怎样实现全盘搜索脚本

本文目录导读：

1. Python 实现
2. 命令行方式
3. 高级 Python 脚本
4. 使用示例
5. 注意事项

Python 实现

基础全盘搜索

import os
import sys
def search_files(search_term, root_path='/' if sys.platform != 'win32' else 'C:\\'):
    """全盘搜索文件"""
    results = []
    try:
        for root, dirs, files in os.walk(root_path):
            # 搜索文件名
            for file in files:
                if search_term.lower() in file.lower():
                    results.append(os.path.join(root, file))
            # 搜索目录名
            for dir_name in dirs:
                if search_term.lower() in dir_name.lower():
                    results.append(os.path.join(root, dir_name))
    except (PermissionError, OSError) as e:
        print(f"访问被拒绝: {e}")
    return results
# 使用示例
search_term = input("请输入搜索内容: ")
results = search_files(search_term)
print(f"找到 {len(results)} 个结果:")
for r in results[:20]:  # 只显示前20个
    print(r)

带进度的多盘搜索

import os
import threading
from pathlib import Path
class FullDiskSearch:
    def __init__(self, search_term):
        self.search_term = search_term.lower()
        self.results = []
        self.scanned = 0
    def search_disk(self, disk_path):
        """搜索单个磁盘"""
        try:
            for root, dirs, files in os.walk(disk_path, topdown=True):
                # 跳过系统目录
                skip_dirs = {'windows', 'system32', '$recycle.bin', 
                           'system volume information', 'pagefile.sys'}
                dirs[:] = [d for d in dirs if d.lower() not in skip_dirs]
                self.scanned += len(files) + len(dirs)
                for item in dirs + files:
                    if self.search_term in item.lower():
                        self.results.append(os.path.join(root, item))
        except Exception as e:
            pass
    def search_all_disks(self):
        """搜索所有磁盘"""
        import platform
        if platform.system() == "Windows":
            # Windows 搜索所有盘符
            for letter in 'ABCDEFGHIJKLMNOPQRSTUVWXYZ':
                disk = f"{letter}:\\"
                if os.path.exists(disk):
                    print(f"正在搜索 {disk}...")
                    self.search_disk(disk)
        else:
            # Linux/Unix 搜索根目录
            print("正在搜索 / ...")
            self.search_disk('/')
        return self.results
# 使用
searcher = FullDiskSearch("重要文件")
results = searcher.search_all_disks()

命令行方式

Windows (PowerShell)

# 搜索所有文件
Get-ChildItem -Path C:\ -Recurse -Filter "*关键词*" -ErrorAction SilentlyContinue
# 搜索特定类型
Get-ChildItem -Path D:\ -Recurse -Filter "*.pdf" -ErrorAction SilentlyContinue

Linux/Mac (Shell)

#!/bin/bash
# 全盘搜索文件
find / -name "*关键词*" 2>/dev/null
# 搜索文本内容
grep -r "关键词" / 2>/dev/null
# 排除某些目录
find / -name "*关键词*" -not -path "*/proc/*" -not -path "*/sys/*" 2>/dev/null

