Linux Python下文件搜索与索引

在 Linux 系统中，使用 Python 进行文件搜索和索引可以通过多种方法实现

1. 使用 os 模块遍历目录：

import os

def search_files(directory, extension=None):
    found_files = []
    for root, dirs, files in os.walk(directory):
        for file in files:
            if extension is None or file.endswith(extension):
                found_files.append(os.path.join(root, file))
    return found_files

directory = '/path/to/search'
extension = '.txt'  # 要搜索的文件扩展名，如 .txt、.py 等，设为 None 以搜索所有文件
found_files = search_files(directory, extension)
print(found_files)

2. 使用 glob 模块搜索特定模式的文件：

import glob

def search_files_glob(pattern):
    return glob.glob(pattern, recursive=True)

directory = '/path/to/search'
extension = '*.txt'  # 要搜索的文件模式，如 *.txt、*.py 等
pattern = os.path.join(directory, '**', extension)
found_files = search_files_glob(pattern)
print(found_files)

3. 使用第三方库 Whoosh 进行全文搜索和索引：

首先安装 Whoosh 库：

pip install whoosh

然后创建一个简单的搜索和索引示例：

from whoosh.index import create_in, open_dir
from whoosh.fields import Schema, TEXT, ID
from whoosh.qparser import QueryParser
import os

# 创建索引目录
index_dir = 'indexdir'
if not os.path.exists(index_dir):
    os.mkdir(index_dir)

# 创建文件索引
def index_files(directory, index_dir):
    schema = Schema(path=ID(stored=True), content=TEXT)
    ix = create_in(index_dir, schema)
    writer = ix.writer()

    for root, dirs, files in os.walk(directory):
        for file in files:
            path = os.path.join(root, file)
            with open(path, 'r') as f:
                content = f.read()
                writer.add_document(path=path, content=content)

    writer.commit()

# 搜索文件内容
def search_files(query, index_dir):
    ix = open_dir(index_dir)
    with ix.searcher() as searcher:
        query_obj = QueryParser('content', ix.schema).parse(query)
        results = searcher.search(query_obj)
        return [result['path'] for result in results]

# 示例用法
directory = '/path/to/search'
index_files(directory, index_dir)

query = 'your search term'
found_files = search_files(query, index_dir)
print(found_files)

这些示例展示了如何使用 Python 在 Linux 系统中搜索和索引文件。你可以根据需求调整代码以满足特定的搜索和索引需求。