This commit is contained in:
2025-11-18 14:45:41 +01:00
parent 2e80d64ff6
commit 84fce9a82c
19 changed files with 2437 additions and 3 deletions

View File

@@ -0,0 +1,239 @@
"""
User Interest Profile API routes for Munich News Daily.
Provides endpoints to view and manage user interest profiles.
"""
from flask import Blueprint, request, jsonify
from services.interest_profiling_service import (
get_user_interests,
get_top_interests,
build_interests_from_history,
decay_user_interests,
get_interest_statistics,
delete_user_interests
)
interests_bp = Blueprint('interests', __name__)
@interests_bp.route('/api/interests/<email>', methods=['GET'])
def get_interests(email):
"""
Get user interest profile.
Args:
email: Email address of the user
Returns:
JSON response with user interest profile
"""
try:
profile = get_user_interests(email)
if not profile:
return jsonify({
'success': False,
'error': 'User profile not found'
}), 404
# Remove MongoDB _id field
if '_id' in profile:
del profile['_id']
return jsonify({
'success': True,
'profile': profile
}), 200
except Exception as e:
return jsonify({
'success': False,
'error': str(e)
}), 500
@interests_bp.route('/api/interests/<email>/top', methods=['GET'])
def get_top_user_interests(email):
"""
Get user's top interests sorted by score.
Query parameters:
top_n: Number of top interests to return (default: 10)
Args:
email: Email address of the user
Returns:
JSON response with top categories and keywords
"""
try:
top_n = request.args.get('top_n', 10, type=int)
top_interests = get_top_interests(email, top_n)
return jsonify({
'success': True,
'email': email,
'top_categories': [
{'category': cat, 'score': score}
for cat, score in top_interests['top_categories']
],
'top_keywords': [
{'keyword': kw, 'score': score}
for kw, score in top_interests['top_keywords']
]
}), 200
except Exception as e:
return jsonify({
'success': False,
'error': str(e)
}), 500
@interests_bp.route('/api/interests/<email>/rebuild', methods=['POST'])
def rebuild_interests(email):
"""
Rebuild user interest profile from click history.
Request body (optional):
{
"days_lookback": 30 // Number of days of history to analyze
}
Args:
email: Email address of the user
Returns:
JSON response with rebuilt profile
"""
try:
data = request.get_json() or {}
days_lookback = data.get('days_lookback', 30)
# Validate days_lookback
if not isinstance(days_lookback, int) or days_lookback < 1:
return jsonify({
'success': False,
'error': 'days_lookback must be a positive integer'
}), 400
profile = build_interests_from_history(email, days_lookback)
# Remove MongoDB _id field
if '_id' in profile:
del profile['_id']
return jsonify({
'success': True,
'message': f'Profile rebuilt from {days_lookback} days of history',
'profile': profile
}), 200
except Exception as e:
return jsonify({
'success': False,
'error': str(e)
}), 500
@interests_bp.route('/api/interests/decay', methods=['POST'])
def decay_interests():
"""
Decay interest scores for inactive users.
Request body (optional):
{
"decay_factor": 0.95, // Multiplier for scores (default: 0.95)
"days_threshold": 7 // Only decay profiles older than N days
}
Returns:
JSON response with decay statistics
"""
try:
data = request.get_json() or {}
decay_factor = data.get('decay_factor', 0.95)
days_threshold = data.get('days_threshold', 7)
# Validate parameters
if not isinstance(decay_factor, (int, float)) or decay_factor <= 0 or decay_factor > 1:
return jsonify({
'success': False,
'error': 'decay_factor must be between 0 and 1'
}), 400
if not isinstance(days_threshold, int) or days_threshold < 1:
return jsonify({
'success': False,
'error': 'days_threshold must be a positive integer'
}), 400
result = decay_user_interests(decay_factor, days_threshold)
return jsonify({
'success': True,
'message': f'Decayed interests for profiles older than {days_threshold} days',
'statistics': result
}), 200
except Exception as e:
return jsonify({
'success': False,
'error': str(e)
}), 500
@interests_bp.route('/api/interests/statistics', methods=['GET'])
def get_statistics():
"""
Get statistics about user interests across all users.
Returns:
JSON response with interest statistics
"""
try:
stats = get_interest_statistics()
return jsonify({
'success': True,
'statistics': stats
}), 200
except Exception as e:
return jsonify({
'success': False,
'error': str(e)
}), 500
@interests_bp.route('/api/interests/<email>', methods=['DELETE'])
def delete_interests(email):
"""
Delete user interest profile (GDPR compliance).
Args:
email: Email address of the user
Returns:
JSON response with confirmation
"""
try:
deleted = delete_user_interests(email)
if not deleted:
return jsonify({
'success': False,
'error': 'User profile not found'
}), 404
return jsonify({
'success': True,
'message': f'Interest profile deleted for {email}'
}), 200
except Exception as e:
return jsonify({
'success': False,
'error': str(e)
}), 500

