Update app.py

app.py

@@ -22,8 +22,7 @@ from bs4 import BeautifulSoup
 import requests
 from io import BytesIO
 
-class ImageScraper:
-    def __init__(self):
+def __init__(self):
         self.PIXABAY_API_KEY = "48069976-37e20099248207cee12385560"
         self.headers = {
             'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36'
@@ -116,17 +115,104 @@ class ImageScraper:
                 return category
         return 'general'
 
+
+    def extract_key_topics(self, script: str) -> List[str]:
+        """Extract key topics from a long text prompt with improved accuracy"""
+        try:
+            # Define relevant categories for VaultGenix
+            categories = {
+                'security': ['security', 'encryption', 'protection', 'privacy', 'safe', 'secure'],
+                'digital': ['digital', 'online', 'virtual', 'cyber', 'electronic'],
+                'legacy': ['legacy', 'inheritance', 'heir', 'posthumous', 'estate'],
+                'management': ['management', 'planning', 'organization', 'control', 'administration'],
+                'technology': ['AI', 'artificial intelligence', 'technology', 'platform', 'system'],
+                'family': ['family', 'heir', 'custodian', 'relative', 'loved ones']
+            }
+            
+            # Process text
+            text = script.lower()
+            found_topics = set()
+            
+            # Extract single-word matches
+            words = text.split()
+            for category, terms in categories.items():
+                for term in terms:
+                    if term in text:
+                        found_topics.add(term)
+                        found_topics.add(category)
+            
+            # Extract meaningful phrases
+            important_phrases = [
+                'digital legacy',
+                'legacy management',
+                'digital security',
+                'data protection',
+                'artificial intelligence',
+                'digital estate',
+                'digital identity',
+                'secure platform',
+                'family protection',
+                'digital inheritance'
+            ]
+            
+            for phrase in important_phrases:
+                if phrase in text:
+                    found_topics.add(phrase)
+            
+            # Combine related topics
+            combined_topics = []
+            for topic in found_topics:
+                # Create meaningful combinations
+                if topic in ['digital', 'secure', 'smart', 'AI']:
+                    related = ['legacy', 'security', 'protection', 'management']
+                    for rel in related:
+                        if rel in found_topics:
+                            combined_topics.append(f"{topic} {rel}")
+            
+            # Add combined topics to results
+            found_topics.update(combined_topics)
+            
+            # Prioritize topics
+            priority_topics = [
+                topic for topic in found_topics 
+                if any(key in topic for key in ['digital', 'security', 'legacy', 'AI'])
+            ]
+            
+            # Ensure we have enough topics
+            if len(priority_topics) < 3:
+                priority_topics.extend(['digital security', 'legacy management', 'data protection'][:3 - len(priority_topics)])
+            
+            return list(set(priority_topics))[:5]  # Return top 5 unique topics
+            
+        except Exception as e:
+            print(f"Topic extraction error: {e}")
+            return ['digital security', 'legacy management', 'data protection']
+
     def get_images_for_keyword(self, keyword: str) -> List[Dict[str, str]]:
-        """Get images for a specific keyword with metadata"""
+        """Get images for a specific keyword with improved relevance"""
         try:
+            # Enhance keyword for better search results
+            enhanced_keywords = {
+                'digital': 'digital technology security',
+                'security': 'cybersecurity protection',
+                'legacy': 'digital legacy inheritance',
+                'management': 'digital management system',
+                'AI': 'artificial intelligence technology',
+                'protection': 'data protection security'
+            }
+            
+            search_term = enhanced_keywords.get(keyword, keyword)
+            
             base_url = "https://pixabay.com/api/"
             params = {
                 'key': self.PIXABAY_API_KEY,
-                'q': keyword,
+                'q': search_term,
                 'image_type': 'photo',
                 'per_page': 5,
                 'safesearch': True,
-                'lang': 'en'
+                'lang': 'en',
+                'category': 'technology',  # Focus on technology category
+                'orientation': 'horizontal'  # Better for video
             }
             
             response = requests.get(base_url, params=params, headers=self.headers)
@@ -137,10 +223,11 @@ class ImageScraper:
                     return [{
                         'url': img['largeImageURL'],
                         'keyword': keyword,
-                        'relevance': 'Primary match' if keyword in img['tags'] else 'Related',
+                        'relevance': 'Primary match' if keyword.lower() in img['tags'].lower() else 'Related',
                         'tags': img['tags']
                     } for img in data['hits']]
             return []
+            
         except Exception as e:
             print(f"Error fetching images for keyword {keyword}: {e}")
             return []
@@ -791,41 +878,6 @@ class EnhancedVideoGenerator:
         
         return text.strip()
 
-    def extract_key_topics(self, script: str) -> List[str]:
-        """Extract key topics from a long text prompt"""
-        try:
-            # Common tech-related terms to look for
-            tech_terms = {
-                'security', 'digital', 'technology', 'data', 'encryption', 
-                'privacy', 'protection', 'software', 'platform', 'system',
-                'AI', 'artificial intelligence', 'computing', 'cyber'
-            }
-            
-            # Split into words and get unique terms
-            words = script.lower().split()
-            topics = set()
-            
-            # Extract single word topics
-            for word in words:
-                if word in tech_terms:
-                    topics.add(word)
-            
-            # Extract two-word phrases
-            for i in range(len(words) - 1):
-                phrase = f"{words[i]} {words[i+1]}"
-                if any(term in phrase for term in tech_terms):
-                    topics.add(phrase)
-            
-            # Add some default topics if none found
-            if not topics:
-                topics = {'digital security', 'data protection', 'technology'}
-            
-            return list(topics)[:5]  # Return top 5 topics
-            
-        except Exception as e:
-            print(f"Topic extraction error: {e}")
-            return ['digital security']
-
     def generate_ai_image(self, prompt: str, style: str) -> Optional[Image.Image]:
         """Generate an AI image using Stability AI"""
         try: