import os
import shutil
from pathlib import Path
from collections import defaultdict

def get_disk_usage():
    """獲取所有磁盤分區(qū)的使用情況"""
    print("=" * 60)
    print(f"{'盤符':<8}{'總?cè)萘?:<12}{'已用':<12}{'可用':<12}{'使用率':<8}")
    print("=" * 60)

    results = []
    for partition in os.popen("wmic logicaldisk get caption,size,freespace").readlines()[1:]:
        parts = partition.strip().split()
        if len(parts) < 3:
            continue

        drive = parts[0]
        total = int(parts[1])  # 字節(jié)
        free = int(parts[2])
        used = total - free
        usage_percent = (used / total * 100) if total > 0 else 0

        # 格式化顯示
        total_gb = total / 1024**3
        used_gb = used / 1024**3
        free_gb = free / 1024**3

        # 根據(jù)使用率選擇顯示標(biāo)記
        if usage_percent >= 90:
            icon = "??"
        elif usage_percent >= 80:
            icon = "??"
        else:
            icon = "??"

        print(f"{icon} {drive:<6}{total_gb:>8.1f} GB{used_gb:>8.1f} GB"
              f"{free_gb:>8.1f} GB{usage_percent:>6.1f}%")

        results.append({
            "drive": drive,
            "total_gb": total_gb,
            "used_gb": used_gb,
            "free_gb": free_gb,
            "usage_percent": usage_percent,
        })

    return results


# 使用
# disks = get_disk_usage()

def scan_large_files(
    directory,
    min_size_mb=100,
    top_n=20,
    exclude_dirs=None
):
    """
    掃描大文件
    directory: 掃描目錄
    min_size_mb: 最小文件大?。∕B）
    top_n: 返回前 N 個
    exclude_dirs: 排除的目錄列表
    """
    if exclude_dirs is None:
        exclude_dirs = [
            r"C:\Windows", r"C:\Program Files",
            r"C:\Program Files (x86)",
        ]

    large_files = []
    min_size_bytes = min_size_mb * 1024 * 1024

    print(f"正在掃描 {directory}（最小 {min_size_mb} MB）...")

    for root, dirs, files in os.walk(directory):
        # 排除目錄
        dirs[:] = [
            d for d in dirs
            if not any(
                os.path.normpath(os.path.join(root, d)).startswith(
                    os.path.normpath(excl)
                )
                for excl in exclude_dirs
            )
        ]

        for file in files:
            try:
                filepath = os.path.join(root, file)
                size = os.path.getsize(filepath)
                if size >= min_size_bytes:
                    mtime = os.path.getmtime(filepath)
                    large_files.append({
                        "path": filepath,
                        "size_mb": round(size / 1024**2, 1),
                        "size_bytes": size,
                        "modified": mtime,
                    })
            except (PermissionError, OSError):
                continue

    # 按大小排序
    large_files.sort(key=lambda x: x["size_bytes"], reverse=True)

    print(f"\n發(fā)現(xiàn) {len(large_files)} 個大文件，TOP {top_n}：\n")

    for f in large_files[:top_n]:
        from datetime import datetime
        mod_time = datetime.fromtimestamp(f["modified"]).strftime("%Y-%m-%d")
        print(f"  {f['size_mb']:>8.1f} MB  {mod_time}  {f['path']}")

    return large_files


# 使用：掃描 D 盤超過 500MB 的文件
# large_files = scan_large_files(r"D:\", min_size_mb=500, top_n=30)

def get_directory_sizes(
    root_dir,
    max_depth=2,
    top_n=15,
    exclude_dirs=None
):
    """
    分析目錄大小
    max_depth: 遞歸深度
    """
    if exclude_dirs is None:
        exclude_dirs = []

    dir_sizes = defaultdict(int)

    print(f"正在分析 {root_dir} 的目錄大小...")

    for root, dirs, files in os.walk(root_dir):
        # 計算當(dāng)前深度
        rel_path = os.path.relpath(root, root_dir)
        depth = rel_path.count(os.sep) + (1 if rel_path != "." else 0)

        if depth > max_depth:
            dirs.clear()  # 不再深入
            continue

        # 排除目錄
        dirs[:] = [
            d for d in dirs
            if not any(os.path.join(root, d).startswith(excl) for excl in exclude_dirs)
        ]

