utils.py

import logging, os, re, asyncio, requests, aiohttp 
from pyrogram.errors import InputUserDeactivated, UserNotParticipant, FloodWait, UserIsBlocked, PeerIdInvalid                             
from pyrogram.types import Message, InlineKeyboardButton
from pyrogram import filters, enums
from info import AUTH_CHANNEL, LONG_IMDB_DESCRIPTION, MAX_LIST_ELM, SHORT_URL, SHORT_API
from imdb import Cinemagoer
from typing import Union, List
from datetime import datetime, timedelta
from database.users_chats_db import db
from bs4 import BeautifulSoup

logger = logging.getLogger(__name__)
logger.setLevel(logging.INFO)

BTN_URL_REGEX = re.compile(r"(\[([^\[]+?)\]\((buttonurl|buttonalert):(?:/{0,2})(.+?)(:same)?\))")
BANNED = {}
SMART_OPEN = '“'
SMART_CLOSE = '”'
START_CHAR = ('\'', '"', SMART_OPEN)

# temp db for banned 
class temp(object):
    BANNED_USERS = []
    BANNED_CHATS = []
    CURRENT = 0
    CANCEL = False
    MELCOW = {}
    U_NAME = None
    B_NAME = None
    SETTINGS = {}
    GP_BUTTONS = {}
    PM_BUTTONS = {}
    PM_SPELL = {}
    GP_SPELL = {}

async def is_subscribed(bot, query):
    logger.info(f"Checking subscription for user_id: {query.from_user.id} in AUTH_CHANNEL: {AUTH_CHANNEL}")
    try:
        user = await bot.get_chat_member(AUTH_CHANNEL, query.from_user.id)
        logger.debug(f"User {query.from_user.id} is subscribed.")
    except UserNotParticipant:
        logger.debug(f"User {query.from_user.id} is not subscribed.")
        pass
    except Exception as e:
        logger.error(f"Error checking subscription: {e}")
        print(e)
    else:
        if user.status != enums.ChatMemberStatus.BANNED:
            logger.debug(f"User {query.from_user.id} is not banned.")
            return True
    logger.debug(f"User {query.from_user.id} is not subscribed.")
    return False

async def get_poster(query, bulk=False, id=False, file=None):
    logger.info(f"Fetching poster for query: {query}, bulk: {bulk}, id: {id}, file: {file}")
    imdb = Cinemagoer() 
    if not id:   
        query = (query.strip()).lower()
        title = query
        year = re.findall(r'[1-2]\d{3}$', query, re.IGNORECASE)
        if year:
            year = list_to_str(year[:1])
            title = (query.replace(year, "")).strip()
            logger.debug(f"Extracted year: {year}, title: {title}")
        elif file is not None:
            year = re.findall(r'[1-2]\d{3}', file, re.IGNORECASE)
            if year:
                year = list_to_str(year[:1]) 
                logger.debug(f"Extracted year from file: {year}")
        else:
            year = None
            logger.debug("Year not found.")
        try:
            movieid = imdb.search_movie(title.lower(), results=10)
            logger.debug(f"Found movie IDs: {movieid}")
        except Exception as e:
            logger.error(f"Error searching movie: {e}")
            return None
        if not movieid:
            logger.debug("No movie IDs found.")
            return None
        if year:
            filtered=list(filter(lambda k: str(k.get('year')) == str(year), movieid))
            if not filtered:
                filtered = movieid
                logger.debug("No filtered results. Using original results.")
            logger.debug(f"Filtered results: {filtered}")
        else:
            filtered = movieid
            logger.debug("Using original results.")
        movieid=list(filter(lambda k: k.get('kind') in ['movie', 'tv series'], filtered))
        if not movieid:
            movieid = filtered
            logger.debug("No movie or tv series results. Using original results.")
        logger.debug(f"Final movie IDs: {movieid}")
        if bulk:
            logger.debug("Returning bulk results.")
            return movieid
        movieid = movieid[0].movieID
        logger.debug(f"Selected movie ID: {movieid}")
    else:
        movieid = query
        logger.debug(f"Using provided movie ID: {movieid}")
    movie = imdb.get_movie(movieid)
    if movie.get("original air date"):
        date = movie["original air date"]
        logger.debug(f"Original air date: {date}")
    elif movie.get("year"):
        date = movie.get("year")
        logger.debug(f"Year: {date}")
    else:
        date = "N/A"
        logger.debug("Date not found. Setting to N/A.")
    plot = ""
    if not LONG_IMDB_DESCRIPTION:
        plot = movie.get('plot')
        if plot and len(plot) > 0:
            plot = plot[0]
            logger.debug(f"Plot: {plot}")
    else:
        plot = movie.get('plot outline')
        logger.debug(f"Plot outline: {plot}")
    if plot and len(plot) > 800:
        plot = plot[0:800] + "..."
        logger.debug(f"Truncated plot: {plot}")
    return {
        'title': movie.get('title'),
        'votes': movie.get('votes'),
        "aka": list_to_str(movie.get("akas")),
        "seasons": movie.get("number of seasons"),
        "box_office": movie.get('box office'),
        'localized_title': movie.get('localized title'),
        'kind': movie.get("kind"),
        "imdb_id": f"tt{movie.get('imdbID')}",
        "cast": list_to_str(movie.get("cast")),
        "runtime": list_to_str(movie.get("runtimes")),
        "countries": list_to_str(movie.get("countries")),
        "certificates": list_to_str(movie.get("certificates")),
        "languages": list_to_str(movie.get("languages")),
        "director": list_to_str(movie.get("director")),
        "writer":list_to_str(movie.get("writer")),
        "producer":list_to_str(movie.get("producer")),
        "composer":list_to_str(movie.get("composer")) ,
        "cinematographer":list_to_str(movie.get("cinematographer")),
        "music_team": list_to_str(movie.get("music department")),
        "distributors": list_to_str(movie.get("distributors")),
        'release_date': date,
        'year': movie.get('year'),
        'genres': list_to_str(movie.get("genres")),
        'poster': movie.get('full-size cover url'),
        'plot': plot,
        'rating': str(movie.get("rating")),
        'url':f'https://www.imdb.com/title/tt{movieid}'
    }