高级 Python 脚本

#!/usr/bin/env python3
import os
import sys
import argparse
from concurrent.futures import ThreadPoolExecutor, as_completed
import time
class EnhancedFileSearch:
    def __init__(self):
        self.results = []
        self.total_files = 0
        self.start_time = None
    def search_directory(self, root_path, search_term, file_types=None):
        """搜索目录（支持文件类型过滤）"""
        local_results = []
        try:
            for root, dirs, files in os.walk(root_path, topdown=True):
                # 跳过系统目录
                skip_dirs = {'.git', '__pycache__', 'node_modules', 
                           'System32', 'Windows', 'AppData'}
                dirs[:] = [d for d in dirs if d not in skip_dirs]
                for file in files:
                    self.total_files += 1
                    # 文件类型过滤
                    if file_types:
                        ext = os.path.splitext(file)[1].lower()
                        if ext not in file_types:
                            continue
                    # 搜索文件名
                    if search_term.lower() in file.lower():
                        filepath = os.path.join(root, file)
                        local_results.append({
                            'path': filepath,
                            'size': os.path.getsize(filepath),
                            'modified': os.path.getmtime(filepath)
                        })
        except (PermissionError, OSError):
            pass
        return local_results
    def get_all_drives(self):
        """获取所有可访问的驱动器"""
        if sys.platform == 'win32':
            import string
            drives = []
            for letter in string.ascii_uppercase:
                drive = f"{letter}:\\"
                if os.path.exists(drive):
                    drives.append(drive)
            return drives
        else:
            return ['/']
    def search_all(self, search_term, file_types=None, max_workers=4):
        """并行搜索所有驱动器"""
        self.start_time = time.time()
        drives = self.get_all_drives()
        print(f"开始全盘搜索: '{search_term}'")
        print(f"扫描驱动器: {', '.join(drives)}")
        with ThreadPoolExecutor(max_workers=max_workers) as executor:
            futures = []
            for drive in drives:
                future = executor.submit(
                    self.search_directory, 
                    drive, 
                    search_term, 
                    file_types
                )
                futures.append(future)
            for future in as_completed(futures):
                self.results.extend(future.result())
        elapsed = time.time() - self.start_time
        return self.results
    def display_results(self, max_results=50):
        """显示结果"""
        print(f"\n搜索完成！共扫描 {self.total_files} 个文件")
        print(f"找到 {len(self.results)} 个匹配项")
        print(f"用时: {time.time() - self.start_time:.2f} 秒\n")
        if not self.results:
            print("未找到匹配的文件")
            return
        # 按修改时间排序
        self.results.sort(key=lambda x: x['modified'], reverse=True)
        for i, result in enumerate(self.results[:max_results], 1):
            size_mb = result['size'] / (1024 * 1024)
            mod_time = time.strftime(
                '%Y-%m-%d %H:%M:%S', 
                time.localtime(result['modified'])
            )
            print(f"{i:3}. {result['path']}")
            print(f"     大小: {size_mb:.2f} MB, 修改时间: {mod_time}")
        if len(self.results) > max_results:
            print(f"\n... 还有 {len(self.results) - max_results} 个结果未显示")
def main():
    parser = argparse.ArgumentParser(description='全盘文件搜索工具')
    parser.add_argument('search_term', help='搜索关键词')
    parser.add_argument('-t', '--types', nargs='*', 
                       help='文件类型过滤 (如 .pdf .txt .doc)')
    parser.add_argument('-w', '--workers', type=int, default=4,
                       help='并行工作线程数')
    parser.add_argument('-n', '--max-results', type=int, default=50,
                       help='显示最大结果数')
    args = parser.parse_args()
    searcher = EnhancedFileSearch()
    # 格式化文件类型
    file_types = None
    if args.types:
        file_types = [t.lower() if t.startswith('.') else f'.{t.lower()}' 
                     for t in args.types]
    # 执行搜索
    results = searcher.search_all(
        args.search_term, 
        file_types,
        args.workers
    )
    # 显示结果
    searcher.display_results(args.max_results)
if __name__ == "__main__":
    main()

使用示例

# 简单搜索
python search_script.py "重要文档"
# 搜索PDF文件
python search_script.py "报告" --types .pdf
# 使用8个线程并行搜索
python search_script.py "代码" --workers 8
# 显示更多结果
python search_script.py "照片" --max-results 100

注意事项

1. 性能影响：全盘搜索会消耗大量CPU和磁盘I/O
2. 权限问题：某些系统目录可能需要管理员权限
3. 缓存考虑：对于频繁搜索，建议建立索引缓存
4. 安全警告：不要在生产环境随意执行全盘搜索

这些脚本可以根据你的具体需求进行修改和扩展。