kindle标注行按书名整理

kindlehelper.py

# -*- coding:utf-8 -*-
from collections import defaultdict

shinewords = open('cli.txt','r').read().decode('utf-8')
section = shinewords.strip().split("==========\r\n")
books = defaultdict(lambda : "")
for i in section:
	try:
		i = i.split('\n')
		books[i[0]] += i[3]+'\n\n'
	#最后一个分割为文档结束符，它并没有前面全部正常
	except IndexError:
		pass

with open('note.txt','wb') as f:
	for i in books:
		f.write(i.encode('utf-8') + '\n\n' + books[i].encode('utf-8') + '==========\n')
f.close()