提取坚果云思维导图的文字到md文件

分析

素材文件在文末

观察nbmx文件，猜测是压缩文档，尝试解压，得到content.json文件。观察content.json，部分内容如下：

{
    "data": {
        "expandState": "expand",
        "text": "先进制造系统（Advanced Manufacturing System）",
        "font-family": "黑体, SimHei",
        "font-weight": "bold"
    },
    "children": [
        {
            "data": {
                "text": "第 1 章",
                "connect-color": "#7FBADF",
                "expandState": "expand"
            },
            "children": [
                {
                    "data": {
                        "text": "AMS特点",
                        "connect-color": "#7FBADF",
                        "expandState": "expand"
                    },
                    "children": [
                        {
                            "data": {
                             ... ...

思路

1. 解压nbmx思维导图文件
2. 读取content.json
3. 解析json，递归读取每个"text"键的值，同时记录其层次深度
4. 以markdown格式保存为文件

实现

#--encoding:utf-8--
# Author: Allen Lv
# Time: 2021-05-14
# 转载请著名出处

import json

def getText(path: str) -> str:
    '''获取content.json的文本'''
    text = ""
    with open(path, "r", encoding="utf-8") as f:
        text = f.read()
    return text

def pickLines(info: dict, lines: list, depth=1) -> list:
    '''读取json字典，把每条信息保存到列表中'''
    # 取出信息行，然后标记层次
    ln = "${}$ {}".format(depth, info["data"]["text"])
    lines.append(ln)
    # 递归取得信息行
    if info.get("children", 0):
        for child_info in info["children"]:
            pickLines(child_info, lines, depth+1)

def mdFormat(lines: list) -> str:
    '''把信息行逐个格式化为md格式'''
    md_lines = []
    for line in lines:
        # 取得层次号
        i = int(line[1])
        symbol = "$" + str(i) + "$"
        new_symbol = "ERROR"
        # 前三层都是标题，之后都是无序列表
        if i <= 3:
            new_symbol = "#" * i
        else:
            new_symbol = "  " * (i-4) + "-"
        # 替换换行符
        _line = line.replace("\n", "\\n")
        # 替换层次标记符
        new_ln = _line.replace(symbol, new_symbol)
        md_lines.append(new_ln)       
    # 返回md格式文本
    return "\n\n".join(md_lines)

def saveMD(path: str, md_text: str):
    '''保存到md文件'''
    with open(path, "w", encoding="utf-8") as f:
        f.write(md_text)

def main():
    json_path = r".\content.json"
    json_text = getText(json_path)
    info = json.loads(json_text)
    lines = []
    pickLines(info, lines)
    md_text = mdFormat(lines)
    md_path = r".\思维导图文字提取.md"
    saveMD(md_path, md_text)
    # 程序顺利结束
    print(200)

main()

素材

素材链接
提取码: c6k7