main.py

import asyncio
import aiohttp
import feedparser
from bs4 import BeautifulSoup
from pyrogram import Client, filters, __version__ as pyrogram_version
from pyrogram.types import InlineKeyboardButton, InlineKeyboardMarkup
from pyrogram.enums import ParseMode
from pymongo import MongoClient
import psutil
import os
from config import (
    API_ID,
    API_HASH,
    BOT_TOKEN,
    MONGO_URI,
    DB_NAME,
    COLLECTION_NAME,
    CHANNEL_USERNAME
)
# TechCrunch RSS feed URL
RSS_FEED_URL = "https://techcrunch.com/feed/"

# Initialize Pyrogram bot
app = Client("TechCrunchBot", api_id=API_ID, api_hash=API_HASH, bot_token=BOT_TOKEN, workers=10)

# MongoDB client
mongo_client = MongoClient(MONGO_URI)
db = mongo_client[DB_NAME]
collection = db[COLLECTION_NAME]

# Directory to save downloaded images
IMAGE_DIR = "images"
os.makedirs(IMAGE_DIR, exist_ok=True)

# Async function to fetch and parse RSS feed
async def fetch_rss():
    async with aiohttp.ClientSession() as session:
        async with session.get(RSS_FEED_URL) as response:
            if response.status == 200:
                feed = feedparser.parse(await response.text())
                return feed.entries
            else:
                print(f"Failed to fetch RSS feed. Status code: {response.status}")
                return []

# Async function to scrape details from the article page
async def scrape_article(link):
    async with aiohttp.ClientSession() as session:
        try:
            async with session.get(link) as response:
                if response.status == 200:
                    soup = BeautifulSoup(await response.text(), "html.parser")
                    
                    # Extract image URL
                    image_tag = soup.find("meta", property="og:image")
                    image_url = image_tag["content"] if image_tag and image_tag.get("content") else None
                    
                    # Extract additional details
                    detail_section = soup.find("div", class_="article-content")
                    more_details = detail_section.text.strip()[:500] + "..." if detail_section else "No additional details available."
                    
                    return image_url, more_details
        except Exception as e:
            print(f"Error scraping article {link}: {e}")
        return None, "No additional details available."

# Async function to download an image from a URL
async def download_image(image_url, filename):
    try:
        async with aiohttp.ClientSession() as session:
            async with session.get(image_url) as response:
                if response.status == 200:
                    with open(filename, "wb") as f:
                        f.write(await response.read())
                    return filename
    except Exception as e:
        print(f"Error downloading image: {e}")
    return None

# Async function to fetch and process news
async def fetch_and_process_news(force_post=False):
    news_list = await fetch_rss()
    new_articles = []

    for entry in news_list:
        # If it's the first run, post all articles regardless of duplicates
        if force_post or not collection.find_one({"link": entry.link}):
            image_url, more_details = await scrape_article(entry.link)
            article = {
                "title": entry.title,
                "link": entry.link,
                "summary": entry.summary,
                "image_url": image_url,
                "more_details": more_details
            }
            new_articles.append(article)
            
            # Add to the database
            collection.insert_one(article)

    return new_articles

# Async function to post articles to Telegram
async def post_articles(articles):
    for article in articles:
        # Download the image
        image_path = None
        if article["image_url"]:
            image_filename = os.path.join(IMAGE_DIR, f"{article['title'].replace(' ', '_')}.jpg")
            image_path = await download_image(article["image_url"], image_filename)

        # Prepare the caption
        caption = (
            f"📌 **{article['title']}**\n\n"
            f"📖 Summary: {article['summary']}\n"
            f"🔍 More Details: {article['more_details']}"
        )

        # URL for sharing
        share_url = f"https://t.me/share/url?url={article['link']}&text=Check@TheSmartDevForMoreInfo"

        # Add custom buttons
        keyboard = InlineKeyboardMarkup(
            [
                [InlineKeyboardButton("♻️ Refresh ♻️", callback_data="refresh_news")],
                [InlineKeyboardButton("🔗 Read More 🔗", url=article['link'])],
                [InlineKeyboardButton("✉️ Join Always Free Tech News ✉️", url="https://t.me/abir_x_official_free_course")],
                [InlineKeyboardButton("🤝 Share 🤝", url=share_url)]
            ]
        )

        # Send the image with caption, or just the caption if no image
        if image_path and os.path.exists(image_path):
            await app.send_photo(CHANNEL_USERNAME, photo=image_path, caption=caption, reply_markup=keyboard, parse_mode=ParseMode.MARKDOWN)
            os.remove(image_path)  # Clean up the downloaded image
        else:
            await app.send_message(CHANNEL_USERNAME, caption, reply_markup=keyboard, parse_mode=ParseMode.MARKDOWN)

        await asyncio.sleep(5)  # Avoid hitting Telegram API limits

# Background task to fetch and post news every 40 minutes
async def periodic_news_fetch():
    # Fetch and post all articles on the first run
    print("First run: Fetching and posting all articles...")
    new_articles = await fetch_and_process_news(force_post=True)
    if new_articles:
        await post_articles(new_articles)
    else:
        print("No articles found during the first run.")

    # Continue fetching and posting new articles every 40 minutes
    while True:
        print("Fetching and posting new articles...")
        new_articles = await fetch_and_process_news()
        if new_articles:
            await post_articles(new_articles)
        else:
            print("No new articles found.")
        await asyncio.sleep(2400)  # Wait 40 minutes

# Callback query handler for "Refresh" button
@app.on_callback_query(filters.regex("refresh_news"))
async def refresh_news_callback(client, callback_query):
    print("Refresh button clicked. Fetching news...")
    new_articles = await fetch_and_process_news()

    if new_articles:
        await post_articles(new_articles)
    else:
        await callback_query.answer("No New News Bruh!", show_alert=True)

# Start the bot
@app.on_message(filters.command("start"))
async def start(client, message):
    await message.reply("🤖 Hello! I'm the TechCrunch News Bot. I'll post the latest tech news to the channel!")

if __name__ == "__main__":
    # Print success message with Pyrogram version and system resource stats
    process = psutil.Process()
    memory_info = process.memory_info()
    cpu_percent = psutil.cpu_percent(interval=1)

    print(f"Bot Is Up And Running On Pyrogram {pyrogram_version}")
    print(f"Memory Usage: {memory_info.rss / 1024 ** 2:.2f} MB")
    print(f"CPU Usage: {cpu_percent}%")
    
    loop = asyncio.get_event_loop()
    loop.create_task(periodic_news_fetch())  # Start the background task
    app.run()