def list_to_str(k):
    logger.debug(f"Converting list to string: {k}")
    if not k: 
        logger.debug("List is empty. Returning 'N/A'.")
        return "N/A"
    elif len(k) == 1: 
        logger.debug(f"List has one element. Returning: {k[0]}")
        return str(k[0])
    elif MAX_LIST_ELM:
        k = k[:int(MAX_LIST_ELM)]
        result = ' '.join(f'{elem}, ' for elem in k)
        logger.debug(f"Truncated list to {MAX_LIST_ELM} elements. Returning: {result}")
        return result
    else:
        result = ' '.join(f'{elem}, ' for elem in k)
        logger.debug(f"Returning full list as string: {result}")
        return result

__repo__ = "https://github.com/MrMKN/PROFESSOR-BOT"
logger.debug(f"Repository URL: {__repo__}")
__version__ = "PROFESSOR-BOT ᴠ4.5.0"
logger.debug(f"Version: {__version__}")
__license__ = "GNU GENERAL PUBLIC LICENSE V2"
logger.debug(f"License: {__license__}")
__copyright__ = "Copyright (C) 2023-present MrMKN <https://github.com/MrMKN>"
logger.debug(f"Copyright: {__copyright__}")

async def search_gagala(text):
    logger.info(f"Searching Google for text: {text}")
    usr_agent = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/61.0.3163.100 Safari/537.36'
    }
    text = text.replace(" ", '+')
    url = f'https://www.google.com/search?q={text}'
    response = requests.get(url, headers=usr_agent)
    response.raise_for_status()
    soup = BeautifulSoup(response.text, 'html.parser')
    titles = soup.find_all('h3')
    result = [title.getText() for title in titles]
    logger.debug(f"Found titles: {result}")
    return result

async def get_settings(group_id):
    logger.info(f"Getting settings for group_id: {group_id}")
    settings = temp.SETTINGS.get(group_id)
    if not settings:
        settings = await db.get_settings(group_id)
        temp.SETTINGS[group_id] = settings
        logger.debug(f"Settings retrieved from database: {settings}")
    else:
        logger.debug(f"Settings retrieved from cache: {settings}")
    return settings
    
async def save_group_settings(group_id, key, value):
    logger.info(f"Saving setting {key} with value {value} for group_id: {group_id}")
    current = await get_settings(group_id)
    current[key] = value
    temp.SETTINGS[group_id] = current
    await db.update_settings(group_id, current)
    logger.debug(f"Updated settings: {current}")

def get_size(size):
    logger.debug(f"Converting size: {size}")
    units = ["Bytes", "KB", "MB", "GB", "TB", "PB", "EB"]
    size = float(size)
    i = 0
    while size >= 1024.0 and i < len(units):
        i += 1
        size /= 1024.0
    result = "%.2f %s" % (size, units[i])
    logger.debug(f"Converted size: {result}")
    return result

