Files
Munich-news/backend/check_categories.py
2025-11-20 19:15:41 +01:00

61 lines
2.1 KiB
Python

#!/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")