Update app.py

app.py

@@ -8,6 +8,7 @@ import faiss
 import numpy as np
 import asyncio
 import aiohttp
+import re
 
 # Initialize models and variables
 embedding_model = SentenceTransformer('all-MiniLM-L6-v2')
@@ -15,6 +16,30 @@ faiss_index = None
 bookmarks = []
 fetch_cache = {}
 
+# Define the categories
+CATEGORIES = [
+    "Social Media",
+    "News and Media",
+    "Education and Learning",
+    "Entertainment",
+    "Shopping and E-commerce",
+    "Finance and Banking",
+    "Technology",
+    "Health and Fitness",
+    "Travel and Tourism",
+    "Food and Recipes",
+    "Sports",
+    "Arts and Culture",
+    "Government and Politics",
+    "Business and Economy",
+    "Science and Research",
+    "Personal Blogs and Journals",
+    "Job Search and Careers",
+    "Music and Audio",
+    "Videos and Movies",
+    "Reference and Knowledge Bases",
+]
+
 def parse_bookmarks(file_content):
     soup = BeautifulSoup(file_content, 'html.parser')
     extracted_bookmarks = []
@@ -89,6 +114,45 @@ def generate_summary(bookmark):
             bookmark['summary'] = 'No summary available.'
     return bookmark
 
+def assign_category(bookmark):
+    summary = bookmark.get('summary', '').lower()
+    assigned_category = 'Uncategorized'
+
+    # Keywords associated with each category
+    category_keywords = {
+        "Social Media": ["social media", "networking", "friends", "connect", "posts", "profile"],
+        "News and Media": ["news", "journalism", "media", "headlines", "breaking news"],
+        "Education and Learning": ["education", "learning", "courses", "tutorial", "university", "academy", "study"],
+        "Entertainment": ["entertainment", "movies", "tv shows", "games", "comics", "fun"],
+        "Shopping and E-commerce": ["shopping", "e-commerce", "buy", "sell", "marketplace", "deals", "store"],
+        "Finance and Banking": ["finance", "banking", "investment", "money", "economy", "stock", "trading"],
+        "Technology": ["technology", "tech", "gadgets", "software", "computers", "innovation"],
+        "Health and Fitness": ["health", "fitness", "medical", "wellness", "exercise", "diet"],
+        "Travel and Tourism": ["travel", "tourism", "destinations", "hotels", "flights", "vacation"],
+        "Food and Recipes": ["food", "recipes", "cooking", "cuisine", "restaurant", "dining"],
+        "Sports": ["sports", "scores", "teams", "athletics", "matches", "leagues"],
+        "Arts and Culture": ["arts", "culture", "museum", "gallery", "exhibition", "artistic"],
+        "Government and Politics": ["government", "politics", "policy", "election", "public service"],
+        "Business and Economy": ["business", "corporate", "industry", "economy", "markets"],
+        "Science and Research": ["science", "research", "experiment", "laboratory", "study", "scientific"],
+        "Personal Blogs and Journals": ["blog", "journal", "personal", "diary", "thoughts", "opinions"],
+        "Job Search and Careers": ["jobs", "careers", "recruitment", "resume", "employment", "hiring"],
+        "Music and Audio": ["music", "audio", "songs", "albums", "artists", "bands"],
+        "Videos and Movies": ["video", "movies", "film", "clips", "trailers", "cinema"],
+        "Reference and Knowledge Bases": ["reference", "encyclopedia", "dictionary", "wiki", "knowledge", "information"],
+    }
+
+    for category, keywords in category_keywords.items():
+        for keyword in keywords:
+            if re.search(r'\b' + re.escape(keyword) + r'\b', summary):
+                assigned_category = category
+                break
+        if assigned_category != 'Uncategorized':
+            break
+
+    bookmark['category'] = assigned_category
+    return bookmark
+
 def vectorize_and_index(bookmarks):
     summaries = [bookmark['summary'] for bookmark in bookmarks]
     embeddings = embedding_model.encode(summaries)
@@ -106,6 +170,7 @@ def display_bookmarks():
         url = bookmark['url']
         etag = bookmark.get('etag', 'N/A')
         summary = bookmark.get('summary', '')
+        category = bookmark.get('category', 'Uncategorized')
 
         # Apply inline styles for dead links
         if bookmark.get('dead_link'):
@@ -119,6 +184,7 @@ def display_bookmarks():
         <div class="card" style="{card_style}">
             <div class="card-content">
                 <h3 style="{text_style}">{index}. {title}</h3>
+                <p style="{text_style}"><strong>Category:</strong> {category}</p>
                 <p style="{text_style}"><strong>URL:</strong> <a href="{url}" target="_blank" style="{text_style}">{url}</a></p>
                 <p style="{text_style}"><strong>Status:</strong> {status}</p>
                 <p style="{text_style}"><strong>ETag:</strong> {etag}</p>
@@ -146,9 +212,10 @@ def process_uploaded_file(file):
     # Asynchronously fetch bookmark info
     asyncio.run(process_bookmarks_async(bookmarks))
 
-    # Generate summaries using descriptions
+    # Generate summaries and assign categories
     for bookmark in bookmarks:
         generate_summary(bookmark)
+        assign_category(bookmark)
 
     faiss_index, embeddings = vectorize_and_index(bookmarks)
     message = f"Successfully processed {len(bookmarks)} bookmarks."
@@ -169,7 +236,7 @@ def chatbot_response(user_query):
         if idx < len(bookmarks):
             bookmark = bookmarks[idx]
             index = bookmarks.index(bookmark) + 1  # Start index at 1
-            response += f"{index}. Title: {bookmark['title']}\nURL: {bookmark['url']}\nSummary: {bookmark['summary']}\n\n"
+            response += f"{index}. Title: {bookmark['title']}\nURL: {bookmark['url']}\nCategory: {bookmark.get('category', 'Uncategorized')}\nSummary: {bookmark['summary']}\n\n"
     return response.strip()
 
 def edit_bookmark(bookmark_idx, new_title, new_url):
@@ -183,6 +250,7 @@ def edit_bookmark(bookmark_idx, new_title, new_url):
         # Re-fetch bookmark info
         asyncio.run(process_bookmarks_async([bookmarks[bookmark_idx]]))
         generate_summary(bookmarks[bookmark_idx])
+        assign_category(bookmarks[bookmark_idx])
         # Rebuild the FAISS index
         faiss_index, embeddings = vectorize_and_index(bookmarks)
         message = "Bookmark updated successfully."