def get_file_id(msg: Message):
    logger.debug(f"Getting file ID from message: {msg}")
    if not msg.media: 
        logger.debug("No media in message.")
        return None
    for message_type in ("photo", "animation", "audio", "document", "video", "video_note", "voice", "sticker"):
        obj = getattr(msg, message_type)
        if obj:
            setattr(obj, "message_type", message_type)
            logger.debug(f"Found file ID: {obj.file_id}")
            return obj

def extract_user(message: Message) -> Union[int, str]:
    logger.debug(f"Extracting user from message: {message}")
    user_id = None
    user_first_name = None
    if message.reply_to_message:
        user_id = message.reply_to_message.from_user.id
        user_first_name = message.reply_to_message.from_user.first_name
        logger.debug(f"User extracted from reply: {user_id}, {user_first_name}")
    elif len(message.command) > 1:
        if (len(message.entities) > 1 and message.entities[1].type == enums.MessageEntityType.TEXT_MENTION):
            required_entity = message.entities[1]
            user_id = required_entity.user.id
            user_first_name = required_entity.user.first_name
            logger.debug(f"User extracted from text mention: {user_id}, {user_first_name}")
        else:
            user_id = message.command[1]
            user_first_name = user_id
            logger.debug(f"User extracted from command: {user_id}, {user_first_name}")
            try:
                user_id = int(user_id)
                logger.debug(f"Converted user_id to integer: {user_id}")
            except ValueError: 
                logger.debug("Failed to convert user_id to integer.")
                pass
    else:
        user_id = message.from_user.id
        user_first_name = message.from_user.first_name
        logger.debug(f"User extracted from message sender: {user_id}, {user_first_name}")
    return (user_id, user_first_name)

def split_quotes(text: str) -> List:
    logger.debug(f"Splitting quotes from text: {text}")
    if not any(text.startswith(char) for char in START_CHAR):
        result = text.split(None, 1)
        logger.debug(f"No quotes found. Split result: {result}")
        return result
    counter = 1  # ignore first char -> is some kind of quote
    while counter < len(text):
        if text[counter] == "\\":
            counter += 1
        elif text[counter] == text[0] or (text[0] == SMART_OPEN and text[counter] == SMART_CLOSE):
            break
        counter += 1
    else:
        result = text.split(None, 1)
        logger.debug(f"No closing quote found. Split result: {result}")
        return result

    # 1 to avoid starting quote, and counter is exclusive so avoids ending
    key = remove_escapes(text[1:counter].strip())
    # index will be in range, or `else` would have been executed and returned
    rest = text[counter + 1:].strip()
    if not key:
        key = text[0] + text[0]
        logger.debug(f"No key found. Using default key: {key}")
    result = list(filter(None, [key, rest]))
    logger.debug(f"Split result: {result}")
    return result

def parser(text, keyword, cb_data):
    logger.debug(f"Parsing text: {text}, keyword: {keyword}, cb_data: {cb_data}")
    if "buttonalert" in text: 
        text = (text.replace("\n", "\\n").replace("\t", "\\t"))
        logger.debug(f"Text after replacing newline and tab: {text}")
    buttons = []
    note_data = ""
    prev = 0
    i = 0
    alerts = []
    for match in BTN_URL_REGEX.finditer(text):
        n_escapes = 0
        to_check = match.start(1) - 1
        while to_check > 0 and text[to_check] == "\\":
            n_escapes += 1
            to_check -= 1
        # if even, not escaped -> create button
        if n_escapes % 2 == 0:
            note_data += text[prev:match.start(1)]
            prev = match.end(1)
            if match.group(3) == "buttonalert":
                # create a thruple with button label, url, and newline status
                if bool(match.group(5)) and buttons:
                    buttons[-1].append(InlineKeyboardButton(match.group(2), callback_data=f"{cb_data}:{i}:{keyword}"))
                    logger.debug(f"Added buttonalert button: {match.group(2)}, {match.group(4)}, {match.group(5)}")
                else:
                    buttons.append([InlineKeyboardButton(match.group(2), callback_data=f"{cb_data}:{i}:{keyword}")])
                    logger.debug(f"Created buttonalert button: {match.group(2)}, {match.group(4)}, {match.group(5)}")
                i += 1
                alerts.append(match.group(4))
                logger.debug(f"Added alert: {match.group(4)}")
            elif bool(match.group(5)) and buttons:
                buttons[-1].append(InlineKeyboardButton(match.group(2), url=match.group(4).replace(" ", "")))
                logger.debug(f"Added button: {match.group(2)}, {match.group(4)}")
            else:
                buttons.append([InlineKeyboardButton(match.group(2), url=match.group(4).replace(" ", ""))])
                logger.debug(f"Created button: {match.group(2)}, {match.group(4)}")
        else:
            note_data += text[prev:to_check]
            prev = match.start(1) - 1
            logger.debug(f"Escaped button: {match.group(2)}")
    else: 
        note_data += text[prev:]
        logger.debug(f"Note data after parsing: {note_data}")
    try: 
        result = (note_data, buttons, alerts)
        logger.debug(f"Parsing successful. Result: {result}")
        return result
    except Exception as e:
        logger.error(f"Parsing failed: {e}")
        return note_data, buttons, None

