News Selection:
In manual mode, admins can review and select news articles for summarization and rephrasing.
This allows for greater control over the content that gets published.
6. RSS Feed Generation:
Each news module has a dedicated RSS feed.
Summarized and rephrased news articles are published in the respective RSS feeds.

My Role

System Development:
Developed the entire system from scratch, including backend, dashboard, and deployment.
Ensured the platform operates smoothly and efficiently.
Integrated AI for effective news scraping, summarization, and rephrasing.
Implemented a user-friendly and intuitive dashboard for easy system management.
2. Performance Optimization:
Ensured fast and reliable performance of the platform.
Optimized AI algorithms for accurate and relevant news selection and summarization.
3. UI/UX Design:
Designed an intuitive dashboard UI/UX to facilitate easy control and management by the admin.
4. Deployment:
Successfully deployed the platform, ensuring it is fully operational and meets all client requirements.

Outcome

The platform effectively automates the news scraping and summarization process, providing a valuable tool for the news company to manage and disseminate news efficiently. Admins have complete control over the news selection process, and the generated RSS feeds ensure easy distribution of the summarized content.
Partner With Rami
View Services

More Projects by Rami