请参阅：从PDF中提取目录 或者 java : pdfbox 读取 PDF文件内书签
pip install lxml ;
lxml-5.1.0-cp310-cp310-win_amd64.whl (3.9 MB)
读目录.txt文件，使用 lxml 生成思维导图 Freemind（.mm）文件
编写 txt_etree_mm.py 如下
# -*- coding: utf-8 -*-
""" 读目录.txt文件，使用 lxml 生成思维导图 Freemind（.mm）文件"""
import os
import sys
import codecs
from lxml import etreeif len( sys.argv ) ==2:f1 = sys.argv[1]
else:print(u'usage: txt_etree_mm.py file1.txt')sys.exit(1)fn,ext = os.path.splitext(f1)
if ext.lower() != '.txt':print('ext is not .txt')sys.exit(2)# 创建根节点
map = etree.Element("map")
map.set('version', '1.0.1')fp = codecs.open(f1, mode="r", encoding="utf-8")
# 读取第一行：书名
title = fp.readline()
# 创建主题节点
root: etree.ElementBase = etree.Element("node")
root.set('ID', '0')
root.set('STYLE', 'bubble') # 泡框
root.set('TEXT', title.strip())
map.append(root)# 定义连线的颜色：红色
edge: etree.ElementBase = etree.Element("edge")
edge.set('COLOR', "#ff0000")
root.append(edge)
# 用缩排表现层级关系，假设最多5个层级
indent1 = ' '*2
indent2 = ' '*4
indent3 = ' '*6
indent4 = ' '*8n = 1
for line in fp:if len(line.strip()) ==0:continueelif len(line.strip()) >0 and line[0] !=' ':# 创建主题的子节点（1级节点）node1: etree.ElementBase = etree.Element("node")node1.set('ID', str(n))node1.set('POSITION', "right")node1.set('TEXT', line.strip())root.append(node1)p_node = node1 # 寄存父节点elif line.startswith(indent1) and line[2] !=' ':# 创建node1的子节点（2级节点）node2: etree.ElementBase = etree.Element("node")node2.set('ID', str(n))node2.set('TEXT', line.strip())node1.append(node2)p_node = node2elif line.startswith(indent2) and line[4] !=' ':# 创建node2的子节点（3级节点）node3: etree.ElementBase = etree.Element("node")node3.set('FLODED', "true") node3.set('ID', str(n))node3.set('TEXT', line.strip())try:node2.append(node3)except:p_node.append(node3)p_node = node3elif line.startswith(indent3) and line[6] !=' ':# 创建node3的子节点（4级节点）node4: etree.ElementBase = etree.Element("node")node4.set('ID', str(n))node4.set('TEXT', line.strip())try:node3.append(node4)except:p_node.append(node4)p_node = node4elif line.startswith(indent4) and line[8] !=' ':# 创建node4的子节点（5级节点）node5: etree.ElementBase = etree.Element("node")node5.set('ID', str(n))node5.set('TEXT', line.strip())p_node.append(node5)else:print(line)n += 1
fp.close()# 转换成 str，方便导出
map_bytes = etree.tostring(map, pretty_print=True)# 导出到 .mm 格式的文件中
f2 = fn +'.mm'
with open(f2, 'w+b') as fp:fp.write(map_bytes)print(f"line number: {n}")
运行 python txt_etree_mm.py your_pdf_dir.txt
)
 （一）)
