NewsArchiverV2/ap_processor.py

#!/usr/bin/env python3
"""AP News Processor for NewsArchiver - Phase 2.6

Processes AP News front page to extract article URLs and archive them.
Uses direct HTML parsing since AP doesn't provide RSS feeds.
"""

import argparse
import json
import logging
import re
import sys
import time
from datetime import datetime
from pathlib import Path
from typing import List

try:
    import requests
except ImportError:
    print("WARNING: requests not installed. URL fetching may not work.")
    print("Install with: pip install requests")
    requests = None

try:
    import sqlite3
except ImportError:
    print("ERROR: sqlite3 is required (should be built-in)")
    sys.exit(1)

try:
    import storage_manager
except ImportError:
    print("ERROR: storage_manager module not found")
    sys.exit(1)

try:
    from rss_processor import is_duplicate
except ImportError:
    print("ERROR: rss_processor module not found")
    sys.exit(1)

SCRIPT_DIR = Path(__file__).parent
ARCHIVE_DIR = SCRIPT_DIR / 'archival_data'
ARCHIVE_DIR.mkdir(exist_ok=True)

logging.basicConfig(
    level=logging.INFO,
    format='%(asctime)s - %(levelname)s - %(message)s',
    handlers=[
        logging.StreamHandler(sys.stdout),
        logging.FileHandler(ARCHIVE_DIR / 'processing.log', encoding='utf-8')
    ]
)
logger = logging.getLogger(__name__)


def fetch_ap_frontpage(timeout: int = 30) -> str:
    """Fetch AP News front page HTML.
    
    Args:
        timeout: Request timeout in seconds
        
    Returns:
        HTML string or empty string on failure
    """
    if requests is None:
        logger.error("requests library not available")
        return ""
    
    url = "https://apnews.com"
    
    try:
        headers = {
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36'
        }
        response = requests.get(url, timeout=timeout, headers=headers)
        response.raise_for_status()
        
        logger.info("Fetched AP front page: %s", url)
        return response.text
        
    except Exception as e:
        logger.error("Failed to fetch AP front page: %s", str(e))
        return ""


def extract_article_links(html: str) -> List[str]:
    """Extract AP article URLs from HTML.
    
    Args:
        html: Raw HTML string
        
    Returns:
        List of unique article URLs
    """
    pattern = r'href="https://apnews\.com/article/[^"]*"'
    matches = re.findall(pattern, html)
    
    urls = []
    for match in matches:
        url = match.replace('href="', '').replace('"', '')
        if url not in urls:
            urls.append(url)
    
    logger.info("Extracted %d unique article links", len(urls))
    return urls


def process_ap_articles(
    output_dir: Path,
    db_path: Path = ARCHIVE_DIR / 'cache.db',
    dry_run: bool = False
) -> dict:
    """Process AP News articles from front page.
    
    Args:
        output_dir: Output directory for archived content
        db_path: SQLite cache database path
        dry_run: If True, preview without archiving
        
    Returns:
        Dictionary with results summary
    """
    results = {
        'source': 'Associated Press',
        'processed': 0,
        'archived': 0,
        'skipped': 0,
        'failed': 0,
        'urls': []
    }
    
    html = fetch_ap_frontpage()
    if not html:
        logger.error("Failed to fetch AP front page")
        return results
    
    article_urls = extract_article_links(html)
    
    for article_url in article_urls:
        results['processed'] += 1
        results['urls'].append(article_url)
        
        if is_duplicate(article_url, 'Associated Press', db_path):
            logger.debug("Skipping duplicate: %s", article_url[:60])
            results['skipped'] += 1
            continue
        
        if dry_run:
            logger.info("[DRY-RUN] Would archive: %s", article_url[:60])
            results['archived'] += 1
            continue
        
        try:
            from archive_engine import archive_and_extract
            
            extraction_result = archive_and_extract(
                article_url,
                'Associated Press',
                output_dir
            )
            
            if extraction_result['success']:
                results['archived'] += 1
                storage_manager.save_article('Associated Press', extraction_result['article_data'])
            else:
                results['failed'] += 1
                logger.error("Failed to archive %s: %s", article_url[:60], 
                           extraction_result.get('error', 'Unknown error'))
                
        except Exception as e:
            results['failed'] += 1
            logger.error("Error processing %s: %s", article_url[:60], str(e))
        
        time.sleep(0.5)
    
    logger.info("AP processing complete: %d processed, %d archived, %d skipped, %d failed",
                results['processed'], results['archived'], results['skipped'], results['failed'])
    
    return results


def main():
    parser = argparse.ArgumentParser(description='AP News Front Page Processor')
    parser.add_argument('--output', type=Path, default=ARCHIVE_DIR,
                        help='Output directory for archived content')
    parser.add_argument('--dry-run', action='store_true', help='Preview without archiving')
    parser.add_argument('--verbose', action='store_true', help='Enable verbose logging')
    args = parser.parse_args()
    
    if args.verbose:
        logger.setLevel(logging.DEBUG)
    
    logger.info("=" * 60)
    logger.info("AP News Front Page Processor - Phase 2.6")
    logger.info("=" * 60)
    
    storage_manager.initialize_storage()
    
    results = process_ap_articles(args.output, ARCHIVE_DIR / 'cache.db', args.dry_run)
    
    print("\n" + "=" * 60)
    print("AP NEWS PROCESSING COMPLETE")
    print("=" * 60)
    print(f"Processed: {results['processed']}")
    print(f"Archived: {results['archived']}")
    print(f"Skipped: {results['skipped']}")
    print(f"Failed: {results['failed']}")
    if results['urls']:
        print("\nArticle URLs:")
        for url in results['urls'][:10]:
            print(f"  - {url[:70]}")
        if len(results['urls']) > 10:
            print(f"  ... and {len(results['urls']) - 10} more")
    print("=" * 60)


if __name__ == '__main__':
    main()