        # 統(tǒng)計當(dāng)前目錄下文件大小
        current_size = 0
        for file in files:
            try:
                current_size += os.path.getsize(os.path.join(root, file))
            except (PermissionError, OSError):
                pass

        # 累加到各級父目錄
        if depth <= max_depth:
            dir_sizes[root] += current_size

    # 排序
    sorted_dirs = sorted(dir_sizes.items(), key=lambda x: x[1], reverse=True)

    print(f"\nTOP {top_n} 目錄：\n")
    total = sum(s for _, s in sorted_dirs)

    for path, size in sorted_dirs[:top_n]:
        size_gb = size / 1024**3
        percent = (size / total * 100) if total > 0 else 0
        # 進(jìn)度條可視化
        bar_len = 30
        filled = int(bar_len * percent / 100)
        bar = "█" * filled + "?" * (bar_len - filled)
        print(f"  {size_gb:>8.2f} GB  {bar} {percent:>5.1f}%")
        print(f"             {path}")

    return sorted_dirs


# 使用
# dirs = get_directory_sizes(r"C:\Users", max_depth=2, exclude_dirs=[r"C:\Users\Default"])

import hashlib

def get_file_hash(filepath, block_size=65536):
    """計算文件的 MD5 哈希"""
    hasher = hashlib.md5()
    try:
        with open(filepath, "rb") as f:
            for block in iter(lambda: f.read(block_size), b""):
                hasher.update(block)
        return hasher.hexdigest()
    except (PermissionError, OSError):
        return None


def find_duplicate_files(directory, min_size_kb=100):
    """
    找出重復(fù)文件（基于文件大小+MD5雙重校驗）
    min_size_kb: 只檢測大于此大小的文件
    """
    # 第一步：按文件大小分組
    print("第一步：按文件大小分組...")
    size_groups = defaultdict(list)

    for root, dirs, files in os.walk(directory):
        for file in files:
            try:
                filepath = os.path.join(root, file)
                size = os.path.getsize(filepath)
                if size >= min_size_kb * 1024:
                    size_groups[size].append(filepath)
            except (PermissionError, OSError):
                continue

    # 只保留有多個文件的組
    potential_duplicates = {
        size: files for size, files in size_groups.items()
        if len(files) >= 2
    }

    print(f"發(fā)現(xiàn) {len(potential_duplicates)} 組大小相同的文件")

    # 第二步：對大小相同的文件計算 MD5
    print("第二步：計算 MD5 確認(rèn)重復(fù)...")
    duplicates = {}  # hash -> [filepath, ...]

    total_to_check = sum(len(files) for files in potential_duplicates.values())
    checked = 0

    for size, files in potential_duplicates.items():
        for filepath in files:
            file_hash = get_file_hash(filepath)
            checked += 1

            if file_hash:
                if file_hash not in duplicates:
                    duplicates[file_hash] = []
                duplicates[file_hash].append(filepath)

    # 只保留真正重復(fù)的
    true_duplicates = {
        h: files for h, files in duplicates.items()
        if len(files) >= 2
    }

    # 統(tǒng)計可釋放空間
    total_wasted = 0
    for h, files in true_duplicates.items():
        # 保留一個，其余都是浪費
        size = os.path.getsize(files[0])
        total_wasted += size * (len(files) - 1)

    print(f"\n發(fā)現(xiàn) {len(true_duplicates)} 組重復(fù)文件")
    print(f"可釋放空間: {total_wasted / 1024**3:.2f} GB\n")

    # 按浪費空間排序
    dup_sorted = sorted(
        true_duplicates.items(),
        key=lambda x: os.path.getsize(x[1][0]) * (len(x[1]) - 1),
        reverse=True
    )

    for h, files in dup_sorted[:10]:
        size = os.path.getsize(files[0])
        wasted = size * (len(files) - 1)
        print(f"  重復(fù) {len(files)} 份, 各 {size/1024**2:.1f} MB, "
              f"浪費 {wasted/1024**2:.1f} MB")
        for f in files:
            print(f"    {f}")
        print()

    return true_duplicates


def cleanup_duplicates(duplicate_map, dry_run=True):
    """
    清理重復(fù)文件（保留每組中的第一個）
    dry_run: True=只報告不刪除
    """
    total_freed = 0

