implement distinct title search and selection for premium users

Script.py

@@ -2,7 +2,7 @@ class script(object):
 
     START_TXT = """<b>ʜᴇʏ {}, <i>{}</i>
 
-ɪ ᴀᴍ ᴘᴏᴡᴇʀғᴜʟ ᴀᴜᴛᴏ ғɪʟᴛᴇʀ ᴡɪᴛʜ ʟɪɴᴋ sʜᴏʀᴛᴇɴᴇʀ ʙᴏᴛ. ʏᴏᴜ ᴄᴀɴ ᴜꜱᴇ ᴀꜱ ᴀᴜᴛᴏ ғɪʟᴛᴇʀ ᴡɪᴛʜ ʟɪɴᴋ sʜᴏʀᴛᴇɴᴇʀ ɪɴ ʏᴏᴜʀ ɢʀᴏᴜᴘ... ɪᴛ'ꜱ ᴇᴀꜱʏ ᴛᴏ ᴜꜱᴇ ᴊᴜsᴛ ᴀᴅᴅ ᴍᴇ ᴀꜱ ᴀᴅᴍɪɴ ɪɴ ʏᴏᴜʀ ɢʀᴏᴜᴘ ɪ ᴡɪʟʟ ᴘʀᴏᴠɪᴅᴇ ᴛʜᴇʀᴇ ᴍᴏᴠɪᴇꜱ ᴡɪᴛʜ ʏᴏᴜʀ ʟɪɴᴋ ꜱʜᴏʀᴛᴇɴᴇʀ... ♻️</b>"""
+ɪ ᴀᴍ ᴘᴏᴡᴇʀғᴜʟ ᴀᴜᴛᴏ ғɪʟᴛᴇʀ ʙᴏᴛ. ʏᴏᴜ ᴄᴀɴ ᴜꜱᴇ ɪɴ ʏᴏᴜʀ ɢʀᴏᴜᴘ. ɪᴛ'ꜱ ᴇᴀꜱʏ ᴛᴏ ᴜꜱᴇ ᴊᴜsᴛ ᴀᴅᴅ ᴍᴇ ᴀꜱ ᴀᴅᴍɪɴ ɪɴ ʏᴏᴜʀ ɢʀᴏᴜᴘ ɪ ᴡɪʟʟ ᴘʀᴏᴠɪᴅᴇ ᴛʜᴇʀᴇ ᴍᴏᴠɪᴇꜱ</b>"""
 
     MY_ABOUT_TXT = """★ Server: <a href=https://www.heroku.com>Heroku</a>
 ★ Database: <a href=https://www.mongodb.com>MongoDB</a>
@@ -44,21 +44,11 @@ class script(object):
 👉 Please read the Instructions to get better results.
 👉 Or not been released yet."""
 
-    IMDB_TEMPLATE = """✅ I Found: <code>{query}</code>
-
-🏷 Title: <a href={url}>{title}</a>
+    IMDB_TEMPLATE = """🏷 Title: <a href={url}>{title}</a>
 🎭 Genres: {genres}
-📆 Year: <a href={url}/releaseinfo>{year}</a>
-🌟 Rating: <a href={url}/ratings>{rating} / 10</a>
-☀️ Languages: {languages}
-📀 RunTime: {runtime} Minutes
-
-🗣 Requested by: {message.from_user.mention}
-©️ Powered by: <b>{message.chat.title}</b>"""
-
-    FILE_CAPTION = """<i>{file_name}</i>
+🌟 Rating: <a href={url}/ratings>{rating} / 10</a></b>"""
 
-🚫 ᴘʟᴇᴀsᴇ ᴄʟɪᴄᴋ ᴏɴ ᴛʜᴇ ᴄʟᴏsᴇ ʙᴜᴛᴛᴏɴ ɪꜰ ʏᴏᴜ ʜᴀᴠᴇ sᴇᴇɴ ᴛʜᴇ ᴍᴏᴠɪᴇ 🚫"""
+    FILE_CAPTION = """<b><a href='https://t.me/MovieCabanBot'>{file_name}</a></b>"""
 
