JSON Output

Provides patterns for generating JSON output.

Writing JSON Files

import json
from pathlib import Path
from typing import Any
from datetime import datetime

def write_json(filepath: str, data: Any, indent: int = 2):
    """Write data to JSON file with formatting."""
    Path(filepath).parent.mkdir(parents=True, exist_ok=True)

    def json_serializer(obj):
        if isinstance(obj, datetime):
            return obj.isoformat()
        raise TypeError(f"Object of type {type(obj)} is not JSON serializable")

    with open(filepath, 'w', encoding='utf-8') as f:
        json.dump(data, f, indent=indent, default=json_serializer, ensure_ascii=False)

Report Generation

from datetime import datetime
from typing import List, Dict, Any

def create_aggregation_report(
    results: List[Dict],
    sources: List[str],
    query: str
) -> Dict[str, Any]:
    """Create a structured aggregation report."""
    return {
        "report_type": "content_aggregation",
        "generated_at": datetime.now().isoformat(),
        "query": query,
        "sources": sources,
        "summary": {
            "total_results": len(results),
            "unique_domains": len(set(
                result.get("url", "").split("/")[2] if "://" in result.get("url", "") else ""
                for result in results
            )),
            "avg_score": sum(r.get("computed_score", 0) for r in results) / len(results) if results else 0
        },
        "results": results
    }

Structured Output

def format_result(result: Dict, include_content: bool = True) -> Dict:
    """Format a single result for output."""
    formatted = {
        "url": result.get("url"),
        "title": result.get("title"),
        "description": result.get("description"),
        "score": round(result.get("computed_score", 0), 3),
        "source": result.get("source"),
        "metadata": {
            "author": result.get("author"),
            "published_date": result.get("published_date"),
            "domain": result.get("url", "").split("/")[2] if "://" in result.get("url", "") else ""
        }
    }

    if include_content:
        formatted["content_preview"] = result.get("content", "")[:500]

    return formatted

def format_results(results: List[Dict], include_content: bool = True) -> List[Dict]:
    """Format all results for output."""
    return [format_result(r, include_content) for r in results]