Python关键词搜索工具无结果且耗时过长问题求助

一、核心问题排查 #

1. 关键词读取验证 #

先确认脚本是否正确读取keywords.txt，避免编码或空白字符问题：

with open('keywords.txt', 'r', encoding='utf-8') as f:
    # 过滤空行和首尾空白
    keywords = [line.strip() for line in f if line.strip()]
# 打印调试，确认关键词已读入
print(f"已加载关键词：{keywords}")

2. 遍历效率优化 #

耗时极长大概率是因为无差别遍历了所有文件/目录，跳过无关内容：

import os

# 定义要排除的目录和非文本文件后缀
EXCLUDE_DIRS = {'.git', 'node_modules', '__pycache__', 'venv'}
EXCLUDE_EXTS = {'.exe', '.png', '.jpg', '.zip', '.rar'}

def traverse_target_dir(root_dir):
    all_files = []
    for root, dirs, files in os.walk(root_dir):
        # 移除要排除的目录，避免递归进入
        dirs[:] = [d for d in dirs if d not in EXCLUDE_DIRS]
        for file in files:
            file_ext = os.path.splitext(file)[1].lower()
            if file_ext not in EXCLUDE_EXTS:
                all_files.append(os.path.join(root, file))
    return all_files

3. 匹配逻辑修正 #

检查是否存在匹配逻辑错误，比如大小写不敏感、匹配符误用：

def check_keyword_match(file_content, keywords):
    content_lower = file_content.lower()
    # 统一转为小写，避免大小写遗漏
    return any(keyword.lower() in content_lower for keyword in keywords)

二、生成目录结构式输出 #

要输出类似目录树的结果，需按层级整理文件并标记匹配项：

def build_directory_tree(root_dir, matched_files):
    tree_lines = []
    for root, dirs, files in os.walk(root_dir):
        # 计算当前目录层级，生成缩进
        depth = root.replace(root_dir, '').count(os.sep)
        indent = '│   ' * depth + '├── '
        # 添加目录节点
        tree_lines.append(f"{indent}{os.path.basename(root)}/")
        
        file_indent = '│   ' * (depth + 1) + '├── '
        for file in files:
            full_path = os.path.join(root, file)
            # 用[✓]标记匹配的文件，[ ]标记未匹配
            status = '[✓] ' if full_path in matched_files else '[ ] '
            tree_lines.append(f"{file_indent}{status}{file}")
    return '\n'.join(tree_lines)

# 最后写入output.txt
with open('output.txt', 'w', encoding='utf-8') as f:
    if matched_files:
        f.write(build_directory_tree(target_directory, matched_files))
    else:
        f.write("未找到包含关键词的文件")

三、提速优化 #

如果文件数量极大，用线程池并行处理文件读取和匹配：

from concurrent.futures import ThreadPoolExecutor

def process_single_file(file_path, keywords):
    try:
        # 忽略编码错误，避免因个别文件中断
        with open(file_path, 'r', encoding='utf-8', errors='ignore') as f:
            content = f.read()
        if check_keyword_match(content, keywords):
            return file_path
    except Exception:
        # 跳过无法读取的文件
        return None

# 调用示例
target_files = traverse_target_dir(target_directory)
matched_files = set()

with ThreadPoolExecutor(max_workers=4) as executor:
    results = executor.map(lambda path: process_single_file(path, keywords), target_files)
    matched_files = {res for res in results if res is not None}

内容的提问来源于stack exchange，提问作者Дима Пузырин