torrents/94 WhatWehaveAlreadyDownloaded.py

import pymysql
import bencodepy
import os
from pathlib import Path

# ============================================================
# CONFIGURATION
# ============================================================
# Your network path (Use raw string r"..." for backslashes)
# PHYSICAL_DIR = Path(r"\\tower\torrents\downloads")
PHYSICAL_DIR = Path(r"\\tower1\#Colddata\Porno")

DB_CONFIG = {
    "host": "192.168.1.50",
    "port": 3306,
    "user": "root",
    "password": "Vlado9674+",
    "database": "torrents",
    "charset": "utf8mb4",
    "autocommit": True,
}


# ============================================================
# HELPER FUNCTIONS
# ============================================================
def decode_bytes(b):
    """
    Decodes bytes from Bencode into a string.
    Tries UTF-8 first, then common fallbacks.
    """
    if isinstance(b, str): return b
    encodings = ['utf-8', 'windows-1250', 'latin-1', 'cp1252']
    for enc in encodings:
        try:
            return b.decode(enc)
        except:
            continue
    return b.decode('utf-8', errors='ignore')


def check_torrent_in_filesystem(torrent_blob, root_path):
    """
    Parses the binary BLOB, calculates expected paths,
    and checks if they exist in the root_path.
    """
    try:
        # Decode the binary BLOB
        data = bencodepy.decode(torrent_blob)
        info = data.get(b'info')
        if not info: return False

        # Get the name of the root file/folder defined in the torrent
        name = decode_bytes(info.get(b'name'))

        # Calculate expected location
        target_path = root_path / name

        # 1. Check if the main path exists
        if not target_path.exists():
            return False

        # 2. Size Verification (Basic)
        # If it's a single file
        if b'files' not in info:
            expected_size = info[b'length']
            real_size = target_path.stat().st_size
            # Allow 1% variance or 1KB (sometimes filesystems vary slightly)
            if abs(real_size - expected_size) < 4096:
                return True
            return False

        # If it's a multi-file torrent (folder)
        else:
            # If the folder exists, we assume it's mostly good,
            # but let's check at least one file inside to be sure it's not empty.
            files = info[b'files']
            if not files: return True  # Empty folder torrent? rare but possible.

            # Check the first file in the list
            first_file_path = target_path.joinpath(*[decode_bytes(p) for p in files[0][b'path']])
            return first_file_path.exists()

    except Exception as e:
        # If Bencode fails or path is weird
        return False


# ============================================================
# MAIN EXECUTION
# ============================================================
if __name__ == "__main__":
    if not PHYSICAL_DIR.exists():
        print(f"❌ ERROR: Cannot access path: {PHYSICAL_DIR}")
        print("Make sure the drive is mapped or the network path is accessible.")
        exit()

    print(f"📂 Scanning storage: {PHYSICAL_DIR}")
    print("🚀 Connecting to Database...")

    db = pymysql.connect(**DB_CONFIG)
    cursor = db.cursor()

    # 1. Get all torrents that have content (BLOB)
    # We only select ID and Content to keep memory usage reasonable
    cursor.execute(
        "SELECT torrent_hash, title_visible, torrent_content FROM torrents WHERE torrent_content IS NOT NULL")

    rows = cursor.fetchall()
    total = len(rows)
    print(f"📋 Analysing {total} torrents from database against disk files...")

    found_count = 0
    missing_count = 0

    # 2. Iterate and Check
    updates = []  # Store successful hashes to batch update later

    for index, row in enumerate(rows):
        t_hash, title, blob = row

        is_downloaded = check_torrent_in_filesystem(blob, PHYSICAL_DIR)

        if is_downloaded:
            found_count += 1
            updates.append(t_hash)
            # Print only every 50th line to reduce clutter, or if found
            # print(f"✅ Found: {title[:50]}")
        else:
            missing_count += 1

        if index % 100 == 0:
            print(f"   Processed {index}/{total} ... (Found: {found_count})")

    # 3. Batch Update Database
    print(f"\n💾 Updating Database: Marking {len(updates)} torrents as 'physical_exists = 1'...")

    # Reset everything to 0 first (in case you deleted files since last run)
    cursor.execute("UPDATE torrents SET physical_exists = 0")

    if updates:
        # Update in chunks of 1000 to be safe
        chunk_size = 1000
        for i in range(0, len(updates), chunk_size):
            chunk = updates[i:i + chunk_size]
            format_strings = ','.join(['%s'] * len(chunk))
            cursor.execute(f"UPDATE torrents SET physical_exists = 1 WHERE torrent_hash IN ({format_strings})",
                           tuple(chunk))
            db.commit()

    db.close()

    print("\n" + "=" * 40)
    print(f"🏁 SCAN COMPLETE")
    print(f"✅ Physically Available: {found_count}")
    print(f"❌ Missing / Not Downloaded: {missing_count}")
    print(f"📊 Completion Rate: {int((found_count / total) * 100)}%")
    print("=" * 40)