database.py

from sqlalchemy import create_engine, Column, Integer, String, Float, Text
from sqlalchemy.ext.declarative import declarative_base
from sqlalchemy.orm import sessionmaker
import os

Base = declarative_base()

class Article(Base):
    __tablename__ = 'articles'
    
    id = Column(Integer, primary_key=True)
    url = Column(String(500), unique=True)
    title = Column(String(500))
    content = Column(Text)
    source = Column(String(100))
    sentiment = Column(Float)
    subjectivity = Column(Float)
    bias = Column(String(50))
    bias_score = Column(Float)

def init_db():
    engine = create_engine('sqlite:///news_dashboard.db')
    Base.metadata.create_all(engine)
    return engine

def save_article(article_data):
    engine = init_db()
    Session = sessionmaker(bind=engine)
    session = Session()
    
    article = Article(
        url=article_data["url"],
        title=article_data["title"],
        content=article_data["content"],
        source=article_data["source"],
        sentiment=article_data["sentiment"],
        subjectivity=article_data["subjectivity"],
        bias=article_data["bias"],
        bias_score=article_data["bias_score"]
    )
    
    try:
        session.add(article)
        session.commit()
    except:
        session.rollback()
        raise
    finally:
        session.close()

def get_articles():
    engine = init_db()
    Session = sessionmaker(bind=engine)
    session = Session()
    
    articles = session.query(Article).all()
    session.close()
    
    return [{
        "id": a.id,
        "url": a.url,
        "title": a.title,
        "content": a.content,
        "source": a.source,
        "sentiment": a.sentiment,
        "subjectivity": a.subjectivity,
        "bias": a.bias,
        "bias_score": a.bias_score
    } for a in articles]

def get_comparable_articles():
    engine = init_db()
    Session = sessionmaker(bind=engine)
    session = Session()
    
    # Get articles with similar titles (potential same events)
    articles = session.query(Article).all()
    session.close()
    
    # Simple grouping by first few words of title
    title_groups = {}
    for a in articles:
        key = ' '.join(a.title.split()[:5]).lower()
        if key not in title_groups:
            title_groups[key] = []
        title_groups[key].append({
            "id": a.id,
            "url": a.url,
            "title": a.title,
            "content": a.content,
            "source": a.source,
            "sentiment": a.sentiment,
            "subjectivity": a.subjectivity,
            "bias": a.bias,
            "bias_score": a.bias_score
        })
    
    # Only return groups with at least 2 articles from different sources
    comparable = []
    for group in title_groups.values():
        if len(group) >= 2 and len(set(a["source"] for a in group)) >= 2:
            comparable.extend(group)
    
    return comparable