blob: 1769c8cde10b079429de5315769126a6956587d9 (
plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
|
#!/usr/bin/env python
# -*- coding: utf-8 -*-
r"""
extract book highlights to orgmode
==================================
Extracts from exported html notes from kindle to org subtree
"""
# Created: Sat Jul 14 02:10:24 2018
# Author: Óscar Nájera
# License: GPL-3
import argparse
from textwrap import fill as filltxt
from bs4 import BeautifulSoup
def html_notes2org(page):
soup = BeautifulSoup(page, "lxml")
docs = ""
for div in soup.find_all("div"):
hcl = div.attrs.get("class")
if "bookTitle" in hcl:
docs += "* {}".format(div.text.strip())
if "authors" in hcl:
docs += " -- {}\n".format(div.text.strip())
if "sectionHeading" in hcl:
docs += "** " + div.text.lstrip()
if "noteText" in hcl:
docs += "#+begin_quote\n{}\n#+end_quote\n\n".format(
filltxt(div.text.strip())
)
return docs
def main():
parser = argparse.ArgumentParser(description=__doc__)
parser.add_argument("file", help="HTML file from kindle export")
args = parser.parse_args()
with open(args.file, "rb") as fid:
page = fid.read()
docs = html_notes2org(page)
with open("sub.org", "w") as fid:
fid.write(docs)
if __name__ == "__main__":
main()
|