     WELCOME_TEXT = """👋 Hello {mention}, Welcome to {title} group! 💞"""
 

database/ia_filterdb.py

@@ -42,14 +42,14 @@ async def save_file(media):
     file_id = unpack_new_file_id(media.file_id)
     file_name = re.sub(r"@\w+|(_|\-|\.|\+)", " ", str(media.file_name))
     file_caption = re.sub(r"@\w+|(_|\-|\.|\+)", " ", str(media.caption))
-    
+
     document = {
         '_id': file_id,
         'file_name': file_name,
         'file_size': media.file_size,
         'caption': file_caption
     }
-    
+
     try:
         collection.insert_one(document)
         logger.info(f'Saved - {file_name}')
@@ -78,7 +78,7 @@ async def get_search_results(query, max_results=MAX_BTN, offset=0, lang=None):
         raw_pattern = r'(\b|[\.\+\-_])' + query + r'(\b|[\.\+\-_])'
     else:
         raw_pattern = query.replace(' ', r'.*[\s\.\+\-_]')
-    
+
     try:
         regex = re.compile(raw_pattern, flags=re.IGNORECASE)
     except:
@@ -109,7 +109,7 @@ async def get_search_results(query, max_results=MAX_BTN, offset=0, lang=None):
     files = results[offset:][:max_results]
     next_offset = offset + max_results
     if next_offset >= total_results:
-        next_offset = ''   
+        next_offset = ''
     return files, next_offset, total_results
 
 async def delete_files(query):
@@ -120,24 +120,24 @@ async def delete_files(query):
         raw_pattern = r'(\b|[\.\+\-_])' + query + r'(\b|[\.\+\-_])'
     else:
         raw_pattern = query.replace(' ', r'.*[\s\.\+\-_]')
-    
+
     try:
         regex = re.compile(raw_pattern, flags=re.IGNORECASE)
     except:
         regex = query
-        
+
     filter = {'file_name': regex}
-    
+
     result1 = collection.delete_many(filter)
-    
+
     result2 = None
     if SECOND_FILES_DATABASE_URL:
         result2 = second_collection.delete_many(filter)
-    
+
     total_deleted = result1.deleted_count
     if result2:
         total_deleted += result2.deleted_count
-    
+
     return total_deleted
 
