import os
import pandas as pd

# 要扫描的根目录
root_dir = '/home/onlylian/sorted_modality_files'

# 为 DataFrame 准备数据
data = []

# 遍历目录
for subdir, _, files in os.walk(root_dir):
    for file in files:
        if file.endswith('.nii.gz'):
            parts = subdir.split('/')
            try:
                if len(parts) >= 8:  # 标准结构
                    modalities = parts[4]  # 提取模态类型
                    patient_id = parts[5]  # 提取患者信息
                    date = parts[6]  # 提取日期
                    name = file  # 提取文件名
                elif len(parts) == 7:  # 当模态类型与具体模态合并时
                    modalities = parts[4]  # 提取模态类型
                    patient_id = parts[5]  # 提取患者信息
                    date = parts[6]  # 提取日期
                    name = file  # 提取文件名
                elif len(parts) == 6:  # 当只有日期和模态类型时
                    modalities = parts[4]  # 提取模态类型
                    patient_id = parts[5]  # 提取患者信息
                    date = ''  # 没有日期信息
                    name = file  # 提取文件名
                else:
                    print(f"Path {subdir} does not have enough parts to extract data")
                    continue
                data.append([modalities, patient_id, date, name])
                print(f"Added: {modalities}/{patient_id}/{date}/{name}")  # 调试信息
            except IndexError as e:
                print(f"Error processing path {subdir}: {e}")

# 检查数据是否已经添加
if not data:
    print("No data found. Please check the directory structure and files.")

# 创建 DataFrame
df = pd.DataFrame(data, columns=['Modalities', 'patient_id', 'date', 'name'])
# 输出到 Excel
output_path = '/home/onlylian/patient_modalities_files.xlsx'
df.to_excel(output_path, index=False)

print(f"Excel 文件已生成在: {output_path}")