    for h, files in duplicate_map.items():
        # 保留第一個，刪除其余
        keep = files[0]
        remove = files[1:]

        for filepath in remove:
            if dry_run:
                size = os.path.getsize(filepath)
                total_freed += size
                print(f"  [模擬刪除] {filepath} ({size/1024**2:.1f} MB)")
            else:
                try:
                    size = os.path.getsize(filepath)
                    os.remove(filepath)
                    total_freed += size
                    print(f"  [已刪除] {filepath} ({size/1024**2:.1f} MB)")
                except Exception as e:
                    print(f"  [失敗] {filepath}: {e}")

    action = "可釋放" if dry_run else "已釋放"
    print(f"\n{action}空間: {total_freed / 1024**3:.2f} GB")

    if dry_run:
        print("\n?? 這是模擬運(yùn)行，沒有實際刪除文件。")
        print("確認(rèn)無誤后，設(shè)置 dry_run=False 重新運(yùn)行。")

    return total_freed


# 使用
# dups = find_duplicate_files(r"D:\Data", min_size_kb=1024)
# cleanup_duplicates(dups, dry_run=True)  # 先模擬
# cleanup_duplicates(dups, dry_run=False)  # 確認(rèn)后刪除

from datetime import datetime, timedelta
import re

class DiskCleaner:
    """智能磁盤清理器"""

    # 常見可清理的目錄和模式
    CLEANUP_TARGETS = {
        "Windows 臨時文件": r"C:\Windows\Temp",
        "用戶臨時文件": os.path.join(os.environ.get("TEMP", ""), ""),
        "縮略圖緩存": os.path.join(
            os.environ.get("LOCALAPPDATA", ""), "Microsoft", "Windows", "Explorer"
        ),
        "Windows 更新緩存": r"C:\Windows\SoftwareDistribution\Download",
        "Prefetch 緩存": r"C:\Windows\Prefetch",
    }

    # 可清理的文件模式
    CLEANUP_PATTERNS = {
        "日志文件": [r"\.log$"],
        "臨時文件": [r"\.tmp$", r"\.temp$", r"~\$"],
        "緩存文件": [r"\.cache$", r"\.bak$"],
        "縮略圖數(shù)據(jù)庫": [r"thumbcache_.*\.db$"],
    }

    # 可清理的目錄模式
    CLEANUP_DIR_PATTERNS = {
        "node_modules": r"node_modules$",
        "__pycache__": r"__pycache__$",
        ".pytest_cache": r"\.pytest_cache$",
        "pip cache": r"pip[\\/]cache$",
    }

    def __init__(self, dry_run=True):
        self.dry_run = dry_run
        self.report = defaultdict(lambda: {"count": 0, "size": 0})

    def clean_temp_directories(self):
        """清理系統(tǒng)臨時目錄"""
        print("\n=== 清理臨時目錄 ===")

        for name, path in self.CLEANUP_TARGETS.items():
            if not os.path.exists(path):
                continue

            total_size = 0
            file_count = 0

            for item in os.listdir(path):
                item_path = os.path.join(path, item)
                try:
                    if os.path.isfile(item_path):
                        size = os.path.getsize(item_path)
                        total_size += size
                        file_count += 1
                        if not self.dry_run:
                            os.remove(item_path)
                    elif os.path.isdir(item_path):
                        size = sum(
                            os.path.getsize(os.path.join(dp, f))
                            for dp, dn, fn in os.walk(item_path)
                            for f in fn
                        )
                        total_size += size
                        file_count += 1
                        if not self.dry_run:
                            shutil.rmtree(item_path)
                except (PermissionError, OSError):
                    pass

            self.report[name]["count"] = file_count
            self.report[name]["size"] = total_size

            action = "可清理" if self.dry_run else "已清理"
            if file_count > 0:
                print(f"  {name}: {action} {file_count} 項 "
                      f"({total_size/1024/1024:.1f} MB)")

    def clean_old_logs(self, days=30, log_dirs=None):
        """清理 N 天前的舊日志"""
        print(f"\n=== 清理 {days} 天前的日志 ===")

        if log_dirs is None:
            log_dirs = [
                r"C:\inetpub\logs",
                r"C:\Windows\System32\winevt\Logs",
            ]

        cutoff = time.time() - (days * 86400)
        total_cleaned = 0

        for log_dir in log_dirs:
            if not os.path.exists(log_dir):
                continue

            for root, dirs, files in os.walk(log_dir):
                for file in files:
                    if not file.endswith(".log"):
                        continue

                    filepath = os.path.join(root, file)
                    try:
                        mtime = os.path.getmtime(filepath)
                        if mtime < cutoff:
                            size = os.path.getsize(filepath)
                            total_cleaned += size