 async def get_file_details(query):
@@ -170,4 +170,93 @@ def unpack_new_file_id(new_file_id):
             decoded.access_hash
         )
     )
-    return file_id
+    return file_id
+
+def clean_title(filename):
+    """Clean filename to extract just the movie/show title"""
+    title = filename
+
+    # Remove file extensions first
+    title = re.sub(r'\.(mkv|mp4|avi|mov|wmv|flv|webm|m4v|3gp|ts|m2ts)$', '', title, flags=re.IGNORECASE)
+
+    # Strategy: Extract title from beginning until we hit dates or season markers
+    # Most titles are clean alphanumeric at the start, noise comes after
+
+    # Find where the title likely ends by looking for:
+    # 1. Year patterns (1900-2099)
+    # 2. Season/Episode patterns (S01, S1, Season 1, etc.)
+    # 3. Quality indicators that commonly appear after titles
+
+    # Look for year patterns (movies): "Title.2023" or "Title (2023)" or "Title 2023"
+    year_match = re.search(r'[\.\s\-_\(]+(19|20)\d{2}[\.\s\-_\)]', title)
+    if year_match:
+        title = title[:year_match.start()]
+
+    # Look for season/episode patterns (series): "Title.S01E02" or "Title S1 E1"
+    season_match = re.search(r'[\.\s\-_]+(S\d{1,2}|Season\s*\d{1,2})', title, flags=re.IGNORECASE)
+    if season_match:
+        title = title[:season_match.start()]
+
+    # Look for common quality indicators that appear after titles
+    quality_match = re.search(r'[\.\s\-_]+(480p|720p|1080p|2160p|4k|HD|FHD|UHD|BluRay|WEB|HDCAM|DVDRip|BDRip|WEBRip)', title, flags=re.IGNORECASE)
+    if quality_match:
+        title = title[:quality_match.start()]
+
+    # Convert common separators to spaces
+    title = re.sub(r'[\.\-_]+', ' ', title)
+
+    # Clean up multiple spaces
+    title = re.sub(r'\s+', ' ', title)
+
+    # Remove leading/trailing whitespace
+    title = title.strip()
+
+    # Remove common prefixes that might appear at the start
+    title = re.sub(r'^(www\.|download\s+|free\s+)', '', title, flags=re.IGNORECASE)
+
+    # Handle special cases where title might have colons (like "Avengers: Endgame")
+    # Keep colons as they're part of legitimate titles
+
+    return title
+
+async def get_distinct_titles(query):
+    """Get distinct titles matching the search query"""
+    query = str(query).strip()
+    if not query:
+        raw_pattern = '.'
+    elif ' ' not in query:
+        raw_pattern = r'(\b|[\.\+\-_])' + query + r'(\b|[\.\+\-_])'
+    else:
+        raw_pattern = query.replace(' ', r'.*[\s\.\+\-_]')
+
+    try:
+        regex = re.compile(raw_pattern, flags=re.IGNORECASE)
+    except:
+        regex = query
+
+    # Get distinct titles from both databases
+    titles = set()
+
+    # Search in primary database
+    cursor = collection.find({'file_name': regex})
+    for doc in cursor:
+        # Clean the filename to extract just the title
+        clean_title_text = clean_title(doc['file_name'])
+        if clean_title_text and len(clean_title_text.strip()) > 2:  # Only add non-empty titles
+            titles.add(clean_title_text)
+
+    # Search in secondary database if available
+    if SECOND_FILES_DATABASE_URL:
+        cursor2 = second_collection.find({'file_name': regex})
+        for doc in cursor2:
+            clean_title_text = clean_title(doc['file_name'])
+            if clean_title_text and len(clean_title_text.strip()) > 2:  # Only add non-empty titles
+                titles.add(clean_title_text)
+
+    # Filter out very short or meaningless titles
+    filtered_titles = []
+    for title in titles:
+        if len(title.strip()) > 2 and not title.lower() in ['the', 'and', 'or', 'of', 'in', 'on', 'at', 'to', 'for']:
+            filtered_titles.append(title.strip())
+
+    return sorted(list(set(filtered_titles)))

info.py

@@ -110,10 +110,11 @@ def is_valid_ip(ip):
 USE_CAPTION_FILTER = is_enabled('USE_CAPTION_FILTER', False)
 IS_VERIFY = is_enabled('IS_VERIFY', False)
 AUTO_DELETE = is_enabled('AUTO_DELETE', False)
-WELCOME = is_enabled('WELCOME', False)
+WELCOME = is_enabled('WELCOME', True)
 PROTECT_CONTENT = is_enabled('PROTECT_CONTENT', False)
 LONG_IMDB_DESCRIPTION = is_enabled("LONG_IMDB_DESCRIPTION", False)
-LINK_MODE = is_enabled("LINK_MODE", True)
+LINK_MODE = is_enabled("LINK_MODE", False)
+AUTO_FILTER = is_enabled('AUTO_FILTER', True)
 IMDB = is_enabled('IMDB', True)
 SPELL_CHECK = is_enabled("SPELL_CHECK", True)
 SHORTLINK = is_enabled('SHORTLINK', False)
@@ -158,4 +159,4 @@ def is_valid_ip(ip):
 if len(UPI_ID) == 0 or len(UPI_NAME) == 0:
     logger.info('IS_PREMIUM disabled due to empty UPI_ID or UPI_NAME')
     IS_PREMIUM = False
-
+

plugins/commands.py

@@ -29,8 +29,7 @@ async def start(client, message):
         wish = get_wish()
         user = message.from_user.mention if message.from_user else "Dear"
         btn = [[
-            InlineKeyboardButton('⚡️ ᴜᴘᴅᴀᴛᴇs ᴄʜᴀɴɴᴇʟ ⚡️', url=UPDATES_LINK),
-            InlineKeyboardButton('💡 sᴜᴘᴘᴏʀᴛ ɢʀᴏᴜᴘ 💡', url=SUPPORT_LINK)
+            InlineKeyboardButton('⚡️ ᴜᴘᴅᴀᴛᴇs ᴄʜᴀɴɴᴇʟ ⚡️', url=UPDATES_LINK)
         ]]
         await message.reply(text=f"<b>ʜᴇʏ {user}, <i>{wish}</i>\nʜᴏᴡ ᴄᴀɴ ɪ ʜᴇʟᴘ ʏᴏᴜ??</b>", reply_markup=InlineKeyboardMarkup(btn))
         return 
@@ -54,7 +53,7 @@ async def start(client, message):
 
