You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
124 lines
3.3 KiB
124 lines
3.3 KiB
import os
|
|
import shutil
|
|
from pathlib import Path
|
|
import logging
|
|
|
|
class FileUtils:
|
|
"""文件工具类，提供文件操作相关的功能"""
|
|
|
|
@staticmethod
|
|
def ensure_dir(dir_path):
|
|
"""
|
|
确保目录存在，如果不存在则创建
|
|
|
|
Args:
|
|
dir_path: 目录路径
|
|
|
|
Returns:
|
|
bool: 操作是否成功
|
|
"""
|
|
try:
|
|
Path(dir_path).mkdir(parents=True, exist_ok=True)
|
|
return True
|
|
except Exception as e:
|
|
logging.error(f"创建目录失败: {e}")
|
|
return False
|
|
|
|
@staticmethod
|
|
def is_valid_pdf(file_path):
|
|
"""
|
|
检查文件是否是有效的PDF文件
|
|
|
|
Args:
|
|
file_path: 文件路径
|
|
|
|
Returns:
|
|
bool: 是否是有效的PDF文件
|
|
"""
|
|
if not Path(file_path).exists():
|
|
return False
|
|
|
|
# 简单检查文件扩展名
|
|
if not str(file_path).lower().endswith('.pdf'):
|
|
return False
|
|
|
|
# 检查文件头部是否包含PDF标识
|
|
try:
|
|
with open(file_path, 'rb') as f:
|
|
header = f.read(5)
|
|
return header == b'%PDF-'
|
|
except Exception:
|
|
return False
|
|
|
|
@staticmethod
|
|
def get_pdf_files_in_dir(dir_path, recursive=False):
|
|
"""
|
|
获取目录中的所有PDF文件
|
|
|
|
Args:
|
|
dir_path: 目录路径
|
|
recursive: 是否递归搜索子目录
|
|
|
|
Returns:
|
|
list: PDF文件路径列表
|
|
"""
|
|
pdf_files = []
|
|
dir_path = Path(dir_path)
|
|
|
|
if not dir_path.exists() or not dir_path.is_dir():
|
|
return pdf_files
|
|
|
|
if recursive:
|
|
for root, _, files in os.walk(dir_path):
|
|
for file in files:
|
|
file_path = Path(root) / file
|
|
if FileUtils.is_valid_pdf(file_path):
|
|
pdf_files.append(str(file_path))
|
|
else:
|
|
for file in dir_path.iterdir():
|
|
if file.is_file() and FileUtils.is_valid_pdf(file):
|
|
pdf_files.append(str(file))
|
|
|
|
return pdf_files
|
|
|
|
@staticmethod
|
|
def get_file_size_str(file_path):
|
|
"""
|
|
获取文件大小的字符串表示
|
|
|
|
Args:
|
|
file_path: 文件路径
|
|
|
|
Returns:
|
|
str: 文件大小字符串，如 "1.2 MB"
|
|
"""
|
|
try:
|
|
size = Path(file_path).stat().st_size
|
|
|
|
for unit in ['B', 'KB', 'MB', 'GB', 'TB']:
|
|
if size < 1024.0:
|
|
return f"{size:.1f} {unit}"
|
|
size /= 1024.0
|
|
|
|
return f"{size:.1f} PB"
|
|
except Exception:
|
|
return "未知大小"
|
|
|
|
@staticmethod
|
|
def copy_file(src, dst):
|
|
"""
|
|
复制文件
|
|
|
|
Args:
|
|
src: 源文件路径
|
|
dst: 目标文件路径
|
|
|
|
Returns:
|
|
bool: 操作是否成功
|
|
"""
|
|
try:
|
|
shutil.copy2(src, dst)
|
|
return True
|
|
except Exception as e:
|
|
logging.error(f"复制文件失败: {e}")
|
|
return False |