python3 分析 tree命令输出信息，并保存到excel中

python3 a_tree_dir_file_excel.py ./nvlink 3  nvlink_tree.xlsx
python3 a_tree_dir_file_excel.py ./zz_nvlink 3  zz_nvlink_tree.xlsx

# Python3默认使用Unicode编码，可以直接处理中文字符
# 但如果你需要确保编码，可以在文件开头添加编码声明
# -*- coding: utf-8 -*-

import pandas as pd
import os
import sys

def main():
    # 参数个数 (包括脚本名本身)
    arg_count = len(sys.argv)

    # 参数内容列表
    args = sys.argv

    print(f"参数个数: {arg_count}")
    print(f"参数列表: {args}")
    if 4 != arg_count:
        print(f"错误: {e}", file=sys.stderr)
        sys.exit(1)

    print(f"args[0]={args[0]} args[1]={args[1]} args[2]={args[2]}")

    cmdTree1 = "tree --noreport -n -L "
    cmdTree = cmdTree1 + args[2] + " " + args[1]
    outputfile = args[3]
    print(f"outputfile={outputfile}")
    # 生成 tree 文本并解析
    #tree_text = os.popen('tree --noreport -n -L 4 /home/gaozenghua/ACClink_Device/kernel/nvlink').read()
    tree_text = os.popen(cmdTree).read()
    #lines = [line.strip() for line in tree_text.split('\n') if line.strip()]
    lines = []
    for line in tree_text.split('\n'):
        stripped_line = line.strip()
        if stripped_line:  # 检查是否非空
            lines.append(line)
    # 转换为 DataFrame
    data = []
    shitname = ["序号1", "根文件", "第二级目录文件", "第三级目录文件", 
                "第四级目录文件", "第五级目录文件", "第六级目录文件", 
                "第七级目录文件", "第八级目录文件", "第九级目录文件", "第十级目录文件"]

    baseStr = ["├── ", "└── ", "│   ├── ", "│   └── ", "│   │   ├── ", "│   │   └── ", "│   │   │   ├── ", "│   │   │   └── "]
    firstDir =["├── ", "└── ", "│"]
    len1 = [len(s) for s in baseStr]
    #print(len1)
    indexDirFile = 0
    count = 0
    countMax = 0
    for line in lines:
        count = line.count('│')
        if count > countMax:
            countMax = count
    #print(f"countMax={countMax} count={count}")
    def contains_any_substring(main_string, substrings_list):
        """检查字符串是否包含列表中的任意子字符串"""
        if any(substring in main_string for substring in substrings_list):
            return 0  # 包含
        else:
            return -1  # 不包含
    def append_str_list():
        tmp = (countMax + 1) * 2
        for i in range(tmp):
            listArray.append(baseStr[i])
        return tmp

    # 初始化一个空列表
    listArray = []

    listCount = append_str_list()
    #print(f"countMax={countMax} listCount={listCount}")

    '''
    for str in listArray:
        print(f"listArray str={str}")
    '''
    runCnt = 0
    nameNULL = ""
    s = "Hello, 世界"  # 包含英文和中文
    length = len(s)    # 计算字符数（不是字节数）
    #print(length)      # 输出：8（H,e,l,l,o,, ,世,界）
    flagString1 = "│   "
    flagString2 = "├── "
    flagString3 = "└── "
    flagString4 = "    "

    flagStrSize = 4
    flagStrSize = len(flagString1)
    #print(f" flagString1={flagString1} flagStrSize={flagStrSize}=len(flagString1)")
    flagStrSize = len(flagString2)
    ##print(f" flagString2={flagString2} flagStrSize={flagStrSize}=len(flagString2)")
    flagStrSize = len(flagString3)
    #print(f" flagString3={flagString3} flagStrSize={flagStrSize}=len(flagString3)")
    ##print("\n\n")

    for line in lines:
        usefullBufIndex = 0
        if line.startswith((flagString1, flagString2, flagString3, flagString4)):
            #print(f"-1- listCount={listCount} line={line}")
            indexDirFile = indexDirFile + 1

            flagStrSize = line.find(flagString2)
            if -1 == flagStrSize:
                flagStrSize = line.find(flagString3)
            else:
                usefullBufIndex = len(flagString2)
            if -1 == flagStrSize:
                print(f"************Unusefull listCount={listCount} line=({line})")
            else:
                usefullBufIndex = len(flagString3)
                usefullBufIndex = usefullBufIndex + flagStrSize
                lineIndex = line[usefullBufIndex:]
                if (usefullBufIndex / len(flagString2)) > (usefullBufIndex / len(flagString3)):
                    bufferIndex = (int)(usefullBufIndex / len(flagString2))
                else:
                    bufferIndex = (int)(usefullBufIndex / len(flagString3))
                #print(f"usefull indexDirFile={indexDirFile} line=\"{line}\" lineIndex=\"{lineIndex}\" bufferIndex={bufferIndex} flagStrSize={flagStrSize} usefullBufIndex={usefullBufIndex}")
                if 1 == bufferIndex:
                    data.append({shitname[0]: indexDirFile, shitname[1]: lineIndex})
                elif 2 == bufferIndex:
                    data.append({shitname[0]: indexDirFile, shitname[1]: nameNULL, shitname[2]: lineIndex})
                elif 3 == bufferIndex:
                    data.append({shitname[0]: indexDirFile, shitname[1]: nameNULL, shitname[2]: nameNULL, shitname[3]: lineIndex})
                elif 4 == bufferIndex:
                    data.append({shitname[0]: indexDirFile, shitname[1]: nameNULL, shitname[2]: nameNULL, shitname[3]: nameNULL, shitname[4]: lineIndex})
        else:
            print(f"Unusefull listCount={listCount} line={line}")

    df = pd.DataFrame(data)

    # 保存为 Excel
    df.to_excel(outputfile, index=False, engine='openpyxl')

if __name__ == "__main__":
    main()