本文目录导读：
Python脚本（跨平台）
#!/usr/bin/env python3
import os
import re
from pathlib import Path
def search_files(directory, keyword, file_extensions=None):
"""按关键词搜索文件内容"""
results = []
directory = Path(directory)
if not directory.exists():
print(f"目录 {directory} 不存在")
return results
for file_path in directory.rglob('*'):
# 检查文件扩展名
if file_extensions and file_path.suffix not in file_extensions:
continue
# 只处理文件，跳过目录
if not file_path.is_file():
continue
try:
# 尝试以文本方式读取
with open(file_path, 'r', encoding='utf-8', errors='ignore') as f:
content = f.read()
# 搜索关键词
if keyword.lower() in content.lower():
# 找到关键词出现的位置（前后显示一些上下文）
lines = content.split('\n')
for i, line in enumerate(lines, 1):
if keyword.lower() in line.lower():
results.append({
'file': str(file_path),
'line': i,
'content': line.strip()
})
except (IOError, OSError):
# 跳过无法读取的文件
continue
return results
# 使用示例
if __name__ == "__main__":
search_dir = "/path/to/search" # 修改为要搜索的目录
keyword = "your_keyword" # 修改为要搜索的关键词
# 可选：只搜索特定类型文件
extensions = ['.txt', '.py', '.md', '.js', '.html']
results = search_files(search_dir, keyword, extensions)
print(f"找到 {len(results)} 个匹配结果：")
for result in results[:20]: # 只显示前20个结果
print(f"{result['file']}:{result['line']} - {result['content'][:100]}")
Linux/Unix Shell脚本
#!/bin/bash
关键词搜索文件
search_directory=$1
keyword=$2
file_pattern=$3
if [ -z "$search_directory" ] || [ -z "$keyword" ]; then
echo "用法: $0 <搜索目录> <关键词> [文件模式]"
echo "示例: $0 /home/user 'important' '*.txt'"
exit 1
fi
if [ -z "$file_pattern" ]; then
# 默认搜索所有文件
find "$search_directory" -type f -exec grep -l -i "$keyword" {} \; 2>/dev/null
else
# 按文件模式搜索
find "$search_directory" -type f -name "$file_pattern" -exec grep -l -i "$keyword" {} \; 2>/dev/null
fi
Windows PowerShell脚本
param(
[string]$SearchPath = ".",
[string]$Keyword,
[string]$FilePattern = "*.*"
)
function Search-Files {
param(
[string]$Path,
[string]$Keyword,
[string]$Pattern
)
if (-not (Test-Path $Path)) {
Write-Error "路径不存在: $Path"
return
}
Get-ChildItem -Path $Path -Recurse -File -Filter $Pattern |
ForEach-Object {
try {
$content = Get-Content -Path $_.FullName -Raw -ErrorAction Stop
if ($content -match $Keyword) {
[PSCustomObject]@{
File = $_.FullName
Size = $_.Length
Modified = $_.LastWriteTime
}
}
}
catch {
# 跳过无法读取的文件
}
}
}
# 使用示例
Search-Files -Path "C:\Documents" -Keyword "report" -Pattern "*.docx"高级Python脚本（带进度显示和多种选项）
#!/usr/bin/env python3
import os
import argparse
import fnmatch
from pathlib import Path
from concurrent.futures import ThreadPoolExecutor
class FileSearcher:
def __init__(self, root_dir, keyword, extensions=None, case_sensitive=False):
self.root_dir = Path(root_dir)
self.keyword = keyword if case_sensitive else keyword.lower()
self.extensions = extensions
self.case_sensitive = case_sensitive
self.results = []
def search_file(self, file_path):
"""在单个文件中搜索关键词"""
try:
with open(file_path, 'r', encoding='utf-8', errors='ignore') as f:
lines = f.readlines()
matches = []
for line_num, line in enumerate(lines, 1):
content = line if self.case_sensitive else line.lower()
if self.keyword in content:
matches.append({
'file': str(file_path),
'line': line_num,
'content': line.strip()[:200]
})
return matches
except Exception:
return []
def search(self, max_workers=4):
"""并行搜索所有文件"""
files_to_search = []
# 收集所有需要搜索的文件
for file_path in self.root_dir.rglob('*'):
if not file_path.is_file():
continue
# 检查文件扩展名
if self.extensions:
if file_path.suffix not in self.extensions:
continue
files_to_search.append(file_path)
# 使用线程池并行搜索
with ThreadPoolExecutor(max_workers=max_workers) as executor:
futures = [executor.submit(self.search_file, f) for f in files_to_search]
for future in futures:
result = future.result()
if result:
self.results.extend(result)
return self.results
def main():
parser = argparse.ArgumentParser(description='按内容关键词搜索文件')
parser.add_argument('directory', help='要搜索的目录')
parser.add_argument('keyword', help='搜索关键词')
parser.add_argument('-e', '--extensions', nargs='+',
help='文件扩展名过滤，如 .txt .py')
parser.add_argument('-c', '--case-sensitive', action='store_true',
help='区分大小写')
parser.add_argument('-w', '--max-workers', type=int, default=4,
help='最大并行工作线程数')
parser.add_argument('--limit', type=int, default=50,
help='显示结果数量限制')
args = parser.parse_args()
searcher = FileSearcher(
args.directory,
args.keyword,
args.extensions,
args.case_sensitive
)
print(f"正在搜索关键词 '{args.keyword}'...")
results = searcher.search(args.max_workers)
print(f"\n找到 {len(results)} 个匹配结果：")
for result in results[:args.limit]:
print(f"[{result['file']}:{result['line']}] {result['content']}")
if len(results) > args.limit:
print(f"... 还有 {len(results) - args.limit} 个结果未显示")
if __name__ == "__main__":
main()
使用示例
-
Python脚本：
python file_searcher.py /home/user/documents "重要信息" -e .txt .docx
-
Shell脚本：
chmod +x search.sh ./search.sh /home/user "keyword" "*.txt"
-
PowerShell：
.\search.ps1 -SearchPath "C:\Documents" -Keyword "report" -FilePattern "*.txt"
注意事项
- 性能优化：搜索大文件时可能较慢，建议限制文件类型
- 编码处理：脚本使用UTF-8编码，处理其他编码可能需要调整
- 权限问题：确保有读取目标文件的权限
- 二进制文件：脚本会自动跳过无法以文本打开的文件
这些脚本可以根据您的具体需求进行修改和扩展。
