Skip to content

Latest commit

 

History

1 Commit

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 
 
 

Repository files navigation

🌐 Multilingual FinNews Agent

An AI-powered agent that scrapes financial news and generates a 3-point summary with market sentiment in English, 繁體中文, and 日本語 — built for fast-paced, cross-border investment teams.

💡 Why OpenRouter?

OpenAI's official API is geo-blocked in Hong Kong. This project uses OpenRouter — an OpenAI-compatible API gateway — so it runs directly in HK without a VPN, and can switch between models (Llama, GPT, Gemini, Claude) by changing one line in .env.

✨ Features

  • 🕷️ Web Scraping: Extracts article body text with requests + BeautifulSoup4 (with anti-noise filtering)
  • 🤖 LLM Analysis: 3-bullet summary + Bullish/Bearish/Neutral sentiment classification
  • 🌏 Trilingual Output: English / Traditional Chinese / Japanese in one pass
  • 🧪 Demo Mode: Built-in sample article for instant testing without scraping
  • 💾 Auto-report: Saves every run as a timestamped Markdown file in outputs/

🛠️ Tech Stack

Python · OpenRouter (OpenAI-compatible API) · BeautifulSoup4 · Prompt Engineering

🚀 Quick Start

pip install -r requirements.txt
cp .env.example .env   # 然後喺 .env 填入你嘅 OpenRouter API Key
python fin_news_agent.py --demo
python fin_news_agent.py "https://finance.yahoo.com/news/..."

About

An LLM-powered financial data agent that automates web scraping and generates aligned, production-grade 3-point market sentiment summaries in English, Traditional Chinese, and Japanese via an OpenRouter-complianced routing gateway.

Topics

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages