Skip to content

Computerization/media-filter

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Media Filter (信息鉴别助手)

A mobile application designed to help the elderly identify fake news and misleading information online.

Project Structure

media_filter/
├── backend/          # Python FastAPI Backend
│   ├── main.py       # API Service
│   ├── requirements.txt
│   └── .env.example
├── ios/              # Primary iOS App (Kotlin Multiplatform + SwiftUI)
│   ├── composeApp/   # Shared Kotlin logic
│   └── iosApp/       # SwiftUI app + Share Extension
└── web/              # Web App (Expo)
    ├── app/          # Application Pages (Router)
    └── lib/          # Utilities & API client

Quick Start

1. Start Backend

cd backend

# Create virtual environment
python3 -m venv venv
source venv/bin/activate  # Windows: venv\Scripts\activate

# Install dependencies
pip install -r requirements.txt

# Configure API Key
cp .env.example .env
# Edit .env and fill in your DEEPSEEK_API_KEY
# Note: Currently uses DeepSeek API (OpenAI compatible)

# Start service
python main.py

The backend will run at http://localhost:8000

2. Run iOS App

cd ios
./gradlew :composeApp:linkDebugFrameworkIosSimulatorArm64

Then open ios/iosApp/iosApp.xcodeproj in Xcode and run.

Note: For physical device testing, update baseUrl in ios/composeApp/src/commonMain/kotlin/.../network/MediaFilterApi.kt to your Mac's LAN IP.

3. Run Web App

cd web
npm install
npm run web

The web app will run at http://localhost:8081

Features

  • WeChat Official Account article link analysis
  • Direct text input analysis
  • Credibility assessment (Reliable / Caution / Misleading)
  • Detailed analysis explanations
  • iOS Share Extension (share directly from Safari/WeChat)
  • Dark/Light theme support
  • Douyin video analysis (Planned)
  • WeChat Video Channel analysis (Planned)

Tech Stack

  • Backend: Python, FastAPI, BeautifulSoup, DeepSeek API
  • iOS: Kotlin Multiplatform, SwiftUI, Ktor
  • Web: React Native (Expo), TypeScript

Computerization

Developed by the Computerization club, with the assistance of deep neural networks (to learn more, see AI Lab). We are dedicated to helping the community through technology.

About

Information verification assistant for the elderly

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published