View File

@@ -0,0 +1,135 @@
"""
Personalization API routes for Munich News Daily.
Provides endpoints to test and preview personalized content.
"""
from flask import Blueprint, request, jsonify
from datetime import datetime, timedelta
from database import articles_collection
from services.personalization_service import (
rank_articles_for_user,
select_personalized_articles,
get_personalization_explanation,
get_personalization_stats
)
personalization_bp = Blueprint('personalization', __name__)
@personalization_bp.route('/api/personalize/preview/<email>', methods=['GET'])
def preview_personalized_newsletter(email):
"""
Preview personalized newsletter for a user.
Query parameters:
max_articles: Maximum articles to return (default: 10)
hours_lookback: Hours of articles to consider (default: 24)
Returns:
JSON with personalized article selection and statistics
"""
try:
max_articles = request.args.get('max_articles', 10, type=int)
hours_lookback = request.args.get('hours_lookback', 24, type=int)
# Get recent articles
cutoff_date = datetime.utcnow() - timedelta(hours=hours_lookback)
articles = list(articles_collection.find({
'created_at': {'$gte': cutoff_date},
'summary': {'$exists': True, '$ne': None}
}).sort('created_at', -1))
# Select personalized articles
personalized = select_personalized_articles(
articles,
email,
max_articles=max_articles
)
# Get statistics
stats = get_personalization_stats(personalized, email)
# Format response
articles_response = []
for article in personalized:
articles_response.append({
'title': article.get('title', ''),
'title_en': article.get('title_en'),
'summary': article.get('summary', ''),
'link': article.get('link', ''),
'category': article.get('category', 'general'),
'keywords': article.get('keywords', []),
'personalization_score': article.get('personalization_score', 0.0),
'published_at': article.get('published_at', '')
})
return jsonify({
'success': True,
'email': email,
'articles': articles_response,
'statistics': stats
}), 200
except Exception as e:
return jsonify({
'success': False,
'error': str(e)
}), 500
@personalization_bp.route('/api/personalize/explain', methods=['POST'])
def explain_recommendation():
"""
Explain why an article was recommended to a user.
Request body:
{
"email": "user@example.com",
"article_id": "article-id-here"
}
Returns:
JSON with explanation of recommendation
"""
try:
data = request.get_json()
if not data or 'email' not in data or 'article_id' not in data:
return jsonify({
'success': False,
'error': 'email and article_id required'
}), 400
email = data['email']
article_id = data['article_id']
# Get article
from bson import ObjectId
article = articles_collection.find_one({'_id': ObjectId(article_id)})
if not article:
return jsonify({
'success': False,
'error': 'Article not found'
}), 404
# Get user interests
from services.interest_profiling_service import get_user_interests
user_interests = get_user_interests(email)
# Generate explanation
explanation = get_personalization_explanation(article, user_interests)
return jsonify({
'success': True,
'email': email,
'article_title': article.get('title', ''),
'explanation': explanation
}), 200
except Exception as e:
return jsonify({
'success': False,
'error': str(e)
}), 500

View File

@@ -79,8 +79,8 @@ def track_click(tracking_id):
"""
Track link clicks and redirect to original article URL.
Logs the click event and redirects the user to the original article URL.
Handles invalid tracking_id by redirecting to homepage.
Logs the click event, updates user interest profile, and redirects the user
to the original article URL. Handles invalid tracking_id by redirecting to homepage.
Ensures redirect completes within 200ms.
Args:
@@ -115,6 +115,19 @@ def track_click(tracking_id):
}
}
)
# Update user interest profile (Phase 3)
subscriber_email = tracking_record.get('subscriber_email')
keywords = tracking_record.get('keywords', [])
category = tracking_record.get('category', 'general')
if subscriber_email and subscriber_email != 'anonymized':
try:
from services.interest_profiling_service import update_user_interests
update_user_interests(subscriber_email, keywords, category)
except Exception as e:
# Don't fail the redirect if interest update fails
print(f"Error updating user interests: {str(e)}")
except Exception as e:
# Log error but still redirect
print(f"Error tracking click for {tracking_id}: {str(e)}")