📰 {source} • {score:.1f}/10
{self.truncate_text(description, 300)}
"""
html += f"""
"""
return html
def format_markdown(self, articles: List[Dict[str, Any]], title: str) -> str:
"""Format digest as clean markdown."""
markdown = f"# {title}\n\n"
markdown += f"*{len(articles)} top AI stories for {datetime.now().strftime('%B %d, %Y')}*\n\n"
for i, article in enumerate(articles, 1):
title_text = article.get('title', 'Untitled')
description = self.clean_text(article.get('description', ''))
source = article.get('source', {}).get('name', 'Unknown')
link = article.get('link', '')
score = article.get('ai_score', {}).get('overall', 0)
markdown += f"## {i}. {title_text}\n\n"
markdown += f"**Source:** {source} | **Score:** {score:.1f}/10\n\n"
if description:
markdown += f"{self.truncate_text(description, 300)}\n\n"
if link:
markdown += f"[Read full article]({link})\n\n"
markdown += "---\n\n"
markdown += f"*Generated on {datetime.now().strftime('%B %d, %Y at %H:%M UTC')} by AI News Digest Bot*\n"
return markdown
def format_text(self, articles: List[Dict[str, Any]], title: str) -> str:
"""Format digest as plain text."""
text = f"{title}\n"
text += "=" * len(title) + "\n\n"
for i, article in enumerate(articles, 1):
title_text = article.get('title', 'Untitled')
description = self.clean_text(article.get('description', ''))
source = article.get('source', {}).get('name', 'Unknown')
link = article.get('link', '')
score = article.get('ai_score', {}).get('overall', 0)
text += f"{i}. {title_text}\n"
text += f"Source: {source} | Score: {score:.1f}/10\n"
if description:
wrapped_desc = textwrap.fill(self.truncate_text(description, 300), width=80)
text += f"{wrapped_desc}\n"
if link:
text += f"Link: {link}\n"
text += "-" * 80 + "\n\n"
text += f"Generated on {datetime.now().strftime('%B %d, %Y at %H:%M UTC')}\n"
text += "Powered by AI News Digest Bot\n"
return text
def format_article_discord(self, article: Dict[str, Any]) -> str:
"""Format a single article for Discord."""
emoji = self.get_article_emoji(article)
title = article.get('title', 'Untitled')
source = article.get('source', {}).get('name', 'Unknown')
score = article.get('ai_score', {}).get('overall', 0)
link = article.get('link', '')
formatted = f"{emoji} **[{title}]({link})**\n"
formatted += f"📊 {score:.1f}/10 • 📰 {source}\n"
# Add description if available
description = article.get('description', '')
if description:
clean_desc = self.clean_text(description)
short_desc = self.truncate_text(clean_desc, 200)
formatted += f"*{short_desc}*\n"
return formatted
def get_article_emoji(self, article: Dict[str, Any]) -> str:
"""Get appropriate emoji for article based on category and content."""
category = article.get('ai_score', {}).get('category', 'other')
# Check for specific keywords in title for more specific emojis
title = article.get('title', '').lower()
if any(word in title for word in ['gpt', 'claude', 'gemini', 'llm', 'language model']):
return '🧠'
elif any(word in title for word in ['funding', 'investment', 'billion', 'million']):
return '💰'
elif any(word in title for word in ['breakthrough', 'achieves', 'first time']):
return '⚡'
elif any(word in title for word in ['regulation', 'law', 'government']):
return '⚖️'
else:
return self.emoji_map.get(category, '📰')
def clean_text(self, text: str) -> str:
"""Clean text by removing HTML tags and normalizing whitespace."""
if not text:
return ""
# Remove HTML tags
text = re.sub(r'<[^>]+>', '', text)
# Normalize whitespace
text = re.sub(r'\s+', ' ', text)
# Remove extra punctuation
text = re.sub(r'\.{2,}', '...', text)
return text.strip()
def truncate_text(self, text: str, max_length: int) -> str:
"""Truncate text to specified length with ellipsis."""
if not text or len(text) <= max_length:
return text
# Try to break at word boundaries
truncated = text[:max_length]
if ' ' in truncated:
truncated = truncated.rsplit(' ', 1)[0]
return truncated + "..."
def create_summary_stats(self, articles: List[Dict[str, Any]]) -> Dict[str, Any]:
"""Create summary statistics for the digest."""
if not articles:
return {}
stats = {
'total_articles': len(articles),
'avg_score': sum(article.get('ai_score', {}).get('overall', 0) for article in articles) / len(articles),
'top_sources': {},
'categories': {},
'score_distribution': {'high': 0, 'medium': 0, 'low': 0}
}
for article in articles:
# Source statistics
source = article.get('source', {}).get('name', 'Unknown')
stats['top_sources'][source] = stats['top_sources'].get(source, 0) + 1
# Category statistics
category = article.get('ai_score', {}).get('category', 'other')
stats['categories'][category] = stats['categories'].get(category, 0) + 1
# Score distribution
score = article.get('ai_score', {}).get('overall', 0)
if score >= 8:
stats['score_distribution']['high'] += 1
elif score >= 6:
stats['score_distribution']['medium'] += 1
else:
stats['score_distribution']['low'] += 1
return stats
def main():
"""Main function for command-line usage."""
import argparse
parser = argparse.ArgumentParser(description='Compile AI news digest from filtered articles')
parser.add_argument('input', help='Input JSON file with filtered articles')
parser.add_argument('--format', choices=['discord', 'telegram', 'email', 'markdown', 'text'],
default='markdown', help='Output format')
parser.add_argument('--output', help='Output file path')
parser.add_argument('--title', help='Custom title for the digest')
args = parser.parse_args()
# Load articles
try:
with open(args.input, 'r') as f:
data = json.load(f)
articles = data.get('articles', [])
except FileNotFoundError:
print(f"Error: Input file not found: {args.input}")
return
except json.JSONDecodeError as e:
print(f"Error parsing input file: {e}")
return
# Compile digest
compiler = DigestCompiler()
digest = compiler.compile_digest(articles, args.format, args.title)
# Save output
if args.output:
try:
with open(args.output, 'w', encoding='utf-8') as f:
f.write(digest)
print(f"Digest saved to: {args.output}")
except Exception as e:
print(f"Error saving digest: {e}")
else:
print(digest)
# Print stats
stats = compiler.create_summary_stats(articles)
print(f"\nDigest Stats:")
print(f"- {stats.get('total_articles', 0)} articles")
print(f"- Average score: {stats.get('avg_score', 0):.1f}/10")
print(f"- Top category: {max(stats.get('categories', {}).items(), key=lambda x: x[1])[0] if stats.get('categories') else 'None'}")
if __name__ == "__main__":
main()