first commit

This commit is contained in:
2026-01-26 12:34:00 +01:00
commit e64465a7e6
29 changed files with 2952 additions and 0 deletions

153
src/main.py Normal file
View File

@@ -0,0 +1,153 @@
"""Main orchestrator for News Agent"""
import asyncio
from datetime import datetime
from .config import get_config
from .logger import setup_logger, get_logger
from .storage.database import Database
from .storage.models import DigestEntry
from .aggregator.rss_fetcher import RSSFetcher
from .ai.client import OpenRouterClient
from .ai.filter import ArticleFilter
from .ai.summarizer import ArticleSummarizer
from .email.generator import EmailGenerator
from .email.sender import EmailSender
async def main():
"""Main execution flow"""
# Setup logging
setup_logger()
logger = get_logger()
logger.info("=" * 60)
logger.info("News Agent starting...")
logger.info("=" * 60)
try:
# Load configuration
config = get_config()
# Initialize database
db = Database(config.database.path)
await db.initialize()
# Clean up old articles
await db.cleanup_old_articles(config.database.retention_days)
# Initialize RSS fetcher
fetcher = RSSFetcher()
# Fetch articles from all sources
logger.info(f"Fetching from {len(config.rss_sources)} RSS sources...")
articles = await fetcher.fetch_all(config.rss_sources)
if not articles:
logger.warning("No articles fetched from any source")
await fetcher.close()
return
# Save articles to database (deduplication)
new_articles_count = await db.save_articles(articles)
logger.info(
f"Saved {new_articles_count} new articles (filtered {len(articles) - new_articles_count} duplicates)"
)
await fetcher.close()
# Get unprocessed articles
unprocessed = await db.get_unprocessed_articles()
if not unprocessed:
logger.info("No new articles to process")
return
logger.info(f"Processing {len(unprocessed)} new articles with AI...")
# Initialize AI components
ai_client = OpenRouterClient()
filter_ai = ArticleFilter(ai_client)
summarizer = ArticleSummarizer(ai_client)
# Filter articles by relevance
logger.info("Filtering articles by relevance...")
filtered_articles = await filter_ai.filter_articles(
unprocessed, max_articles=config.ai.filtering.max_articles
)
if not filtered_articles:
logger.warning("No relevant articles found after filtering")
# Mark all as processed but not included
for article in unprocessed:
await db.update_article_processing(
article.id, relevance_score=0.0, ai_summary="", included=False
)
return
logger.info(f"Selected {len(filtered_articles)} relevant articles")
# Summarize filtered articles
logger.info("Generating AI summaries...")
digest_entries = []
for article, score in filtered_articles:
summary = await summarizer.summarize(article)
# Update database
await db.update_article_processing(
article.id, relevance_score=score, ai_summary=summary, included=True
)
# Create digest entry
entry = DigestEntry(
article=article,
relevance_score=score,
ai_summary=summary,
category=article.category,
)
digest_entries.append(entry)
# Mark remaining unprocessed articles as processed but not included
processed_ids = {article.id for article, _ in filtered_articles}
for article in unprocessed:
if article.id not in processed_ids:
await db.update_article_processing(
article.id, relevance_score=0.0, ai_summary="", included=False
)
# Generate email
logger.info("Generating email digest...")
generator = EmailGenerator()
date_str = datetime.now().strftime("%A, %B %d, %Y")
subject = config.email.subject_template.format(date=date_str)
html_content, text_content = generator.generate_digest_email(
digest_entries, date_str, subject
)
# Send email
logger.info("Sending email...")
sender = EmailSender()
success = sender.send(subject, html_content, text_content)
if success:
logger.info("=" * 60)
logger.info(f"Daily digest sent successfully with {len(digest_entries)} articles!")
logger.info("=" * 60)
else:
logger.error("Failed to send email")
except Exception as e:
logger.error(f"Fatal error in main execution: {e}", exc_info=True)
raise
def run():
"""Entry point for command-line execution"""
asyncio.run(main())
if __name__ == "__main__":
run()