def remove_escapes(text: str) -> str:
    logger.debug(f"Removing escapes from text: {text}")
    res = ""
    is_escaped = False
    for counter in range(len(text)):
        if is_escaped:
            res += text[counter]
            is_escaped = False
        elif text[counter] == "\\":
            is_escaped = True
        else:
            res += text[counter]
            logger.debug(f"Processed character: {text[counter]}, result so far: {res}")
    logger.debug(f"Final result after removing escapes: {res}")
    return res
   
def humanbytes(size):
    logger.debug(f"Converting size to human-readable format: {size}")
    if not size:
        logger.debug("Size is zero. Returning empty string.")
        return ""
    power = 2**10
    n = 0
    Dic_powerN = {0: ' ', 1: 'Ki', 2: 'Mi', 3: 'Gi', 4: 'Ti'}
    while size > power:
        size /= power
        n += 1
        logger.debug(f"Converted size: {size}, power: {power}, n: {n}")
    result = str(round(size, 2)) + " " + Dic_powerN[n] + 'B'
    logger.debug(f"Human-readable size: {result}")
    return result
    
async def get_shortlink(link):
    logger.info(f"Generating shortlink for link: {link}")
    url = f'{SHORT_URL}/api'
    params = {'api': SHORT_API, 'url': link}
    try:
        async with aiohttp.ClientSession() as session:
            async with session.get(url, params=params, raise_for_status=True, ssl=False) as response:
                data = await response.json()
                logger.debug(f"Shortlink API response: {data}")
                if data["status"] == "success":
                    logger.debug(f"Shortlink generated: {data['shortenedUrl']}")
                    return data['shortenedUrl']
                else:
                    logger.error(f"Error generating shortlink: {data['message']}")
                    return link
    except Exception as e:
        logger.error(f"Exception generating shortlink: {e}")
        return link

def extract_time(time_val):
    logger.debug(f"Extracting time from time_val: {time_val}")
    if any(time_val.endswith(unit) for unit in ("s", "m", "h", "d")):
        unit = time_val[-1]
        time_num = time_val[:-1]  # type: str
        if not time_num.isdigit():
            logger.debug("Time value is not a digit.")
            return None

        if unit == "s":
            bantime = datetime.now() + timedelta(seconds=int(time_num)) 
            logger.debug(f"Bantime set for seconds: {bantime}")
        elif unit == "m":
            bantime = datetime.now() + timedelta(minutes=int(time_num))
            logger.debug(f"Bantime set for minutes: {bantime}")
        elif unit == "h":
            bantime = datetime.now() + timedelta(hours=int(time_num))
            logger.debug(f"Bantime set for hours: {bantime}")
        elif unit == "d":
            bantime = datetime.now() + timedelta(days=int(time_num))
            logger.debug(f"Bantime set for days: {bantime}")
        else:
            logger.debug("Invalid time unit.")
            return None
        logger.debug(f"Extracted bantime: {bantime}")
        return bantime
    else:
        logger.debug("Time value does not end with s, m, h, or d.")
        return None

async def admin_check(message: Message) -> bool:
    logger.info(f"Checking admin status for message: {message}")
    if not message.from_user: 
        logger.debug("Message does not have a from_user.")
        return False
    if message.chat.type not in [enums.ChatType.GROUP, enums.ChatType.SUPERGROUP]: 
        logger.debug("Chat type is not GROUP or SUPERGROUP.")
        return False
    if message.from_user.id in [777000, 1087968824]: 
        logger.debug("User is a system user.")
        return True
    client = message._client
    chat_id = message.chat.id
    user_id = message.from_user.id
    check_status = await client.get_chat_member(chat_id=chat_id,user_id=user_id)
    admin_strings = [enums.ChatMemberStatus.OWNER, enums.ChatMemberStatus.ADMINISTRATOR]
    if check_status.status not in admin_strings: 
        logger.debug("User is not an admin.")
        return False
    else: 
        logger.debug("User is an admin.")
        return True

async def admin_filter(filt, client, message):
    logger.info(f"Applying admin filter for message: {message}")
    result = await admin_check(message)
    logger.debug(f"Admin filter result: {result}")
    return result