From 1c0926a7f05da991d2918b5c1f0cd0f4061edc58 Mon Sep 17 00:00:00 2001
From: Dongho Kim <dongho@ekstrah.com>
Date: Thu, 20 Nov 2025 19:15:41 +0100
Subject: [PATCH] update

---
 backend/add_categories_to_feeds.py | 77 ++++++++++++++++++++++++++++++
 backend/check_categories.py        | 60 +++++++++++++++++++++++
 2 files changed, 137 insertions(+)
 create mode 100644 backend/add_categories_to_feeds.py
 create mode 100644 backend/check_categories.py

diff --git a/backend/add_categories_to_feeds.py b/backend/add_categories_to_feeds.py
new file mode 100644
index 0000000..a094df2
--- /dev/null
+++ b/backend/add_categories_to_feeds.py
@@ -0,0 +1,77 @@
+#!/usr/bin/env python
+"""
+Script to add categories to existing RSS feeds
+"""
+from pymongo import MongoClient
+from config import Config
+
+client = MongoClient(Config.MONGODB_URI)
+db = client[Config.DB_NAME]
+rss_feeds_collection = db['rss_feeds']
+
+print("\n" + "="*70)
+print("📡 Adding Categories to RSS Feeds")
+print("="*70)
+
+# Get all feeds
+all_feeds = list(rss_feeds_collection.find())
+print(f"\nFound {len(all_feeds)} RSS feeds")
+
+# Category mapping based on feed names/URLs
+category_mapping = {
+    'münchen': 'local',
+    'munich': 'local',
+    'lokales': 'local',
+    'sport': 'sports',
+    'fussball': 'sports',
+    'fc bayern': 'sports',
+    'wissenschaft': 'science',
+    'science': 'science',
+    'tech': 'science',
+    'technologie': 'science',
+}
+
+updated = 0
+for feed in all_feeds:
+    name = feed.get('name', '').lower()
+    url = feed.get('url', '').lower()
+    current_category = feed.get('category')
+    
+    # Skip if already has a category
+    if current_category:
+        print(f"  ✓ {feed['name']}: Already has category '{current_category}'")
+        continue
+    
+    # Try to determine category from name or URL
+    detected_category = 'general'  # Default
+    
+    for keyword, category in category_mapping.items():
+        if keyword in name or keyword in url:
+            detected_category = category
+            break
+    
+    # Update the feed
+    rss_feeds_collection.update_one(
+        {'_id': feed['_id']},
+        {'$set': {'category': detected_category}}
+    )
+    
+    print(f"  ✓ {feed['name']}: Set category to '{detected_category}'")
+    updated += 1
+
+print("\n" + "="*70)
+print("📊 Summary")
+print("="*70)
+print(f"✓ Updated: {updated} feeds")
+print(f"✓ Already had categories: {len(all_feeds) - updated} feeds")
+print("="*70 + "\n")
+
+# Show final category distribution
+print("Category distribution:")
+categories = rss_feeds_collection.aggregate([
+    {'$group': {'_id': '$category', 'count': {'$sum': 1}}}
+])
+for cat in categories:
+    print(f"  {cat['_id']}: {cat['count']} feeds")
+
+print("\n✅ Done! Now run the migration script to update subscriber categories.")
diff --git a/backend/check_categories.py b/backend/check_categories.py
new file mode 100644
index 0000000..924171b
--- /dev/null
+++ b/backend/check_categories.py
@@ -0,0 +1,60 @@
+#!/usr/bin/env python
+"""
+Check what categories exist in RSS feeds and articles
+"""
+from pymongo import MongoClient
+from config import Config
+
+client = MongoClient(Config.MONGODB_URI)
+db = client[Config.DB_NAME]
+
+print("\n" + "="*70)
+print("📊 Category Analysis")
+print("="*70)
+
+# Check RSS feed categories
+print("\n🔹 RSS Feed Categories:")
+rss_feeds_collection = db['rss_feeds']
+feed_categories = rss_feeds_collection.distinct('category')
+print(f"  Unique categories: {feed_categories}")
+print(f"  Total: {len(feed_categories)} categories")
+
+# Count feeds per category
+print("\n  Feeds per category:")
+for cat in feed_categories:
+    count = rss_feeds_collection.count_documents({'category': cat})
+    feeds = list(rss_feeds_collection.find({'category': cat}, {'name': 1, '_id': 0}))
+    print(f"    {cat}: {count} feeds")
+    for feed in feeds:
+        print(f"      - {feed['name']}")
+
+# Check article categories
+print("\n🔹 Article Categories:")
+articles_collection = db['articles']
+article_categories = articles_collection.distinct('category')
+print(f"  Unique categories: {article_categories}")
+print(f"  Total: {len(article_categories)} categories")
+
+# Count articles per category
+print("\n  Articles per category:")
+for cat in article_categories:
+    count = articles_collection.count_documents({'category': cat})
+    with_summary = articles_collection.count_documents({'category': cat, 'summary': {'$exists': True, '$ne': None}})
+    print(f"    {cat}: {count} articles ({with_summary} with summaries)")
+
+# Check subscriber categories
+print("\n🔹 Subscriber Categories:")
+subscribers_collection = db['subscribers']
+total_subs = subscribers_collection.count_documents({'status': 'active'})
+print(f"  Total active subscribers: {total_subs}")
+
+# Sample a few subscribers to see their categories
+sample_subs = list(subscribers_collection.find({'status': 'active'}, {'email': 1, 'categories': 1, '_id': 0}).limit(5))
+print("\n  Sample subscriber preferences:")
+for sub in sample_subs:
+    cats = sub.get('categories', 'None')
+    print(f"    {sub['email']}: {cats}")
+
+print("\n" + "="*70)
+print("✅ Analysis Complete")
+print("="*70 + "\n")