                            if self.dry_run:
                                from datetime import datetime as dt
                                mod_date = dt.fromtimestamp(mtime).strftime("%Y-%m-%d")
                                print(f"  [模擬] {filepath} ({size/1024/1024:.1f} MB, {mod_date})")
                            else:
                                os.remove(filepath)
                    except (PermissionError, OSError):
                        pass

        action = "可釋放" if self.dry_run else "已釋放"
        print(f"\n日志清理: {action} {total_cleaned/1024/1024:.1f} MB")

    def clean_recycle_bin(self):
        """清空回收站"""
        import ctypes

        print("\n=== 清空回收站 ===")

        if self.dry_run:
            # 估算回收站大小
            print("  [模擬] 清空回收站")
            return

        try:
            # Windows API 清空回收站
            result = ctypes.windll.shell32.SHEmptyRecycleBinW(None, None, 7)
            if result == 0:
                print("  回收站已清空")
            else:
                print(f"  清空回收站返回: {result}")
        except Exception as e:
            print(f"  清空回收站失敗: {e}")

    def run_full_cleanup(self):
        """執(zhí)行完整清理"""
        mode = "模擬" if self.dry_run else "實際"
        print(f"{'=' * 60}")
        print(f"  磁盤清理 ({mode}模式)")
        print(f"{'=' * 60}")

        self.clean_temp_directories()
        self.clean_old_logs(days=30)
        self.clean_recycle_bin()

        # 匯總
        total_size = sum(item["size"] for item in self.report.values())
        print(f"\n{'=' * 60}")
        action = "總計可釋放" if self.dry_run else "總計已釋放"
        print(f"  {action}: {total_size / 1024 / 1024:.1f} MB")
        print(f"{'=' * 60}")

        if self.dry_run:
            print("\n確認(rèn)無誤后，使用 DiskCleaner(dry_run=False) 執(zhí)行實際清理")

        return total_size


import time

# 使用示例
# cleaner = DiskCleaner(dry_run=True)   # 先模擬
# cleaner.run_full_cleanup()
# cleaner = DiskCleaner(dry_run=False)   # 確認(rèn)后執(zhí)行
# cleaner.run_full_cleanup()

import json
from datetime import datetime, timedelta
from pathlib import Path

class DiskMonitor:
    """磁盤空間持續(xù)監(jiān)控器"""

    def __init__(self, data_file="disk_history.json"):
        self.data_file = Path(data_file)
        self.history = self._load_history()
        self.threshold_warning = 80  # 警告閾值 %
        self.threshold_critical = 95  # 嚴(yán)重閾值 %

    def _load_history(self):
        """加載歷史數(shù)據(jù)"""
        if self.data_file.exists():
            with open(self.data_file, "r") as f:
                return json.load(f)
        return []

    def _save_history(self):
        """保存歷史數(shù)據(jù)"""
        with open(self.data_file, "w") as f:
            json.dump(self.history, f, ensure_ascii=False, indent=2)

    def record_snapshot(self):
        """記錄當(dāng)前磁盤快照"""
        snapshot = {
            "timestamp": datetime.now().isoformat(),
            "drives": [],
        }

        for partition in os.popen(
            "wmic logicaldisk get caption,size,freespace"
        ).readlines()[1:]:
            parts = partition.strip().split()
            if len(parts) < 3:
                continue

            total = int(parts[1])
            free = int(parts[2])
            usage = ((total - free) / total * 100) if total > 0 else 0

            snapshot["drives"].append({
                "drive": parts[0],
                "total_gb": round(total / 1024**3, 2),
                "free_gb": round(free / 1024**3, 2),
                "usage_percent": round(usage, 1),
            })

        self.history.append(snapshot)

