slight update

news_crawler/crawler_service.py

@@ -54,7 +54,8 @@ def get_active_rss_feeds():
         feeds.append({
             'id': str(feed['_id']),
             'name': feed.get('name', ''),
-            'url': feed.get('url', '')
+            'url': feed.get('url', ''),
+            'category': feed.get('category', 'general')
         })
     return feeds
 
@@ -303,7 +304,7 @@ def extract_main_content(soup):
     return content_text
 
 
-def crawl_rss_feed(feed_url, feed_name, max_articles=10):
+def crawl_rss_feed(feed_url, feed_name, feed_category='general', max_articles=10):
     """
     Crawl articles from an RSS feed
     Returns: dict with statistics
@@ -369,6 +370,7 @@ def crawl_rss_feed(feed_url, feed_name, max_articles=10):
                     'word_count': article_data.get('word_count', 0),
                     'summary_word_count': summary_result['summary_word_count'] if summary_result and summary_result['success'] else None,
                     'source': feed_name,
+                    'category': feed_category,
                     'published_at': extract_published_date(entry) or article_data.get('published_date', ''),
                     'crawled_at': article_data.get('crawled_at'),
                     'summarized_at': datetime.utcnow() if summary_result and summary_result['success'] else None,
@@ -442,6 +444,7 @@ def crawl_all_feeds(max_articles_per_feed=10):
         result = crawl_rss_feed(
             feed['url'],
             feed['name'],
+            feed['category'],
             max_articles=max_articles_per_feed
         )
         total_crawled += result['crawled']