     if (len(message.command) != 2) or (len(message.command) == 2 and message.command[1] == 'start'):
         buttons = [[
-            InlineKeyboardButton("+ ᴀᴅᴅ ᴍᴇ ᴛᴏ ʏᴏᴜʀ ɢʀᴏᴜᴘ +", url=f'http://t.me/{temp.U_NAME}?startgroup=start')
+            InlineKeyboardButton('ᴜᴘᴅᴀᴛᴇs', url=UPDATES_LINK)
         ],[
             InlineKeyboardButton('ℹ️ ᴜᴘᴅᴀᴛᴇs', url=UPDATES_LINK),
             InlineKeyboardButton('🧑‍💻 sᴜᴘᴘᴏʀᴛ', url=SUPPORT_LINK)
@@ -161,17 +160,11 @@ async def start(client, message):
                 btn = [[
                     InlineKeyboardButton("✛ ᴡᴀᴛᴄʜ & ᴅᴏᴡɴʟᴏᴀᴅ ✛", callback_data=f"stream#{file['_id']}")
                 ],[
-                    InlineKeyboardButton('⚡️ ᴜᴘᴅᴀᴛᴇs', url=UPDATES_LINK),
-                    InlineKeyboardButton('💡 ꜱᴜᴘᴘᴏʀᴛ', url=SUPPORT_LINK)
-                ],[
-                    InlineKeyboardButton('⁉️ ᴄʟᴏsᴇ ⁉️', callback_data='close_data')
+                    InlineKeyboardButton('❌ Delete Files ❌', callback_data='close_data')
                 ]]
             else:
                 btn = [[
-                    InlineKeyboardButton('⚡️ ᴜᴘᴅᴀᴛᴇs', url=UPDATES_LINK),
-                    InlineKeyboardButton('💡 ꜱᴜᴘᴘᴏʀᴛ', url=SUPPORT_LINK)
-                ],[
-                    InlineKeyboardButton('⁉️ ᴄʟᴏsᴇ ⁉️', callback_data='close_data')
+                    InlineKeyboardButton('❌ Delete Files ❌', callback_data='close_data')
                 ]]
 
             msg = await client.send_cached_media(
@@ -220,17 +213,11 @@ async def start(client, message):
         btn = [[
             InlineKeyboardButton("✛ ᴡᴀᴛᴄʜ & ᴅᴏᴡɴʟᴏᴀᴅ ✛", callback_data=f"stream#{file_id}")
         ],[
-            InlineKeyboardButton('⚡️ ᴜᴘᴅᴀᴛᴇs', url=UPDATES_LINK),
-            InlineKeyboardButton('💡 ꜱᴜᴘᴘᴏʀᴛ', url=SUPPORT_LINK)
-        ],[
-            InlineKeyboardButton('⁉️ ᴄʟᴏsᴇ ⁉️', callback_data='close_data')
+            InlineKeyboardButton('❌ Delete Files ❌', callback_data='close_data')
         ]]
     else:
         btn = [[
-            InlineKeyboardButton('⚡️ ᴜᴘᴅᴀᴛᴇs', url=UPDATES_LINK),
-            InlineKeyboardButton('💡 ꜱᴜᴘᴘᴏʀᴛ', url=SUPPORT_LINK)
-        ],[
-            InlineKeyboardButton('⁉️ ᴄʟᴏsᴇ ⁉️', callback_data='close_data')
+            InlineKeyboardButton('❌ Delete Files ❌', callback_data='close_data')
         ]]
     vp = await client.send_cached_media(
         chat_id=message.from_user.id,