        # 只保留最近 90 天的數(shù)據(jù)
        cutoff = (datetime.now() - timedelta(days=90)).isoformat()
        self.history = [
            h for h in self.history
            if h["timestamp"] >= cutoff
        ]
        self._save_history()

        return snapshot

    def check_alerts(self, snapshot=None):
        """檢查是否需要告警"""
        if not snapshot:
            snapshot = self.record_snapshot()

        alerts = []

        for drive in snapshot["drives"]:
            usage = drive["usage_percent"]
            free_gb = drive["free_gb"]

            if usage >= self.threshold_critical:
                alerts.append({
                    "severity": "CRITICAL",
                    "drive": drive["drive"],
                    "message": (
                        f"{drive['drive']} 磁盤空間嚴(yán)重不足！"
                        f"已用 {usage}%，僅剩 {free_gb:.1f} GB"
                    ),
                })
            elif usage >= self.threshold_warning:
                alerts.append({
                    "severity": "WARNING",
                    "drive": drive["drive"],
                    "message": (
                        f"{drive['drive']} 磁盤空間不足警告："
                        f"已用 {usage}%，剩余 {free_gb:.1f} GB"
                    ),
                })

        return alerts

    def analyze_trend(self, drive_letter, days=30):
        """分析磁盤使用趨勢"""
        cutoff = (datetime.now() - timedelta(days=days)).isoformat()
        recent = [
            h for h in self.history
            if h["timestamp"] >= cutoff
        ]

        # 提取目標(biāo)盤符的數(shù)據(jù)點
        data_points = []
        for h in recent:
            for d in h["drives"]:
                if d["drive"] == drive_letter:
                    data_points.append({
                        "time": h["timestamp"],
                        "usage": d["usage_percent"],
                        "free_gb": d["free_gb"],
                    })
                    break

        if len(data_points) < 2:
            print(f"數(shù)據(jù)不足（需要至少 2 個數(shù)據(jù)點，當(dāng)前 {len(data_points)} 個）")
            return None

        # 計算趨勢
        first = data_points[0]
        last = data_points[-1]

        usage_change = last["usage"] - first["usage"]
        free_change = last["free_gb"] - first["free_gb"]
        days_span = len(data_points)  # 近似天數(shù)

        daily_usage_increase = usage_change / days_span if days_span > 0 else 0
        daily_free_decrease = abs(free_change) / days_span if days_span > 0 else 0

        # 預(yù)計何時達(dá)到閾值
        if daily_usage_increase > 0:
            days_to_warning = (self.threshold_warning - last["usage"]) / daily_usage_increase
            days_to_critical = (self.threshold_critical - last["usage"]) / daily_usage_increase
        else:
            days_to_warning = float('inf')
            days_to_critical = float('inf')

        report = {
            "drive": drive_letter,
            "period": f"最近 {days} 天",
            "data_points": len(data_points),
            "current_usage": f"{last['usage']}%",
            "current_free": f"{last['free_gb']} GB",
            "usage_change": f"+{usage_change:.1f}%" if usage_change > 0 else f"{usage_change:.1f}%",
            "free_change": f"{free_change:.1f} GB",
            "daily_increase": f"+{daily_usage_increase:.2f}%" if daily_usage_increase > 0 else "穩(wěn)定",
            "days_to_warning": f"{days_to_warning:.0f} 天" if days_to_warning < 365 else "無風(fēng)險",
            "days_to_critical": f"{days_to_critical:.0f} 天" if days_to_critical < 365 else "無風(fēng)險",
        }

        print(f"\n=== {drive_letter} 磁盤使用趨勢 ({report['period']}) ===")
        print(f"  當(dāng)前使用率: {report['current_usage']}, 剩余: {report['current_free']}")
        print(f"  變化: 使用率 {report['usage_change']}, 空間 {report['free_change']}")
        print(f"  日均增長: {report['daily_increase']}")
        print(f"  預(yù)計觸發(fā)警告: {report['days_to_warning']}")
        print(f"  預(yù)計磁盤滿: {report['days_to_critical']}")

        return report


# 使用示例
# monitor = DiskMonitor()
# monitor.record_snapshot()  # 記錄快照
# alerts = monitor.check_alerts()
# monitor.analyze_trend("C:", days=30)